Unnamed: 0
int64 0
2.93k
| code
stringlengths 101
62.2k
| docs
stringlengths 51
10.7k
| doc_len
int64 4
1.74k
| words
int64 4
4.82k
| lang
stringclasses 1
value | prompt
stringlengths 320
71.2k
|
---|---|---|---|---|---|---|
600 | def get_model_dir(cfg):
for key in cfg.keys():
if type(cfg[key]) == dict and \
("enable" in cfg[key].keys() and cfg[key]['enable']
or "enable" not in cfg[key].keys()):
if "model_dir" in cfg[key].keys():
model_dir = cfg[key]["model_dir"]
downloaded_model_dir = auto_download_model(model_dir)
if downloaded_model_dir:
model_dir = downloaded_model_dir
cfg[key]["model_dir"] = model_dir
print(key, " model dir: ", model_dir)
elif key == "VEHICLE_PLATE":
det_model_dir = cfg[key]["det_model_dir"]
downloaded_det_model_dir = auto_download_model(det_model_dir)
if downloaded_det_model_dir:
det_model_dir = downloaded_det_model_dir
cfg[key]["det_model_dir"] = det_model_dir
print("det_model_dir model dir: ", det_model_dir)
rec_model_dir = cfg[key]["rec_model_dir"]
downloaded_rec_model_dir = auto_download_model(rec_model_dir)
if downloaded_rec_model_dir:
rec_model_dir = downloaded_rec_model_dir
cfg[key]["rec_model_dir"] = rec_model_dir
print("rec_model_dir model dir: ", rec_model_dir)
elif key == "MOT": # for idbased and skeletonbased actions
model_dir = cfg[key]["model_dir"]
downloaded_model_dir = auto_download_model(model_dir)
if downloaded_model_dir:
model_dir = downloaded_model_dir
cfg[key]["model_dir"] = model_dir
print("mot_model_dir model_dir: ", model_dir)
|
Auto download inference model if the model_path is a url link.
Otherwise it will use the model_path directly.
| 18 | 116 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_model_dir(cfg):
for key in cfg.keys():
if type(cfg[key]) == dict and \
("enable" in cfg[key].keys() and cfg[key]['enable']
or "enable" not in cfg[key].keys()):
if "model_dir" in cfg[key].keys():
model_dir = cfg[key]["model_dir"]
downloaded_model_dir = auto_download_model(model_dir)
if downloaded_model_dir:
model_dir = downloaded_model_dir
cfg[key]["model_dir"] = model_dir
print(key, " model dir: ", model_dir)
elif key == "VEHICLE_PLATE":
det_model_dir = cfg[key]["det_model_dir"]
downloaded_det_model_dir = auto_download_model(det_model_dir)
if downloaded_det_model_dir:
det_model_dir = downloaded_det_model_dir
cfg[key]["det_model_dir"] = det_model_dir
print("det_model_dir model dir: ", det_model_dir)
rec_model_dir = cfg[key]["rec_model_dir"]
downloaded_rec_model_dir = auto_download_model(rec_model_dir)
if downloaded_rec_model_dir:
rec_model_dir = downloaded_rec_model_dir
cfg[key]["rec_model_dir"] = rec_model_dir
print("rec_model_dir model dir: ", rec_model_dir)
elif key == "MOT": # for idbased and skeletonbased actions
model_dir = cfg[key]["model_dir"]
downloaded_model_dir = auto_download_model(model_dir)
if downloaded_model_dir:
model_dir = downloaded_model_dir
cfg[key]["model_dir"] = model_dir
print("mot_model_dir model_dir: ", model_dir)
```
###Assistant :
Auto download inference model if the model_path is a url link.
Otherwise it will use the model_path directly.
|
601 | def component(self, x, y):
if x >= 0 and x < self.__height and y >= 0 and y < self.__width:
return self.__matrix[x][y]
else:
raise Exception("changeComponent: indices out of bounds")
|
returns the specified (x,y) component
| 5 | 29 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def component(self, x, y):
if x >= 0 and x < self.__height and y >= 0 and y < self.__width:
return self.__matrix[x][y]
else:
raise Exception("changeComponent: indices out of bounds")
```
###Assistant :
returns the specified (x,y) component
|
602 | def toggle(self, all=None, ticks=None, ticklabels=None, label=None):
if all:
_ticks, _ticklabels, _label = True, True, True
elif all is not None:
_ticks, _ticklabels, _label = False, False, False
else:
_ticks, _ticklabels, _label = None, None, None
if ticks is not None:
_ticks = ticks
if ticklabels is not None:
_ticklabels = ticklabels
if label is not None:
_label = label
if _ticks is not None:
self.major_ticks.set_visible(_ticks)
self.minor_ticks.set_visible(_ticks)
if _ticklabels is not None:
self.major_ticklabels.set_visible(_ticklabels)
self.minor_ticklabels.set_visible(_ticklabels)
if _label is not None:
self.label.set_visible(_label)
|
Toggle visibility of ticks, ticklabels, and (axis) label.
To turn all off, ::
axis.toggle(all=False)
To turn all off but ticks on ::
axis.toggle(all=False, ticks=True)
To turn all on but (axis) label off ::
axis.toggle(all=True, label=False)
| 35 | 79 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def toggle(self, all=None, ticks=None, ticklabels=None, label=None):
if all:
_ticks, _ticklabels, _label = True, True, True
elif all is not None:
_ticks, _ticklabels, _label = False, False, False
else:
_ticks, _ticklabels, _label = None, None, None
if ticks is not None:
_ticks = ticks
if ticklabels is not None:
_ticklabels = ticklabels
if label is not None:
_label = label
if _ticks is not None:
self.major_ticks.set_visible(_ticks)
self.minor_ticks.set_visible(_ticks)
if _ticklabels is not None:
self.major_ticklabels.set_visible(_ticklabels)
self.minor_ticklabels.set_visible(_ticklabels)
if _label is not None:
self.label.set_visible(_label)
```
###Assistant :
Toggle visibility of ticks, ticklabels, and (axis) label.
To turn all off, ::
axis.toggle(all=False)
To turn all off but ticks on ::
axis.toggle(all=False, ticks=True)
To turn all on but (axis) label off ::
axis.toggle(all=True, label=False)
|
603 | def mock_json_schema(request, monkeypatch, tmp_path):
# Do not patch integration tests
if "integration" in request.keywords:
return
# Mock the subclasses list to make it very small, containing only mock nodes
monkeypatch.setattr(
haystack.nodes._json_schema,
"find_subclasses_in_modules",
lambda *a, **k: [(conftest, MockDocumentStore), (conftest, MockReader), (conftest, MockRetriever)],
)
# Point the JSON schema path to tmp_path
monkeypatch.setattr(haystack.pipelines.config, "JSON_SCHEMAS_PATH", tmp_path)
# Generate mock schema in tmp_path
filename = f"haystack-pipeline-master.schema.json"
test_schema = _json_schema.get_json_schema(filename=filename, version="ignore")
with open(tmp_path / filename, "w") as schema_file:
json.dump(test_schema, schema_file, indent=4)
#
# Integration
#
@pytest.mark.integration
@pytest.mark.elasticsearch |
JSON schema with the master version and only mocked nodes.
| 10 | 82 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def mock_json_schema(request, monkeypatch, tmp_path):
# Do not patch integration tests
if "integration" in request.keywords:
return
# Mock the subclasses list to make it very small, containing only mock nodes
monkeypatch.setattr(
haystack.nodes._json_schema,
"find_subclasses_in_modules",
lambda *a, **k: [(conftest, MockDocumentStore), (conftest, MockReader), (conftest, MockRetriever)],
)
# Point the JSON schema path to tmp_path
monkeypatch.setattr(haystack.pipelines.config, "JSON_SCHEMAS_PATH", tmp_path)
# Generate mock schema in tmp_path
filename = f"haystack-pipeline-master.schema.json"
test_schema = _json_schema.get_json_schema(filename=filename, version="ignore")
with open(tmp_path / filename, "w") as schema_file:
json.dump(test_schema, schema_file, indent=4)
#
# Integration
#
@pytest.mark.integration
@pytest.mark.elasticsearch
```
###Assistant :
JSON schema with the master version and only mocked nodes.
|
604 | def _has_nchw_support():
explicitly_on_cpu = _is_current_explicit_device("CPU")
gpus_available = bool(_get_available_gpus())
return not explicitly_on_cpu and gpus_available
# VARIABLE MANIPULATION
| Check whether the current scope supports NCHW ops.
TensorFlow does not support NCHW on CPU. Therefore we check if we are not
explicitly put on
CPU, and have GPUs available. In this case there will be soft-placing on the
GPU device.
Returns:
bool: if the current scope device placement would support nchw
| 52 | 16 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _has_nchw_support():
explicitly_on_cpu = _is_current_explicit_device("CPU")
gpus_available = bool(_get_available_gpus())
return not explicitly_on_cpu and gpus_available
# VARIABLE MANIPULATION
```
###Assistant : Check whether the current scope supports NCHW ops.
TensorFlow does not support NCHW on CPU. Therefore we check if we are not
explicitly put on
CPU, and have GPUs available. In this case there will be soft-placing on the
GPU device.
Returns:
bool: if the current scope device placement would support nchw
|
605 | def tensor2img(tensor, out_type=np.uint8, min_max=(0, 1)):
tensor = tensor.squeeze().float().cpu().clamp_(*min_max) # squeeze first, then clamp
tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0]) # to range [0,1]
n_dim = tensor.dim()
if n_dim == 4:
n_img = len(tensor)
img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 3:
img_np = tensor.numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 2:
img_np = tensor.numpy()
else:
raise TypeError(
'Only support 4D, 3D and 2D tensor. But received with dimension: {:d}'.format(n_dim))
if out_type == np.uint8:
img_np = (img_np * 255.0).round()
# Important. Unlike matlab, numpy.unit8() WILL NOT round by default.
return img_np.astype(out_type)
|
Converts a torch Tensor into an image Numpy array of BGR channel order
Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
# --------------------------------------------
# Augmentation, flipe and/or rotate
# --------------------------------------------
# The following two are enough.
# (1) augmet_img: numpy image of WxHxC or WxH
# (2) augment_img_tensor4: tensor image 1xCxWxH
# --------------------------------------------
| 62 | 117 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def tensor2img(tensor, out_type=np.uint8, min_max=(0, 1)):
tensor = tensor.squeeze().float().cpu().clamp_(*min_max) # squeeze first, then clamp
tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0]) # to range [0,1]
n_dim = tensor.dim()
if n_dim == 4:
n_img = len(tensor)
img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 3:
img_np = tensor.numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 2:
img_np = tensor.numpy()
else:
raise TypeError(
'Only support 4D, 3D and 2D tensor. But received with dimension: {:d}'.format(n_dim))
if out_type == np.uint8:
img_np = (img_np * 255.0).round()
# Important. Unlike matlab, numpy.unit8() WILL NOT round by default.
return img_np.astype(out_type)
```
###Assistant :
Converts a torch Tensor into an image Numpy array of BGR channel order
Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
# --------------------------------------------
# Augmentation, flipe and/or rotate
# --------------------------------------------
# The following two are enough.
# (1) augmet_img: numpy image of WxHxC or WxH
# (2) augment_img_tensor4: tensor image 1xCxWxH
# --------------------------------------------
|
606 | def get_local_ip_address() -> str:
try:
ip_address = requests.get(
"https://checkip.amazonaws.com/", timeout=3
).text.strip()
except (requests.ConnectionError, requests.exceptions.ReadTimeout):
ip_address = "No internet connection"
return ip_address
| Gets the public IP address or returns the string "No internet connection" if unable to obtain it. | 17 | 21 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_local_ip_address() -> str:
try:
ip_address = requests.get(
"https://checkip.amazonaws.com/", timeout=3
).text.strip()
except (requests.ConnectionError, requests.exceptions.ReadTimeout):
ip_address = "No internet connection"
return ip_address
```
###Assistant : Gets the public IP address or returns the string "No internet connection" if unable to obtain it.
|
607 | def get_tip(self):
tips = self.get_tips()
if len(tips) == 0:
raise Exception("tip not found")
else:
return tips[0]
| Returns the TipableVMobject instance's (first) tip,
otherwise throws an exception. | 10 | 16 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_tip(self):
tips = self.get_tips()
if len(tips) == 0:
raise Exception("tip not found")
else:
return tips[0]
```
###Assistant : Returns the TipableVMobject instance's (first) tip,
otherwise throws an exception.
|
608 | def shuffle(self, func, lengths, **kwargs):
num_splits = len(lengths)
# We add these to kwargs and will pop them off before performing the operation.
kwargs["manual_partition"] = True
kwargs["_lengths"] = lengths
args = [self.axis, func, num_splits, False]
args.extend(self.list_of_blocks)
return self._wrap_partitions(self.deploy_axis_func(*args, **kwargs))
|
Shuffle the order of the data in this axis partition based on the `lengths`.
Parameters
----------
func : callable
The function to apply before splitting.
lengths : list
The list of partition lengths to split the result into.
**kwargs : dict
Additional keywords arguments to be passed in `func`.
Returns
-------
list
A list of `PandasDataframePartition` objects split by `lengths`.
| 60 | 39 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def shuffle(self, func, lengths, **kwargs):
num_splits = len(lengths)
# We add these to kwargs and will pop them off before performing the operation.
kwargs["manual_partition"] = True
kwargs["_lengths"] = lengths
args = [self.axis, func, num_splits, False]
args.extend(self.list_of_blocks)
return self._wrap_partitions(self.deploy_axis_func(*args, **kwargs))
```
###Assistant :
Shuffle the order of the data in this axis partition based on the `lengths`.
Parameters
----------
func : callable
The function to apply before splitting.
lengths : list
The list of partition lengths to split the result into.
**kwargs : dict
Additional keywords arguments to be passed in `func`.
Returns
-------
list
A list of `PandasDataframePartition` objects split by `lengths`.
|
609 | def test_background_add_room_type_column(self):
# Create a room without a type
room_id = self._generate_room()
# Get event_id of the m.room.create event
event_id = self.get_success(
self.store.db_pool.simple_select_one_onecol(
table="current_state_events",
keyvalues={
"room_id": room_id,
"type": "m.room.create",
},
retcol="event_id",
)
)
# Fake a room creation event with a room type
event = {
"content": {
"creator": "@user:server.org",
"room_version": "9",
"type": RoomTypes.SPACE,
},
"type": "m.room.create",
}
self.get_success(
self.store.db_pool.simple_update(
table="event_json",
keyvalues={"event_id": event_id},
updatevalues={"json": json.dumps(event)},
desc="test",
)
)
# Insert and run the background update
self.get_success(
self.store.db_pool.simple_insert(
"background_updates",
{
"update_name": _BackgroundUpdates.ADD_ROOM_TYPE_COLUMN,
"progress_json": "{}",
},
)
)
# ... and tell the DataStore that it hasn't finished all updates yet
self.store.db_pool.updates._all_done = False
# Now let's actually drive the updates to completion
self.wait_for_background_updates()
# Make sure the background update filled in the room type
room_type_after = self.get_success(
self.store.db_pool.simple_select_one_onecol(
table="room_stats_state",
keyvalues={"room_id": room_id},
retcol="room_type",
allow_none=True,
)
)
self.assertEqual(room_type_after, RoomTypes.SPACE)
| Test that the background update to populate the `room_type` column in
`room_stats_state` works properly.
| 14 | 136 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_background_add_room_type_column(self):
# Create a room without a type
room_id = self._generate_room()
# Get event_id of the m.room.create event
event_id = self.get_success(
self.store.db_pool.simple_select_one_onecol(
table="current_state_events",
keyvalues={
"room_id": room_id,
"type": "m.room.create",
},
retcol="event_id",
)
)
# Fake a room creation event with a room type
event = {
"content": {
"creator": "@user:server.org",
"room_version": "9",
"type": RoomTypes.SPACE,
},
"type": "m.room.create",
}
self.get_success(
self.store.db_pool.simple_update(
table="event_json",
keyvalues={"event_id": event_id},
updatevalues={"json": json.dumps(event)},
desc="test",
)
)
# Insert and run the background update
self.get_success(
self.store.db_pool.simple_insert(
"background_updates",
{
"update_name": _BackgroundUpdates.ADD_ROOM_TYPE_COLUMN,
"progress_json": "{}",
},
)
)
# ... and tell the DataStore that it hasn't finished all updates yet
self.store.db_pool.updates._all_done = False
# Now let's actually drive the updates to completion
self.wait_for_background_updates()
# Make sure the background update filled in the room type
room_type_after = self.get_success(
self.store.db_pool.simple_select_one_onecol(
table="room_stats_state",
keyvalues={"room_id": room_id},
retcol="room_type",
allow_none=True,
)
)
self.assertEqual(room_type_after, RoomTypes.SPACE)
```
###Assistant : Test that the background update to populate the `room_type` column in
`room_stats_state` works properly.
|
610 | def get_feedback():
labels = DOCUMENT_STORE.get_all_labels()
return labels
@router.delete("/feedback") |
This endpoint allows the API user to retrieve all the feedback that has been submitted
through the `POST /feedback` endpoint.
| 20 | 8 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_feedback():
labels = DOCUMENT_STORE.get_all_labels()
return labels
@router.delete("/feedback")
```
###Assistant :
This endpoint allows the API user to retrieve all the feedback that has been submitted
through the `POST /feedback` endpoint.
|
611 | def get_formatter_for_filename(fn, **options):
fn = basename(fn)
for modname, name, _, filenames, _ in FORMATTERS.values():
for filename in filenames:
if _fn_matches(fn, filename):
if name not in _formatter_cache:
_load_formatters(modname)
return _formatter_cache[name](**options)
for cls in find_plugin_formatters():
for filename in cls.filenames:
if _fn_matches(fn, filename):
return cls(**options)
raise ClassNotFound("no formatter found for file name %r" % fn)
| Lookup and instantiate a formatter by filename pattern.
Raises ClassNotFound if not found.
| 13 | 52 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_formatter_for_filename(fn, **options):
fn = basename(fn)
for modname, name, _, filenames, _ in FORMATTERS.values():
for filename in filenames:
if _fn_matches(fn, filename):
if name not in _formatter_cache:
_load_formatters(modname)
return _formatter_cache[name](**options)
for cls in find_plugin_formatters():
for filename in cls.filenames:
if _fn_matches(fn, filename):
return cls(**options)
raise ClassNotFound("no formatter found for file name %r" % fn)
```
###Assistant : Lookup and instantiate a formatter by filename pattern.
Raises ClassNotFound if not found.
|
612 | def setup_sigterm_on_parent_death():
try:
import ctypes
import signal
libc = ctypes.CDLL("libc.so.6")
# Set the parent process death signal of the command process to SIGTERM.
libc.prctl(1, signal.SIGTERM) # PR_SET_PDEATHSIG, see prctl.h
except OSError as e:
_logger.warning(f"Setup libc.prctl PR_SET_PDEATHSIG failed, error {repr(e)}.")
|
Uses prctl to automatically send SIGTERM to the child process when its parent is
dead. The child process itself should handle SIGTERM properly.
| 23 | 39 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def setup_sigterm_on_parent_death():
try:
import ctypes
import signal
libc = ctypes.CDLL("libc.so.6")
# Set the parent process death signal of the command process to SIGTERM.
libc.prctl(1, signal.SIGTERM) # PR_SET_PDEATHSIG, see prctl.h
except OSError as e:
_logger.warning(f"Setup libc.prctl PR_SET_PDEATHSIG failed, error {repr(e)}.")
```
###Assistant :
Uses prctl to automatically send SIGTERM to the child process when its parent is
dead. The child process itself should handle SIGTERM properly.
|
613 | def force_reads(self) -> "Dataset[T]":
blocks = self.get_internal_block_refs()
bar = ProgressBar("Force reads", len(blocks))
bar.block_until_complete(blocks)
return self
| Force full evaluation of the blocks of this dataset.
This can be used to read all blocks into memory. By default, Datasets
doesn't read blocks from the datasource until the first transform.
| 32 | 15 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def force_reads(self) -> "Dataset[T]":
blocks = self.get_internal_block_refs()
bar = ProgressBar("Force reads", len(blocks))
bar.block_until_complete(blocks)
return self
```
###Assistant : Force full evaluation of the blocks of this dataset.
This can be used to read all blocks into memory. By default, Datasets
doesn't read blocks from the datasource until the first transform.
|
614 | def __iter__(self) -> Iterator[tuple[Widget, Region, Region, Size, Size]]:
layers = sorted(self.map.items(), key=lambda item: item[1].order, reverse=True)
intersection = Region.intersection
for widget, (region, _order, clip, virtual_size, container_size) in layers:
yield (
widget,
intersection(region, clip),
region,
virtual_size,
container_size,
)
| Iterate map with information regarding each widget and is position
Yields:
Iterator[tuple[Widget, Region, Region, Size, Size]]: Iterates a tuple of
Widget, clip region, region, virtual size, and container size.
| 29 | 36 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def __iter__(self) -> Iterator[tuple[Widget, Region, Region, Size, Size]]:
layers = sorted(self.map.items(), key=lambda item: item[1].order, reverse=True)
intersection = Region.intersection
for widget, (region, _order, clip, virtual_size, container_size) in layers:
yield (
widget,
intersection(region, clip),
region,
virtual_size,
container_size,
)
```
###Assistant : Iterate map with information regarding each widget and is position
Yields:
Iterator[tuple[Widget, Region, Region, Size, Size]]: Iterates a tuple of
Widget, clip region, region, virtual size, and container size.
|
615 | def get_names_flat(adtype):
listnames = []
names = adtype.names
for name in names:
listnames.append(name)
current = adtype[name]
if current.names is not None:
listnames.extend(get_names_flat(current))
return tuple(listnames)
|
Returns the field names of the input datatype as a tuple. Input datatype
has to have fields otherwise error is raised.
Nested structure are flattened beforehand.
Parameters
----------
adtype : dtype
Input datatype
Examples
--------
>>> from numpy.lib import recfunctions as rfn
>>> rfn.get_names_flat(np.empty((1,), dtype=[('A', int)]).dtype) is None
False
>>> rfn.get_names_flat(np.empty((1,), dtype=[('A',int), ('B', str)]).dtype)
('A', 'B')
>>> adtype = np.dtype([('a', int), ('b', [('ba', int), ('bb', int)])])
>>> rfn.get_names_flat(adtype)
('a', 'b', 'ba', 'bb')
| 72 | 24 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_names_flat(adtype):
listnames = []
names = adtype.names
for name in names:
listnames.append(name)
current = adtype[name]
if current.names is not None:
listnames.extend(get_names_flat(current))
return tuple(listnames)
```
###Assistant :
Returns the field names of the input datatype as a tuple. Input datatype
has to have fields otherwise error is raised.
Nested structure are flattened beforehand.
Parameters
----------
adtype : dtype
Input datatype
Examples
--------
>>> from numpy.lib import recfunctions as rfn
>>> rfn.get_names_flat(np.empty((1,), dtype=[('A', int)]).dtype) is None
False
>>> rfn.get_names_flat(np.empty((1,), dtype=[('A',int), ('B', str)]).dtype)
('A', 'B')
>>> adtype = np.dtype([('a', int), ('b', [('ba', int), ('bb', int)])])
>>> rfn.get_names_flat(adtype)
('a', 'b', 'ba', 'bb')
|
616 | def test_memory_leak(self):
import gc
import weakref
results = {}
for kind in plotting.PlotAccessor._all_kinds:
args = {}
if kind in ["hexbin", "scatter", "pie"]:
df = DataFrame(
{
"A": np.random.uniform(size=20),
"B": np.random.uniform(size=20),
"C": np.arange(20) + np.random.uniform(size=20),
}
)
args = {"x": "A", "y": "B"}
elif kind == "area":
df = tm.makeTimeDataFrame().abs()
else:
df = tm.makeTimeDataFrame()
# Use a weakref so we can see if the object gets collected without
# also preventing it from being collected
results[kind] = weakref.proxy(df.plot(kind=kind, **args))
# have matplotlib delete all the figures
tm.close()
# force a garbage collection
gc.collect()
msg = "weakly-referenced object no longer exists"
for key in results:
# check that every plot was collected
with pytest.raises(ReferenceError, match=msg):
# need to actually access something to get an error
results[key].lines
| Check that every plot type gets properly collected. | 8 | 124 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_memory_leak(self):
import gc
import weakref
results = {}
for kind in plotting.PlotAccessor._all_kinds:
args = {}
if kind in ["hexbin", "scatter", "pie"]:
df = DataFrame(
{
"A": np.random.uniform(size=20),
"B": np.random.uniform(size=20),
"C": np.arange(20) + np.random.uniform(size=20),
}
)
args = {"x": "A", "y": "B"}
elif kind == "area":
df = tm.makeTimeDataFrame().abs()
else:
df = tm.makeTimeDataFrame()
# Use a weakref so we can see if the object gets collected without
# also preventing it from being collected
results[kind] = weakref.proxy(df.plot(kind=kind, **args))
# have matplotlib delete all the figures
tm.close()
# force a garbage collection
gc.collect()
msg = "weakly-referenced object no longer exists"
for key in results:
# check that every plot was collected
with pytest.raises(ReferenceError, match=msg):
# need to actually access something to get an error
results[key].lines
```
###Assistant : Check that every plot type gets properly collected.
|
617 | def disabled_excepthook() -> Iterator[None]:
old_excepthook = sys.excepthook
sys.excepthook = sys.__excepthook__
try:
yield
finally:
# If the code we did run did change sys.excepthook, we leave it
# unchanged. Otherwise, we reset it.
if sys.excepthook is sys.__excepthook__:
sys.excepthook = old_excepthook
| Run code with the exception hook temporarily disabled. | 8 | 39 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def disabled_excepthook() -> Iterator[None]:
old_excepthook = sys.excepthook
sys.excepthook = sys.__excepthook__
try:
yield
finally:
# If the code we did run did change sys.excepthook, we leave it
# unchanged. Otherwise, we reset it.
if sys.excepthook is sys.__excepthook__:
sys.excepthook = old_excepthook
```
###Assistant : Run code with the exception hook temporarily disabled.
|
618 | def trigger_import(*dfs):
if ASV_USE_STORAGE_FORMAT != "hdk" or ASV_USE_IMPL == "pandas":
return
from modin.experimental.core.execution.native.implementations.hdk_on_native.db_worker import (
DbWorker,
)
for df in dfs:
df.shape # to trigger real execution
df._query_compiler._modin_frame._partitions[0][
0
].frame_id = DbWorker().import_arrow_table(
df._query_compiler._modin_frame._partitions[0][0].get()
) # to trigger real execution
|
Trigger import execution for DataFrames obtained by HDK engine.
Parameters
----------
*dfs : iterable
DataFrames to trigger import.
| 18 | 39 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def trigger_import(*dfs):
if ASV_USE_STORAGE_FORMAT != "hdk" or ASV_USE_IMPL == "pandas":
return
from modin.experimental.core.execution.native.implementations.hdk_on_native.db_worker import (
DbWorker,
)
for df in dfs:
df.shape # to trigger real execution
df._query_compiler._modin_frame._partitions[0][
0
].frame_id = DbWorker().import_arrow_table(
df._query_compiler._modin_frame._partitions[0][0].get()
) # to trigger real execution
```
###Assistant :
Trigger import execution for DataFrames obtained by HDK engine.
Parameters
----------
*dfs : iterable
DataFrames to trigger import.
|
619 | def _jacfwd(f, primals):
jac_flat = []
flat_primals = tf.nest.flatten(primals)
tangent_mask = [tf.zeros_like(primal) for primal in flat_primals]
for primal_index, primal in enumerate(flat_primals):
primal_vector = tf.reshape(primal, [-1])
primal_vector_length = tf.size(primal_vector)
jac_columns = []
for element_index in tf.range(primal_vector_length):
mask = tf.one_hot(element_index, primal_vector_length)
tangent_mask[primal_index] = tf.reshape(mask, tf.shape(primal))
jac_columns.append(
tf.nest.map_structure(
functools.partial(tf.reshape, shape=[-1]),
_jvp(
f,
primals,
tf.nest.pack_sequence_as(primals, tangent_mask),
)[1],
)
)
jac_flat.append(tf.stack(jac_columns, axis=1))
tangent_mask[primal_index] = tf.zeros_like(primal)
return tf.nest.pack_sequence_as(primals, jac_flat)
| Compute the jacobian of `f` at `primals` using forward-mode autodiff. | 10 | 63 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _jacfwd(f, primals):
jac_flat = []
flat_primals = tf.nest.flatten(primals)
tangent_mask = [tf.zeros_like(primal) for primal in flat_primals]
for primal_index, primal in enumerate(flat_primals):
primal_vector = tf.reshape(primal, [-1])
primal_vector_length = tf.size(primal_vector)
jac_columns = []
for element_index in tf.range(primal_vector_length):
mask = tf.one_hot(element_index, primal_vector_length)
tangent_mask[primal_index] = tf.reshape(mask, tf.shape(primal))
jac_columns.append(
tf.nest.map_structure(
functools.partial(tf.reshape, shape=[-1]),
_jvp(
f,
primals,
tf.nest.pack_sequence_as(primals, tangent_mask),
)[1],
)
)
jac_flat.append(tf.stack(jac_columns, axis=1))
tangent_mask[primal_index] = tf.zeros_like(primal)
return tf.nest.pack_sequence_as(primals, jac_flat)
```
###Assistant : Compute the jacobian of `f` at `primals` using forward-mode autodiff.
|
620 | def record_timing(name, duration=None, description=None):
timing_information = getattr(flask.g, "timing_information", {})
if name in timing_information:
raise KeyError(f'Duplicate resource name "{name}" found.')
timing_information[name] = {"dur": round(duration * 1000), "desc": description}
setattr(flask.g, "timing_information", timing_information)
| Records timing information for a server resource.
:param name: The name of the resource.
:type name: string
:param duration: The time in seconds to report. Internally, this
is rounded to the nearest millisecond.
:type duration: float or None
:param description: A description of the resource.
:type description: string or None
| 50 | 30 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def record_timing(name, duration=None, description=None):
timing_information = getattr(flask.g, "timing_information", {})
if name in timing_information:
raise KeyError(f'Duplicate resource name "{name}" found.')
timing_information[name] = {"dur": round(duration * 1000), "desc": description}
setattr(flask.g, "timing_information", timing_information)
```
###Assistant : Records timing information for a server resource.
:param name: The name of the resource.
:type name: string
:param duration: The time in seconds to report. Internally, this
is rounded to the nearest millisecond.
:type duration: float or None
:param description: A description of the resource.
:type description: string or None
|
621 | def admin_actions(context):
context["action_index"] = context.get("action_index", -1) + 1
return context
@register.tag(name="admin_actions") |
Track the number of times the action field has been rendered on the page,
so we know which value to use.
| 21 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def admin_actions(context):
context["action_index"] = context.get("action_index", -1) + 1
return context
@register.tag(name="admin_actions")
```
###Assistant :
Track the number of times the action field has been rendered on the page,
so we know which value to use.
|
622 | async def test_lights(hass, mock_bridge_v2, v2_resources_test_data):
await mock_bridge_v2.api.load_test_data(v2_resources_test_data)
await setup_platform(hass, mock_bridge_v2, "light")
# there shouldn't have been any requests at this point
assert len(mock_bridge_v2.mock_requests) == 0
# 6 entities should be created from test data (grouped_lights are disabled by default)
assert len(hass.states.async_all()) == 6
# test light which supports color and color temperature
light_1 = hass.states.get("light.hue_light_with_color_and_color_temperature_1")
assert light_1 is not None
assert (
light_1.attributes["friendly_name"]
== "Hue light with color and color temperature 1"
)
assert light_1.state == "on"
assert light_1.attributes["brightness"] == int(46.85 / 100 * 255)
assert light_1.attributes["mode"] == "normal"
assert light_1.attributes["color_mode"] == COLOR_MODE_XY
assert set(light_1.attributes["supported_color_modes"]) == {
COLOR_MODE_COLOR_TEMP,
COLOR_MODE_XY,
}
assert light_1.attributes["xy_color"] == (0.5614, 0.4058)
assert light_1.attributes["min_mireds"] == 153
assert light_1.attributes["max_mireds"] == 500
assert light_1.attributes["dynamics"] == "dynamic_palette"
assert light_1.attributes["effect_list"] == ["None", "candle", "fire"]
assert light_1.attributes["effect"] == "None"
# test light which supports color temperature only
light_2 = hass.states.get("light.hue_light_with_color_temperature_only")
assert light_2 is not None
assert (
light_2.attributes["friendly_name"] == "Hue light with color temperature only"
)
assert light_2.state == "off"
assert light_2.attributes["mode"] == "normal"
assert light_2.attributes["supported_color_modes"] == [COLOR_MODE_COLOR_TEMP]
assert light_2.attributes["min_mireds"] == 153
assert light_2.attributes["max_mireds"] == 454
assert light_2.attributes["dynamics"] == "none"
assert light_2.attributes["effect_list"] == ["None", "candle", "sunrise"]
# test light which supports color only
light_3 = hass.states.get("light.hue_light_with_color_only")
assert light_3 is not None
assert light_3.attributes["friendly_name"] == "Hue light with color only"
assert light_3.state == "on"
assert light_3.attributes["brightness"] == 128
assert light_3.attributes["mode"] == "normal"
assert light_3.attributes["supported_color_modes"] == [COLOR_MODE_XY]
assert light_3.attributes["color_mode"] == COLOR_MODE_XY
assert light_3.attributes["dynamics"] == "dynamic_palette"
# test light which supports on/off only
light_4 = hass.states.get("light.hue_on_off_light")
assert light_4 is not None
assert light_4.attributes["friendly_name"] == "Hue on/off light"
assert light_4.state == "off"
assert light_4.attributes["mode"] == "normal"
assert light_4.attributes["supported_color_modes"] == []
| Test if all v2 lights get created with correct features. | 10 | 264 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def test_lights(hass, mock_bridge_v2, v2_resources_test_data):
await mock_bridge_v2.api.load_test_data(v2_resources_test_data)
await setup_platform(hass, mock_bridge_v2, "light")
# there shouldn't have been any requests at this point
assert len(mock_bridge_v2.mock_requests) == 0
# 6 entities should be created from test data (grouped_lights are disabled by default)
assert len(hass.states.async_all()) == 6
# test light which supports color and color temperature
light_1 = hass.states.get("light.hue_light_with_color_and_color_temperature_1")
assert light_1 is not None
assert (
light_1.attributes["friendly_name"]
== "Hue light with color and color temperature 1"
)
assert light_1.state == "on"
assert light_1.attributes["brightness"] == int(46.85 / 100 * 255)
assert light_1.attributes["mode"] == "normal"
assert light_1.attributes["color_mode"] == COLOR_MODE_XY
assert set(light_1.attributes["supported_color_modes"]) == {
COLOR_MODE_COLOR_TEMP,
COLOR_MODE_XY,
}
assert light_1.attributes["xy_color"] == (0.5614, 0.4058)
assert light_1.attributes["min_mireds"] == 153
assert light_1.attributes["max_mireds"] == 500
assert light_1.attributes["dynamics"] == "dynamic_palette"
assert light_1.attributes["effect_list"] == ["None", "candle", "fire"]
assert light_1.attributes["effect"] == "None"
# test light which supports color temperature only
light_2 = hass.states.get("light.hue_light_with_color_temperature_only")
assert light_2 is not None
assert (
light_2.attributes["friendly_name"] == "Hue light with color temperature only"
)
assert light_2.state == "off"
assert light_2.attributes["mode"] == "normal"
assert light_2.attributes["supported_color_modes"] == [COLOR_MODE_COLOR_TEMP]
assert light_2.attributes["min_mireds"] == 153
assert light_2.attributes["max_mireds"] == 454
assert light_2.attributes["dynamics"] == "none"
assert light_2.attributes["effect_list"] == ["None", "candle", "sunrise"]
# test light which supports color only
light_3 = hass.states.get("light.hue_light_with_color_only")
assert light_3 is not None
assert light_3.attributes["friendly_name"] == "Hue light with color only"
assert light_3.state == "on"
assert light_3.attributes["brightness"] == 128
assert light_3.attributes["mode"] == "normal"
assert light_3.attributes["supported_color_modes"] == [COLOR_MODE_XY]
assert light_3.attributes["color_mode"] == COLOR_MODE_XY
assert light_3.attributes["dynamics"] == "dynamic_palette"
# test light which supports on/off only
light_4 = hass.states.get("light.hue_on_off_light")
assert light_4 is not None
assert light_4.attributes["friendly_name"] == "Hue on/off light"
assert light_4.state == "off"
assert light_4.attributes["mode"] == "normal"
assert light_4.attributes["supported_color_modes"] == []
```
###Assistant : Test if all v2 lights get created with correct features.
|
623 | def setup_data(self, path):
for message, new_episode in super().setup_data(path):
assert (
message['text'] == '__SILENCE__'
), 'The expected original context string is not found!'
message['text'] = 'Person 1:'
yield message, new_episode
|
Modify each output message to add in an OPT-compatible context string.
| 11 | 29 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def setup_data(self, path):
for message, new_episode in super().setup_data(path):
assert (
message['text'] == '__SILENCE__'
), 'The expected original context string is not found!'
message['text'] = 'Person 1:'
yield message, new_episode
```
###Assistant :
Modify each output message to add in an OPT-compatible context string.
|
624 | def _get_input_locations(self) -> List[str]:
if not self._args.batch_mode or os.path.isfile(self._args.input_dir):
return [self._args.input_dir] # Not batch mode or a single file
retval = [os.path.join(self._args.input_dir, fname)
for fname in os.listdir(self._args.input_dir)
if os.path.isdir(os.path.join(self._args.input_dir, fname))
or os.path.splitext(fname)[-1].lower() in _video_extensions]
logger.debug("Input locations: %s", retval)
return retval
| Obtain the full path to input locations. Will be a list of locations if batch mode is
selected, or a containing a single location if batch mode is not selected.
Returns
-------
list:
The list of input location paths
| 39 | 40 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _get_input_locations(self) -> List[str]:
if not self._args.batch_mode or os.path.isfile(self._args.input_dir):
return [self._args.input_dir] # Not batch mode or a single file
retval = [os.path.join(self._args.input_dir, fname)
for fname in os.listdir(self._args.input_dir)
if os.path.isdir(os.path.join(self._args.input_dir, fname))
or os.path.splitext(fname)[-1].lower() in _video_extensions]
logger.debug("Input locations: %s", retval)
return retval
```
###Assistant : Obtain the full path to input locations. Will be a list of locations if batch mode is
selected, or a containing a single location if batch mode is not selected.
Returns
-------
list:
The list of input location paths
|
625 | def get_party_gle_currency(party_type, party, company):
def generator():
existing_gle_currency = frappe.db.sql(
,
{"company": company, "party_type": party_type, "party": party},
)
return existing_gle_currency[0][0] if existing_gle_currency else None
return frappe.local_cache(
"party_gle_currency", (party_type, party, company), generator, regenerate_if_none=True
)
| select account_currency from `tabGL Entry`
where docstatus=1 and company=%(company)s and party_type=%(party_type)s and party=%(party)s
limit 1 | 15 | 32 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_party_gle_currency(party_type, party, company):
def generator():
existing_gle_currency = frappe.db.sql(
,
{"company": company, "party_type": party_type, "party": party},
)
return existing_gle_currency[0][0] if existing_gle_currency else None
return frappe.local_cache(
"party_gle_currency", (party_type, party, company), generator, regenerate_if_none=True
)
```
###Assistant : select account_currency from `tabGL Entry`
where docstatus=1 and company=%(company)s and party_type=%(party_type)s and party=%(party)s
limit 1
|
626 | def load_breast_cancer(*, return_X_y=False, as_frame=False):
data_file_name = "breast_cancer.csv"
data, target, target_names, fdescr = load_csv_data(
data_file_name=data_file_name, descr_file_name="breast_cancer.rst"
)
feature_names = np.array(
[
"mean radius",
"mean texture",
"mean perimeter",
"mean area",
"mean smoothness",
"mean compactness",
"mean concavity",
"mean concave points",
"mean symmetry",
"mean fractal dimension",
"radius error",
"texture error",
"perimeter error",
"area error",
"smoothness error",
"compactness error",
"concavity error",
"concave points error",
"symmetry error",
"fractal dimension error",
"worst radius",
"worst texture",
"worst perimeter",
"worst area",
"worst smoothness",
"worst compactness",
"worst concavity",
"worst concave points",
"worst symmetry",
"worst fractal dimension",
]
)
frame = None
target_columns = [
"target",
]
if as_frame:
frame, data, target = _convert_data_dataframe(
"load_breast_cancer", data, target, feature_names, target_columns
)
if return_X_y:
return data, target
return Bunch(
data=data,
target=target,
frame=frame,
target_names=target_names,
DESCR=fdescr,
feature_names=feature_names,
filename=data_file_name,
data_module=DATA_MODULE,
)
| Load and return the breast cancer wisconsin dataset (classification).
The breast cancer dataset is a classic and very easy binary classification
dataset.
================= ==============
Classes 2
Samples per class 212(M),357(B)
Samples total 569
Dimensionality 30
Features real, positive
================= ==============
The copy of UCI ML Breast Cancer Wisconsin (Diagnostic) dataset is
downloaded from:
https://goo.gl/U2Uwz2
Read more in the :ref:`User Guide <breast_cancer_dataset>`.
Parameters
----------
return_X_y : bool, default=False
If True, returns ``(data, target)`` instead of a Bunch object.
See below for more information about the `data` and `target` object.
.. versionadded:: 0.18
as_frame : bool, default=False
If True, the data is a pandas DataFrame including columns with
appropriate dtypes (numeric). The target is
a pandas DataFrame or Series depending on the number of target columns.
If `return_X_y` is True, then (`data`, `target`) will be pandas
DataFrames or Series as described below.
.. versionadded:: 0.23
Returns
-------
data : :class:`~sklearn.utils.Bunch`
Dictionary-like object, with the following attributes.
data : {ndarray, dataframe} of shape (569, 30)
The data matrix. If `as_frame=True`, `data` will be a pandas
DataFrame.
target : {ndarray, Series} of shape (569,)
The classification target. If `as_frame=True`, `target` will be
a pandas Series.
feature_names : list
The names of the dataset columns.
target_names : list
The names of target classes.
frame : DataFrame of shape (569, 31)
Only present when `as_frame=True`. DataFrame with `data` and
`target`.
.. versionadded:: 0.23
DESCR : str
The full description of the dataset.
filename : str
The path to the location of the data.
.. versionadded:: 0.20
(data, target) : tuple if ``return_X_y`` is True
A tuple of two ndarrays by default. The first contains a 2D ndarray of
shape (569, 30) with each row representing one sample and each column
representing the features. The second ndarray of shape (569,) contains
the target samples. If `as_frame=True`, both arrays are pandas objects,
i.e. `X` a dataframe and `y` a series.
.. versionadded:: 0.18
Examples
--------
Let's say you are interested in the samples 10, 50, and 85, and want to
know their class name.
>>> from sklearn.datasets import load_breast_cancer
>>> data = load_breast_cancer()
>>> data.target[[10, 50, 85]]
array([0, 1, 0])
>>> list(data.target_names)
['malignant', 'benign']
| 356 | 125 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def load_breast_cancer(*, return_X_y=False, as_frame=False):
data_file_name = "breast_cancer.csv"
data, target, target_names, fdescr = load_csv_data(
data_file_name=data_file_name, descr_file_name="breast_cancer.rst"
)
feature_names = np.array(
[
"mean radius",
"mean texture",
"mean perimeter",
"mean area",
"mean smoothness",
"mean compactness",
"mean concavity",
"mean concave points",
"mean symmetry",
"mean fractal dimension",
"radius error",
"texture error",
"perimeter error",
"area error",
"smoothness error",
"compactness error",
"concavity error",
"concave points error",
"symmetry error",
"fractal dimension error",
"worst radius",
"worst texture",
"worst perimeter",
"worst area",
"worst smoothness",
"worst compactness",
"worst concavity",
"worst concave points",
"worst symmetry",
"worst fractal dimension",
]
)
frame = None
target_columns = [
"target",
]
if as_frame:
frame, data, target = _convert_data_dataframe(
"load_breast_cancer", data, target, feature_names, target_columns
)
if return_X_y:
return data, target
return Bunch(
data=data,
target=target,
frame=frame,
target_names=target_names,
DESCR=fdescr,
feature_names=feature_names,
filename=data_file_name,
data_module=DATA_MODULE,
)
```
###Assistant : Load and return the breast cancer wisconsin dataset (classification).
The breast cancer dataset is a classic and very easy binary classification
dataset.
================= ==============
Classes 2
Samples per class 212(M),357(B)
Samples total 569
Dimensionality 30
Features real, positive
================= ==============
The copy of UCI ML Breast Cancer Wisconsin (Diagnostic) dataset is
downloaded from:
https://goo.gl/U2Uwz2
Read more in the :ref:`User Guide <breast_cancer_dataset>`.
Parameters
----------
return_X_y : bool, default=False
If True, returns ``(data, target)`` instead of a Bunch object.
See below for more information about the `data` and `target` object.
.. versionadded:: 0.18
as_frame : bool, default=False
If True, the data is a pandas DataFrame including columns with
appropriate dtypes (numeric). The target is
a pandas DataFrame or Series depending on the number of target columns.
If `return_X_y` is True, then (`data`, `target`) will be pandas
DataFrames or Series as described below.
.. versionadded:: 0.23
Returns
-------
data : :class:`~sklearn.utils.Bunch`
Dictionary-like object, with the following attributes.
data : {ndarray, dataframe} of shape (569, 30)
The data matrix. If `as_frame=True`, `data` will be a pandas
DataFrame.
target : {ndarray, Series} of shape (569,)
The classification target. If `as_frame=True`, `target` will be
a pandas Series.
feature_names : list
The names of the dataset columns.
target_names : list
The names of target classes.
frame : DataFrame of shape (569, 31)
Only present when `as_frame=True`. DataFrame with `data` and
`target`.
.. versionadded:: 0.23
DESCR : str
The full description of the dataset.
filename : str
The path to the location of the data.
.. versionadded:: 0.20
(data, target) : tuple if ``return_X_y`` is True
A tuple of two ndarrays by default. The first contains a 2D ndarray of
shape (569, 30) with each row representing one sample and each column
representing the features. The second ndarray of shape (569,) contains
the target samples. If `as_frame=True`, both arrays are pandas objects,
i.e. `X` a dataframe and `y` a series.
.. versionadded:: 0.18
Examples
--------
Let's say you are interested in the samples 10, 50, and 85, and want to
know their class name.
>>> from sklearn.datasets import load_breast_cancer
>>> data = load_breast_cancer()
>>> data.target[[10, 50, 85]]
array([0, 1, 0])
>>> list(data.target_names)
['malignant', 'benign']
|
627 | def get_filter_by_name(filtername, **options):
cls = find_filter_class(filtername)
if cls:
return cls(**options)
else:
raise ClassNotFound('filter %r not found' % filtername)
| Return an instantiated filter.
Options are passed to the filter initializer if wanted.
Raise a ClassNotFound if not found.
| 19 | 18 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_filter_by_name(filtername, **options):
cls = find_filter_class(filtername)
if cls:
return cls(**options)
else:
raise ClassNotFound('filter %r not found' % filtername)
```
###Assistant : Return an instantiated filter.
Options are passed to the filter initializer if wanted.
Raise a ClassNotFound if not found.
|
628 | def wide_resnet50_2(pretrained=False, **kwargs):
kwargs['width'] = 64 * 2
return _resnet('wide_resnet50_2', BottleneckBlock, 50, pretrained, **kwargs)
| Wide ResNet-50-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
Examples:
.. code-block:: python
import paddle
from paddle.vision.models import wide_resnet50_2
# build model
model = wide_resnet50_2()
# build model and load imagenet pretrained weight
# model = wide_resnet50_2(pretrained=True)
x = paddle.rand([1, 3, 224, 224])
out = model(x)
print(out.shape)
| 57 | 14 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def wide_resnet50_2(pretrained=False, **kwargs):
kwargs['width'] = 64 * 2
return _resnet('wide_resnet50_2', BottleneckBlock, 50, pretrained, **kwargs)
```
###Assistant : Wide ResNet-50-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
Examples:
.. code-block:: python
import paddle
from paddle.vision.models import wide_resnet50_2
# build model
model = wide_resnet50_2()
# build model and load imagenet pretrained weight
# model = wide_resnet50_2(pretrained=True)
x = paddle.rand([1, 3, 224, 224])
out = model(x)
print(out.shape)
|
629 | def test_username_available(self) -> None:
url = "%s?username=%s" % (self.url, "allowed")
channel = self.make_request("GET", url, access_token=self.admin_user_tok)
self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body)
self.assertTrue(channel.json_body["available"])
|
The endpoint should return a HTTPStatus.OK response if the username does not exist
| 13 | 19 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_username_available(self) -> None:
url = "%s?username=%s" % (self.url, "allowed")
channel = self.make_request("GET", url, access_token=self.admin_user_tok)
self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body)
self.assertTrue(channel.json_body["available"])
```
###Assistant :
The endpoint should return a HTTPStatus.OK response if the username does not exist
|
630 | def test_with_include_glob_filtering_case4a_include_strong():
incl_dom = {}
incl_glob = {"*working"}
incl_ent = {"binary_sensor.specificly_included"}
excl_dom = {}
excl_glob = {"*broken", "*notworking", "binary_sensor.*"}
excl_ent = {"light.ignoreme"}
testfilter = generate_filter(
incl_dom, incl_ent, excl_dom, excl_ent, incl_glob, excl_glob
)
assert testfilter("sensor.working") is True
assert testfilter("sensor.notworking") is True # include is stronger
assert testfilter("sensor.broken") is False
assert testfilter("light.test") is False
assert testfilter("light.notworking") is True # include is stronger
assert testfilter("light.ignoreme") is False
assert testfilter("binary_sensor.not_working") is True # include is stronger
assert testfilter("binary_sensor.another") is False
assert testfilter("binary_sensor.specificly_included") is True
assert testfilter("sun.sun") is False
| Test case 4 - include and exclude specified, both have globs, and a specifically included entity. | 16 | 84 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_with_include_glob_filtering_case4a_include_strong():
incl_dom = {}
incl_glob = {"*working"}
incl_ent = {"binary_sensor.specificly_included"}
excl_dom = {}
excl_glob = {"*broken", "*notworking", "binary_sensor.*"}
excl_ent = {"light.ignoreme"}
testfilter = generate_filter(
incl_dom, incl_ent, excl_dom, excl_ent, incl_glob, excl_glob
)
assert testfilter("sensor.working") is True
assert testfilter("sensor.notworking") is True # include is stronger
assert testfilter("sensor.broken") is False
assert testfilter("light.test") is False
assert testfilter("light.notworking") is True # include is stronger
assert testfilter("light.ignoreme") is False
assert testfilter("binary_sensor.not_working") is True # include is stronger
assert testfilter("binary_sensor.another") is False
assert testfilter("binary_sensor.specificly_included") is True
assert testfilter("sun.sun") is False
```
###Assistant : Test case 4 - include and exclude specified, both have globs, and a specifically included entity.
|
631 | def get_sales_orders(self):
so_filter = item_filter = ""
bom_item = "bom.item = so_item.item_code"
date_field_mapper = {
"from_date": (">=", "so.transaction_date"),
"to_date": ("<=", "so.transaction_date"),
"from_delivery_date": (">=", "so_item.delivery_date"),
"to_delivery_date": ("<=", "so_item.delivery_date"),
}
for field, value in date_field_mapper.items():
if self.get(field):
so_filter += f" and {value[1]} {value[0]} %({field})s"
for field in ["customer", "project", "sales_order_status"]:
if self.get(field):
so_field = "status" if field == "sales_order_status" else field
so_filter += f" and so.{so_field} = %({field})s"
if self.item_code and frappe.db.exists("Item", self.item_code):
bom_item = self.get_bom_item() or bom_item
item_filter += " and so_item.item_code = %(item_code)s"
open_so = frappe.db.sql(
f,
self.as_dict(),
as_dict=1,
)
return open_so
@frappe.whitelist() |
select distinct so.name, so.transaction_date, so.customer, so.base_grand_total
from `tabSales Order` so, `tabSales Order Item` so_item
where so_item.parent = so.name
and so.docstatus = 1 and so.status not in ("Stopped", "Closed")
and so.company = %(company)s
and so_item.qty > so_item.work_order_qty {so_filter} {item_filter}
and (exists (select name from `tabBOM` bom where {bom_item}
and bom.is_active = 1)
or exists (select name from `tabPacked Item` pi
where pi.parent = so.name and pi.parent_item = so_item.item_code
and exists (select name from `tabBOM` bom where bom.item=pi.item_code
and bom.is_active = 1)))
| 80 | 93 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_sales_orders(self):
so_filter = item_filter = ""
bom_item = "bom.item = so_item.item_code"
date_field_mapper = {
"from_date": (">=", "so.transaction_date"),
"to_date": ("<=", "so.transaction_date"),
"from_delivery_date": (">=", "so_item.delivery_date"),
"to_delivery_date": ("<=", "so_item.delivery_date"),
}
for field, value in date_field_mapper.items():
if self.get(field):
so_filter += f" and {value[1]} {value[0]} %({field})s"
for field in ["customer", "project", "sales_order_status"]:
if self.get(field):
so_field = "status" if field == "sales_order_status" else field
so_filter += f" and so.{so_field} = %({field})s"
if self.item_code and frappe.db.exists("Item", self.item_code):
bom_item = self.get_bom_item() or bom_item
item_filter += " and so_item.item_code = %(item_code)s"
open_so = frappe.db.sql(
f,
self.as_dict(),
as_dict=1,
)
return open_so
@frappe.whitelist()
```
###Assistant :
select distinct so.name, so.transaction_date, so.customer, so.base_grand_total
from `tabSales Order` so, `tabSales Order Item` so_item
where so_item.parent = so.name
and so.docstatus = 1 and so.status not in ("Stopped", "Closed")
and so.company = %(company)s
and so_item.qty > so_item.work_order_qty {so_filter} {item_filter}
and (exists (select name from `tabBOM` bom where {bom_item}
and bom.is_active = 1)
or exists (select name from `tabPacked Item` pi
where pi.parent = so.name and pi.parent_item = so_item.item_code
and exists (select name from `tabBOM` bom where bom.item=pi.item_code
and bom.is_active = 1)))
|
632 | def test_copy_published_emits_signal(self):
christmas_page = EventPage.objects.get(url_path="/home/events/christmas/")
signal_fired = False
signal_page = None
| Test that copying of a published page emits a page_published signal. | 11 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_copy_published_emits_signal(self):
christmas_page = EventPage.objects.get(url_path="/home/events/christmas/")
signal_fired = False
signal_page = None
```
###Assistant : Test that copying of a published page emits a page_published signal.
|
633 | def get_all_tests():
test_root_dir = os.path.join(PATH_TO_TRANFORMERS, "tests")
# test folders/files directly under `tests` folder
tests = os.listdir(test_root_dir)
tests = sorted(
list(filter(lambda x: os.path.isdir(x) or x.startswith("tests/test_"), [f"tests/{x}" for x in tests]))
)
# model specific test folders
model_tests_folders = os.listdir(os.path.join(test_root_dir, "models"))
model_test_folders = sorted(list(filter(os.path.isdir, [f"tests/models/{x}" for x in model_tests_folders])))
tests.remove("tests/models")
tests = model_test_folders + tests
return tests
|
Return a list of paths to all test folders and files under `tests`. All paths are rooted at `tests`.
- folders under `tests`: `tokenization`, `pipelines`, etc. The folder `models` is excluded.
- folders under `tests/models`: `bert`, `gpt2`, etc.
- test files under `tests`: `test_modeling_common.py`, `test_tokenization_common.py`, etc.
| 46 | 55 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_all_tests():
test_root_dir = os.path.join(PATH_TO_TRANFORMERS, "tests")
# test folders/files directly under `tests` folder
tests = os.listdir(test_root_dir)
tests = sorted(
list(filter(lambda x: os.path.isdir(x) or x.startswith("tests/test_"), [f"tests/{x}" for x in tests]))
)
# model specific test folders
model_tests_folders = os.listdir(os.path.join(test_root_dir, "models"))
model_test_folders = sorted(list(filter(os.path.isdir, [f"tests/models/{x}" for x in model_tests_folders])))
tests.remove("tests/models")
tests = model_test_folders + tests
return tests
```
###Assistant :
Return a list of paths to all test folders and files under `tests`. All paths are rooted at `tests`.
- folders under `tests`: `tokenization`, `pipelines`, etc. The folder `models` is excluded.
- folders under `tests/models`: `bert`, `gpt2`, etc.
- test files under `tests`: `test_modeling_common.py`, `test_tokenization_common.py`, etc.
|
634 | def test_vtrace(self):
seq_len = 5
batch_size = 10
# Create log_rhos such that rho will span from near-zero to above the
# clipping thresholds. In particular, calculate log_rhos in
# [-2.5, 2.5),
# so that rho is in approx [0.08, 12.2).
space_w_time = Box(-1.0, 1.0, (seq_len, batch_size), np.float32)
space_only_batch = Box(-1.0, 1.0, (batch_size,), np.float32)
log_rhos = space_w_time.sample() / (batch_size * seq_len)
log_rhos = 5 * (log_rhos - 0.5) # [0.0, 1.0) -> [-2.5, 2.5).
values = {
"log_rhos": log_rhos,
# T, B where B_i: [0.9 / (i+1)] * T
"discounts": np.array(
[[0.9 / (b + 1) for b in range(batch_size)] for _ in range(seq_len)]
),
"rewards": space_w_time.sample(),
"values": space_w_time.sample() / batch_size,
"bootstrap_value": space_only_batch.sample() + 1.0,
"clip_rho_threshold": 3.7,
"clip_pg_rho_threshold": 2.2,
}
for fw, sess in framework_iterator(frameworks=("torch", "tf"), session=True):
vtrace = vtrace_tf if fw != "torch" else vtrace_torch
output = vtrace.from_importance_weights(**values)
if sess:
output = sess.run(output)
ground_truth_v = _ground_truth_calculation(vtrace, **values)
check(output, ground_truth_v)
| Tests V-trace against ground truth data calculated in python. | 9 | 150 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_vtrace(self):
seq_len = 5
batch_size = 10
# Create log_rhos such that rho will span from near-zero to above the
# clipping thresholds. In particular, calculate log_rhos in
# [-2.5, 2.5),
# so that rho is in approx [0.08, 12.2).
space_w_time = Box(-1.0, 1.0, (seq_len, batch_size), np.float32)
space_only_batch = Box(-1.0, 1.0, (batch_size,), np.float32)
log_rhos = space_w_time.sample() / (batch_size * seq_len)
log_rhos = 5 * (log_rhos - 0.5) # [0.0, 1.0) -> [-2.5, 2.5).
values = {
"log_rhos": log_rhos,
# T, B where B_i: [0.9 / (i+1)] * T
"discounts": np.array(
[[0.9 / (b + 1) for b in range(batch_size)] for _ in range(seq_len)]
),
"rewards": space_w_time.sample(),
"values": space_w_time.sample() / batch_size,
"bootstrap_value": space_only_batch.sample() + 1.0,
"clip_rho_threshold": 3.7,
"clip_pg_rho_threshold": 2.2,
}
for fw, sess in framework_iterator(frameworks=("torch", "tf"), session=True):
vtrace = vtrace_tf if fw != "torch" else vtrace_torch
output = vtrace.from_importance_weights(**values)
if sess:
output = sess.run(output)
ground_truth_v = _ground_truth_calculation(vtrace, **values)
check(output, ground_truth_v)
```
###Assistant : Tests V-trace against ground truth data calculated in python.
|
635 | def pdfdump(self, filename=None, **kargs):
# type: (Optional[str], **Any) -> None
from scapy.config import conf
from scapy.utils import get_temp_file, ContextManagerSubprocess
canvas = self.canvas_dump(**kargs)
if filename is None:
fname = get_temp_file(autoext=kargs.get("suffix", ".pdf"))
canvas.writePDFfile(fname)
if WINDOWS and not conf.prog.pdfreader:
os.startfile(fname)
else:
with ContextManagerSubprocess(conf.prog.pdfreader):
subprocess.Popen([conf.prog.pdfreader, fname])
else:
canvas.writePDFfile(filename)
print()
|
pdfdump(filename=None, layer_shift=0, rebuild=1)
Creates a PDF file describing a packet. If filename is not provided a
temporary file is created and xpdf is called.
:param filename: the file's filename
| 29 | 45 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def pdfdump(self, filename=None, **kargs):
# type: (Optional[str], **Any) -> None
from scapy.config import conf
from scapy.utils import get_temp_file, ContextManagerSubprocess
canvas = self.canvas_dump(**kargs)
if filename is None:
fname = get_temp_file(autoext=kargs.get("suffix", ".pdf"))
canvas.writePDFfile(fname)
if WINDOWS and not conf.prog.pdfreader:
os.startfile(fname)
else:
with ContextManagerSubprocess(conf.prog.pdfreader):
subprocess.Popen([conf.prog.pdfreader, fname])
else:
canvas.writePDFfile(filename)
print()
```
###Assistant :
pdfdump(filename=None, layer_shift=0, rebuild=1)
Creates a PDF file describing a packet. If filename is not provided a
temporary file is created and xpdf is called.
:param filename: the file's filename
|
636 | def index_sample(x, index):
x_s = x.shape
dim = len(index.shape) - 1
assert x_s[:dim] == index.shape[:dim]
if len(x_s) == 3 and dim == 1:
r_x = paddle.reshape(x, shape=[-1, x_s[1], x_s[-1]])
else:
r_x = paddle.reshape(x, shape=[-1, x_s[-1]])
index = paddle.reshape(index, shape=[len(r_x), -1, 1])
# Generate arange index, shape like index
arr_index = paddle.arange(start=0, end=len(index), dtype=index.dtype)
arr_index = paddle.unsqueeze(arr_index, axis=[1, 2])
arr_index = paddle.expand(arr_index, index.shape)
# Genrate new index
new_index = paddle.concat((arr_index, index), -1)
new_index = paddle.reshape(new_index, (-1, 2))
# Get output
out = paddle.gather_nd(r_x, new_index)
if len(x_s) == 3 and dim == 2:
out = paddle.reshape(out, shape=[x_s[0], x_s[1], -1])
else:
out = paddle.reshape(out, shape=[x_s[0], -1])
return out
|
Select input value according to index
Arags:
input: input matrix
index: index matrix
Returns:
output
>>> input
[
[1, 2, 3],
[4, 5, 6]
]
>>> index
[
[1, 2],
[0, 1]
]
>>> index_sample(input, index)
[
[2, 3],
[4, 5]
]
| 42 | 105 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def index_sample(x, index):
x_s = x.shape
dim = len(index.shape) - 1
assert x_s[:dim] == index.shape[:dim]
if len(x_s) == 3 and dim == 1:
r_x = paddle.reshape(x, shape=[-1, x_s[1], x_s[-1]])
else:
r_x = paddle.reshape(x, shape=[-1, x_s[-1]])
index = paddle.reshape(index, shape=[len(r_x), -1, 1])
# Generate arange index, shape like index
arr_index = paddle.arange(start=0, end=len(index), dtype=index.dtype)
arr_index = paddle.unsqueeze(arr_index, axis=[1, 2])
arr_index = paddle.expand(arr_index, index.shape)
# Genrate new index
new_index = paddle.concat((arr_index, index), -1)
new_index = paddle.reshape(new_index, (-1, 2))
# Get output
out = paddle.gather_nd(r_x, new_index)
if len(x_s) == 3 and dim == 2:
out = paddle.reshape(out, shape=[x_s[0], x_s[1], -1])
else:
out = paddle.reshape(out, shape=[x_s[0], -1])
return out
```
###Assistant :
Select input value according to index
Arags:
input: input matrix
index: index matrix
Returns:
output
>>> input
[
[1, 2, 3],
[4, 5, 6]
]
>>> index
[
[1, 2],
[0, 1]
]
>>> index_sample(input, index)
[
[2, 3],
[4, 5]
]
|
637 | def __new__(cls, name, patch, symbols=None, relations={}, **kwargs):
if not isinstance(name, Str):
name = Str(name)
# canonicallize the symbols
if symbols is None:
names = kwargs.get('names', None)
if names is None:
symbols = Tuple(
*[Symbol('%s_%s' % (name.name, i), real=True)
for i in range(patch.dim)]
)
else:
sympy_deprecation_warning(
f,
deprecated_since_version="1.7",
active_deprecations_target="deprecated-diffgeom-mutable",
)
symbols = Tuple(
*[Symbol(n, real=True) for n in names]
)
else:
syms = []
for s in symbols:
if isinstance(s, Symbol):
syms.append(Symbol(s.name, **s._assumptions.generator))
elif isinstance(s, str):
sympy_deprecation_warning(
f,
deprecated_since_version="1.7",
active_deprecations_target="deprecated-diffgeom-mutable",
)
syms.append(Symbol(s, real=True))
symbols = Tuple(*syms)
# canonicallize the relations
rel_temp = {}
for k,v in relations.items():
s1, s2 = k
if not isinstance(s1, Str):
s1 = Str(s1)
if not isinstance(s2, Str):
s2 = Str(s2)
key = Tuple(s1, s2)
# Old version used Lambda as a value.
if isinstance(v, Lambda):
v = (tuple(v.signature), tuple(v.expr))
else:
v = (tuple(v[0]), tuple(v[1]))
rel_temp[key] = v
relations = Dict(rel_temp)
# construct the object
obj = super().__new__(cls, name, patch, symbols, relations)
# Add deprecated attributes
obj.transforms = _deprecated_dict(
, {})
obj._names = [str(n) for n in symbols]
obj.patch.coord_systems.append(obj) # deprecated
obj._dummies = [Dummy(str(n)) for n in symbols] # deprecated
obj._dummy = Dummy()
return obj
|
The 'names' argument to CoordSystem is deprecated. Use 'symbols' instead. That
is, replace
CoordSystem(..., names={names})
with
CoordSystem(..., symbols=[{', '.join(["Symbol(" + repr(n) + ", real=True)" for n in names])}])
Passing a string as the coordinate symbol name to CoordSystem is deprecated.
Pass a Symbol with the appropriate name and assumptions instead.
That is, replace {s} with Symbol({s!r}, real=True).
CoordSystem.transforms is deprecated. The CoordSystem class is now
immutable. Use the 'relations' keyword argument to the
CoordSystems() constructor to specify relations.
| 78 | 188 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def __new__(cls, name, patch, symbols=None, relations={}, **kwargs):
if not isinstance(name, Str):
name = Str(name)
# canonicallize the symbols
if symbols is None:
names = kwargs.get('names', None)
if names is None:
symbols = Tuple(
*[Symbol('%s_%s' % (name.name, i), real=True)
for i in range(patch.dim)]
)
else:
sympy_deprecation_warning(
f,
deprecated_since_version="1.7",
active_deprecations_target="deprecated-diffgeom-mutable",
)
symbols = Tuple(
*[Symbol(n, real=True) for n in names]
)
else:
syms = []
for s in symbols:
if isinstance(s, Symbol):
syms.append(Symbol(s.name, **s._assumptions.generator))
elif isinstance(s, str):
sympy_deprecation_warning(
f,
deprecated_since_version="1.7",
active_deprecations_target="deprecated-diffgeom-mutable",
)
syms.append(Symbol(s, real=True))
symbols = Tuple(*syms)
# canonicallize the relations
rel_temp = {}
for k,v in relations.items():
s1, s2 = k
if not isinstance(s1, Str):
s1 = Str(s1)
if not isinstance(s2, Str):
s2 = Str(s2)
key = Tuple(s1, s2)
# Old version used Lambda as a value.
if isinstance(v, Lambda):
v = (tuple(v.signature), tuple(v.expr))
else:
v = (tuple(v[0]), tuple(v[1]))
rel_temp[key] = v
relations = Dict(rel_temp)
# construct the object
obj = super().__new__(cls, name, patch, symbols, relations)
# Add deprecated attributes
obj.transforms = _deprecated_dict(
, {})
obj._names = [str(n) for n in symbols]
obj.patch.coord_systems.append(obj) # deprecated
obj._dummies = [Dummy(str(n)) for n in symbols] # deprecated
obj._dummy = Dummy()
return obj
```
###Assistant :
The 'names' argument to CoordSystem is deprecated. Use 'symbols' instead. That
is, replace
CoordSystem(..., names={names})
with
CoordSystem(..., symbols=[{', '.join(["Symbol(" + repr(n) + ", real=True)" for n in names])}])
Passing a string as the coordinate symbol name to CoordSystem is deprecated.
Pass a Symbol with the appropriate name and assumptions instead.
That is, replace {s} with Symbol({s!r}, real=True).
CoordSystem.transforms is deprecated. The CoordSystem class is now
immutable. Use the 'relations' keyword argument to the
CoordSystems() constructor to specify relations.
|
638 | def tab_focus(*, info):
model = _tabs(win_id_filter=lambda win_id: win_id == info.win_id,
add_win_id=False, current_win_id=info.win_id)
special = [
("last", "Focus the last-focused tab"),
("stack-next", "Go forward through a stack of focused tabs"),
("stack-prev", "Go backward through a stack of focused tabs"),
]
model.add_category(listcategory.ListCategory("Special", special))
return model
| A model to complete on open tabs in the current window. | 11 | 43 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def tab_focus(*, info):
model = _tabs(win_id_filter=lambda win_id: win_id == info.win_id,
add_win_id=False, current_win_id=info.win_id)
special = [
("last", "Focus the last-focused tab"),
("stack-next", "Go forward through a stack of focused tabs"),
("stack-prev", "Go backward through a stack of focused tabs"),
]
model.add_category(listcategory.ListCategory("Special", special))
return model
```
###Assistant : A model to complete on open tabs in the current window.
|
639 | def get_mode_of_payment_details(filters):
mode_of_payment_details = {}
invoice_list = get_invoices(filters)
invoice_list_names = ",".join("'" + invoice["name"] + "'" for invoice in invoice_list)
if invoice_list:
inv_mop_detail = frappe.db.sql(
.format(
invoice_list_names=invoice_list_names
),
as_dict=1,
)
inv_change_amount = frappe.db.sql(
.format(
invoice_list_names=invoice_list_names
),
as_dict=1,
)
for d in inv_change_amount:
for det in inv_mop_detail:
if (
det["owner"] == d["owner"]
and det["posting_date"] == d["posting_date"]
and det["mode_of_payment"] == d["mode_of_payment"]
):
paid_amount = det["paid_amount"] - d["change_amount"]
det["paid_amount"] = paid_amount
for d in inv_mop_detail:
mode_of_payment_details.setdefault(d["owner"] + cstr(d["posting_date"]), []).append(
(d.mode_of_payment, d.paid_amount)
)
return mode_of_payment_details
|
select t.owner,
t.posting_date,
t.mode_of_payment,
sum(t.paid_amount) as paid_amount
from (
select a.owner, a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(b.base_amount) as paid_amount
from `tabSales Invoice` a, `tabSales Invoice Payment` b
where a.name = b.parent
and a.docstatus = 1
and a.name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
union
select a.owner,a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(c.allocated_amount) as paid_amount
from `tabSales Invoice` a, `tabPayment Entry` b,`tabPayment Entry Reference` c
where a.name = c.reference_name
and b.name = c.parent
and b.docstatus = 1
and a.name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
union
select a.owner, a.posting_date,
ifnull(a.voucher_type,'') as mode_of_payment, sum(b.credit)
from `tabJournal Entry` a, `tabJournal Entry Account` b
where a.name = b.parent
and a.docstatus = 1
and b.reference_type = 'Sales Invoice'
and b.reference_name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
) t
group by t.owner, t.posting_date, t.mode_of_payment
select a.owner, a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(a.base_change_amount) as change_amount
from `tabSales Invoice` a, `tabSales Invoice Payment` b
where a.name = b.parent
and a.name in ({invoice_list_names})
and b.type = 'Cash'
and a.base_change_amount > 0
group by a.owner, a.posting_date, mode_of_payment | 169 | 80 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_mode_of_payment_details(filters):
mode_of_payment_details = {}
invoice_list = get_invoices(filters)
invoice_list_names = ",".join("'" + invoice["name"] + "'" for invoice in invoice_list)
if invoice_list:
inv_mop_detail = frappe.db.sql(
.format(
invoice_list_names=invoice_list_names
),
as_dict=1,
)
inv_change_amount = frappe.db.sql(
.format(
invoice_list_names=invoice_list_names
),
as_dict=1,
)
for d in inv_change_amount:
for det in inv_mop_detail:
if (
det["owner"] == d["owner"]
and det["posting_date"] == d["posting_date"]
and det["mode_of_payment"] == d["mode_of_payment"]
):
paid_amount = det["paid_amount"] - d["change_amount"]
det["paid_amount"] = paid_amount
for d in inv_mop_detail:
mode_of_payment_details.setdefault(d["owner"] + cstr(d["posting_date"]), []).append(
(d.mode_of_payment, d.paid_amount)
)
return mode_of_payment_details
```
###Assistant :
select t.owner,
t.posting_date,
t.mode_of_payment,
sum(t.paid_amount) as paid_amount
from (
select a.owner, a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(b.base_amount) as paid_amount
from `tabSales Invoice` a, `tabSales Invoice Payment` b
where a.name = b.parent
and a.docstatus = 1
and a.name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
union
select a.owner,a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(c.allocated_amount) as paid_amount
from `tabSales Invoice` a, `tabPayment Entry` b,`tabPayment Entry Reference` c
where a.name = c.reference_name
and b.name = c.parent
and b.docstatus = 1
and a.name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
union
select a.owner, a.posting_date,
ifnull(a.voucher_type,'') as mode_of_payment, sum(b.credit)
from `tabJournal Entry` a, `tabJournal Entry Account` b
where a.name = b.parent
and a.docstatus = 1
and b.reference_type = 'Sales Invoice'
and b.reference_name in ({invoice_list_names})
group by a.owner, a.posting_date, mode_of_payment
) t
group by t.owner, t.posting_date, t.mode_of_payment
select a.owner, a.posting_date,
ifnull(b.mode_of_payment, '') as mode_of_payment, sum(a.base_change_amount) as change_amount
from `tabSales Invoice` a, `tabSales Invoice Payment` b
where a.name = b.parent
and a.name in ({invoice_list_names})
and b.type = 'Cash'
and a.base_change_amount > 0
group by a.owner, a.posting_date, mode_of_payment
|
640 | def get_config_context(self):
data = {}
if not hasattr(self, 'config_context_data'):
# The annotation is not available, so we fall back to manually querying for the config context objects
config_context_data = ConfigContext.objects.get_for_object(self, aggregate_data=True)
else:
# The attribute may exist, but the annotated value could be None if there is no config context data
config_context_data = self.config_context_data or []
for context in config_context_data:
data = deepmerge(data, context)
# If the object has local config context data defined, merge it last
if self.local_context_data:
data = deepmerge(data, self.local_context_data)
return data
|
Compile all config data, overwriting lower-weight values with higher-weight values where a collision occurs.
Return the rendered configuration context for a device or VM.
| 24 | 85 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_config_context(self):
data = {}
if not hasattr(self, 'config_context_data'):
# The annotation is not available, so we fall back to manually querying for the config context objects
config_context_data = ConfigContext.objects.get_for_object(self, aggregate_data=True)
else:
# The attribute may exist, but the annotated value could be None if there is no config context data
config_context_data = self.config_context_data or []
for context in config_context_data:
data = deepmerge(data, context)
# If the object has local config context data defined, merge it last
if self.local_context_data:
data = deepmerge(data, self.local_context_data)
return data
```
###Assistant :
Compile all config data, overwriting lower-weight values with higher-weight values where a collision occurs.
Return the rendered configuration context for a device or VM.
|
641 | def test_displayname_is_set_avatar_is_none(self) -> None:
channel = self.make_request(
"POST",
self.url,
access_token=self.admin_user_tok,
content={
"user_id": self.other_user,
"content": {"msgtype": "m.text", "body": "test msg"},
},
)
self.assertEqual(200, channel.code, msg=channel.json_body)
# user has one invite
self._check_invite_and_join_status(self.other_user, 1, 0)
|
Tests that sending a server notices is successfully,
if a display_name is set, avatar_url is `None` and
"check avatar size and mime type" is set.
| 25 | 32 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_displayname_is_set_avatar_is_none(self) -> None:
channel = self.make_request(
"POST",
self.url,
access_token=self.admin_user_tok,
content={
"user_id": self.other_user,
"content": {"msgtype": "m.text", "body": "test msg"},
},
)
self.assertEqual(200, channel.code, msg=channel.json_body)
# user has one invite
self._check_invite_and_join_status(self.other_user, 1, 0)
```
###Assistant :
Tests that sending a server notices is successfully,
if a display_name is set, avatar_url is `None` and
"check avatar size and mime type" is set.
|
642 | def cur_iter_done(self) -> bool:
return all(
self._get_result_time(result) >= self._cumul_r
for result in self._live_trials.values()
)
| Checks if all iterations have completed.
TODO(rliaw): also check that `t.iterations == self._r` | 13 | 14 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def cur_iter_done(self) -> bool:
return all(
self._get_result_time(result) >= self._cumul_r
for result in self._live_trials.values()
)
```
###Assistant : Checks if all iterations have completed.
TODO(rliaw): also check that `t.iterations == self._r`
|
643 | def get_attendance_years():
year_list = frappe.db.sql_list(
)
if not year_list:
year_list = [getdate().year]
return "\n".join(str(year) for year in year_list)
| select distinct YEAR(date) from `tabStudent Attendance` ORDER BY YEAR(date) DESC | 10 | 18 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_attendance_years():
year_list = frappe.db.sql_list(
)
if not year_list:
year_list = [getdate().year]
return "\n".join(str(year) for year in year_list)
```
###Assistant : select distinct YEAR(date) from `tabStudent Attendance` ORDER BY YEAR(date) DESC
|
644 | async def test_discovery_notification(hass):
mock_integration(hass, MockModule("test"))
mock_entity_platform(hass, "config_flow.test", None)
with patch.dict(config_entries.HANDLERS):
| Test that we create/dismiss a notification when source is discovery. | 10 | 10 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def test_discovery_notification(hass):
mock_integration(hass, MockModule("test"))
mock_entity_platform(hass, "config_flow.test", None)
with patch.dict(config_entries.HANDLERS):
```
###Assistant : Test that we create/dismiss a notification when source is discovery.
|
645 | def get_preference(self, identifier, resolutions, candidates, information):
raise NotImplementedError
| Produce a sort key for given requirement based on preference.
The preference is defined as "I think this requirement should be
resolved first". The lower the return value is, the more preferred
this group of arguments is.
:param identifier: An identifier as returned by ``identify()``. This
identifies the dependency matches of which should be returned.
:param resolutions: Mapping of candidates currently pinned by the
resolver. Each key is an identifier, and the value a candidate.
The candidate may conflict with requirements from ``information``.
:param candidates: Mapping of each dependency's possible candidates.
Each value is an iterator of candidates.
:param information: Mapping of requirement information of each package.
Each value is an iterator of *requirement information*.
A *requirement information* instance is a named tuple with two members:
* ``requirement`` specifies a requirement contributing to the current
list of candidates.
* ``parent`` specifies the candidate that provides (dependend on) the
requirement, or ``None`` to indicate a root requirement.
The preference could depend on a various of issues, including (not
necessarily in this order):
* Is this package pinned in the current resolution result?
* How relaxed is the requirement? Stricter ones should probably be
worked on first? (I don't know, actually.)
* How many possibilities are there to satisfy this requirement? Those
with few left should likely be worked on first, I guess?
* Are there any known conflicts for this requirement? We should
probably work on those with the most known conflicts.
A sortable value should be returned (this will be used as the ``key``
parameter of the built-in sorting function). The smaller the value is,
the more preferred this requirement is (i.e. the sorting function
is called with ``reverse=False``).
| 279 | 8 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_preference(self, identifier, resolutions, candidates, information):
raise NotImplementedError
```
###Assistant : Produce a sort key for given requirement based on preference.
The preference is defined as "I think this requirement should be
resolved first". The lower the return value is, the more preferred
this group of arguments is.
:param identifier: An identifier as returned by ``identify()``. This
identifies the dependency matches of which should be returned.
:param resolutions: Mapping of candidates currently pinned by the
resolver. Each key is an identifier, and the value a candidate.
The candidate may conflict with requirements from ``information``.
:param candidates: Mapping of each dependency's possible candidates.
Each value is an iterator of candidates.
:param information: Mapping of requirement information of each package.
Each value is an iterator of *requirement information*.
A *requirement information* instance is a named tuple with two members:
* ``requirement`` specifies a requirement contributing to the current
list of candidates.
* ``parent`` specifies the candidate that provides (dependend on) the
requirement, or ``None`` to indicate a root requirement.
The preference could depend on a various of issues, including (not
necessarily in this order):
* Is this package pinned in the current resolution result?
* How relaxed is the requirement? Stricter ones should probably be
worked on first? (I don't know, actually.)
* How many possibilities are there to satisfy this requirement? Those
with few left should likely be worked on first, I guess?
* Are there any known conflicts for this requirement? We should
probably work on those with the most known conflicts.
A sortable value should be returned (this will be used as the ``key``
parameter of the built-in sorting function). The smaller the value is,
the more preferred this requirement is (i.e. the sorting function
is called with ``reverse=False``).
|
646 | def prepare_metadata(self) -> None:
assert self.source_dir
details = self.name or f"from {self.link}"
if self.use_pep517:
assert self.pep517_backend is not None
if (
self.editable
and self.permit_editable_wheels
and self.supports_pyproject_editable()
):
self.metadata_directory = generate_editable_metadata(
build_env=self.build_env,
backend=self.pep517_backend,
details=details,
)
else:
self.metadata_directory = generate_metadata(
build_env=self.build_env,
backend=self.pep517_backend,
details=details,
)
else:
self.metadata_directory = generate_metadata_legacy(
build_env=self.build_env,
setup_py_path=self.setup_py_path,
source_dir=self.unpacked_source_directory,
isolated=self.isolated,
details=details,
)
# Act on the newly generated metadata, based on the name and version.
if not self.name:
self._set_requirement()
else:
self.warn_on_mismatching_name()
self.assert_source_matches_version()
| Ensure that project metadata is available.
Under PEP 517 and PEP 660, call the backend hook to prepare the metadata.
Under legacy processing, call setup.py egg-info.
| 26 | 72 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def prepare_metadata(self) -> None:
assert self.source_dir
details = self.name or f"from {self.link}"
if self.use_pep517:
assert self.pep517_backend is not None
if (
self.editable
and self.permit_editable_wheels
and self.supports_pyproject_editable()
):
self.metadata_directory = generate_editable_metadata(
build_env=self.build_env,
backend=self.pep517_backend,
details=details,
)
else:
self.metadata_directory = generate_metadata(
build_env=self.build_env,
backend=self.pep517_backend,
details=details,
)
else:
self.metadata_directory = generate_metadata_legacy(
build_env=self.build_env,
setup_py_path=self.setup_py_path,
source_dir=self.unpacked_source_directory,
isolated=self.isolated,
details=details,
)
# Act on the newly generated metadata, based on the name and version.
if not self.name:
self._set_requirement()
else:
self.warn_on_mismatching_name()
self.assert_source_matches_version()
```
###Assistant : Ensure that project metadata is available.
Under PEP 517 and PEP 660, call the backend hook to prepare the metadata.
Under legacy processing, call setup.py egg-info.
|
647 | def get_image_filename(self, image, filterspec):
name, ext = os.path.splitext(os.path.basename(image.file.name))
return "{}images/{}.{}{}".format(settings.MEDIA_URL, name, filterspec, ext)
|
Get the generated filename for a resized image
| 8 | 13 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_image_filename(self, image, filterspec):
name, ext = os.path.splitext(os.path.basename(image.file.name))
return "{}images/{}.{}{}".format(settings.MEDIA_URL, name, filterspec, ext)
```
###Assistant :
Get the generated filename for a resized image
|
648 | def min(self, other, context=None):
other = _convert_other(other, raiseit=True)
if context is None:
context = getcontext()
if self._is_special or other._is_special:
# If one operand is a quiet NaN and the other is number, then the
# number is always returned
sn = self._isnan()
on = other._isnan()
if sn or on:
if on == 1 and sn == 0:
return self._fix(context)
if sn == 1 and on == 0:
return other._fix(context)
return self._check_nans(other, context)
c = self._cmp(other)
if c == 0:
c = self.compare_total(other)
if c == -1:
ans = self
else:
ans = other
return ans._fix(context)
| Returns the smaller value.
Like min(self, other) except if one is not a number, returns
NaN (and signals if one is sNaN). Also rounds.
| 24 | 95 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def min(self, other, context=None):
other = _convert_other(other, raiseit=True)
if context is None:
context = getcontext()
if self._is_special or other._is_special:
# If one operand is a quiet NaN and the other is number, then the
# number is always returned
sn = self._isnan()
on = other._isnan()
if sn or on:
if on == 1 and sn == 0:
return self._fix(context)
if sn == 1 and on == 0:
return other._fix(context)
return self._check_nans(other, context)
c = self._cmp(other)
if c == 0:
c = self.compare_total(other)
if c == -1:
ans = self
else:
ans = other
return ans._fix(context)
```
###Assistant : Returns the smaller value.
Like min(self, other) except if one is not a number, returns
NaN (and signals if one is sNaN). Also rounds.
|
649 | def test_simplelistfilter_with_none_returning_lookups(self):
modeladmin = DecadeFilterBookAdminWithNoneReturningLookups(Book, site)
request = self.request_factory.get("/", {})
request.user = self.alfred
changelist = modeladmin.get_changelist_instance(request)
filterspec = changelist.get_filters(request)[0]
self.assertEqual(len(filterspec), 0)
|
A SimpleListFilter lookups method can return None but disables the
filter completely.
| 12 | 21 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_simplelistfilter_with_none_returning_lookups(self):
modeladmin = DecadeFilterBookAdminWithNoneReturningLookups(Book, site)
request = self.request_factory.get("/", {})
request.user = self.alfred
changelist = modeladmin.get_changelist_instance(request)
filterspec = changelist.get_filters(request)[0]
self.assertEqual(len(filterspec), 0)
```
###Assistant :
A SimpleListFilter lookups method can return None but disables the
filter completely.
|
650 | def precompute_fill_value(dataset_cols, feature, preprocessing_parameters, backend):
missing_value_strategy = preprocessing_parameters["missing_value_strategy"]
if missing_value_strategy == FILL_WITH_CONST:
return preprocessing_parameters["fill_value"]
elif missing_value_strategy == FILL_WITH_MODE:
return dataset_cols[feature[COLUMN]].value_counts().index[0]
elif missing_value_strategy == FILL_WITH_MEAN:
if feature[TYPE] != NUMBER:
raise ValueError(
f"Filling missing values with mean is supported "
f"only for number types, not for type {feature[TYPE]}.",
)
return backend.df_engine.compute(dataset_cols[feature[COLUMN]].mean())
elif missing_value_strategy == FILL_WITH_FALSE:
distinct_values = backend.df_engine.compute(
dataset_cols[feature[COLUMN]].drop_duplicates().dropna()
).values.tolist()
if len(distinct_values) > 2:
raise ValueError(
f"Missing value strategy `fill_with_false` "
f"for column {feature[COLUMN]} expects 2 distinct values, "
f"found: {len(distinct_values)} (ex: {distinct_values[:10]})"
)
# Determine the False label.
# Distinct values are sorted in reverse to mirror the selection of the default fallback_true_label (in
# binary_feature.get_feature_meta) for binary columns with unconventional boolean values, "human"/"bot".
for v in sorted(distinct_values, reverse=True):
fallback_true_label = preprocessing_parameters.get("fallback_true_label", "true")
if strings_utils.str2bool(v, fallback_true_label) is False:
return v
raise ValueError(
f"Unable to determine False value for column {feature[COLUMN]} with distinct values: {distinct_values}."
)
# Otherwise, we cannot precompute the fill value for this dataset
return None
| Precomputes the fill value for a feature.
NOTE: this is called before NaNs are removed from the dataset. Modifications here must handle NaNs gracefully.
| 24 | 157 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def precompute_fill_value(dataset_cols, feature, preprocessing_parameters, backend):
missing_value_strategy = preprocessing_parameters["missing_value_strategy"]
if missing_value_strategy == FILL_WITH_CONST:
return preprocessing_parameters["fill_value"]
elif missing_value_strategy == FILL_WITH_MODE:
return dataset_cols[feature[COLUMN]].value_counts().index[0]
elif missing_value_strategy == FILL_WITH_MEAN:
if feature[TYPE] != NUMBER:
raise ValueError(
f"Filling missing values with mean is supported "
f"only for number types, not for type {feature[TYPE]}.",
)
return backend.df_engine.compute(dataset_cols[feature[COLUMN]].mean())
elif missing_value_strategy == FILL_WITH_FALSE:
distinct_values = backend.df_engine.compute(
dataset_cols[feature[COLUMN]].drop_duplicates().dropna()
).values.tolist()
if len(distinct_values) > 2:
raise ValueError(
f"Missing value strategy `fill_with_false` "
f"for column {feature[COLUMN]} expects 2 distinct values, "
f"found: {len(distinct_values)} (ex: {distinct_values[:10]})"
)
# Determine the False label.
# Distinct values are sorted in reverse to mirror the selection of the default fallback_true_label (in
# binary_feature.get_feature_meta) for binary columns with unconventional boolean values, "human"/"bot".
for v in sorted(distinct_values, reverse=True):
fallback_true_label = preprocessing_parameters.get("fallback_true_label", "true")
if strings_utils.str2bool(v, fallback_true_label) is False:
return v
raise ValueError(
f"Unable to determine False value for column {feature[COLUMN]} with distinct values: {distinct_values}."
)
# Otherwise, we cannot precompute the fill value for this dataset
return None
```
###Assistant : Precomputes the fill value for a feature.
NOTE: this is called before NaNs are removed from the dataset. Modifications here must handle NaNs gracefully.
|
651 | def loss_labels(self, outputs, targets, indices, num_boxes, log=True):
if "logits" not in outputs:
raise ValueError("No logits were found in the outputs")
source_logits = outputs["logits"]
idx = self._get_source_permutation_idx(indices)
target_classes_o = torch.cat([t["class_labels"][J] for t, (_, J) in zip(targets, indices)])
target_classes = torch.full(
source_logits.shape[:2], self.num_classes, dtype=torch.int64, device=source_logits.device
)
target_classes[idx] = target_classes_o
target_classes_onehot = torch.zeros(
[source_logits.shape[0], source_logits.shape[1], source_logits.shape[2] + 1],
dtype=source_logits.dtype,
layout=source_logits.layout,
device=source_logits.device,
)
target_classes_onehot.scatter_(2, target_classes.unsqueeze(-1), 1)
target_classes_onehot = target_classes_onehot[:, :, :-1]
loss_ce = (
sigmoid_focal_loss(source_logits, target_classes_onehot, num_boxes, alpha=self.focal_alpha, gamma=2)
* source_logits.shape[1]
)
losses = {"loss_ce": loss_ce}
return losses
| Classification loss (NLL)
targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]
| 16 | 84 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def loss_labels(self, outputs, targets, indices, num_boxes, log=True):
if "logits" not in outputs:
raise ValueError("No logits were found in the outputs")
source_logits = outputs["logits"]
idx = self._get_source_permutation_idx(indices)
target_classes_o = torch.cat([t["class_labels"][J] for t, (_, J) in zip(targets, indices)])
target_classes = torch.full(
source_logits.shape[:2], self.num_classes, dtype=torch.int64, device=source_logits.device
)
target_classes[idx] = target_classes_o
target_classes_onehot = torch.zeros(
[source_logits.shape[0], source_logits.shape[1], source_logits.shape[2] + 1],
dtype=source_logits.dtype,
layout=source_logits.layout,
device=source_logits.device,
)
target_classes_onehot.scatter_(2, target_classes.unsqueeze(-1), 1)
target_classes_onehot = target_classes_onehot[:, :, :-1]
loss_ce = (
sigmoid_focal_loss(source_logits, target_classes_onehot, num_boxes, alpha=self.focal_alpha, gamma=2)
* source_logits.shape[1]
)
losses = {"loss_ce": loss_ce}
return losses
```
###Assistant : Classification loss (NLL)
targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]
|
652 | def test_stacking_classifier_multilabel_predict_proba(estimator):
X_train, X_test, y_train, y_test = train_test_split(
X_multilabel, y_multilabel, stratify=y_multilabel, random_state=42
)
n_outputs = 3
estimators = [("est", estimator)]
stacker = StackingClassifier(
estimators=estimators,
final_estimator=KNeighborsClassifier(),
stack_method="predict_proba",
).fit(X_train, y_train)
X_trans = stacker.transform(X_test)
assert X_trans.shape == (X_test.shape[0], n_outputs)
# we should not have any collinear classes and thus nothing should sum to 1
assert not any(np.isclose(X_trans.sum(axis=1), 1.0))
y_pred = stacker.predict(X_test)
assert y_pred.shape == y_test.shape
| Check the behaviour for the multilabel classification case and the
`predict_proba` stacking method.
Estimators are not consistent with the output arrays and we need to ensure that
we handle all cases.
| 31 | 62 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_stacking_classifier_multilabel_predict_proba(estimator):
X_train, X_test, y_train, y_test = train_test_split(
X_multilabel, y_multilabel, stratify=y_multilabel, random_state=42
)
n_outputs = 3
estimators = [("est", estimator)]
stacker = StackingClassifier(
estimators=estimators,
final_estimator=KNeighborsClassifier(),
stack_method="predict_proba",
).fit(X_train, y_train)
X_trans = stacker.transform(X_test)
assert X_trans.shape == (X_test.shape[0], n_outputs)
# we should not have any collinear classes and thus nothing should sum to 1
assert not any(np.isclose(X_trans.sum(axis=1), 1.0))
y_pred = stacker.predict(X_test)
assert y_pred.shape == y_test.shape
```
###Assistant : Check the behaviour for the multilabel classification case and the
`predict_proba` stacking method.
Estimators are not consistent with the output arrays and we need to ensure that
we handle all cases.
|
653 | def get_page(self, url):
# http://peak.telecommunity.com/DevCenter/EasyInstall#package-index-api
scheme, netloc, path, _, _, _ = urlparse(url)
if scheme == 'file' and os.path.isdir(url2pathname(path)):
url = urljoin(ensure_slash(url), 'index.html')
if url in self._page_cache:
result = self._page_cache[url]
logger.debug('Returning %s from cache: %s', url, result)
else:
host = netloc.split(':', 1)[0]
result = None
if host in self._bad_hosts:
logger.debug('Skipping %s due to bad host %s', url, host)
else:
req = Request(url, headers={'Accept-encoding': 'identity'})
try:
logger.debug('Fetching %s', url)
resp = self.opener.open(req, timeout=self.timeout)
logger.debug('Fetched %s', url)
headers = resp.info()
content_type = headers.get('Content-Type', '')
if HTML_CONTENT_TYPE.match(content_type):
final_url = resp.geturl()
data = resp.read()
encoding = headers.get('Content-Encoding')
if encoding:
decoder = self.decoders[encoding] # fail if not found
data = decoder(data)
encoding = 'utf-8'
m = CHARSET.search(content_type)
if m:
encoding = m.group(1)
try:
data = data.decode(encoding)
except UnicodeError: # pragma: no cover
data = data.decode('latin-1') # fallback
result = Page(data, final_url)
self._page_cache[final_url] = result
except HTTPError as e:
if e.code != 404:
logger.exception('Fetch failed: %s: %s', url, e)
except URLError as e: # pragma: no cover
logger.exception('Fetch failed: %s: %s', url, e)
with self._lock:
self._bad_hosts.add(host)
except Exception as e: # pragma: no cover
logger.exception('Fetch failed: %s: %s', url, e)
finally:
self._page_cache[url] = result # even if None (failure)
return result
_distname_re = re.compile('<a href=[^>]*>([^<]+)<')
|
Get the HTML for an URL, possibly from an in-memory cache.
XXX TODO Note: this cache is never actually cleared. It's assumed that
the data won't get stale over the lifetime of a locator instance (not
necessarily true for the default_locator).
| 41 | 199 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_page(self, url):
# http://peak.telecommunity.com/DevCenter/EasyInstall#package-index-api
scheme, netloc, path, _, _, _ = urlparse(url)
if scheme == 'file' and os.path.isdir(url2pathname(path)):
url = urljoin(ensure_slash(url), 'index.html')
if url in self._page_cache:
result = self._page_cache[url]
logger.debug('Returning %s from cache: %s', url, result)
else:
host = netloc.split(':', 1)[0]
result = None
if host in self._bad_hosts:
logger.debug('Skipping %s due to bad host %s', url, host)
else:
req = Request(url, headers={'Accept-encoding': 'identity'})
try:
logger.debug('Fetching %s', url)
resp = self.opener.open(req, timeout=self.timeout)
logger.debug('Fetched %s', url)
headers = resp.info()
content_type = headers.get('Content-Type', '')
if HTML_CONTENT_TYPE.match(content_type):
final_url = resp.geturl()
data = resp.read()
encoding = headers.get('Content-Encoding')
if encoding:
decoder = self.decoders[encoding] # fail if not found
data = decoder(data)
encoding = 'utf-8'
m = CHARSET.search(content_type)
if m:
encoding = m.group(1)
try:
data = data.decode(encoding)
except UnicodeError: # pragma: no cover
data = data.decode('latin-1') # fallback
result = Page(data, final_url)
self._page_cache[final_url] = result
except HTTPError as e:
if e.code != 404:
logger.exception('Fetch failed: %s: %s', url, e)
except URLError as e: # pragma: no cover
logger.exception('Fetch failed: %s: %s', url, e)
with self._lock:
self._bad_hosts.add(host)
except Exception as e: # pragma: no cover
logger.exception('Fetch failed: %s: %s', url, e)
finally:
self._page_cache[url] = result # even if None (failure)
return result
_distname_re = re.compile('<a href=[^>]*>([^<]+)<')
```
###Assistant :
Get the HTML for an URL, possibly from an in-memory cache.
XXX TODO Note: this cache is never actually cleared. It's assumed that
the data won't get stale over the lifetime of a locator instance (not
necessarily true for the default_locator).
|
654 | def enable_all_warnings() -> None:
__diag__.enable_all_warnings()
# hide abstract class
del __config_flags
|
Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`).
| 8 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def enable_all_warnings() -> None:
__diag__.enable_all_warnings()
# hide abstract class
del __config_flags
```
###Assistant :
Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`).
|
655 | def export_yaml(self):
yaml_data = [obj.to_yaml() for obj in self.queryset]
return '---\n'.join(yaml_data)
|
Export the queryset of objects as concatenated YAML documents.
| 9 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def export_yaml(self):
yaml_data = [obj.to_yaml() for obj in self.queryset]
return '---\n'.join(yaml_data)
```
###Assistant :
Export the queryset of objects as concatenated YAML documents.
|
656 | def url_has_allowed_host_and_scheme(url, allowed_hosts, require_https=False):
if url is not None:
url = url.strip()
if not url:
return False
if allowed_hosts is None:
allowed_hosts = set()
elif isinstance(allowed_hosts, str):
allowed_hosts = {allowed_hosts}
# Chrome treats \ completely as / in paths but it could be part of some
# basic auth credentials so we need to check both URLs.
return _url_has_allowed_host_and_scheme(
url, allowed_hosts, require_https=require_https
) and _url_has_allowed_host_and_scheme(
url.replace("\\", "/"), allowed_hosts, require_https=require_https
)
# Copied from urllib.parse.urlparse() but uses fixed urlsplit() function. |
Return ``True`` if the url uses an allowed host and a safe scheme.
Always return ``False`` on an empty url.
If ``require_https`` is ``True``, only 'https' will be considered a valid
scheme, as opposed to 'http' and 'https' with the default, ``False``.
Note: "True" doesn't entail that a URL is "safe". It may still be e.g.
quoted incorrectly. Ensure to also use django.utils.encoding.iri_to_uri()
on the path component of untrusted URLs.
| 70 | 79 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def url_has_allowed_host_and_scheme(url, allowed_hosts, require_https=False):
if url is not None:
url = url.strip()
if not url:
return False
if allowed_hosts is None:
allowed_hosts = set()
elif isinstance(allowed_hosts, str):
allowed_hosts = {allowed_hosts}
# Chrome treats \ completely as / in paths but it could be part of some
# basic auth credentials so we need to check both URLs.
return _url_has_allowed_host_and_scheme(
url, allowed_hosts, require_https=require_https
) and _url_has_allowed_host_and_scheme(
url.replace("\\", "/"), allowed_hosts, require_https=require_https
)
# Copied from urllib.parse.urlparse() but uses fixed urlsplit() function.
```
###Assistant :
Return ``True`` if the url uses an allowed host and a safe scheme.
Always return ``False`` on an empty url.
If ``require_https`` is ``True``, only 'https' will be considered a valid
scheme, as opposed to 'http' and 'https' with the default, ``False``.
Note: "True" doesn't entail that a URL is "safe". It may still be e.g.
quoted incorrectly. Ensure to also use django.utils.encoding.iri_to_uri()
on the path component of untrusted URLs.
|
657 | def get_ps(module, pattern):
found = False
if platform.system() == 'SunOS':
flags = '-ef'
else:
flags = 'auxww'
psbin = module.get_bin_path('ps', True)
(rc, psout, pserr) = module.run_command([psbin, flags])
if rc == 0:
for line in psout.splitlines():
if pattern in line:
# FIXME: should add logic to prevent matching 'self', though that should be extremely rare
found = True
break
return found
|
Last resort to find a service by trying to match pattern to programs in memory
| 15 | 60 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_ps(module, pattern):
found = False
if platform.system() == 'SunOS':
flags = '-ef'
else:
flags = 'auxww'
psbin = module.get_bin_path('ps', True)
(rc, psout, pserr) = module.run_command([psbin, flags])
if rc == 0:
for line in psout.splitlines():
if pattern in line:
# FIXME: should add logic to prevent matching 'self', though that should be extremely rare
found = True
break
return found
```
###Assistant :
Last resort to find a service by trying to match pattern to programs in memory
|
658 | def apply(self, sample, context=None):
im = sample['image']
im = im.astype(np.float32, copy=False)
if self.is_scale:
scale = 1.0 / 255.0
im *= scale
if self.norm_type == 'mean_std':
mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
std = np.array(self.std)[np.newaxis, np.newaxis, :]
im -= mean
im /= std
sample['image'] = im
return sample
@register_op | Normalize the image.
Operators:
1.(optional) Scale the pixel to [0,1]
2.(optional) Each pixel minus mean and is divided by std
| 20 | 47 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def apply(self, sample, context=None):
im = sample['image']
im = im.astype(np.float32, copy=False)
if self.is_scale:
scale = 1.0 / 255.0
im *= scale
if self.norm_type == 'mean_std':
mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
std = np.array(self.std)[np.newaxis, np.newaxis, :]
im -= mean
im /= std
sample['image'] = im
return sample
@register_op
```
###Assistant : Normalize the image.
Operators:
1.(optional) Scale the pixel to [0,1]
2.(optional) Each pixel minus mean and is divided by std
|
659 | def _check_m2m_through_same_relationship(cls):
errors = []
seen_intermediary_signatures = []
fields = cls._meta.local_many_to_many
# Skip when the target model wasn't found.
fields = (f for f in fields if isinstance(f.remote_field.model, ModelBase))
# Skip when the relationship model wasn't found.
fields = (f for f in fields if isinstance(f.remote_field.through, ModelBase))
for f in fields:
signature = (
f.remote_field.model,
cls,
f.remote_field.through,
f.remote_field.through_fields,
)
if signature in seen_intermediary_signatures:
errors.append(
checks.Error(
"The model has two identical many-to-many relations "
"through the intermediate model '%s'."
% f.remote_field.through._meta.label,
obj=cls,
id="models.E003",
)
)
else:
seen_intermediary_signatures.append(signature)
return errors
| Check if no relationship model is used by more than one m2m field. | 13 | 88 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _check_m2m_through_same_relationship(cls):
errors = []
seen_intermediary_signatures = []
fields = cls._meta.local_many_to_many
# Skip when the target model wasn't found.
fields = (f for f in fields if isinstance(f.remote_field.model, ModelBase))
# Skip when the relationship model wasn't found.
fields = (f for f in fields if isinstance(f.remote_field.through, ModelBase))
for f in fields:
signature = (
f.remote_field.model,
cls,
f.remote_field.through,
f.remote_field.through_fields,
)
if signature in seen_intermediary_signatures:
errors.append(
checks.Error(
"The model has two identical many-to-many relations "
"through the intermediate model '%s'."
% f.remote_field.through._meta.label,
obj=cls,
id="models.E003",
)
)
else:
seen_intermediary_signatures.append(signature)
return errors
```
###Assistant : Check if no relationship model is used by more than one m2m field.
|
660 | def image(self) -> "np.ndarray":
assert self._image is not None
return self._image
| :class:`numpy.ndarray`: The source frame for this object. | 7 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def image(self) -> "np.ndarray":
assert self._image is not None
return self._image
```
###Assistant : :class:`numpy.ndarray`: The source frame for this object.
|
661 | def test_sends_deployment_notification(self, record_analytics):
release = self.create_release()
version_parsed = self.version_parsed = parse_release(release.version)["description"]
url = f"/api/0/organizations/{self.organization.slug}/releases/{release.version}/deploys/"
with self.tasks():
response = self.client.post(
url, format="json", data={"environment": self.environment.name}
)
assert response.status_code == 201, response.content
msg = mail.outbox[0]
# check the txt version
assert f"Version {version_parsed} was deployed to {self.environment.name} on" in msg.body
# check the html version
assert (
f"Version {version_parsed} was deployed to {self.environment.name}\n </h2>\n"
in msg.alternatives[0][0]
)
attachment, text = get_attachment()
assert (
text
== f"Release {version_parsed} was deployed to {self.environment.name} for this project"
)
assert (
attachment["actions"][0]["url"]
== f"http://testserver/organizations/{self.organization.slug}/releases/{release.version}/?project={self.project.id}&unselectedSeries=Healthy/"
)
assert (
attachment["footer"]
== f"{self.project.slug} | <http://testserver/settings/account/notifications/deploy/?referrer=release_activity-slack-user|Notification Settings>"
)
assert analytics_called_with_args(
record_analytics,
"integrations.email.notification_sent",
user_id=self.user.id,
actor_id=self.user.actor_id,
organization_id=self.organization.id,
)
assert analytics_called_with_args(
record_analytics,
"integrations.slack.notification_sent",
user_id=self.user.id,
actor_id=self.user.actor_id,
organization_id=self.organization.id,
)
|
Test that an email AND Slack notification are sent with
the expected values when a release is deployed.
| 18 | 113 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_sends_deployment_notification(self, record_analytics):
release = self.create_release()
version_parsed = self.version_parsed = parse_release(release.version)["description"]
url = f"/api/0/organizations/{self.organization.slug}/releases/{release.version}/deploys/"
with self.tasks():
response = self.client.post(
url, format="json", data={"environment": self.environment.name}
)
assert response.status_code == 201, response.content
msg = mail.outbox[0]
# check the txt version
assert f"Version {version_parsed} was deployed to {self.environment.name} on" in msg.body
# check the html version
assert (
f"Version {version_parsed} was deployed to {self.environment.name}\n </h2>\n"
in msg.alternatives[0][0]
)
attachment, text = get_attachment()
assert (
text
== f"Release {version_parsed} was deployed to {self.environment.name} for this project"
)
assert (
attachment["actions"][0]["url"]
== f"http://testserver/organizations/{self.organization.slug}/releases/{release.version}/?project={self.project.id}&unselectedSeries=Healthy/"
)
assert (
attachment["footer"]
== f"{self.project.slug} | <http://testserver/settings/account/notifications/deploy/?referrer=release_activity-slack-user|Notification Settings>"
)
assert analytics_called_with_args(
record_analytics,
"integrations.email.notification_sent",
user_id=self.user.id,
actor_id=self.user.actor_id,
organization_id=self.organization.id,
)
assert analytics_called_with_args(
record_analytics,
"integrations.slack.notification_sent",
user_id=self.user.id,
actor_id=self.user.actor_id,
organization_id=self.organization.id,
)
```
###Assistant :
Test that an email AND Slack notification are sent with
the expected values when a release is deployed.
|
662 | def get_all_mode_of_payments(doc):
return frappe.db.sql(
,
{"company": doc.company},
as_dict=1,
)
|
select mpa.default_account, mpa.parent, mp.type as type
from `tabMode of Payment Account` mpa,`tabMode of Payment` mp
where mpa.parent = mp.name and mpa.company = %(company)s and mp.enabled = 1 | 27 | 9 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_all_mode_of_payments(doc):
return frappe.db.sql(
,
{"company": doc.company},
as_dict=1,
)
```
###Assistant :
select mpa.default_account, mpa.parent, mp.type as type
from `tabMode of Payment Account` mpa,`tabMode of Payment` mp
where mpa.parent = mp.name and mpa.company = %(company)s and mp.enabled = 1
|
663 | def _on_move(self, event):
if not self.button_pressed:
return
if self.get_navigate_mode() is not None:
# we don't want to rotate if we are zooming/panning
# from the toolbar
return
if self.M is None:
return
x, y = event.xdata, event.ydata
# In case the mouse is out of bounds.
if x is None or event.inaxes != self:
return
dx, dy = x - self._sx, y - self._sy
w = self._pseudo_w
h = self._pseudo_h
# Rotation
if self.button_pressed in self._rotate_btn:
# rotate viewing point
# get the x and y pixel coords
if dx == 0 and dy == 0:
return
roll = np.deg2rad(self.roll)
delev = -(dy/h)*180*np.cos(roll) + (dx/w)*180*np.sin(roll)
dazim = -(dy/h)*180*np.sin(roll) - (dx/w)*180*np.cos(roll)
self.elev = self.elev + delev
self.azim = self.azim + dazim
self.stale = True
elif self.button_pressed in self._pan_btn:
# Start the pan event with pixel coordinates
px, py = self.transData.transform([self._sx, self._sy])
self.start_pan(px, py, 2)
# pan view (takes pixel coordinate input)
self.drag_pan(2, None, event.x, event.y)
self.end_pan()
# Zoom
elif self.button_pressed in self._zoom_btn:
# zoom view (dragging down zooms in)
scale = h/(h - dy)
self._scale_axis_limits(scale, scale, scale)
# Store the event coordinates for the next time through.
self._sx, self._sy = x, y
# Always request a draw update at the end of interaction
self.figure.canvas.draw_idle()
|
Mouse moving.
By default, button-1 rotates, button-2 pans, and button-3 zooms;
these buttons can be modified via `mouse_init`.
| 18 | 203 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _on_move(self, event):
if not self.button_pressed:
return
if self.get_navigate_mode() is not None:
# we don't want to rotate if we are zooming/panning
# from the toolbar
return
if self.M is None:
return
x, y = event.xdata, event.ydata
# In case the mouse is out of bounds.
if x is None or event.inaxes != self:
return
dx, dy = x - self._sx, y - self._sy
w = self._pseudo_w
h = self._pseudo_h
# Rotation
if self.button_pressed in self._rotate_btn:
# rotate viewing point
# get the x and y pixel coords
if dx == 0 and dy == 0:
return
roll = np.deg2rad(self.roll)
delev = -(dy/h)*180*np.cos(roll) + (dx/w)*180*np.sin(roll)
dazim = -(dy/h)*180*np.sin(roll) - (dx/w)*180*np.cos(roll)
self.elev = self.elev + delev
self.azim = self.azim + dazim
self.stale = True
elif self.button_pressed in self._pan_btn:
# Start the pan event with pixel coordinates
px, py = self.transData.transform([self._sx, self._sy])
self.start_pan(px, py, 2)
# pan view (takes pixel coordinate input)
self.drag_pan(2, None, event.x, event.y)
self.end_pan()
# Zoom
elif self.button_pressed in self._zoom_btn:
# zoom view (dragging down zooms in)
scale = h/(h - dy)
self._scale_axis_limits(scale, scale, scale)
# Store the event coordinates for the next time through.
self._sx, self._sy = x, y
# Always request a draw update at the end of interaction
self.figure.canvas.draw_idle()
```
###Assistant :
Mouse moving.
By default, button-1 rotates, button-2 pans, and button-3 zooms;
these buttons can be modified via `mouse_init`.
|
664 | def install(name=None, refresh=False, pkgs=None, version=None, test=False, **kwargs):
targets = salt.utils.args.split_input(pkgs) if pkgs else [name]
if not targets:
return {}
if pkgs:
log.debug("Removing these fileset(s)/rpm package(s) %s: %s", name, targets)
# Get a list of the currently installed pkgs.
old = list_pkgs()
# Install the fileset (normally ends with bff or rte) or rpm package(s)
errors = []
for target in targets:
filename = os.path.basename(target)
if filename.endswith(".bff") or filename.endswith(".rte"):
if _is_installed(target):
continue
cmd = "/usr/sbin/installp -acYXg"
if test:
cmd += "p"
cmd += " -d "
dirpath = os.path.dirname(target)
cmd += dirpath + " " + filename
out = __salt__["cmd.run_all"](cmd, python_shell=False)
else:
if _is_installed_rpm(filename.split(".aix")[0]):
continue
# assume use dnf or yum
cmdflags = " install --allowerasing "
if pathlib.Path("/opt/freeware/bin/dnf").is_file():
cmdexe = "/opt/freeware/bin/dnf"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
if refresh:
cmdflags += " --refresh"
elif pathlib.Path("/opt/freeware/bin/yum").is_file():
cmdexe = "/opt/freeware/bin/yum"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
if refresh:
cmdflags += " --refresh"
elif pathlib.Path("/usr/bin/yum").is_file():
cmdexe = "/usr/bin/yum"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
else:
cmdexe = "/usr/bin/rpm"
cmdflags = " -Uivh "
if test:
cmdflags += " --test"
cmd = [cmdexe, cmdflags, target]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
if 0 != out["retcode"]:
errors.append(out["stderr"])
# Get a list of the packages after the uninstall
__context__.pop("pkg.list_pkgs", None)
new = list_pkgs()
ret = salt.utils.data.compare_dicts(old, new)
if errors:
raise CommandExecutionError(
"Problems encountered installing filesets(s)/package(s)",
info={"changes": ret, "errors": errors},
)
# No error occurred
if test:
return "Test succeeded."
return ret
|
Install the named fileset(s)/rpm package(s).
.. versionadded:: 3005
preference to install rpm packages are to use in the following order:
/opt/freeware/bin/dnf
/opt/freeware/bin/yum
/usr/bin/yum
/usr/bin/rpm
Note: use of rpm to install implies that rpm's dependencies must have been previously installed.
dnf and yum automatically install rpm's dependencies as part of the install process
name
The name of the fileset or rpm package to be installed.
refresh
Whether or not to update the yum database before executing.
Multiple Package Installation Options:
pkgs
A list of filesets and/or rpm packages to install.
Must be passed as a python list. The ``name`` parameter will be
ignored if this option is passed.
version
Install a specific version of a fileset/rpm package.
(Unused at present).
test
Verify that command functions correctly:
Returns a dict containing the new fileset(s)/rpm package(s) names and versions:
{'<package>': {'old': '<old-version>',
'new': '<new-version>'}}
CLI Example:
.. code-block:: bash
salt '*' pkg.install /stage/middleware/AIX/bash-4.2-3.aix6.1.ppc.rpm
salt '*' pkg.install /stage/middleware/AIX/bash-4.2-3.aix6.1.ppc.rpm refresh=True
salt '*' pkg.install /stage/middleware/AIX/VIOS2211_update/tpc_4.1.1.85.bff
salt '*' pkg.install /stage/middleware/AIX/Xlc/usr/sys/inst.images/xlC.rte
salt '*' pkg.install /stage/middleware/AIX/Firefox/ppc-AIX53/Firefox.base
salt '*' pkg.install pkgs='["foo", "bar"]'
| 172 | 248 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def install(name=None, refresh=False, pkgs=None, version=None, test=False, **kwargs):
targets = salt.utils.args.split_input(pkgs) if pkgs else [name]
if not targets:
return {}
if pkgs:
log.debug("Removing these fileset(s)/rpm package(s) %s: %s", name, targets)
# Get a list of the currently installed pkgs.
old = list_pkgs()
# Install the fileset (normally ends with bff or rte) or rpm package(s)
errors = []
for target in targets:
filename = os.path.basename(target)
if filename.endswith(".bff") or filename.endswith(".rte"):
if _is_installed(target):
continue
cmd = "/usr/sbin/installp -acYXg"
if test:
cmd += "p"
cmd += " -d "
dirpath = os.path.dirname(target)
cmd += dirpath + " " + filename
out = __salt__["cmd.run_all"](cmd, python_shell=False)
else:
if _is_installed_rpm(filename.split(".aix")[0]):
continue
# assume use dnf or yum
cmdflags = " install --allowerasing "
if pathlib.Path("/opt/freeware/bin/dnf").is_file():
cmdexe = "/opt/freeware/bin/dnf"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
if refresh:
cmdflags += " --refresh"
elif pathlib.Path("/opt/freeware/bin/yum").is_file():
cmdexe = "/opt/freeware/bin/yum"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
if refresh:
cmdflags += " --refresh"
elif pathlib.Path("/usr/bin/yum").is_file():
cmdexe = "/usr/bin/yum"
if test:
cmdflags += " --assumeno"
else:
cmdflags += " --assumeyes"
else:
cmdexe = "/usr/bin/rpm"
cmdflags = " -Uivh "
if test:
cmdflags += " --test"
cmd = [cmdexe, cmdflags, target]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
if 0 != out["retcode"]:
errors.append(out["stderr"])
# Get a list of the packages after the uninstall
__context__.pop("pkg.list_pkgs", None)
new = list_pkgs()
ret = salt.utils.data.compare_dicts(old, new)
if errors:
raise CommandExecutionError(
"Problems encountered installing filesets(s)/package(s)",
info={"changes": ret, "errors": errors},
)
# No error occurred
if test:
return "Test succeeded."
return ret
```
###Assistant :
Install the named fileset(s)/rpm package(s).
.. versionadded:: 3005
preference to install rpm packages are to use in the following order:
/opt/freeware/bin/dnf
/opt/freeware/bin/yum
/usr/bin/yum
/usr/bin/rpm
Note: use of rpm to install implies that rpm's dependencies must have been previously installed.
dnf and yum automatically install rpm's dependencies as part of the install process
name
The name of the fileset or rpm package to be installed.
refresh
Whether or not to update the yum database before executing.
Multiple Package Installation Options:
pkgs
A list of filesets and/or rpm packages to install.
Must be passed as a python list. The ``name`` parameter will be
ignored if this option is passed.
version
Install a specific version of a fileset/rpm package.
(Unused at present).
test
Verify that command functions correctly:
Returns a dict containing the new fileset(s)/rpm package(s) names and versions:
{'<package>': {'old': '<old-version>',
'new': '<new-version>'}}
CLI Example:
.. code-block:: bash
salt '*' pkg.install /stage/middleware/AIX/bash-4.2-3.aix6.1.ppc.rpm
salt '*' pkg.install /stage/middleware/AIX/bash-4.2-3.aix6.1.ppc.rpm refresh=True
salt '*' pkg.install /stage/middleware/AIX/VIOS2211_update/tpc_4.1.1.85.bff
salt '*' pkg.install /stage/middleware/AIX/Xlc/usr/sys/inst.images/xlC.rte
salt '*' pkg.install /stage/middleware/AIX/Firefox/ppc-AIX53/Firefox.base
salt '*' pkg.install pkgs='["foo", "bar"]'
|
665 | def is_false(self, ds_key_long):
value = self.get_value(ds_key_long)
return False if value is None else not bool(value)
|
Returns `True`/``False` only if the value is set, always `False` otherwise. So use this method to ask the very
specific question of whether the value is set to `False` (and it's not set to `True`` or isn't set).
| 38 | 15 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def is_false(self, ds_key_long):
value = self.get_value(ds_key_long)
return False if value is None else not bool(value)
```
###Assistant :
Returns `True`/``False` only if the value is set, always `False` otherwise. So use this method to ask the very
specific question of whether the value is set to `False` (and it's not set to `True`` or isn't set).
|
666 | def extract_pytorch_structures():
for opt in lmo.optimizer_registry:
# Get the torch class:
optimizer_class = lmo.optimizer_registry[opt][0]
# Parse and clean the class structure:
path = get_fully_qualified_class_name(optimizer_class)
opt_struct = get_pytkdocs_structure_for_path(path, "google")["objects"][0]
prune_pytorch_structures(opt_struct)
# Write it to a file:
parent_dir = str(Path(__file__).parent.parent)
filename = os.path.join(parent_dir, "ludwig/validation/generated/torch/", optimizer_class.__name__) + ".json"
os.makedirs(os.path.dirname(filename), exist_ok=True)
with open(filename, "w") as outfile:
json.dump(
opt_struct,
outfile,
indent=4,
sort_keys=True,
separators=(",", ": "),
)
outfile.write("\n")
| Extracts and saves the parsed structure of all pytorch classes referenced in
`ludwig.modules.optimization_modules.optimizer_registry` as JSON files under
`ludwig/validation/generated/torch/`. | 18 | 62 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def extract_pytorch_structures():
for opt in lmo.optimizer_registry:
# Get the torch class:
optimizer_class = lmo.optimizer_registry[opt][0]
# Parse and clean the class structure:
path = get_fully_qualified_class_name(optimizer_class)
opt_struct = get_pytkdocs_structure_for_path(path, "google")["objects"][0]
prune_pytorch_structures(opt_struct)
# Write it to a file:
parent_dir = str(Path(__file__).parent.parent)
filename = os.path.join(parent_dir, "ludwig/validation/generated/torch/", optimizer_class.__name__) + ".json"
os.makedirs(os.path.dirname(filename), exist_ok=True)
with open(filename, "w") as outfile:
json.dump(
opt_struct,
outfile,
indent=4,
sort_keys=True,
separators=(",", ": "),
)
outfile.write("\n")
```
###Assistant : Extracts and saves the parsed structure of all pytorch classes referenced in
`ludwig.modules.optimization_modules.optimizer_registry` as JSON files under
`ludwig/validation/generated/torch/`.
|
667 | def test_hf_classification_bin(self, mock_handler):
# create predictor
create_sql =
model_name = 'spam_classifier'
predict_sql =
self.hf_test_run(mock_handler, model_name, create_sql, predict_sql)
|
CREATE PREDICTOR huggingface.spam_classifier
predict PRED
USING
task='text-classification',
model_name= "mrm8488/bert-tiny-finetuned-sms-spam-detection",
input_column = 'text_spammy',
labels=['ham','spam']
SELECT h.*
FROM pg.df as t
JOIN huggingface.spam_classifier as h
| 23 | 17 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_hf_classification_bin(self, mock_handler):
# create predictor
create_sql =
model_name = 'spam_classifier'
predict_sql =
self.hf_test_run(mock_handler, model_name, create_sql, predict_sql)
```
###Assistant :
CREATE PREDICTOR huggingface.spam_classifier
predict PRED
USING
task='text-classification',
model_name= "mrm8488/bert-tiny-finetuned-sms-spam-detection",
input_column = 'text_spammy',
labels=['ham','spam']
SELECT h.*
FROM pg.df as t
JOIN huggingface.spam_classifier as h
|
668 | def match_submerged_margins(layoutgrids, fig):
for sfig in fig.subfigs:
match_submerged_margins(layoutgrids, sfig)
axs = [a for a in fig.get_axes()
if a.get_subplotspec() is not None and a.get_in_layout()]
for ax1 in axs:
ss1 = ax1.get_subplotspec()
if ss1.get_gridspec() not in layoutgrids:
axs.remove(ax1)
continue
lg1 = layoutgrids[ss1.get_gridspec()]
# interior columns:
if len(ss1.colspan) > 1:
maxsubl = np.max(
lg1.margin_vals['left'][ss1.colspan[1:]] +
lg1.margin_vals['leftcb'][ss1.colspan[1:]]
)
maxsubr = np.max(
lg1.margin_vals['right'][ss1.colspan[:-1]] +
lg1.margin_vals['rightcb'][ss1.colspan[:-1]]
)
for ax2 in axs:
ss2 = ax2.get_subplotspec()
lg2 = layoutgrids[ss2.get_gridspec()]
if lg2 is not None and len(ss2.colspan) > 1:
maxsubl2 = np.max(
lg2.margin_vals['left'][ss2.colspan[1:]] +
lg2.margin_vals['leftcb'][ss2.colspan[1:]])
if maxsubl2 > maxsubl:
maxsubl = maxsubl2
maxsubr2 = np.max(
lg2.margin_vals['right'][ss2.colspan[:-1]] +
lg2.margin_vals['rightcb'][ss2.colspan[:-1]])
if maxsubr2 > maxsubr:
maxsubr = maxsubr2
for i in ss1.colspan[1:]:
lg1.edit_margin_min('left', maxsubl, cell=i)
for i in ss1.colspan[:-1]:
lg1.edit_margin_min('right', maxsubr, cell=i)
# interior rows:
if len(ss1.rowspan) > 1:
maxsubt = np.max(
lg1.margin_vals['top'][ss1.rowspan[1:]] +
lg1.margin_vals['topcb'][ss1.rowspan[1:]]
)
maxsubb = np.max(
lg1.margin_vals['bottom'][ss1.rowspan[:-1]] +
lg1.margin_vals['bottomcb'][ss1.rowspan[:-1]]
)
for ax2 in axs:
ss2 = ax2.get_subplotspec()
lg2 = layoutgrids[ss2.get_gridspec()]
if lg2 is not None:
if len(ss2.rowspan) > 1:
maxsubt = np.max([np.max(
lg2.margin_vals['top'][ss2.rowspan[1:]] +
lg2.margin_vals['topcb'][ss2.rowspan[1:]]
), maxsubt])
maxsubb = np.max([np.max(
lg2.margin_vals['bottom'][ss2.rowspan[:-1]] +
lg2.margin_vals['bottomcb'][ss2.rowspan[:-1]]
), maxsubb])
for i in ss1.rowspan[1:]:
lg1.edit_margin_min('top', maxsubt, cell=i)
for i in ss1.rowspan[:-1]:
lg1.edit_margin_min('bottom', maxsubb, cell=i)
|
Make the margins that are submerged inside an Axes the same size.
This allows axes that span two columns (or rows) that are offset
from one another to have the same size.
This gives the proper layout for something like::
fig = plt.figure(constrained_layout=True)
axs = fig.subplot_mosaic("AAAB\nCCDD")
Without this routine, the axes D will be wider than C, because the
margin width between the two columns in C has no width by default,
whereas the margins between the two columns of D are set by the
width of the margin between A and B. However, obviously the user would
like C and D to be the same size, so we need to add constraints to these
"submerged" margins.
This routine makes all the interior margins the same, and the spacing
between the three columns in A and the two column in C are all set to the
margins between the two columns of D.
See test_constrained_layout::test_constrained_layout12 for an example.
| 158 | 190 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def match_submerged_margins(layoutgrids, fig):
for sfig in fig.subfigs:
match_submerged_margins(layoutgrids, sfig)
axs = [a for a in fig.get_axes()
if a.get_subplotspec() is not None and a.get_in_layout()]
for ax1 in axs:
ss1 = ax1.get_subplotspec()
if ss1.get_gridspec() not in layoutgrids:
axs.remove(ax1)
continue
lg1 = layoutgrids[ss1.get_gridspec()]
# interior columns:
if len(ss1.colspan) > 1:
maxsubl = np.max(
lg1.margin_vals['left'][ss1.colspan[1:]] +
lg1.margin_vals['leftcb'][ss1.colspan[1:]]
)
maxsubr = np.max(
lg1.margin_vals['right'][ss1.colspan[:-1]] +
lg1.margin_vals['rightcb'][ss1.colspan[:-1]]
)
for ax2 in axs:
ss2 = ax2.get_subplotspec()
lg2 = layoutgrids[ss2.get_gridspec()]
if lg2 is not None and len(ss2.colspan) > 1:
maxsubl2 = np.max(
lg2.margin_vals['left'][ss2.colspan[1:]] +
lg2.margin_vals['leftcb'][ss2.colspan[1:]])
if maxsubl2 > maxsubl:
maxsubl = maxsubl2
maxsubr2 = np.max(
lg2.margin_vals['right'][ss2.colspan[:-1]] +
lg2.margin_vals['rightcb'][ss2.colspan[:-1]])
if maxsubr2 > maxsubr:
maxsubr = maxsubr2
for i in ss1.colspan[1:]:
lg1.edit_margin_min('left', maxsubl, cell=i)
for i in ss1.colspan[:-1]:
lg1.edit_margin_min('right', maxsubr, cell=i)
# interior rows:
if len(ss1.rowspan) > 1:
maxsubt = np.max(
lg1.margin_vals['top'][ss1.rowspan[1:]] +
lg1.margin_vals['topcb'][ss1.rowspan[1:]]
)
maxsubb = np.max(
lg1.margin_vals['bottom'][ss1.rowspan[:-1]] +
lg1.margin_vals['bottomcb'][ss1.rowspan[:-1]]
)
for ax2 in axs:
ss2 = ax2.get_subplotspec()
lg2 = layoutgrids[ss2.get_gridspec()]
if lg2 is not None:
if len(ss2.rowspan) > 1:
maxsubt = np.max([np.max(
lg2.margin_vals['top'][ss2.rowspan[1:]] +
lg2.margin_vals['topcb'][ss2.rowspan[1:]]
), maxsubt])
maxsubb = np.max([np.max(
lg2.margin_vals['bottom'][ss2.rowspan[:-1]] +
lg2.margin_vals['bottomcb'][ss2.rowspan[:-1]]
), maxsubb])
for i in ss1.rowspan[1:]:
lg1.edit_margin_min('top', maxsubt, cell=i)
for i in ss1.rowspan[:-1]:
lg1.edit_margin_min('bottom', maxsubb, cell=i)
```
###Assistant :
Make the margins that are submerged inside an Axes the same size.
This allows axes that span two columns (or rows) that are offset
from one another to have the same size.
This gives the proper layout for something like::
fig = plt.figure(constrained_layout=True)
axs = fig.subplot_mosaic("AAAB\nCCDD")
Without this routine, the axes D will be wider than C, because the
margin width between the two columns in C has no width by default,
whereas the margins between the two columns of D are set by the
width of the margin between A and B. However, obviously the user would
like C and D to be the same size, so we need to add constraints to these
"submerged" margins.
This routine makes all the interior margins the same, and the spacing
between the three columns in A and the two column in C are all set to the
margins between the two columns of D.
See test_constrained_layout::test_constrained_layout12 for an example.
|
669 | def parse_version_info(version_str):
version_info = []
for x in version_str.split('.'):
if x.isdigit():
version_info.append(int(x))
elif x.find('rc') != -1:
patch_version = x.split('rc')
version_info.append(int(patch_version[0]))
version_info.append(f'rc{patch_version[1]}')
return tuple(version_info)
version_info = parse_version_info(__version__)
| Parse a version string into a tuple.
Args:
version_str (str): The version string.
Returns:
tuple[int | str]: The version info, e.g., "1.3.0" is parsed into
(1, 3, 0), and "2.0.0rc1" is parsed into (2, 0, 0, 'rc1').
| 37 | 26 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def parse_version_info(version_str):
version_info = []
for x in version_str.split('.'):
if x.isdigit():
version_info.append(int(x))
elif x.find('rc') != -1:
patch_version = x.split('rc')
version_info.append(int(patch_version[0]))
version_info.append(f'rc{patch_version[1]}')
return tuple(version_info)
version_info = parse_version_info(__version__)
```
###Assistant : Parse a version string into a tuple.
Args:
version_str (str): The version string.
Returns:
tuple[int | str]: The version info, e.g., "1.3.0" is parsed into
(1, 3, 0), and "2.0.0rc1" is parsed into (2, 0, 0, 'rc1').
|
670 | def adjust_settings_for_relay_tests(settings):
settings.ALLOWED_HOSTS = [
"localhost",
"testserver",
"host.docker.internal",
"0.0.0.0",
"127.0.0.1",
]
settings.KAFKA_CLUSTERS = {
"default": {
"common": {"bootstrap.servers": "127.0.0.1:9092"},
"producers": {
"compression.type": "lz4",
"message.max.bytes": 50000000, # 50MB, default is 1MB
},
}
}
settings.SENTRY_RELAY_WHITELIST_PK = ["SMSesqan65THCV6M4qs4kBzPai60LzuDn-xNsvYpuP8"]
settings.SENTRY_USE_RELAY = True
@pytest.fixture |
Adjusts the application settings to accept calls from a Relay instance running inside a
docker container.
:param settings: the app settings
| 21 | 40 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def adjust_settings_for_relay_tests(settings):
settings.ALLOWED_HOSTS = [
"localhost",
"testserver",
"host.docker.internal",
"0.0.0.0",
"127.0.0.1",
]
settings.KAFKA_CLUSTERS = {
"default": {
"common": {"bootstrap.servers": "127.0.0.1:9092"},
"producers": {
"compression.type": "lz4",
"message.max.bytes": 50000000, # 50MB, default is 1MB
},
}
}
settings.SENTRY_RELAY_WHITELIST_PK = ["SMSesqan65THCV6M4qs4kBzPai60LzuDn-xNsvYpuP8"]
settings.SENTRY_USE_RELAY = True
@pytest.fixture
```
###Assistant :
Adjusts the application settings to accept calls from a Relay instance running inside a
docker container.
:param settings: the app settings
|
671 | def clear_backends():
if xc._version < 79:
raise RuntimeError("clear_backends is not supported in the jaxlib used."
"Please update your jaxlib package.")
xb._clear_backends()
jax.lib.xla_bridge._backends = {}
dispatch.xla_callable.cache_clear() # type: ignore
dispatch.xla_primitive_callable.cache_clear()
_cpp_jit_cache.clear()
jax_jit.CompiledFunctionCache.clear_all()
|
Clear all backend clients so that new backend clients can be created later.
| 13 | 31 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def clear_backends():
if xc._version < 79:
raise RuntimeError("clear_backends is not supported in the jaxlib used."
"Please update your jaxlib package.")
xb._clear_backends()
jax.lib.xla_bridge._backends = {}
dispatch.xla_callable.cache_clear() # type: ignore
dispatch.xla_primitive_callable.cache_clear()
_cpp_jit_cache.clear()
jax_jit.CompiledFunctionCache.clear_all()
```
###Assistant :
Clear all backend clients so that new backend clients can be created later.
|
672 | def get_power_utilization(self):
powerfeeds = PowerFeed.objects.filter(rack=self)
available_power_total = sum(pf.available_power for pf in powerfeeds)
print(f'available_power_total: {available_power_total}')
if not available_power_total:
return 0
powerports = []
for powerfeed in powerfeeds:
powerports.extend([
peer for peer in powerfeed.link_peers if isinstance(peer, PowerPort)
])
allocated_draw = 0
for powerport in powerports:
allocated_draw += powerport.get_power_draw()['allocated']
print(f'allocated_draw: {allocated_draw}')
return int(allocated_draw / available_power_total * 100)
|
Determine the utilization rate of power in the rack and return it as a percentage.
| 15 | 54 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_power_utilization(self):
powerfeeds = PowerFeed.objects.filter(rack=self)
available_power_total = sum(pf.available_power for pf in powerfeeds)
print(f'available_power_total: {available_power_total}')
if not available_power_total:
return 0
powerports = []
for powerfeed in powerfeeds:
powerports.extend([
peer for peer in powerfeed.link_peers if isinstance(peer, PowerPort)
])
allocated_draw = 0
for powerport in powerports:
allocated_draw += powerport.get_power_draw()['allocated']
print(f'allocated_draw: {allocated_draw}')
return int(allocated_draw / available_power_total * 100)
```
###Assistant :
Determine the utilization rate of power in the rack and return it as a percentage.
|
673 | def cleanup(self):
orphaned = []
for w in self.workers[::]:
if not w.alive:
# the worker process has exited
# 1. take the task it was running and enqueue the error
# callbacks
# 2. take any pending tasks delivered to its queue and
# send them to another worker
logger.error('worker pid:{} is gone (exit={})'.format(w.pid, w.exitcode))
if w.current_task:
if w.current_task != 'QUIT':
try:
for j in UnifiedJob.objects.filter(celery_task_id=w.current_task['uuid']):
reaper.reap_job(j, 'failed')
except Exception:
logger.exception('failed to reap job UUID {}'.format(w.current_task['uuid']))
orphaned.extend(w.orphaned_tasks)
self.workers.remove(w)
elif (len(self.workers) > self.min_workers) and w.ready_to_scale_down:
# the process has an empty queue (it's idle) and we have
# more processes in the pool than we need (> min)
# send this process a message so it will exit gracefully
# at the next opportunity
logger.info(f'scaling down worker pid:{w.pid} prior total:{len(self.workers)}')
w.quit()
self.workers.remove(w)
if w.alive:
# if we discover a task manager invocation that's been running
# too long, reap it (because otherwise it'll just hold the postgres
# advisory lock forever); the goal of this code is to discover
# deadlocks or other serious issues in the task manager that cause
# the task manager to never do more work
current_task = w.current_task
if current_task and isinstance(current_task, dict):
endings = ['tasks.task_manager', 'tasks.dependency_manager', 'tasks.workflow_manager']
current_task_name = current_task.get('task', '')
if any(current_task_name.endswith(e) for e in endings):
if 'started' not in current_task:
w.managed_tasks[current_task['uuid']]['started'] = time.time()
age = time.time() - current_task['started']
w.managed_tasks[current_task['uuid']]['age'] = age
if age > self.task_manager_timeout:
logger.error(f'{current_task_name} has held the advisory lock for {age}, sending SIGTERM to {w.pid}')
os.kill(w.pid, signal.SIGTERM)
for m in orphaned:
# if all the workers are dead, spawn at least one
if not len(self.workers):
self.up()
idx = random.choice(range(len(self.workers)))
self.write(idx, m)
|
Perform some internal account and cleanup. This is run on
every cluster node heartbeat:
1. Discover worker processes that exited, and recover messages they
were handling.
2. Clean up unnecessary, idle workers.
IMPORTANT: this function is one of the few places in the dispatcher
(aside from setting lookups) where we talk to the database. As such,
if there's an outage, this method _can_ throw various
django.db.utils.Error exceptions. Act accordingly.
| 69 | 270 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def cleanup(self):
orphaned = []
for w in self.workers[::]:
if not w.alive:
# the worker process has exited
# 1. take the task it was running and enqueue the error
# callbacks
# 2. take any pending tasks delivered to its queue and
# send them to another worker
logger.error('worker pid:{} is gone (exit={})'.format(w.pid, w.exitcode))
if w.current_task:
if w.current_task != 'QUIT':
try:
for j in UnifiedJob.objects.filter(celery_task_id=w.current_task['uuid']):
reaper.reap_job(j, 'failed')
except Exception:
logger.exception('failed to reap job UUID {}'.format(w.current_task['uuid']))
orphaned.extend(w.orphaned_tasks)
self.workers.remove(w)
elif (len(self.workers) > self.min_workers) and w.ready_to_scale_down:
# the process has an empty queue (it's idle) and we have
# more processes in the pool than we need (> min)
# send this process a message so it will exit gracefully
# at the next opportunity
logger.info(f'scaling down worker pid:{w.pid} prior total:{len(self.workers)}')
w.quit()
self.workers.remove(w)
if w.alive:
# if we discover a task manager invocation that's been running
# too long, reap it (because otherwise it'll just hold the postgres
# advisory lock forever); the goal of this code is to discover
# deadlocks or other serious issues in the task manager that cause
# the task manager to never do more work
current_task = w.current_task
if current_task and isinstance(current_task, dict):
endings = ['tasks.task_manager', 'tasks.dependency_manager', 'tasks.workflow_manager']
current_task_name = current_task.get('task', '')
if any(current_task_name.endswith(e) for e in endings):
if 'started' not in current_task:
w.managed_tasks[current_task['uuid']]['started'] = time.time()
age = time.time() - current_task['started']
w.managed_tasks[current_task['uuid']]['age'] = age
if age > self.task_manager_timeout:
logger.error(f'{current_task_name} has held the advisory lock for {age}, sending SIGTERM to {w.pid}')
os.kill(w.pid, signal.SIGTERM)
for m in orphaned:
# if all the workers are dead, spawn at least one
if not len(self.workers):
self.up()
idx = random.choice(range(len(self.workers)))
self.write(idx, m)
```
###Assistant :
Perform some internal account and cleanup. This is run on
every cluster node heartbeat:
1. Discover worker processes that exited, and recover messages they
were handling.
2. Clean up unnecessary, idle workers.
IMPORTANT: this function is one of the few places in the dispatcher
(aside from setting lookups) where we talk to the database. As such,
if there's an outage, this method _can_ throw various
django.db.utils.Error exceptions. Act accordingly.
|
674 | def test_token_node_empty_csrf_cookie(self):
req = self._get_request(cookie="")
mw = CsrfViewMiddleware(token_view)
mw.process_view(req, token_view, (), {})
resp = token_view(req)
token = get_token(req)
self.assertIsNotNone(token)
csrf_secret = _unmask_cipher_token(token)
self._check_token_present(resp, csrf_secret)
|
A new token is sent if the csrf_cookie is the empty string.
| 12 | 24 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_token_node_empty_csrf_cookie(self):
req = self._get_request(cookie="")
mw = CsrfViewMiddleware(token_view)
mw.process_view(req, token_view, (), {})
resp = token_view(req)
token = get_token(req)
self.assertIsNotNone(token)
csrf_secret = _unmask_cipher_token(token)
self._check_token_present(resp, csrf_secret)
```
###Assistant :
A new token is sent if the csrf_cookie is the empty string.
|
675 | def save(self, envs):
assert isinstance(envs, list), "envs should be a list"
if len(envs) > 0:
for env in envs:
assert isstr(env), "env should be a string"
return self._send(
{
"data": envs,
},
"save",
)
|
This function allows the user to save envs that are alive on the
Tornado server. The envs can be specified as a list of env ids.
| 26 | 34 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def save(self, envs):
assert isinstance(envs, list), "envs should be a list"
if len(envs) > 0:
for env in envs:
assert isstr(env), "env should be a string"
return self._send(
{
"data": envs,
},
"save",
)
```
###Assistant :
This function allows the user to save envs that are alive on the
Tornado server. The envs can be specified as a list of env ids.
|
676 | def test_has_related_field_in_list_display_o2o(self):
media = Media.objects.create(name="Foo")
Vodcast.objects.create(media=media)
response = self.client.get(reverse("admin:admin_views_vodcast_changelist"), {})
response.context["cl"].list_display = ["media"]
self.assertIs(response.context["cl"].has_related_field_in_list_display(), True)
response.context["cl"].list_display = ["media_id"]
self.assertIs(response.context["cl"].has_related_field_in_list_display(), False)
| Joins shouldn't be performed for <O2O>_id fields in list display. | 10 | 20 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_has_related_field_in_list_display_o2o(self):
media = Media.objects.create(name="Foo")
Vodcast.objects.create(media=media)
response = self.client.get(reverse("admin:admin_views_vodcast_changelist"), {})
response.context["cl"].list_display = ["media"]
self.assertIs(response.context["cl"].has_related_field_in_list_display(), True)
response.context["cl"].list_display = ["media_id"]
self.assertIs(response.context["cl"].has_related_field_in_list_display(), False)
```
###Assistant : Joins shouldn't be performed for <O2O>_id fields in list display.
|
677 | def binary_crossentropy(target, output, from_logits=False):
target = tf.convert_to_tensor(target)
output = tf.convert_to_tensor(output)
# Use logits whenever they are available. `softmax` and `sigmoid`
# activations cache logits on the `output` Tensor.
if hasattr(output, "_keras_logits"):
output = output._keras_logits # pylint: disable=protected-access
if from_logits:
warnings.warn(
'"`binary_crossentropy` received `from_logits=True`, but the `output`'
" argument was produced by a sigmoid or softmax activation and thus "
'does not represent logits. Was this intended?"',
stacklevel=2,
)
from_logits = True
if from_logits:
return tf.nn.sigmoid_cross_entropy_with_logits(
labels=target, logits=output
)
if (
not isinstance(output, (tf.__internal__.EagerTensor, tf.Variable))
and output.op.type == "Sigmoid"
) and not hasattr(output, "_keras_history"):
# When sigmoid activation function is used for output operation, we
# use logits from the sigmoid function directly to compute loss in order
# to prevent collapsing zero when training.
assert len(output.op.inputs) == 1
output = output.op.inputs[0]
return tf.nn.sigmoid_cross_entropy_with_logits(
labels=target, logits=output
)
epsilon_ = _constant_to_tensor(epsilon(), output.dtype.base_dtype)
output = tf.clip_by_value(output, epsilon_, 1.0 - epsilon_)
# Compute cross entropy from probabilities.
bce = target * tf.math.log(output + epsilon())
bce += (1 - target) * tf.math.log(1 - output + epsilon())
return -bce
@keras_export("keras.backend.binary_focal_crossentropy")
@tf.__internal__.dispatch.add_dispatch_support
@doc_controls.do_not_generate_docs | Binary crossentropy between an output tensor and a target tensor.
Args:
target: A tensor with the same shape as `output`.
output: A tensor.
from_logits: Whether `output` is expected to be a logits tensor.
By default, we consider that `output`
encodes a probability distribution.
Returns:
A tensor.
| 46 | 176 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def binary_crossentropy(target, output, from_logits=False):
target = tf.convert_to_tensor(target)
output = tf.convert_to_tensor(output)
# Use logits whenever they are available. `softmax` and `sigmoid`
# activations cache logits on the `output` Tensor.
if hasattr(output, "_keras_logits"):
output = output._keras_logits # pylint: disable=protected-access
if from_logits:
warnings.warn(
'"`binary_crossentropy` received `from_logits=True`, but the `output`'
" argument was produced by a sigmoid or softmax activation and thus "
'does not represent logits. Was this intended?"',
stacklevel=2,
)
from_logits = True
if from_logits:
return tf.nn.sigmoid_cross_entropy_with_logits(
labels=target, logits=output
)
if (
not isinstance(output, (tf.__internal__.EagerTensor, tf.Variable))
and output.op.type == "Sigmoid"
) and not hasattr(output, "_keras_history"):
# When sigmoid activation function is used for output operation, we
# use logits from the sigmoid function directly to compute loss in order
# to prevent collapsing zero when training.
assert len(output.op.inputs) == 1
output = output.op.inputs[0]
return tf.nn.sigmoid_cross_entropy_with_logits(
labels=target, logits=output
)
epsilon_ = _constant_to_tensor(epsilon(), output.dtype.base_dtype)
output = tf.clip_by_value(output, epsilon_, 1.0 - epsilon_)
# Compute cross entropy from probabilities.
bce = target * tf.math.log(output + epsilon())
bce += (1 - target) * tf.math.log(1 - output + epsilon())
return -bce
@keras_export("keras.backend.binary_focal_crossentropy")
@tf.__internal__.dispatch.add_dispatch_support
@doc_controls.do_not_generate_docs
```
###Assistant : Binary crossentropy between an output tensor and a target tensor.
Args:
target: A tensor with the same shape as `output`.
output: A tensor.
from_logits: Whether `output` is expected to be a logits tensor.
By default, we consider that `output`
encodes a probability distribution.
Returns:
A tensor.
|
678 | def test_process_pulled_event_with_missing_state(self) -> None:
return self._test_process_pulled_event_with_missing_state(False)
| Ensure that we correctly handle pulled events with lots of missing state
In this test, we pretend we are processing a "pulled" event (eg, via backfill
or get_missing_events). The pulled event has a prev_event we haven't previously
seen, so the server requests the state at that prev_event. There is a lot
of state we don't have, so we expect the server to make a /state request.
We check that the pulled event is correctly persisted, and that the state is
as we expect.
| 83 | 6 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_process_pulled_event_with_missing_state(self) -> None:
return self._test_process_pulled_event_with_missing_state(False)
```
###Assistant : Ensure that we correctly handle pulled events with lots of missing state
In this test, we pretend we are processing a "pulled" event (eg, via backfill
or get_missing_events). The pulled event has a prev_event we haven't previously
seen, so the server requests the state at that prev_event. There is a lot
of state we don't have, so we expect the server to make a /state request.
We check that the pulled event is correctly persisted, and that the state is
as we expect.
|
679 | def test_resolved_in_release(self, mock_func):
notification = ResolvedInReleaseActivityNotification(
Activity(
project=self.project,
group=self.group,
user=self.user,
type=ActivityType.SET_RESOLVED_IN_RELEASE,
data={"version": "meow"},
)
)
with self.tasks():
notification.send()
attachment, text = get_attachment()
release_name = notification.activity.data["version"]
assert text == f"Issue marked as resolved in {release_name} by {self.name}"
assert (
attachment["footer"]
== f"{self.project.slug} | <http://testserver/settings/account/notifications/workflow/?referrer=resolved_in_release_activity-slack-user|Notification Settings>"
)
|
Test that a Slack message is sent with the expected payload when an issue is resolved in a release
| 19 | 45 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_resolved_in_release(self, mock_func):
notification = ResolvedInReleaseActivityNotification(
Activity(
project=self.project,
group=self.group,
user=self.user,
type=ActivityType.SET_RESOLVED_IN_RELEASE,
data={"version": "meow"},
)
)
with self.tasks():
notification.send()
attachment, text = get_attachment()
release_name = notification.activity.data["version"]
assert text == f"Issue marked as resolved in {release_name} by {self.name}"
assert (
attachment["footer"]
== f"{self.project.slug} | <http://testserver/settings/account/notifications/workflow/?referrer=resolved_in_release_activity-slack-user|Notification Settings>"
)
```
###Assistant :
Test that a Slack message is sent with the expected payload when an issue is resolved in a release
|
680 | def get_vocabulary(self, include_special_tokens=True):
# The lookup table data will not be sorted, so we will create a inverted
# lookup here, and use that to lookup a range of indices [0,
# vocab_size).
if self.lookup_table.size() == 0:
vocab, indices = [], []
else:
keys, values = self.lookup_table.export()
vocab, indices = (values, keys) if self.invert else (keys, values)
vocab, indices = (
self._tensor_vocab_to_numpy(vocab),
indices.numpy(),
)
lookup = collections.defaultdict(
lambda: self.oov_token, zip(indices, vocab)
)
vocab = [lookup[x] for x in range(self.vocabulary_size())]
if self.mask_token is not None and self.output_mode == INT:
vocab[0] = self.mask_token
if not include_special_tokens:
vocab = vocab[self._token_start_index() :]
return vocab
| Returns the current vocabulary of the layer.
Args:
include_special_tokens: If True, the returned vocabulary will include
mask and OOV tokens, and a term's index in the vocabulary will equal
the term's index when calling the layer. If False, the returned
vocabulary will not include any mask or OOV tokens.
| 49 | 100 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_vocabulary(self, include_special_tokens=True):
# The lookup table data will not be sorted, so we will create a inverted
# lookup here, and use that to lookup a range of indices [0,
# vocab_size).
if self.lookup_table.size() == 0:
vocab, indices = [], []
else:
keys, values = self.lookup_table.export()
vocab, indices = (values, keys) if self.invert else (keys, values)
vocab, indices = (
self._tensor_vocab_to_numpy(vocab),
indices.numpy(),
)
lookup = collections.defaultdict(
lambda: self.oov_token, zip(indices, vocab)
)
vocab = [lookup[x] for x in range(self.vocabulary_size())]
if self.mask_token is not None and self.output_mode == INT:
vocab[0] = self.mask_token
if not include_special_tokens:
vocab = vocab[self._token_start_index() :]
return vocab
```
###Assistant : Returns the current vocabulary of the layer.
Args:
include_special_tokens: If True, the returned vocabulary will include
mask and OOV tokens, and a term's index in the vocabulary will equal
the term's index when calling the layer. If False, the returned
vocabulary will not include any mask or OOV tokens.
|
681 | def test_error_raised_with_float_limited_eval_batches():
model = BoringModel()
dl_size = len(model.val_dataloader())
limit_val_batches = 1 / (dl_size + 2)
trainer = Trainer(limit_val_batches=limit_val_batches)
trainer._data_connector.attach_data(model)
with pytest.raises(
MisconfigurationException,
match=fr"{limit_val_batches} \* {dl_size} < 1. Please increase the `limit_val_batches`",
):
trainer._data_connector._reset_eval_dataloader(RunningStage.VALIDATING, model)
@pytest.mark.parametrize(
"val_dl",
[
DataLoader(dataset=RandomDataset(32, 64), shuffle=True),
CombinedLoader(DataLoader(dataset=RandomDataset(32, 64), shuffle=True)),
CombinedLoader(
[DataLoader(dataset=RandomDataset(32, 64)), DataLoader(dataset=RandomDataset(32, 64), shuffle=True)]
),
CombinedLoader(
{
"dl1": DataLoader(dataset=RandomDataset(32, 64)),
"dl2": DataLoader(dataset=RandomDataset(32, 64), shuffle=True),
}
),
],
) | Test that an error is raised if there are not enough batches when passed with float value of
limit_eval_batches. | 19 | 63 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_error_raised_with_float_limited_eval_batches():
model = BoringModel()
dl_size = len(model.val_dataloader())
limit_val_batches = 1 / (dl_size + 2)
trainer = Trainer(limit_val_batches=limit_val_batches)
trainer._data_connector.attach_data(model)
with pytest.raises(
MisconfigurationException,
match=fr"{limit_val_batches} \* {dl_size} < 1. Please increase the `limit_val_batches`",
):
trainer._data_connector._reset_eval_dataloader(RunningStage.VALIDATING, model)
@pytest.mark.parametrize(
"val_dl",
[
DataLoader(dataset=RandomDataset(32, 64), shuffle=True),
CombinedLoader(DataLoader(dataset=RandomDataset(32, 64), shuffle=True)),
CombinedLoader(
[DataLoader(dataset=RandomDataset(32, 64)), DataLoader(dataset=RandomDataset(32, 64), shuffle=True)]
),
CombinedLoader(
{
"dl1": DataLoader(dataset=RandomDataset(32, 64)),
"dl2": DataLoader(dataset=RandomDataset(32, 64), shuffle=True),
}
),
],
)
```
###Assistant : Test that an error is raised if there are not enough batches when passed with float value of
limit_eval_batches.
|
682 | def not_none_device_or_backend_on_jit(backend, device, num_ins):
# TODO(yashkatariya): Remove this entire function when backend and device are
# removed as arguments on jit.
from jax.experimental import sharding
if device is not None and backend is not None:
raise ValueError("can't specify both a device and a backend for jit, "
"got device={} and backend={}".format(device, backend))
if backend is not None:
da = [xb.get_backend(backend).get_default_device_assignment(1)[0]]
else:
assert device is not None
da = [device]
assert len(da) == 1
# Set committed to True for this path because it simulates a device_put on
# behalf of a user.
committed = True
# in_shardings will be marked as replicated regardless of whatever the input
# had. Given that only a single device is allowed above, this is correct.
in_shardings = [sharding.OpShardingSharding.get_replicated(da)] * num_ins
return committed, da, in_shardings
| This is to support the backend and device argument on jit. It's a feature
that's deprecated but needs to be supported for feature parity and so that we
can delete the non-Array paths when Array is switched on.
| 38 | 130 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def not_none_device_or_backend_on_jit(backend, device, num_ins):
# TODO(yashkatariya): Remove this entire function when backend and device are
# removed as arguments on jit.
from jax.experimental import sharding
if device is not None and backend is not None:
raise ValueError("can't specify both a device and a backend for jit, "
"got device={} and backend={}".format(device, backend))
if backend is not None:
da = [xb.get_backend(backend).get_default_device_assignment(1)[0]]
else:
assert device is not None
da = [device]
assert len(da) == 1
# Set committed to True for this path because it simulates a device_put on
# behalf of a user.
committed = True
# in_shardings will be marked as replicated regardless of whatever the input
# had. Given that only a single device is allowed above, this is correct.
in_shardings = [sharding.OpShardingSharding.get_replicated(da)] * num_ins
return committed, da, in_shardings
```
###Assistant : This is to support the backend and device argument on jit. It's a feature
that's deprecated but needs to be supported for feature parity and so that we
can delete the non-Array paths when Array is switched on.
|
683 | def is_mouse_scrolling(self, *args):
return 'button' in self.profile and 'scroll' in self.button
| Returns True if the touch event is a mousewheel scrolling
.. versionadded:: 1.6.0
| 13 | 11 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def is_mouse_scrolling(self, *args):
return 'button' in self.profile and 'scroll' in self.button
```
###Assistant : Returns True if the touch event is a mousewheel scrolling
.. versionadded:: 1.6.0
|
684 | def easy_print(*args, size=(None, None), end=None, sep=None, location=(None, None), relative_location=(None, None), font=None, no_titlebar=False,
no_button=False, grab_anywhere=False, keep_on_top=None, do_not_reroute_stdout=True, echo_stdout=False, text_color=None, background_color=None, colors=None, c=None,
erase_all=False, resizable=True, blocking=None):
if _DebugWin.debug_window is None:
_DebugWin.debug_window = _DebugWin(size=size, location=location, relative_location=relative_location, font=font, no_titlebar=no_titlebar,
no_button=no_button, grab_anywhere=grab_anywhere, keep_on_top=keep_on_top,
do_not_reroute_stdout=do_not_reroute_stdout, echo_stdout=echo_stdout, resizable=resizable, blocking=blocking)
txt_color, bg_color = _parse_colors_parm(c or colors)
_DebugWin.debug_window.Print(*args, end=end, sep=sep, text_color=text_color or txt_color, background_color=background_color or bg_color,
erase_all=erase_all, font=font, blocking=blocking)
|
Works like a "print" statement but with windowing options. Routes output to the "Debug Window"
In addition to the normal text and background colors, you can use a "colors" tuple/string
The "colors" or "c" parameter defines both the text and background in a single parm.
It can be a tuple or a single single. Both text and background colors need to be specified
colors -(str, str) or str. A combined text/background color definition in a single parameter
c - (str, str) - Colors tuple has format (foreground, backgrouned)
c - str - can also be a string of the format "foreground on background" ("white on red")
:param *args: stuff to output
:type *args: (Any)
:param size: (w,h) w=characters-wide, h=rows-high
:type size: (int, int)
:param end: end character
:type end: (str)
:param sep: separator character
:type sep: (str)
:param location: Location of upper left corner of the window
:type location: (int, int)
:param relative_location: (x,y) location relative to the default location of the window, in pixels. Normally the window centers. This location is relative to the location the window would be created. Note they can be negative.
:type relative_location: (int, int)
:param font: specifies the font family, size, etc. Tuple or Single string format 'name size styles'. Styles: italic * roman bold normal underline overstrike
:type font: (str or (str, int[, str]) or None)
:param no_titlebar: If True no titlebar will be shown
:type no_titlebar: (bool)
:param no_button: don't show button
:type no_button: (bool)
:param grab_anywhere: If True: can grab anywhere to move the window (Default = False)
:type grab_anywhere: (bool)
:param background_color: color of background
:type background_color: (str)
:param text_color: color of the text
:type text_color: (str)
:param keep_on_top: If True the window will remain above all current windows
:type keep_on_top: (bool)
:param location: Location of upper left corner of the window
:type location: (int, int)
:param do_not_reroute_stdout: do not reroute stdout and stderr. If False, both stdout and stderr will reroute to here
:type do_not_reroute_stdout: (bool)
:param echo_stdout: If True stdout is sent to both the console and the debug window
:type echo_stdout: (bool)
:param colors: Either a tuple or a string that has both the text and background colors
:type colors: (str) or (str, str)
:param c: Either a tuple or a string that has both the text and background colors
:type c: (str) or (str, str)
:param resizable: if True, the user can resize the debug window. Default is True
:type resizable: (bool)
:param erase_all: If True when erase the output before printing
:type erase_all: (bool)
:param blocking: if True, makes the window block instead of returning immediately. The "Quit" button changers to "More"
:type blocking: (bool | None)
:return:
:rtype:
| 444 | 60 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def easy_print(*args, size=(None, None), end=None, sep=None, location=(None, None), relative_location=(None, None), font=None, no_titlebar=False,
no_button=False, grab_anywhere=False, keep_on_top=None, do_not_reroute_stdout=True, echo_stdout=False, text_color=None, background_color=None, colors=None, c=None,
erase_all=False, resizable=True, blocking=None):
if _DebugWin.debug_window is None:
_DebugWin.debug_window = _DebugWin(size=size, location=location, relative_location=relative_location, font=font, no_titlebar=no_titlebar,
no_button=no_button, grab_anywhere=grab_anywhere, keep_on_top=keep_on_top,
do_not_reroute_stdout=do_not_reroute_stdout, echo_stdout=echo_stdout, resizable=resizable, blocking=blocking)
txt_color, bg_color = _parse_colors_parm(c or colors)
_DebugWin.debug_window.Print(*args, end=end, sep=sep, text_color=text_color or txt_color, background_color=background_color or bg_color,
erase_all=erase_all, font=font, blocking=blocking)
```
###Assistant :
Works like a "print" statement but with windowing options. Routes output to the "Debug Window"
In addition to the normal text and background colors, you can use a "colors" tuple/string
The "colors" or "c" parameter defines both the text and background in a single parm.
It can be a tuple or a single single. Both text and background colors need to be specified
colors -(str, str) or str. A combined text/background color definition in a single parameter
c - (str, str) - Colors tuple has format (foreground, backgrouned)
c - str - can also be a string of the format "foreground on background" ("white on red")
:param *args: stuff to output
:type *args: (Any)
:param size: (w,h) w=characters-wide, h=rows-high
:type size: (int, int)
:param end: end character
:type end: (str)
:param sep: separator character
:type sep: (str)
:param location: Location of upper left corner of the window
:type location: (int, int)
:param relative_location: (x,y) location relative to the default location of the window, in pixels. Normally the window centers. This location is relative to the location the window would be created. Note they can be negative.
:type relative_location: (int, int)
:param font: specifies the font family, size, etc. Tuple or Single string format 'name size styles'. Styles: italic * roman bold normal underline overstrike
:type font: (str or (str, int[, str]) or None)
:param no_titlebar: If True no titlebar will be shown
:type no_titlebar: (bool)
:param no_button: don't show button
:type no_button: (bool)
:param grab_anywhere: If True: can grab anywhere to move the window (Default = False)
:type grab_anywhere: (bool)
:param background_color: color of background
:type background_color: (str)
:param text_color: color of the text
:type text_color: (str)
:param keep_on_top: If True the window will remain above all current windows
:type keep_on_top: (bool)
:param location: Location of upper left corner of the window
:type location: (int, int)
:param do_not_reroute_stdout: do not reroute stdout and stderr. If False, both stdout and stderr will reroute to here
:type do_not_reroute_stdout: (bool)
:param echo_stdout: If True stdout is sent to both the console and the debug window
:type echo_stdout: (bool)
:param colors: Either a tuple or a string that has both the text and background colors
:type colors: (str) or (str, str)
:param c: Either a tuple or a string that has both the text and background colors
:type c: (str) or (str, str)
:param resizable: if True, the user can resize the debug window. Default is True
:type resizable: (bool)
:param erase_all: If True when erase the output before printing
:type erase_all: (bool)
:param blocking: if True, makes the window block instead of returning immediately. The "Quit" button changers to "More"
:type blocking: (bool | None)
:return:
:rtype:
|
685 | def wait_start_success(self):
_timeout = self.args.timeout_ready
if _timeout <= 0:
_timeout = None
else:
_timeout /= 1e3
if self._wait_for_ready_or_shutdown(_timeout):
self._check_failed_to_start()
self.logger.debug(__ready_msg__)
else:
self._fail_start_timeout(_timeout)
| Block until all pods starts successfully.
If not success, it will raise an error hoping the outer function to catch it
| 21 | 22 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def wait_start_success(self):
_timeout = self.args.timeout_ready
if _timeout <= 0:
_timeout = None
else:
_timeout /= 1e3
if self._wait_for_ready_or_shutdown(_timeout):
self._check_failed_to_start()
self.logger.debug(__ready_msg__)
else:
self._fail_start_timeout(_timeout)
```
###Assistant : Block until all pods starts successfully.
If not success, it will raise an error hoping the outer function to catch it
|
686 | def _rank_decomposition(M, iszerofunc=_iszero, simplify=False):
r
F, pivot_cols = M.rref(simplify=simplify, iszerofunc=iszerofunc,
pivots=True)
rank = len(pivot_cols)
C = M.extract(range(M.rows), pivot_cols)
F = F[:rank, :]
return C, F
| Returns a pair of matrices (`C`, `F`) with matching rank
such that `A = C F`.
Parameters
==========
iszerofunc : Function, optional
A function used for detecting whether an element can
act as a pivot. ``lambda x: x.is_zero`` is used by default.
simplify : Bool or Function, optional
A function used to simplify elements when looking for a
pivot. By default SymPy's ``simplify`` is used.
Returns
=======
(C, F) : Matrices
`C` and `F` are full-rank matrices with rank as same as `A`,
whose product gives `A`.
See Notes for additional mathematical details.
Examples
========
>>> from sympy import Matrix
>>> A = Matrix([
... [1, 3, 1, 4],
... [2, 7, 3, 9],
... [1, 5, 3, 1],
... [1, 2, 0, 8]
... ])
>>> C, F = A.rank_decomposition()
>>> C
Matrix([
[1, 3, 4],
[2, 7, 9],
[1, 5, 1],
[1, 2, 8]])
>>> F
Matrix([
[1, 0, -2, 0],
[0, 1, 1, 0],
[0, 0, 0, 1]])
>>> C * F == A
True
Notes
=====
Obtaining `F`, an RREF of `A`, is equivalent to creating a
product
.. math::
E_n E_{n-1} ... E_1 A = F
where `E_n, E_{n-1}, \dots, E_1` are the elimination matrices or
permutation matrices equivalent to each row-reduction step.
The inverse of the same product of elimination matrices gives
`C`:
.. math::
C = \left(E_n E_{n-1} \dots E_1\right)^{-1}
It is not necessary, however, to actually compute the inverse:
the columns of `C` are those from the original matrix with the
same column indices as the indices of the pivot columns of `F`.
References
==========
.. [1] https://en.wikipedia.org/wiki/Rank_factorization
.. [2] Piziak, R.; Odell, P. L. (1 June 1999).
"Full Rank Factorization of Matrices".
Mathematics Magazine. 72 (3): 193. doi:10.2307/2690882
See Also
========
sympy.matrices.matrices.MatrixReductions.rref
| 291 | 25 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _rank_decomposition(M, iszerofunc=_iszero, simplify=False):
r
F, pivot_cols = M.rref(simplify=simplify, iszerofunc=iszerofunc,
pivots=True)
rank = len(pivot_cols)
C = M.extract(range(M.rows), pivot_cols)
F = F[:rank, :]
return C, F
```
###Assistant : Returns a pair of matrices (`C`, `F`) with matching rank
such that `A = C F`.
Parameters
==========
iszerofunc : Function, optional
A function used for detecting whether an element can
act as a pivot. ``lambda x: x.is_zero`` is used by default.
simplify : Bool or Function, optional
A function used to simplify elements when looking for a
pivot. By default SymPy's ``simplify`` is used.
Returns
=======
(C, F) : Matrices
`C` and `F` are full-rank matrices with rank as same as `A`,
whose product gives `A`.
See Notes for additional mathematical details.
Examples
========
>>> from sympy import Matrix
>>> A = Matrix([
... [1, 3, 1, 4],
... [2, 7, 3, 9],
... [1, 5, 3, 1],
... [1, 2, 0, 8]
... ])
>>> C, F = A.rank_decomposition()
>>> C
Matrix([
[1, 3, 4],
[2, 7, 9],
[1, 5, 1],
[1, 2, 8]])
>>> F
Matrix([
[1, 0, -2, 0],
[0, 1, 1, 0],
[0, 0, 0, 1]])
>>> C * F == A
True
Notes
=====
Obtaining `F`, an RREF of `A`, is equivalent to creating a
product
.. math::
E_n E_{n-1} ... E_1 A = F
where `E_n, E_{n-1}, \dots, E_1` are the elimination matrices or
permutation matrices equivalent to each row-reduction step.
The inverse of the same product of elimination matrices gives
`C`:
.. math::
C = \left(E_n E_{n-1} \dots E_1\right)^{-1}
It is not necessary, however, to actually compute the inverse:
the columns of `C` are those from the original matrix with the
same column indices as the indices of the pivot columns of `F`.
References
==========
.. [1] https://en.wikipedia.org/wiki/Rank_factorization
.. [2] Piziak, R.; Odell, P. L. (1 June 1999).
"Full Rank Factorization of Matrices".
Mathematics Magazine. 72 (3): 193. doi:10.2307/2690882
See Also
========
sympy.matrices.matrices.MatrixReductions.rref
|
687 | def normalize(X, norm="l2", *, axis=1, copy=True, return_norm=False):
if norm not in ("l1", "l2", "max"):
raise ValueError("'%s' is not a supported norm" % norm)
if axis == 0:
sparse_format = "csc"
elif axis == 1:
sparse_format = "csr"
else:
raise ValueError("'%d' is not a supported axis" % axis)
X = check_array(
X,
accept_sparse=sparse_format,
copy=copy,
estimator="the normalize function",
dtype=FLOAT_DTYPES,
)
if axis == 0:
X = X.T
if sparse.issparse(X):
if return_norm and norm in ("l1", "l2"):
raise NotImplementedError(
"return_norm=True is not implemented "
"for sparse matrices with norm 'l1' "
"or norm 'l2'"
)
if norm == "l1":
inplace_csr_row_normalize_l1(X)
elif norm == "l2":
inplace_csr_row_normalize_l2(X)
elif norm == "max":
mins, maxes = min_max_axis(X, 1)
norms = np.maximum(abs(mins), maxes)
norms_elementwise = norms.repeat(np.diff(X.indptr))
mask = norms_elementwise != 0
X.data[mask] /= norms_elementwise[mask]
else:
if norm == "l1":
norms = np.abs(X).sum(axis=1)
elif norm == "l2":
norms = row_norms(X)
elif norm == "max":
norms = np.max(abs(X), axis=1)
norms = _handle_zeros_in_scale(norms, copy=False)
X /= norms[:, np.newaxis]
if axis == 0:
X = X.T
if return_norm:
return X, norms
else:
return X
| Scale input vectors individually to unit norm (vector length).
Read more in the :ref:`User Guide <preprocessing_normalization>`.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data to normalize, element by element.
scipy.sparse matrices should be in CSR format to avoid an
un-necessary copy.
norm : {'l1', 'l2', 'max'}, default='l2'
The norm to use to normalize each non zero sample (or each non-zero
feature if axis is 0).
axis : {0, 1}, default=1
axis used to normalize the data along. If 1, independently normalize
each sample, otherwise (if 0) normalize each feature.
copy : bool, default=True
Set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix and if axis is 1).
return_norm : bool, default=False
Whether to return the computed norms.
Returns
-------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
Normalized input X.
norms : ndarray of shape (n_samples, ) if axis=1 else (n_features, )
An array of norms along given axis for X.
When X is sparse, a NotImplementedError will be raised
for norm 'l1' or 'l2'.
See Also
--------
Normalizer : Performs normalization using the Transformer API
(e.g. as part of a preprocessing :class:`~sklearn.pipeline.Pipeline`).
Notes
-----
For a comparison of the different scalers, transformers, and normalizers,
see :ref:`examples/preprocessing/plot_all_scaling.py
<sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.
| 220 | 172 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def normalize(X, norm="l2", *, axis=1, copy=True, return_norm=False):
if norm not in ("l1", "l2", "max"):
raise ValueError("'%s' is not a supported norm" % norm)
if axis == 0:
sparse_format = "csc"
elif axis == 1:
sparse_format = "csr"
else:
raise ValueError("'%d' is not a supported axis" % axis)
X = check_array(
X,
accept_sparse=sparse_format,
copy=copy,
estimator="the normalize function",
dtype=FLOAT_DTYPES,
)
if axis == 0:
X = X.T
if sparse.issparse(X):
if return_norm and norm in ("l1", "l2"):
raise NotImplementedError(
"return_norm=True is not implemented "
"for sparse matrices with norm 'l1' "
"or norm 'l2'"
)
if norm == "l1":
inplace_csr_row_normalize_l1(X)
elif norm == "l2":
inplace_csr_row_normalize_l2(X)
elif norm == "max":
mins, maxes = min_max_axis(X, 1)
norms = np.maximum(abs(mins), maxes)
norms_elementwise = norms.repeat(np.diff(X.indptr))
mask = norms_elementwise != 0
X.data[mask] /= norms_elementwise[mask]
else:
if norm == "l1":
norms = np.abs(X).sum(axis=1)
elif norm == "l2":
norms = row_norms(X)
elif norm == "max":
norms = np.max(abs(X), axis=1)
norms = _handle_zeros_in_scale(norms, copy=False)
X /= norms[:, np.newaxis]
if axis == 0:
X = X.T
if return_norm:
return X, norms
else:
return X
```
###Assistant : Scale input vectors individually to unit norm (vector length).
Read more in the :ref:`User Guide <preprocessing_normalization>`.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data to normalize, element by element.
scipy.sparse matrices should be in CSR format to avoid an
un-necessary copy.
norm : {'l1', 'l2', 'max'}, default='l2'
The norm to use to normalize each non zero sample (or each non-zero
feature if axis is 0).
axis : {0, 1}, default=1
axis used to normalize the data along. If 1, independently normalize
each sample, otherwise (if 0) normalize each feature.
copy : bool, default=True
Set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix and if axis is 1).
return_norm : bool, default=False
Whether to return the computed norms.
Returns
-------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
Normalized input X.
norms : ndarray of shape (n_samples, ) if axis=1 else (n_features, )
An array of norms along given axis for X.
When X is sparse, a NotImplementedError will be raised
for norm 'l1' or 'l2'.
See Also
--------
Normalizer : Performs normalization using the Transformer API
(e.g. as part of a preprocessing :class:`~sklearn.pipeline.Pipeline`).
Notes
-----
For a comparison of the different scalers, transformers, and normalizers,
see :ref:`examples/preprocessing/plot_all_scaling.py
<sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.
|
688 | def find_version_to_install(self, name):
version = Version.parse(name)
if version.patch is not None:
return name
try:
best_match = max(
(
inst_version
for inst_version in self.iter_installable_versions()
if inst_version.matches_minor(version)
),
key=operator.attrgetter("cmpkey"),
)
except ValueError:
raise ValueError(
f"no installable version found for {name!r}",
)
return best_match
| Find a version in the installer from the version supplied.
A ValueError is raised if a matching version cannot be found.
| 21 | 41 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def find_version_to_install(self, name):
version = Version.parse(name)
if version.patch is not None:
return name
try:
best_match = max(
(
inst_version
for inst_version in self.iter_installable_versions()
if inst_version.matches_minor(version)
),
key=operator.attrgetter("cmpkey"),
)
except ValueError:
raise ValueError(
f"no installable version found for {name!r}",
)
return best_match
```
###Assistant : Find a version in the installer from the version supplied.
A ValueError is raised if a matching version cannot be found.
|
689 | def copy_safe_request(request):
meta = {
k: request.META[k]
for k in HTTP_REQUEST_META_SAFE_COPY
if k in request.META and isinstance(request.META[k], str)
}
return NetBoxFakeRequest({
'META': meta,
'COOKIES': request.COOKIES,
'POST': request.POST,
'GET': request.GET,
'FILES': request.FILES,
'user': request.user,
'path': request.path,
'id': getattr(request, 'id', None), # UUID assigned by middleware
})
|
Copy selected attributes from a request object into a new fake request object. This is needed in places where
thread safe pickling of the useful request data is needed.
| 29 | 45 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def copy_safe_request(request):
meta = {
k: request.META[k]
for k in HTTP_REQUEST_META_SAFE_COPY
if k in request.META and isinstance(request.META[k], str)
}
return NetBoxFakeRequest({
'META': meta,
'COOKIES': request.COOKIES,
'POST': request.POST,
'GET': request.GET,
'FILES': request.FILES,
'user': request.user,
'path': request.path,
'id': getattr(request, 'id', None), # UUID assigned by middleware
})
```
###Assistant :
Copy selected attributes from a request object into a new fake request object. This is needed in places where
thread safe pickling of the useful request data is needed.
|
690 | def batchify(self, obs_batch, sort=False):
batch = super().batchify(obs_batch, sort=sort)
if batch.valid_indices is None:
return batch
batch.classifier_label = torch.tensor(
[
[obs_batch[i].get('classifier_label_idx', -1)]
for i in batch.valid_indices
]
)
batch.is_ltr = torch.tensor(
[[obs_batch[i].get('is_ltr', False)] for i in batch.valid_indices]
)
return batch
|
This method calls the parent class's batchify method and then add
classifier_label and is_ltr property to the the batch.
| 19 | 38 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def batchify(self, obs_batch, sort=False):
batch = super().batchify(obs_batch, sort=sort)
if batch.valid_indices is None:
return batch
batch.classifier_label = torch.tensor(
[
[obs_batch[i].get('classifier_label_idx', -1)]
for i in batch.valid_indices
]
)
batch.is_ltr = torch.tensor(
[[obs_batch[i].get('is_ltr', False)] for i in batch.valid_indices]
)
return batch
```
###Assistant :
This method calls the parent class's batchify method and then add
classifier_label and is_ltr property to the the batch.
|
691 | def calculate_post_conv_height(height, kernel_size, stride, pad, n_convs):
for _ in range(n_convs):
height = (height - kernel_size + 2 * pad) // stride + 1
return height
| Height of spec after n convolutions with fixed kernel/stride/pad. | 9 | 25 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def calculate_post_conv_height(height, kernel_size, stride, pad, n_convs):
for _ in range(n_convs):
height = (height - kernel_size + 2 * pad) // stride + 1
return height
```
###Assistant : Height of spec after n convolutions with fixed kernel/stride/pad.
|
692 | async def test_hls_playlist_view(hass, setup_component, hls_stream, stream_worker_sync):
stream = create_stream(hass, STREAM_SOURCE, {}, dynamic_stream_settings())
stream_worker_sync.pause()
hls = stream.add_provider(HLS_PROVIDER)
for i in range(2):
segment = Segment(sequence=i, duration=SEGMENT_DURATION)
hls.put(segment)
await hass.async_block_till_done()
hls_client = await hls_stream(stream)
resp = await hls_client.get("/playlist.m3u8")
assert resp.status == HTTPStatus.OK
assert await resp.text() == make_playlist(
sequence=0, segments=[make_segment(0), make_segment(1)]
)
segment = Segment(sequence=2, duration=SEGMENT_DURATION)
hls.put(segment)
await hass.async_block_till_done()
resp = await hls_client.get("/playlist.m3u8")
assert resp.status == HTTPStatus.OK
assert await resp.text() == make_playlist(
sequence=0, segments=[make_segment(0), make_segment(1), make_segment(2)]
)
stream_worker_sync.resume()
await stream.stop()
| Test rendering the hls playlist with 1 and 2 output segments. | 11 | 76 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def test_hls_playlist_view(hass, setup_component, hls_stream, stream_worker_sync):
stream = create_stream(hass, STREAM_SOURCE, {}, dynamic_stream_settings())
stream_worker_sync.pause()
hls = stream.add_provider(HLS_PROVIDER)
for i in range(2):
segment = Segment(sequence=i, duration=SEGMENT_DURATION)
hls.put(segment)
await hass.async_block_till_done()
hls_client = await hls_stream(stream)
resp = await hls_client.get("/playlist.m3u8")
assert resp.status == HTTPStatus.OK
assert await resp.text() == make_playlist(
sequence=0, segments=[make_segment(0), make_segment(1)]
)
segment = Segment(sequence=2, duration=SEGMENT_DURATION)
hls.put(segment)
await hass.async_block_till_done()
resp = await hls_client.get("/playlist.m3u8")
assert resp.status == HTTPStatus.OK
assert await resp.text() == make_playlist(
sequence=0, segments=[make_segment(0), make_segment(1), make_segment(2)]
)
stream_worker_sync.resume()
await stream.stop()
```
###Assistant : Test rendering the hls playlist with 1 and 2 output segments.
|
693 | def _create_local_rank_map(self) -> Dict:
rank_mapping = {}
ip_dict = defaultdict(int)
for world_rank in range(len(self.worker_group)):
worker = self.worker_group.workers[world_rank]
node_ip = worker.metadata.node_ip
rank_mapping[world_rank] = ip_dict[node_ip]
ip_dict[node_ip] += 1
return rank_mapping
| Create mapping from worker world_rank to local_rank.
Example:
Worker 0: 0.0.0.0
Worker 1: 0.0.0.0
Worker 2: 0.0.0.1
Worker 3: 0.0.0.0
Worker 4: 0.0.0.1
Workers 0, 1, 3 are on 0.0.0.0.
Workers 2, 4 are on 0.0.0.1.
Expected Output:
{
0 -> 0,
1 -> 1,
2 -> 0,
3 -> 2,
4 -> 1
}
| 55 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _create_local_rank_map(self) -> Dict:
rank_mapping = {}
ip_dict = defaultdict(int)
for world_rank in range(len(self.worker_group)):
worker = self.worker_group.workers[world_rank]
node_ip = worker.metadata.node_ip
rank_mapping[world_rank] = ip_dict[node_ip]
ip_dict[node_ip] += 1
return rank_mapping
```
###Assistant : Create mapping from worker world_rank to local_rank.
Example:
Worker 0: 0.0.0.0
Worker 1: 0.0.0.0
Worker 2: 0.0.0.1
Worker 3: 0.0.0.0
Worker 4: 0.0.0.1
Workers 0, 1, 3 are on 0.0.0.0.
Workers 2, 4 are on 0.0.0.1.
Expected Output:
{
0 -> 0,
1 -> 1,
2 -> 0,
3 -> 2,
4 -> 1
}
|
694 | def _output_groups(self) -> None:
is_rename = self._args.sort_method != "none"
logger.info("Creating %s group folders in '%s'.",
len(self._sorter.binned), self._args.output_dir)
bin_names = [f"_{b}" for b in self._sorter.bin_names]
if is_rename:
bin_names = [f"{name}_by_{self._args.sort_method}" for name in bin_names]
for name in bin_names:
folder = os.path.join(self._args.output_dir, name)
if os.path.exists(folder):
rmtree(folder)
os.makedirs(folder)
description = f"{'Copying' if self._args.keep_original else 'Moving'} into groups"
description += " and renaming" if is_rename else ""
pbar = tqdm(range(len(self._sorter.sorted_filelist)),
desc=description,
file=sys.stdout,
leave=False)
idx = 0
for bin_id, bin_ in enumerate(self._sorter.binned):
pbar.set_description(f"{description}: Bin {bin_id + 1} of {len(self._sorter.binned)}")
output_path = os.path.join(self._args.output_dir, bin_names[bin_id])
if not bin_:
logger.debug("Removing empty bin: %s", output_path)
os.rmdir(output_path)
for source in bin_:
basename = os.path.basename(source)
dst_name = f"{idx:06d}_{basename}" if is_rename else basename
dest = os.path.join(output_path, dst_name)
self._sort_file(source, dest)
idx += 1
pbar.update(1)
# Output methods | Move the files to folders.
Obtains the bins and original filenames from :attr:`_sorter` and outputs into appropriate
bins in the output location
| 22 | 124 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _output_groups(self) -> None:
is_rename = self._args.sort_method != "none"
logger.info("Creating %s group folders in '%s'.",
len(self._sorter.binned), self._args.output_dir)
bin_names = [f"_{b}" for b in self._sorter.bin_names]
if is_rename:
bin_names = [f"{name}_by_{self._args.sort_method}" for name in bin_names]
for name in bin_names:
folder = os.path.join(self._args.output_dir, name)
if os.path.exists(folder):
rmtree(folder)
os.makedirs(folder)
description = f"{'Copying' if self._args.keep_original else 'Moving'} into groups"
description += " and renaming" if is_rename else ""
pbar = tqdm(range(len(self._sorter.sorted_filelist)),
desc=description,
file=sys.stdout,
leave=False)
idx = 0
for bin_id, bin_ in enumerate(self._sorter.binned):
pbar.set_description(f"{description}: Bin {bin_id + 1} of {len(self._sorter.binned)}")
output_path = os.path.join(self._args.output_dir, bin_names[bin_id])
if not bin_:
logger.debug("Removing empty bin: %s", output_path)
os.rmdir(output_path)
for source in bin_:
basename = os.path.basename(source)
dst_name = f"{idx:06d}_{basename}" if is_rename else basename
dest = os.path.join(output_path, dst_name)
self._sort_file(source, dest)
idx += 1
pbar.update(1)
# Output methods
```
###Assistant : Move the files to folders.
Obtains the bins and original filenames from :attr:`_sorter` and outputs into appropriate
bins in the output location
|
695 | def _setSharedLibraryRPATHElf(filename, rpath):
# TODO: Might write something that makes a shell script replacement
# in case no rpath is present, or use patchelf, for now our use
# case seems to use rpaths for executables.
# patchelf --set-rpath "$ORIGIN/path/to/library" <executable>
with withEnvironmentVarOverriden("LANG", "C"):
executeToolChecked(
logger=postprocessing_logger,
command=("patchelf", "--set-rpath", rpath, filename),
stderr_filter=_filterPatchelfErrorOutput,
absence_message=,
)
| \
Error, needs 'patchelf' on your system, due to 'RPATH' settings that need to be
set. | 16 | 53 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _setSharedLibraryRPATHElf(filename, rpath):
# TODO: Might write something that makes a shell script replacement
# in case no rpath is present, or use patchelf, for now our use
# case seems to use rpaths for executables.
# patchelf --set-rpath "$ORIGIN/path/to/library" <executable>
with withEnvironmentVarOverriden("LANG", "C"):
executeToolChecked(
logger=postprocessing_logger,
command=("patchelf", "--set-rpath", rpath, filename),
stderr_filter=_filterPatchelfErrorOutput,
absence_message=,
)
```
###Assistant : \
Error, needs 'patchelf' on your system, due to 'RPATH' settings that need to be
set.
|
696 | def _get_columns(self):
if self._columns_cache is None:
self._columns_cache, column_widths = self._compute_axis_labels_and_lengths(
1
)
if self._column_widths_cache is None:
self._column_widths_cache = column_widths
return self._columns_cache
|
Get the columns from the cache object.
Returns
-------
pandas.Index
An index object containing the column labels.
| 17 | 21 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _get_columns(self):
if self._columns_cache is None:
self._columns_cache, column_widths = self._compute_axis_labels_and_lengths(
1
)
if self._column_widths_cache is None:
self._column_widths_cache = column_widths
return self._columns_cache
```
###Assistant :
Get the columns from the cache object.
Returns
-------
pandas.Index
An index object containing the column labels.
|
697 | async def async_update(self) -> None:
# Update values from controller's device dictionary
self._connected = self._controller.is_connected
self._current_temp = self._controller.get_temperature(self._device_id)
self._fan_speed = self._controller.get_fan_speed(self._device_id)
self._power = self._controller.is_on(self._device_id)
self._min_temp = self._controller.get_min_setpoint(self._device_id)
self._max_temp = self._controller.get_max_setpoint(self._device_id)
self._rssi = self._controller.get_rssi(self._device_id)
self._run_hours = self._controller.get_run_hours(self._device_id)
self._target_temp = self._controller.get_setpoint(self._device_id)
self._outdoor_temp = self._controller.get_outdoor_temperature(self._device_id)
# Operation mode
mode = self._controller.get_mode(self._device_id)
self._hvac_mode = MAP_IH_TO_HVAC_MODE.get(mode)
# Preset mode
preset = self._controller.get_preset_mode(self._device_id)
self._preset = MAP_IH_TO_PRESET_MODE.get(preset)
# Swing mode
# Climate module only supports one swing setting.
self._vvane = self._controller.get_vertical_swing(self._device_id)
self._hvane = self._controller.get_horizontal_swing(self._device_id)
# Power usage
self._power_consumption_heat = self._controller.get_heat_power_consumption(
self._device_id
)
self._power_consumption_cool = self._controller.get_cool_power_consumption(
self._device_id
)
| Copy values from controller dictionary to climate device. | 8 | 90 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def async_update(self) -> None:
# Update values from controller's device dictionary
self._connected = self._controller.is_connected
self._current_temp = self._controller.get_temperature(self._device_id)
self._fan_speed = self._controller.get_fan_speed(self._device_id)
self._power = self._controller.is_on(self._device_id)
self._min_temp = self._controller.get_min_setpoint(self._device_id)
self._max_temp = self._controller.get_max_setpoint(self._device_id)
self._rssi = self._controller.get_rssi(self._device_id)
self._run_hours = self._controller.get_run_hours(self._device_id)
self._target_temp = self._controller.get_setpoint(self._device_id)
self._outdoor_temp = self._controller.get_outdoor_temperature(self._device_id)
# Operation mode
mode = self._controller.get_mode(self._device_id)
self._hvac_mode = MAP_IH_TO_HVAC_MODE.get(mode)
# Preset mode
preset = self._controller.get_preset_mode(self._device_id)
self._preset = MAP_IH_TO_PRESET_MODE.get(preset)
# Swing mode
# Climate module only supports one swing setting.
self._vvane = self._controller.get_vertical_swing(self._device_id)
self._hvane = self._controller.get_horizontal_swing(self._device_id)
# Power usage
self._power_consumption_heat = self._controller.get_heat_power_consumption(
self._device_id
)
self._power_consumption_cool = self._controller.get_cool_power_consumption(
self._device_id
)
```
###Assistant : Copy values from controller dictionary to climate device.
|
698 | def test_kb_valid_entities(nlp):
mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=3)
# adding entities
mykb.add_entity(entity="Q1", freq=19, entity_vector=[8, 4, 3])
mykb.add_entity(entity="Q2", freq=5, entity_vector=[2, 1, 0])
mykb.add_entity(entity="Q3", freq=25, entity_vector=[-1, -6, 5])
# adding aliases
mykb.add_alias(alias="douglas", entities=["Q2", "Q3"], probabilities=[0.8, 0.2])
mykb.add_alias(alias="adam", entities=["Q2"], probabilities=[0.9])
# test the size of the corresponding KB
assert mykb.get_size_entities() == 3
assert mykb.get_size_aliases() == 2
# test retrieval of the entity vectors
assert mykb.get_vector("Q1") == [8, 4, 3]
assert mykb.get_vector("Q2") == [2, 1, 0]
assert mykb.get_vector("Q3") == [-1, -6, 5]
# test retrieval of prior probabilities
assert_almost_equal(mykb.get_prior_prob(entity="Q2", alias="douglas"), 0.8)
assert_almost_equal(mykb.get_prior_prob(entity="Q3", alias="douglas"), 0.2)
assert_almost_equal(mykb.get_prior_prob(entity="Q342", alias="douglas"), 0.0)
assert_almost_equal(mykb.get_prior_prob(entity="Q3", alias="douglassssss"), 0.0)
| Test the valid construction of a KB with 3 entities and two aliases | 13 | 94 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_kb_valid_entities(nlp):
mykb = InMemoryLookupKB(nlp.vocab, entity_vector_length=3)
# adding entities
mykb.add_entity(entity="Q1", freq=19, entity_vector=[8, 4, 3])
mykb.add_entity(entity="Q2", freq=5, entity_vector=[2, 1, 0])
mykb.add_entity(entity="Q3", freq=25, entity_vector=[-1, -6, 5])
# adding aliases
mykb.add_alias(alias="douglas", entities=["Q2", "Q3"], probabilities=[0.8, 0.2])
mykb.add_alias(alias="adam", entities=["Q2"], probabilities=[0.9])
# test the size of the corresponding KB
assert mykb.get_size_entities() == 3
assert mykb.get_size_aliases() == 2
# test retrieval of the entity vectors
assert mykb.get_vector("Q1") == [8, 4, 3]
assert mykb.get_vector("Q2") == [2, 1, 0]
assert mykb.get_vector("Q3") == [-1, -6, 5]
# test retrieval of prior probabilities
assert_almost_equal(mykb.get_prior_prob(entity="Q2", alias="douglas"), 0.8)
assert_almost_equal(mykb.get_prior_prob(entity="Q3", alias="douglas"), 0.2)
assert_almost_equal(mykb.get_prior_prob(entity="Q342", alias="douglas"), 0.0)
assert_almost_equal(mykb.get_prior_prob(entity="Q3", alias="douglassssss"), 0.0)
```
###Assistant : Test the valid construction of a KB with 3 entities and two aliases
|
699 | def eye(N, M=None, k=0, dtype=float, order='C', *, like=None):
if like is not None:
return _eye_with_like(N, M=M, k=k, dtype=dtype, order=order, like=like)
if M is None:
M = N
m = zeros((N, M), dtype=dtype, order=order)
if k >= M:
return m
# Ensure M and k are integers, so we don't get any surprise casting
# results in the expressions `M-k` and `M+1` used below. This avoids
# a problem with inputs with type (for example) np.uint64.
M = operator.index(M)
k = operator.index(k)
if k >= 0:
i = k
else:
i = (-k) * M
m[:M-k].flat[i::M+1] = 1
return m
_eye_with_like = array_function_dispatch(
_eye_dispatcher
)(eye)
|
Return a 2-D array with ones on the diagonal and zeros elsewhere.
Parameters
----------
N : int
Number of rows in the output.
M : int, optional
Number of columns in the output. If None, defaults to `N`.
k : int, optional
Index of the diagonal: 0 (the default) refers to the main diagonal,
a positive value refers to an upper diagonal, and a negative value
to a lower diagonal.
dtype : data-type, optional
Data-type of the returned array.
order : {'C', 'F'}, optional
Whether the output should be stored in row-major (C-style) or
column-major (Fortran-style) order in memory.
.. versionadded:: 1.14.0
${ARRAY_FUNCTION_LIKE}
.. versionadded:: 1.20.0
Returns
-------
I : ndarray of shape (N,M)
An array where all elements are equal to zero, except for the `k`-th
diagonal, whose values are equal to one.
See Also
--------
identity : (almost) equivalent function
diag : diagonal 2-D array from a 1-D array specified by the user.
Examples
--------
>>> np.eye(2, dtype=int)
array([[1, 0],
[0, 1]])
>>> np.eye(3, k=1)
array([[0., 1., 0.],
[0., 0., 1.],
[0., 0., 0.]])
| 176 | 104 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def eye(N, M=None, k=0, dtype=float, order='C', *, like=None):
if like is not None:
return _eye_with_like(N, M=M, k=k, dtype=dtype, order=order, like=like)
if M is None:
M = N
m = zeros((N, M), dtype=dtype, order=order)
if k >= M:
return m
# Ensure M and k are integers, so we don't get any surprise casting
# results in the expressions `M-k` and `M+1` used below. This avoids
# a problem with inputs with type (for example) np.uint64.
M = operator.index(M)
k = operator.index(k)
if k >= 0:
i = k
else:
i = (-k) * M
m[:M-k].flat[i::M+1] = 1
return m
_eye_with_like = array_function_dispatch(
_eye_dispatcher
)(eye)
```
###Assistant :
Return a 2-D array with ones on the diagonal and zeros elsewhere.
Parameters
----------
N : int
Number of rows in the output.
M : int, optional
Number of columns in the output. If None, defaults to `N`.
k : int, optional
Index of the diagonal: 0 (the default) refers to the main diagonal,
a positive value refers to an upper diagonal, and a negative value
to a lower diagonal.
dtype : data-type, optional
Data-type of the returned array.
order : {'C', 'F'}, optional
Whether the output should be stored in row-major (C-style) or
column-major (Fortran-style) order in memory.
.. versionadded:: 1.14.0
${ARRAY_FUNCTION_LIKE}
.. versionadded:: 1.20.0
Returns
-------
I : ndarray of shape (N,M)
An array where all elements are equal to zero, except for the `k`-th
diagonal, whose values are equal to one.
See Also
--------
identity : (almost) equivalent function
diag : diagonal 2-D array from a 1-D array specified by the user.
Examples
--------
>>> np.eye(2, dtype=int)
array([[1, 0],
[0, 1]])
>>> np.eye(3, k=1)
array([[0., 1., 0.],
[0., 0., 1.],
[0., 0., 0.]])
|