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
|
---|---|---|---|---|---|---|
200 | def hvac_modes(self) -> list[HVACMode]:
hvac_state = HVAC_MODES_MAPPING[self._climate.get_hvac_state()]
return [HVACMode.AUTO, hvac_state]
| Return the list of available hvac operation modes.
HEAT and COOL mode are exclusive. End user has to enable a mode manually within the Somfy application.
So only one mode can be displayed. Auto mode is a scheduler.
| 38 | 10 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def hvac_modes(self) -> list[HVACMode]:
hvac_state = HVAC_MODES_MAPPING[self._climate.get_hvac_state()]
return [HVACMode.AUTO, hvac_state]
```
###Assistant : Return the list of available hvac operation modes.
HEAT and COOL mode are exclusive. End user has to enable a mode manually within the Somfy application.
So only one mode can be displayed. Auto mode is a scheduler.
|
201 | def _assert_expected_task_states(self, dagrun, expected_states):
tis = dagrun.get_task_instances()
for ti in tis:
try:
expected_state = expected_states[ti.task_id]
except KeyError:
raise ValueError(f"Invalid task id {ti.task_id} found!")
else:
assert ti.state == expected_state
all_downstream_skipped_states = {
"short_circuit": State.SUCCESS,
"op1": State.SKIPPED,
"op2": State.SKIPPED,
}
all_success_states = {"short_circuit": State.SUCCESS, "op1": State.SUCCESS, "op2": State.SUCCESS}
| Helper function that asserts `TaskInstances` of a given `task_id` are in a given state. | 14 | 46 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _assert_expected_task_states(self, dagrun, expected_states):
tis = dagrun.get_task_instances()
for ti in tis:
try:
expected_state = expected_states[ti.task_id]
except KeyError:
raise ValueError(f"Invalid task id {ti.task_id} found!")
else:
assert ti.state == expected_state
all_downstream_skipped_states = {
"short_circuit": State.SUCCESS,
"op1": State.SKIPPED,
"op2": State.SKIPPED,
}
all_success_states = {"short_circuit": State.SUCCESS, "op1": State.SUCCESS, "op2": State.SUCCESS}
```
###Assistant : Helper function that asserts `TaskInstances` of a given `task_id` are in a given state.
|
202 | def set_customer_info(fieldname, customer, value=""):
if fieldname == "loyalty_program":
frappe.db.set_value("Customer", customer, "loyalty_program", value)
contact = frappe.get_cached_value("Customer", customer, "customer_primary_contact")
if not contact:
contact = frappe.db.sql(
,
(customer),
as_dict=1,
)
contact = contact[0].get("parent") if contact else None
if not contact:
new_contact = frappe.new_doc("Contact")
new_contact.is_primary_contact = 1
new_contact.first_name = customer
new_contact.set("links", [{"link_doctype": "Customer", "link_name": customer}])
new_contact.save()
contact = new_contact.name
frappe.db.set_value("Customer", customer, "customer_primary_contact", contact)
contact_doc = frappe.get_doc("Contact", contact)
if fieldname == "email_id":
contact_doc.set("email_ids", [{"email_id": value, "is_primary": 1}])
frappe.db.set_value("Customer", customer, "email_id", value)
elif fieldname == "mobile_no":
contact_doc.set("phone_nos", [{"phone": value, "is_primary_mobile_no": 1}])
frappe.db.set_value("Customer", customer, "mobile_no", value)
contact_doc.save()
@frappe.whitelist() |
SELECT parent FROM `tabDynamic Link`
WHERE
parenttype = 'Contact' AND
parentfield = 'links' AND
link_doctype = 'Customer' AND
link_name = %s
| 21 | 91 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def set_customer_info(fieldname, customer, value=""):
if fieldname == "loyalty_program":
frappe.db.set_value("Customer", customer, "loyalty_program", value)
contact = frappe.get_cached_value("Customer", customer, "customer_primary_contact")
if not contact:
contact = frappe.db.sql(
,
(customer),
as_dict=1,
)
contact = contact[0].get("parent") if contact else None
if not contact:
new_contact = frappe.new_doc("Contact")
new_contact.is_primary_contact = 1
new_contact.first_name = customer
new_contact.set("links", [{"link_doctype": "Customer", "link_name": customer}])
new_contact.save()
contact = new_contact.name
frappe.db.set_value("Customer", customer, "customer_primary_contact", contact)
contact_doc = frappe.get_doc("Contact", contact)
if fieldname == "email_id":
contact_doc.set("email_ids", [{"email_id": value, "is_primary": 1}])
frappe.db.set_value("Customer", customer, "email_id", value)
elif fieldname == "mobile_no":
contact_doc.set("phone_nos", [{"phone": value, "is_primary_mobile_no": 1}])
frappe.db.set_value("Customer", customer, "mobile_no", value)
contact_doc.save()
@frappe.whitelist()
```
###Assistant :
SELECT parent FROM `tabDynamic Link`
WHERE
parenttype = 'Contact' AND
parentfield = 'links' AND
link_doctype = 'Customer' AND
link_name = %s
|
203 | def test_unpublish_not_include_children_view_post(self):
# Post to the unpublish page
response = self.client.post(
reverse("wagtailadmin_pages:unpublish", args=(self.test_page.id,)), {}
)
# Should be redirected to explorer page
self.assertRedirects(
response, reverse("wagtailadmin_explore", args=(self.root_page.id,))
)
# Check that the page was unpublished
self.assertFalse(SimplePage.objects.get(id=self.test_page.id).live)
# Check that the descendant pages were not unpublished
self.assertTrue(SimplePage.objects.get(id=self.test_child_page.id).live)
self.assertTrue(SimplePage.objects.get(id=self.test_another_child_page.id).live)
|
This posts to the unpublish view and checks that the page was unpublished but its descendants were not
| 18 | 46 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_unpublish_not_include_children_view_post(self):
# Post to the unpublish page
response = self.client.post(
reverse("wagtailadmin_pages:unpublish", args=(self.test_page.id,)), {}
)
# Should be redirected to explorer page
self.assertRedirects(
response, reverse("wagtailadmin_explore", args=(self.root_page.id,))
)
# Check that the page was unpublished
self.assertFalse(SimplePage.objects.get(id=self.test_page.id).live)
# Check that the descendant pages were not unpublished
self.assertTrue(SimplePage.objects.get(id=self.test_child_page.id).live)
self.assertTrue(SimplePage.objects.get(id=self.test_another_child_page.id).live)
```
###Assistant :
This posts to the unpublish view and checks that the page was unpublished but its descendants were not
|
204 | def _get_data_from_filepath(self, filepath_or_buffer):
# if it is a string but the file does not exist, it might be a JSON string
filepath_or_buffer = stringify_path(filepath_or_buffer)
if (
not isinstance(filepath_or_buffer, str)
or is_url(filepath_or_buffer)
or is_fsspec_url(filepath_or_buffer)
or file_exists(filepath_or_buffer)
):
self.handles = get_handle(
filepath_or_buffer,
"r",
encoding=self.encoding,
compression=self.compression,
storage_options=self.storage_options,
errors=self.encoding_errors,
)
filepath_or_buffer = self.handles.handle
elif (
isinstance(filepath_or_buffer, str)
and filepath_or_buffer.lower().endswith(
(".json",) + tuple(f".json{c}" for c in _extension_to_compression)
)
and not file_exists(filepath_or_buffer)
):
raise FileNotFoundError(f"File {filepath_or_buffer} does not exist")
return filepath_or_buffer
|
The function read_json accepts three input types:
1. filepath (string-like)
2. file-like object (e.g. open file object, StringIO)
3. JSON string
This method turns (1) into (2) to simplify the rest of the processing.
It returns input types (2) and (3) unchanged.
It raises FileNotFoundError if the input is a string ending in
one of .json, .json.gz, .json.bz2, etc. but no such file exists.
| 64 | 75 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _get_data_from_filepath(self, filepath_or_buffer):
# if it is a string but the file does not exist, it might be a JSON string
filepath_or_buffer = stringify_path(filepath_or_buffer)
if (
not isinstance(filepath_or_buffer, str)
or is_url(filepath_or_buffer)
or is_fsspec_url(filepath_or_buffer)
or file_exists(filepath_or_buffer)
):
self.handles = get_handle(
filepath_or_buffer,
"r",
encoding=self.encoding,
compression=self.compression,
storage_options=self.storage_options,
errors=self.encoding_errors,
)
filepath_or_buffer = self.handles.handle
elif (
isinstance(filepath_or_buffer, str)
and filepath_or_buffer.lower().endswith(
(".json",) + tuple(f".json{c}" for c in _extension_to_compression)
)
and not file_exists(filepath_or_buffer)
):
raise FileNotFoundError(f"File {filepath_or_buffer} does not exist")
return filepath_or_buffer
```
###Assistant :
The function read_json accepts three input types:
1. filepath (string-like)
2. file-like object (e.g. open file object, StringIO)
3. JSON string
This method turns (1) into (2) to simplify the rest of the processing.
It returns input types (2) and (3) unchanged.
It raises FileNotFoundError if the input is a string ending in
one of .json, .json.gz, .json.bz2, etc. but no such file exists.
|
205 | def _run_pip(args, additional_paths=None):
# Run the bootstraping in a subprocess to avoid leaking any state that happens
# after pip has executed. Particulary, this avoids the case when pip holds onto
# the files in *additional_paths*, preventing us to remove them at the end of the
# invocation.
code = f
return subprocess.run([sys.executable, '-W', 'ignore::DeprecationWarning',
"-c", code], check=True).returncode
|
import runpy
import sys
sys.path = {additional_paths or []} + sys.path
sys.argv[1:] = {args}
runpy.run_module("pip", run_name="__main__", alter_sys=True)
| 17 | 58 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _run_pip(args, additional_paths=None):
# Run the bootstraping in a subprocess to avoid leaking any state that happens
# after pip has executed. Particulary, this avoids the case when pip holds onto
# the files in *additional_paths*, preventing us to remove them at the end of the
# invocation.
code = f
return subprocess.run([sys.executable, '-W', 'ignore::DeprecationWarning',
"-c", code], check=True).returncode
```
###Assistant :
import runpy
import sys
sys.path = {additional_paths or []} + sys.path
sys.argv[1:] = {args}
runpy.run_module("pip", run_name="__main__", alter_sys=True)
|
206 | def test_pprint_heap_allocated_type():
module_name = "xxlimited" if sys.version_info < (3, 10) else "xxlimited_35"
expected_output = (
"xxlimited.Null" if sys.version_info < (3, 11) else "xxlimited_35.Null"
)
xxlimited = pytest.importorskip(module_name)
output = pretty.pretty(xxlimited.Null)
assert output == expected_output
|
Test that pprint works for heap allocated types.
| 8 | 34 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_pprint_heap_allocated_type():
module_name = "xxlimited" if sys.version_info < (3, 10) else "xxlimited_35"
expected_output = (
"xxlimited.Null" if sys.version_info < (3, 11) else "xxlimited_35.Null"
)
xxlimited = pytest.importorskip(module_name)
output = pretty.pretty(xxlimited.Null)
assert output == expected_output
```
###Assistant :
Test that pprint works for heap allocated types.
|
207 | def test_orderby_percentile_with_many_fields_transactions_unsupported_fields(self):
response = self.get_response(
self.organization.slug,
field=[
"p50(sentry.transactions.measurements.lcp)",
"sum(user_misery)",
],
statsPeriod="1h",
interval="1h",
datasource="snuba",
groupBy=["project_id", "transaction"],
orderBy="p50(sentry.transactions.measurements.lcp)",
)
assert response.status_code == 400
assert (
response.json()["detail"]
== "Multi-field select order by queries is not supported for metric user_misery"
)
|
Test that contains a field in the `select` that is performance related but currently
not supported should return a 400
| 20 | 37 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_orderby_percentile_with_many_fields_transactions_unsupported_fields(self):
response = self.get_response(
self.organization.slug,
field=[
"p50(sentry.transactions.measurements.lcp)",
"sum(user_misery)",
],
statsPeriod="1h",
interval="1h",
datasource="snuba",
groupBy=["project_id", "transaction"],
orderBy="p50(sentry.transactions.measurements.lcp)",
)
assert response.status_code == 400
assert (
response.json()["detail"]
== "Multi-field select order by queries is not supported for metric user_misery"
)
```
###Assistant :
Test that contains a field in the `select` that is performance related but currently
not supported should return a 400
|
208 | def generate_dependency_map(integration_targets): # type: (t.List[IntegrationTarget]) -> t.Dict[str, t.Set[IntegrationTarget]]
targets_dict = dict((target.name, target) for target in integration_targets)
target_dependencies = analyze_integration_target_dependencies(integration_targets)
dependency_map = {} # type: t.Dict[str, t.Set[IntegrationTarget]]
invalid_targets = set()
for dependency, dependents in target_dependencies.items():
dependency_target = targets_dict.get(dependency)
if not dependency_target:
invalid_targets.add(dependency)
continue
for dependent in dependents:
if dependent not in dependency_map:
dependency_map[dependent] = set()
dependency_map[dependent].add(dependency_target)
if invalid_targets:
raise ApplicationError('Non-existent target dependencies: %s' % ', '.join(sorted(invalid_targets)))
return dependency_map
| Analyze the given list of integration test targets and return a dictionary expressing target names and the targets on which they depend. | 22 | 67 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def generate_dependency_map(integration_targets): # type: (t.List[IntegrationTarget]) -> t.Dict[str, t.Set[IntegrationTarget]]
targets_dict = dict((target.name, target) for target in integration_targets)
target_dependencies = analyze_integration_target_dependencies(integration_targets)
dependency_map = {} # type: t.Dict[str, t.Set[IntegrationTarget]]
invalid_targets = set()
for dependency, dependents in target_dependencies.items():
dependency_target = targets_dict.get(dependency)
if not dependency_target:
invalid_targets.add(dependency)
continue
for dependent in dependents:
if dependent not in dependency_map:
dependency_map[dependent] = set()
dependency_map[dependent].add(dependency_target)
if invalid_targets:
raise ApplicationError('Non-existent target dependencies: %s' % ', '.join(sorted(invalid_targets)))
return dependency_map
```
###Assistant : Analyze the given list of integration test targets and return a dictionary expressing target names and the targets on which they depend.
|
209 | def text(self) -> str:
if self.error is None:
return str(self)
return self.error.databaseText()
| Get a short text description of the error.
This is a string suitable to show to the user as error message.
| 21 | 12 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def text(self) -> str:
if self.error is None:
return str(self)
return self.error.databaseText()
```
###Assistant : Get a short text description of the error.
This is a string suitable to show to the user as error message.
|
210 | def test_recover_start_from_replica_actor_names(serve_instance):
# Test failed to deploy with total of 2 replicas,
# but first constructor call fails. | Test controller is able to recover starting -> running replicas from
actor names.
| 13 | 18 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_recover_start_from_replica_actor_names(serve_instance):
# Test failed to deploy with total of 2 replicas,
# but first constructor call fails.
```
###Assistant : Test controller is able to recover starting -> running replicas from
actor names.
|
211 | def associated_entities(self) -> list[dict[str, Any]]:
ha_entity_registry = self.device.gateway.ha_entity_registry
zha_device_registry = self.device.gateway.device_registry
return [
GroupEntityReference(
ha_entity_registry.async_get(entity_ref.reference_id).name,
ha_entity_registry.async_get(entity_ref.reference_id).original_name,
entity_ref.reference_id,
)._asdict()
for entity_ref in zha_device_registry.get(self.device.ieee)
if list(entity_ref.cluster_channels.values())[
0
].cluster.endpoint.endpoint_id
== self.endpoint_id
]
| Return the list of entities that were derived from this endpoint. | 11 | 29 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def associated_entities(self) -> list[dict[str, Any]]:
ha_entity_registry = self.device.gateway.ha_entity_registry
zha_device_registry = self.device.gateway.device_registry
return [
GroupEntityReference(
ha_entity_registry.async_get(entity_ref.reference_id).name,
ha_entity_registry.async_get(entity_ref.reference_id).original_name,
entity_ref.reference_id,
)._asdict()
for entity_ref in zha_device_registry.get(self.device.ieee)
if list(entity_ref.cluster_channels.values())[
0
].cluster.endpoint.endpoint_id
== self.endpoint_id
]
```
###Assistant : Return the list of entities that were derived from this endpoint.
|
212 | def getheader(self, name, default=None):
if self.headers is None:
raise ResponseNotReady()
headers = self.headers.get_all(name) or default
if isinstance(headers, str) or not hasattr(headers, '__iter__'):
return headers
else:
return ', '.join(headers)
| Returns the value of the header matching *name*.
If there are multiple matching headers, the values are
combined into a single string separated by commas and spaces.
If no matching header is found, returns *default* or None if
the *default* is not specified.
If the headers are unknown, raises http.client.ResponseNotReady.
| 50 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def getheader(self, name, default=None):
if self.headers is None:
raise ResponseNotReady()
headers = self.headers.get_all(name) or default
if isinstance(headers, str) or not hasattr(headers, '__iter__'):
return headers
else:
return ', '.join(headers)
```
###Assistant : Returns the value of the header matching *name*.
If there are multiple matching headers, the values are
combined into a single string separated by commas and spaces.
If no matching header is found, returns *default* or None if
the *default* is not specified.
If the headers are unknown, raises http.client.ResponseNotReady.
|
213 | def test_generate_pipeline_code_2():
pipeline = [
'KNeighborsClassifier',
[
'CombineDFs',
[
'GradientBoostingClassifier',
'input_matrix',
38.0,
5,
5,
5,
0.05,
0.5],
[
'CombineDFs',
[
'MinMaxScaler',
'input_matrix'
],
['ZeroCount',
[
'MaxAbsScaler',
'input_matrix'
]
]
]
],
18,
'uniform',
2
]
expected_code =
assert expected_code == generate_pipeline_code(pipeline, tpot_obj.operators)
| Assert that generate_pipeline_code() returns the correct code given a specific pipeline with two CombineDFs.make_pipeline(
make_union(
StackingEstimator(estimator=GradientBoostingClassifier(learning_rate=38.0, max_depth=5, max_features=5, min_samples_leaf=5, min_samples_split=0.05, n_estimators=0.5)),
make_union(
MinMaxScaler(),
make_pipeline(
MaxAbsScaler(),
ZeroCount()
)
)
),
KNeighborsClassifier(n_neighbors=18, p="uniform", weights=2)
) | 33 | 42 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_generate_pipeline_code_2():
pipeline = [
'KNeighborsClassifier',
[
'CombineDFs',
[
'GradientBoostingClassifier',
'input_matrix',
38.0,
5,
5,
5,
0.05,
0.5],
[
'CombineDFs',
[
'MinMaxScaler',
'input_matrix'
],
['ZeroCount',
[
'MaxAbsScaler',
'input_matrix'
]
]
]
],
18,
'uniform',
2
]
expected_code =
assert expected_code == generate_pipeline_code(pipeline, tpot_obj.operators)
```
###Assistant : Assert that generate_pipeline_code() returns the correct code given a specific pipeline with two CombineDFs.make_pipeline(
make_union(
StackingEstimator(estimator=GradientBoostingClassifier(learning_rate=38.0, max_depth=5, max_features=5, min_samples_leaf=5, min_samples_split=0.05, n_estimators=0.5)),
make_union(
MinMaxScaler(),
make_pipeline(
MaxAbsScaler(),
ZeroCount()
)
)
),
KNeighborsClassifier(n_neighbors=18, p="uniform", weights=2)
)
|
214 | def _script_names(dist, script_name, is_gui):
# type: (Distribution, str, bool) -> List[str]
if dist_in_usersite(dist):
bin_dir = get_bin_user()
else:
bin_dir = get_bin_prefix()
exe_name = os.path.join(bin_dir, script_name)
paths_to_remove = [exe_name]
if WINDOWS:
paths_to_remove.append(exe_name + '.exe')
paths_to_remove.append(exe_name + '.exe.manifest')
if is_gui:
paths_to_remove.append(exe_name + '-script.pyw')
else:
paths_to_remove.append(exe_name + '-script.py')
return paths_to_remove
| Create the fully qualified name of the files created by
{console,gui}_scripts for the given ``dist``.
Returns the list of file names
| 21 | 46 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _script_names(dist, script_name, is_gui):
# type: (Distribution, str, bool) -> List[str]
if dist_in_usersite(dist):
bin_dir = get_bin_user()
else:
bin_dir = get_bin_prefix()
exe_name = os.path.join(bin_dir, script_name)
paths_to_remove = [exe_name]
if WINDOWS:
paths_to_remove.append(exe_name + '.exe')
paths_to_remove.append(exe_name + '.exe.manifest')
if is_gui:
paths_to_remove.append(exe_name + '-script.pyw')
else:
paths_to_remove.append(exe_name + '-script.py')
return paths_to_remove
```
###Assistant : Create the fully qualified name of the files created by
{console,gui}_scripts for the given ``dist``.
Returns the list of file names
|
215 | def bbox_center(boxes):
boxes_cx = (boxes[..., 0] + boxes[..., 2]) / 2
boxes_cy = (boxes[..., 1] + boxes[..., 3]) / 2
return paddle.stack([boxes_cx, boxes_cy], axis=-1)
| Get bbox centers from boxes.
Args:
boxes (Tensor): boxes with shape (..., 4), "xmin, ymin, xmax, ymax" format.
Returns:
Tensor: boxes centers with shape (..., 2), "cx, cy" format.
| 29 | 24 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def bbox_center(boxes):
boxes_cx = (boxes[..., 0] + boxes[..., 2]) / 2
boxes_cy = (boxes[..., 1] + boxes[..., 3]) / 2
return paddle.stack([boxes_cx, boxes_cy], axis=-1)
```
###Assistant : Get bbox centers from boxes.
Args:
boxes (Tensor): boxes with shape (..., 4), "xmin, ymin, xmax, ymax" format.
Returns:
Tensor: boxes centers with shape (..., 2), "cx, cy" format.
|
216 | def predict(self, input):
input_names = self.predictor.get_input_names()
input_tensor = self.predictor.get_input_handle(input_names[0])
output_names = self.predictor.get_output_names()
output_tensor = self.predictor.get_output_handle(output_names[0])
# preprocess
self.recognize_times.preprocess_time_s.start()
if type(input) == str:
inputs = self.preprocess_video(input)
else:
inputs = self.preprocess_frames(input)
self.recognize_times.preprocess_time_s.end()
inputs = np.expand_dims(
inputs, axis=0).repeat(
self.batch_size, axis=0).copy()
input_tensor.copy_from_cpu(inputs)
# model prediction
self.recognize_times.inference_time_s.start()
self.predictor.run()
self.recognize_times.inference_time_s.end()
output = output_tensor.copy_to_cpu()
# postprocess
self.recognize_times.postprocess_time_s.start()
classes, scores = self.postprocess(output)
self.recognize_times.postprocess_time_s.end()
return classes, scores
|
Args:
input (str) or (list): video file path or image data list
Returns:
results (dict):
| 15 | 58 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def predict(self, input):
input_names = self.predictor.get_input_names()
input_tensor = self.predictor.get_input_handle(input_names[0])
output_names = self.predictor.get_output_names()
output_tensor = self.predictor.get_output_handle(output_names[0])
# preprocess
self.recognize_times.preprocess_time_s.start()
if type(input) == str:
inputs = self.preprocess_video(input)
else:
inputs = self.preprocess_frames(input)
self.recognize_times.preprocess_time_s.end()
inputs = np.expand_dims(
inputs, axis=0).repeat(
self.batch_size, axis=0).copy()
input_tensor.copy_from_cpu(inputs)
# model prediction
self.recognize_times.inference_time_s.start()
self.predictor.run()
self.recognize_times.inference_time_s.end()
output = output_tensor.copy_to_cpu()
# postprocess
self.recognize_times.postprocess_time_s.start()
classes, scores = self.postprocess(output)
self.recognize_times.postprocess_time_s.end()
return classes, scores
```
###Assistant :
Args:
input (str) or (list): video file path or image data list
Returns:
results (dict):
|
217 | def deep_deconstruct(self, obj):
if isinstance(obj, list):
return [self.deep_deconstruct(value) for value in obj]
elif isinstance(obj, tuple):
return tuple(self.deep_deconstruct(value) for value in obj)
elif isinstance(obj, dict):
return {key: self.deep_deconstruct(value) for key, value in obj.items()}
elif isinstance(obj, functools.partial):
return (
obj.func,
self.deep_deconstruct(obj.args),
self.deep_deconstruct(obj.keywords),
)
elif isinstance(obj, COMPILED_REGEX_TYPE):
return RegexObject(obj)
elif isinstance(obj, type):
# If this is a type that implements 'deconstruct' as an instance method,
# avoid treating this as being deconstructible itself - see #22951
return obj
elif hasattr(obj, "deconstruct"):
deconstructed = obj.deconstruct()
if isinstance(obj, models.Field):
# we have a field which also returns a name
deconstructed = deconstructed[1:]
path, args, kwargs = deconstructed
return (
path,
[self.deep_deconstruct(value) for value in args],
{key: self.deep_deconstruct(value) for key, value in kwargs.items()},
)
else:
return obj
|
Recursive deconstruction for a field and its arguments.
Used for full comparison for rename/alter; sometimes a single-level
deconstruction will not compare correctly.
| 22 | 121 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def deep_deconstruct(self, obj):
if isinstance(obj, list):
return [self.deep_deconstruct(value) for value in obj]
elif isinstance(obj, tuple):
return tuple(self.deep_deconstruct(value) for value in obj)
elif isinstance(obj, dict):
return {key: self.deep_deconstruct(value) for key, value in obj.items()}
elif isinstance(obj, functools.partial):
return (
obj.func,
self.deep_deconstruct(obj.args),
self.deep_deconstruct(obj.keywords),
)
elif isinstance(obj, COMPILED_REGEX_TYPE):
return RegexObject(obj)
elif isinstance(obj, type):
# If this is a type that implements 'deconstruct' as an instance method,
# avoid treating this as being deconstructible itself - see #22951
return obj
elif hasattr(obj, "deconstruct"):
deconstructed = obj.deconstruct()
if isinstance(obj, models.Field):
# we have a field which also returns a name
deconstructed = deconstructed[1:]
path, args, kwargs = deconstructed
return (
path,
[self.deep_deconstruct(value) for value in args],
{key: self.deep_deconstruct(value) for key, value in kwargs.items()},
)
else:
return obj
```
###Assistant :
Recursive deconstruction for a field and its arguments.
Used for full comparison for rename/alter; sometimes a single-level
deconstruction will not compare correctly.
|
218 | def test_cancellation(self):
deferred: "Deferred[str]" = Deferred()
wrapper_deferred = stop_cancellation(deferred)
# Cancel the new `Deferred`.
wrapper_deferred.cancel()
self.assertTrue(wrapper_deferred.called)
self.failureResultOf(wrapper_deferred, CancelledError)
self.assertFalse(
deferred.called, "Original `Deferred` was unexpectedly cancelled."
)
# Now make the inner `Deferred` fail.
# The `Failure` must be consumed, otherwise unwanted tracebacks will be printed
# in logs.
deferred.errback(ValueError("abc"))
self.assertIsNone(deferred.result, "`Failure` was not consumed")
| Test that cancellation of the new `Deferred` leaves the original running. | 11 | 54 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_cancellation(self):
deferred: "Deferred[str]" = Deferred()
wrapper_deferred = stop_cancellation(deferred)
# Cancel the new `Deferred`.
wrapper_deferred.cancel()
self.assertTrue(wrapper_deferred.called)
self.failureResultOf(wrapper_deferred, CancelledError)
self.assertFalse(
deferred.called, "Original `Deferred` was unexpectedly cancelled."
)
# Now make the inner `Deferred` fail.
# The `Failure` must be consumed, otherwise unwanted tracebacks will be printed
# in logs.
deferred.errback(ValueError("abc"))
self.assertIsNone(deferred.result, "`Failure` was not consumed")
```
###Assistant : Test that cancellation of the new `Deferred` leaves the original running.
|
219 | def getgeneratorlocals(generator):
if not isgenerator(generator):
raise TypeError("{!r} is not a Python generator".format(generator))
frame = getattr(generator, "gi_frame", None)
if frame is not None:
return generator.gi_frame.f_locals
else:
return {}
# ------------------------------------------------ coroutine introspection
CORO_CREATED = 'CORO_CREATED'
CORO_RUNNING = 'CORO_RUNNING'
CORO_SUSPENDED = 'CORO_SUSPENDED'
CORO_CLOSED = 'CORO_CLOSED'
|
Get the mapping of generator local variables to their current values.
A dict is returned, with the keys the local variable names and values the
bound values. | 27 | 43 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def getgeneratorlocals(generator):
if not isgenerator(generator):
raise TypeError("{!r} is not a Python generator".format(generator))
frame = getattr(generator, "gi_frame", None)
if frame is not None:
return generator.gi_frame.f_locals
else:
return {}
# ------------------------------------------------ coroutine introspection
CORO_CREATED = 'CORO_CREATED'
CORO_RUNNING = 'CORO_RUNNING'
CORO_SUSPENDED = 'CORO_SUSPENDED'
CORO_CLOSED = 'CORO_CLOSED'
```
###Assistant :
Get the mapping of generator local variables to their current values.
A dict is returned, with the keys the local variable names and values the
bound values.
|
220 | async def test_last_bin_contains_end_date(client, route):
response = await client.post(
f"/{route}/history",
json=dict(
history_start=str(dt),
history_end=str(dt.add(days=1, minutes=30)),
history_interval_seconds=timedelta(days=1).total_seconds(),
),
)
assert response.status_code == status.HTTP_200_OK
parsed = pydantic.parse_obj_as(List[responses.HistoryResponse], response.json())
assert len(parsed) == 2
assert parsed[0].interval_start == dt
assert parsed[0].interval_end == dt.add(days=1)
assert parsed[1].interval_start == dt.add(days=1)
assert parsed[1].interval_end == dt.add(days=2)
| The last bin contains the end date, so its own end could be after the history end | 17 | 44 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def test_last_bin_contains_end_date(client, route):
response = await client.post(
f"/{route}/history",
json=dict(
history_start=str(dt),
history_end=str(dt.add(days=1, minutes=30)),
history_interval_seconds=timedelta(days=1).total_seconds(),
),
)
assert response.status_code == status.HTTP_200_OK
parsed = pydantic.parse_obj_as(List[responses.HistoryResponse], response.json())
assert len(parsed) == 2
assert parsed[0].interval_start == dt
assert parsed[0].interval_end == dt.add(days=1)
assert parsed[1].interval_start == dt.add(days=1)
assert parsed[1].interval_end == dt.add(days=2)
```
###Assistant : The last bin contains the end date, so its own end could be after the history end
|
221 | def _validate_attributes(self):
# Run config
if not isinstance(self.run_config, RunConfig):
raise ValueError(
f"`run_config` should be an instance of `ray.air.RunConfig`, "
f"found {type(self.run_config)} with value `{self.run_config}`."
)
# Scaling config
# Todo: move to ray.air.ScalingConfig
if not isinstance(self.scaling_config, dict):
raise ValueError(
f"`scaling_config` should be an instance of `dict`, "
f"found {type(self.scaling_config)} with value `{self.scaling_config}`."
)
# Datasets
if not isinstance(self.datasets, dict):
raise ValueError(
f"`datasets` should be a dict mapping from a string to "
f"`ray.data.Dataset` objects, "
f"found {type(self.datasets)} with value `{self.datasets}`."
)
elif any(
not isinstance(ds, ray.data.Dataset) and not callable(ds)
for ds in self.datasets.values()
):
raise ValueError(
f"At least one value in the `datasets` dict is not a "
f"`ray.data.Dataset`: {self.datasets}"
)
# Preprocessor
if self.preprocessor is not None and not isinstance(
self.preprocessor, ray.data.Preprocessor
):
raise ValueError(
f"`preprocessor` should be an instance of `ray.data.Preprocessor`, "
f"found {type(self.preprocessor)} with value `{self.preprocessor}`."
)
if self.resume_from_checkpoint is not None and not isinstance(
self.resume_from_checkpoint, ray.air.Checkpoint
):
raise ValueError(
f"`resume_from_checkpoint` should be an instance of "
f"`ray.air.Checkpoint`, found {type(self.resume_from_checkpoint)} "
f"with value `{self.resume_from_checkpoint}`."
)
| Called on __init()__ to validate trainer attributes. | 7 | 168 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _validate_attributes(self):
# Run config
if not isinstance(self.run_config, RunConfig):
raise ValueError(
f"`run_config` should be an instance of `ray.air.RunConfig`, "
f"found {type(self.run_config)} with value `{self.run_config}`."
)
# Scaling config
# Todo: move to ray.air.ScalingConfig
if not isinstance(self.scaling_config, dict):
raise ValueError(
f"`scaling_config` should be an instance of `dict`, "
f"found {type(self.scaling_config)} with value `{self.scaling_config}`."
)
# Datasets
if not isinstance(self.datasets, dict):
raise ValueError(
f"`datasets` should be a dict mapping from a string to "
f"`ray.data.Dataset` objects, "
f"found {type(self.datasets)} with value `{self.datasets}`."
)
elif any(
not isinstance(ds, ray.data.Dataset) and not callable(ds)
for ds in self.datasets.values()
):
raise ValueError(
f"At least one value in the `datasets` dict is not a "
f"`ray.data.Dataset`: {self.datasets}"
)
# Preprocessor
if self.preprocessor is not None and not isinstance(
self.preprocessor, ray.data.Preprocessor
):
raise ValueError(
f"`preprocessor` should be an instance of `ray.data.Preprocessor`, "
f"found {type(self.preprocessor)} with value `{self.preprocessor}`."
)
if self.resume_from_checkpoint is not None and not isinstance(
self.resume_from_checkpoint, ray.air.Checkpoint
):
raise ValueError(
f"`resume_from_checkpoint` should be an instance of "
f"`ray.air.Checkpoint`, found {type(self.resume_from_checkpoint)} "
f"with value `{self.resume_from_checkpoint}`."
)
```
###Assistant : Called on __init()__ to validate trainer attributes.
|
222 | def longitude(self) -> float | None:
if (
self.extra_state_attributes is not None
and ATTR_LONGITUDE in self.extra_state_attributes
):
longitude: float = self.extra_state_attributes[ATTR_LONGITUDE]
return longitude
return None
| Return longitude if provided in extra_state_attributes or None. | 8 | 25 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def longitude(self) -> float | None:
if (
self.extra_state_attributes is not None
and ATTR_LONGITUDE in self.extra_state_attributes
):
longitude: float = self.extra_state_attributes[ATTR_LONGITUDE]
return longitude
return None
```
###Assistant : Return longitude if provided in extra_state_attributes or None.
|
223 | def user_cache_dir(self) -> str:
path = os.path.normpath(get_win_folder("CSIDL_LOCAL_APPDATA"))
return self._append_parts(path, opinion_value="Cache")
|
:return: cache directory tied to the user (if opinionated with ``Cache`` folder within ``$appname``) e.g.
``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname\\Cache\\$version``
| 16 | 10 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def user_cache_dir(self) -> str:
path = os.path.normpath(get_win_folder("CSIDL_LOCAL_APPDATA"))
return self._append_parts(path, opinion_value="Cache")
```
###Assistant :
:return: cache directory tied to the user (if opinionated with ``Cache`` folder within ``$appname``) e.g.
``%USERPROFILE%\\AppData\\Local\\$appauthor\\$appname\\Cache\\$version``
|
224 | def get_project_config(project, full_config=True, project_keys=None):
with sentry_sdk.push_scope() as scope:
scope.set_tag("project", project.id)
with metrics.timer("relay.config.get_project_config.duration"):
return _get_project_config(project, full_config=full_config, project_keys=project_keys)
| Constructs the ProjectConfig information.
:param project: The project to load configuration for. Ensure that
organization is bound on this object; otherwise it will be loaded from
the database.
:param full_config: True if only the full config is required, False
if only the restricted (for external relays) is required
(default True, i.e. full configuration)
:param project_keys: Pre-fetched project keys for performance. However, if
no project keys are provided it is assumed that the config does not
need to contain auth information (this is the case when used in
python's StoreView)
:return: a ProjectConfig object for the given project
| 97 | 16 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_project_config(project, full_config=True, project_keys=None):
with sentry_sdk.push_scope() as scope:
scope.set_tag("project", project.id)
with metrics.timer("relay.config.get_project_config.duration"):
return _get_project_config(project, full_config=full_config, project_keys=project_keys)
```
###Assistant : Constructs the ProjectConfig information.
:param project: The project to load configuration for. Ensure that
organization is bound on this object; otherwise it will be loaded from
the database.
:param full_config: True if only the full config is required, False
if only the restricted (for external relays) is required
(default True, i.e. full configuration)
:param project_keys: Pre-fetched project keys for performance. However, if
no project keys are provided it is assumed that the config does not
need to contain auth information (this is the case when used in
python's StoreView)
:return: a ProjectConfig object for the given project
|
225 | def _query_kg(self, sparql_query):
try:
response = self.knowledge_graph.query(sparql_query=sparql_query)
# unpack different answer styles
if isinstance(response, list):
if len(response) == 0:
result = ""
else:
result = []
for x in response:
for k, v in x.items():
result.append(v["value"])
elif isinstance(response, bool):
result = str(response)
elif "count" in response[0]:
result = str(int(response[0]["count"]["value"]))
else:
result = ""
except Exception:
result = ""
return result, sparql_query
|
Execute a single SPARQL query on the knowledge graph to retrieve an answer and unpack
different answer styles for boolean queries, count queries, and list queries.
:param sparql_query: SPARQL query that shall be executed on the knowledge graph
| 38 | 61 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _query_kg(self, sparql_query):
try:
response = self.knowledge_graph.query(sparql_query=sparql_query)
# unpack different answer styles
if isinstance(response, list):
if len(response) == 0:
result = ""
else:
result = []
for x in response:
for k, v in x.items():
result.append(v["value"])
elif isinstance(response, bool):
result = str(response)
elif "count" in response[0]:
result = str(int(response[0]["count"]["value"]))
else:
result = ""
except Exception:
result = ""
return result, sparql_query
```
###Assistant :
Execute a single SPARQL query on the knowledge graph to retrieve an answer and unpack
different answer styles for boolean queries, count queries, and list queries.
:param sparql_query: SPARQL query that shall be executed on the knowledge graph
|
226 | def _path_importer_cache(cls, path):
if path == '':
try:
path = _os.getcwd()
except FileNotFoundError:
# Don't cache the failure as the cwd can easily change to
# a valid directory later on.
return None
try:
finder = sys.path_importer_cache[path]
except KeyError:
finder = cls._path_hooks(path)
sys.path_importer_cache[path] = finder
return finder
| Get the finder for the path entry from sys.path_importer_cache.
If the path entry is not in the cache, find the appropriate finder
and cache it. If no finder is available, store None.
| 32 | 47 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _path_importer_cache(cls, path):
if path == '':
try:
path = _os.getcwd()
except FileNotFoundError:
# Don't cache the failure as the cwd can easily change to
# a valid directory later on.
return None
try:
finder = sys.path_importer_cache[path]
except KeyError:
finder = cls._path_hooks(path)
sys.path_importer_cache[path] = finder
return finder
```
###Assistant : Get the finder for the path entry from sys.path_importer_cache.
If the path entry is not in the cache, find the appropriate finder
and cache it. If no finder is available, store None.
|
227 | def test_publish_parts(self):
import docutils
self.assertNotEqual(
docutils.parsers.rst.roles.DEFAULT_INTERPRETED_ROLE, "cmsreference"
)
source = "reST, `interpreted text`, default role."
markup = "<p>reST, <cite>interpreted text</cite>, default role.</p>\n"
parts = docutils.core.publish_parts(source=source, writer_name="html4css1")
self.assertEqual(parts["fragment"], markup)
|
Django shouldn't break the default role for interpreted text
when ``publish_parts`` is used directly, by setting it to
``cmsreference`` (#6681).
| 20 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_publish_parts(self):
import docutils
self.assertNotEqual(
docutils.parsers.rst.roles.DEFAULT_INTERPRETED_ROLE, "cmsreference"
)
source = "reST, `interpreted text`, default role."
markup = "<p>reST, <cite>interpreted text</cite>, default role.</p>\n"
parts = docutils.core.publish_parts(source=source, writer_name="html4css1")
self.assertEqual(parts["fragment"], markup)
```
###Assistant :
Django shouldn't break the default role for interpreted text
when ``publish_parts`` is used directly, by setting it to
``cmsreference`` (#6681).
|
228 | def test_get_backfill_points_in_room(self):
setup_info = self._setup_room_for_backfill_tests()
room_id = setup_info.room_id
depth_map = setup_info.depth_map
# Try at "B"
backfill_points = self.get_success(
self.store.get_backfill_points_in_room(room_id, depth_map["B"], limit=100)
)
backfill_event_ids = [backfill_point[0] for backfill_point in backfill_points]
self.assertListEqual(
backfill_event_ids, ["b6", "b5", "b4", "2", "b3", "b2", "b1"]
)
# Try at "A"
backfill_points = self.get_success(
self.store.get_backfill_points_in_room(room_id, depth_map["A"], limit=100)
)
backfill_event_ids = [backfill_point[0] for backfill_point in backfill_points]
# Event "2" has a depth of 2 but is not included here because we only
# know the approximate depth of 5 from our event "3".
self.assertListEqual(backfill_event_ids, ["b3", "b2", "b1"])
|
Test to make sure only backfill points that are older and come before
the `current_depth` are returned.
| 17 | 88 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_get_backfill_points_in_room(self):
setup_info = self._setup_room_for_backfill_tests()
room_id = setup_info.room_id
depth_map = setup_info.depth_map
# Try at "B"
backfill_points = self.get_success(
self.store.get_backfill_points_in_room(room_id, depth_map["B"], limit=100)
)
backfill_event_ids = [backfill_point[0] for backfill_point in backfill_points]
self.assertListEqual(
backfill_event_ids, ["b6", "b5", "b4", "2", "b3", "b2", "b1"]
)
# Try at "A"
backfill_points = self.get_success(
self.store.get_backfill_points_in_room(room_id, depth_map["A"], limit=100)
)
backfill_event_ids = [backfill_point[0] for backfill_point in backfill_points]
# Event "2" has a depth of 2 but is not included here because we only
# know the approximate depth of 5 from our event "3".
self.assertListEqual(backfill_event_ids, ["b3", "b2", "b1"])
```
###Assistant :
Test to make sure only backfill points that are older and come before
the `current_depth` are returned.
|
229 | def theano_code(expr, cache=None, **kwargs):
sympy_deprecation_warning(
,
deprecated_since_version="1.8",
active_deprecations_target='theanocode-deprecated')
if not theano:
raise ImportError("theano is required for theano_code")
if cache is None:
cache = global_cache
return TheanoPrinter(cache=cache, settings={}).doprint(expr, **kwargs)
|
Convert a SymPy expression into a Theano graph variable.
.. deprecated:: 1.8
``sympy.printing.theanocode`` is deprecated. Theano has been renamed to
Aesara. Use ``sympy.printing.aesaracode`` instead. See
:ref:`theanocode-deprecated` for more information.
Parameters
==========
expr : sympy.core.expr.Expr
SymPy expression object to convert.
cache : dict
Cached Theano variables (see :class:`TheanoPrinter.cache
<TheanoPrinter>`). Defaults to the module-level global cache.
dtypes : dict
Passed to :meth:`.TheanoPrinter.doprint`.
broadcastables : dict
Passed to :meth:`.TheanoPrinter.doprint`.
Returns
=======
theano.gof.graph.Variable
A variable corresponding to the expression's value in a Theano symbolic
expression graph.
sympy.printing.theanocode is deprecated. Theano has been renamed to
Aesara. Use sympy.printing.aesaracode instead. | 94 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def theano_code(expr, cache=None, **kwargs):
sympy_deprecation_warning(
,
deprecated_since_version="1.8",
active_deprecations_target='theanocode-deprecated')
if not theano:
raise ImportError("theano is required for theano_code")
if cache is None:
cache = global_cache
return TheanoPrinter(cache=cache, settings={}).doprint(expr, **kwargs)
```
###Assistant :
Convert a SymPy expression into a Theano graph variable.
.. deprecated:: 1.8
``sympy.printing.theanocode`` is deprecated. Theano has been renamed to
Aesara. Use ``sympy.printing.aesaracode`` instead. See
:ref:`theanocode-deprecated` for more information.
Parameters
==========
expr : sympy.core.expr.Expr
SymPy expression object to convert.
cache : dict
Cached Theano variables (see :class:`TheanoPrinter.cache
<TheanoPrinter>`). Defaults to the module-level global cache.
dtypes : dict
Passed to :meth:`.TheanoPrinter.doprint`.
broadcastables : dict
Passed to :meth:`.TheanoPrinter.doprint`.
Returns
=======
theano.gof.graph.Variable
A variable corresponding to the expression's value in a Theano symbolic
expression graph.
sympy.printing.theanocode is deprecated. Theano has been renamed to
Aesara. Use sympy.printing.aesaracode instead.
|
230 | def _validate_axes_lengths(self):
if self._row_lengths_cache is not None and len(self.index) > 0:
# An empty frame can have 0 rows but a nonempty index. If the frame
# does have rows, the number of rows must equal the size of the
# index.
num_rows = sum(self._row_lengths_cache)
if num_rows > 0:
ErrorMessage.catch_bugs_and_request_email(
num_rows != len(self._index_cache),
f"Row lengths: {num_rows} != {len(self._index_cache)}",
)
ErrorMessage.catch_bugs_and_request_email(
any(val < 0 for val in self._row_lengths_cache),
f"Row lengths cannot be negative: {self._row_lengths_cache}",
)
if self._column_widths_cache is not None and len(self.columns) > 0:
# An empty frame can have 0 column but a nonempty column index. If
# the frame does have columns, the number of columns must equal the
# size of the columns.
num_columns = sum(self._column_widths_cache)
if num_columns > 0:
ErrorMessage.catch_bugs_and_request_email(
num_columns != len(self._columns_cache),
f"Column widths: {num_columns} != {len(self._columns_cache)}",
)
ErrorMessage.catch_bugs_and_request_email(
any(val < 0 for val in self._column_widths_cache),
f"Column widths cannot be negative: {self._column_widths_cache}",
)
| Validate that labels are split correctly if split is known. | 10 | 147 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _validate_axes_lengths(self):
if self._row_lengths_cache is not None and len(self.index) > 0:
# An empty frame can have 0 rows but a nonempty index. If the frame
# does have rows, the number of rows must equal the size of the
# index.
num_rows = sum(self._row_lengths_cache)
if num_rows > 0:
ErrorMessage.catch_bugs_and_request_email(
num_rows != len(self._index_cache),
f"Row lengths: {num_rows} != {len(self._index_cache)}",
)
ErrorMessage.catch_bugs_and_request_email(
any(val < 0 for val in self._row_lengths_cache),
f"Row lengths cannot be negative: {self._row_lengths_cache}",
)
if self._column_widths_cache is not None and len(self.columns) > 0:
# An empty frame can have 0 column but a nonempty column index. If
# the frame does have columns, the number of columns must equal the
# size of the columns.
num_columns = sum(self._column_widths_cache)
if num_columns > 0:
ErrorMessage.catch_bugs_and_request_email(
num_columns != len(self._columns_cache),
f"Column widths: {num_columns} != {len(self._columns_cache)}",
)
ErrorMessage.catch_bugs_and_request_email(
any(val < 0 for val in self._column_widths_cache),
f"Column widths cannot be negative: {self._column_widths_cache}",
)
```
###Assistant : Validate that labels are split correctly if split is known.
|
231 | def test_get_name_capability_sid():
cap_sid = "S-1-15-3-1024-1065365936-1281604716-3511738428-1654721687-432734479-3232135806-4053264122-3456934681"
sid_obj = win32security.ConvertStringSidToSid(cap_sid)
assert salt.utils.win_dacl.get_name(sid_obj) is None
|
Test get_name with a compatibility SID. Should return `None` as we want to
ignore these SIDs
| 16 | 12 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_get_name_capability_sid():
cap_sid = "S-1-15-3-1024-1065365936-1281604716-3511738428-1654721687-432734479-3232135806-4053264122-3456934681"
sid_obj = win32security.ConvertStringSidToSid(cap_sid)
assert salt.utils.win_dacl.get_name(sid_obj) is None
```
###Assistant :
Test get_name with a compatibility SID. Should return `None` as we want to
ignore these SIDs
|
232 | def entry_points(group=None):
eps = importlib.metadata.entry_points()
if group:
try:
return eps.select(group=group)
except AttributeError:
return eps.get(group, [])
return eps
| Returns an iterable of entrypoints.
For compatibility with Python 3.8/3.9.
In 3.10 the return type changed from a dict to an ``importlib.metadata.EntryPoints``.
This compatibility utility can be removed once Python 3.10 is the minimum.
| 34 | 17 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def entry_points(group=None):
eps = importlib.metadata.entry_points()
if group:
try:
return eps.select(group=group)
except AttributeError:
return eps.get(group, [])
return eps
```
###Assistant : Returns an iterable of entrypoints.
For compatibility with Python 3.8/3.9.
In 3.10 the return type changed from a dict to an ``importlib.metadata.EntryPoints``.
This compatibility utility can be removed once Python 3.10 is the minimum.
|
233 | def elliptic_curve(self) -> Optional[str]:
key = self._private_key()
if isinstance(key, EllipticCurvePrivateKey):
return key.curve.name
return None
|
:returns: If the private key is an elliptic key, the name of its curve.
:rtype: str
| 16 | 14 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def elliptic_curve(self) -> Optional[str]:
key = self._private_key()
if isinstance(key, EllipticCurvePrivateKey):
return key.curve.name
return None
```
###Assistant :
:returns: If the private key is an elliptic key, the name of its curve.
:rtype: str
|
234 | def page_type_display_name(self):
if not self.specific_class or self.is_root():
return ""
else:
return self.specific_class.get_verbose_name()
|
A human-readable version of this page's type
| 7 | 12 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def page_type_display_name(self):
if not self.specific_class or self.is_root():
return ""
else:
return self.specific_class.get_verbose_name()
```
###Assistant :
A human-readable version of this page's type
|
235 | def save(self, fname, **kwargs) -> Plot:
# TODO expose important keyword arugments in our signature?
self.plot().save(fname, **kwargs)
return self
|
Render the plot and write it to a buffer or file on disk.
Parameters
----------
fname : str, path, or buffer
Location on disk to save the figure, or a buffer to write into.
Other keyword arguments are passed to :meth:`matplotlib.figure.Figure.savefig`.
| 41 | 19 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def save(self, fname, **kwargs) -> Plot:
# TODO expose important keyword arugments in our signature?
self.plot().save(fname, **kwargs)
return self
```
###Assistant :
Render the plot and write it to a buffer or file on disk.
Parameters
----------
fname : str, path, or buffer
Location on disk to save the figure, or a buffer to write into.
Other keyword arguments are passed to :meth:`matplotlib.figure.Figure.savefig`.
|
236 | def get_install_candidate(self, link_evaluator, link):
# type: (LinkEvaluator, Link) -> Optional[InstallationCandidate]
is_candidate, result = link_evaluator.evaluate_link(link)
if not is_candidate:
if result:
self._log_skipped_link(link, reason=result)
return None
return InstallationCandidate(
name=link_evaluator.project_name,
link=link,
version=result,
)
|
If the link is a candidate for install, convert it to an
InstallationCandidate and return it. Otherwise, return None.
| 19 | 29 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_install_candidate(self, link_evaluator, link):
# type: (LinkEvaluator, Link) -> Optional[InstallationCandidate]
is_candidate, result = link_evaluator.evaluate_link(link)
if not is_candidate:
if result:
self._log_skipped_link(link, reason=result)
return None
return InstallationCandidate(
name=link_evaluator.project_name,
link=link,
version=result,
)
```
###Assistant :
If the link is a candidate for install, convert it to an
InstallationCandidate and return it. Otherwise, return None.
|
237 | def bar(self, x=None, y=None, **kwargs) -> PlotAccessor:
return self(kind="bar", x=x, y=y, **kwargs)
|
Vertical bar plot.
A bar plot is a plot that presents categorical data with
rectangular bars with lengths proportional to the values that they
represent. A bar plot shows comparisons among discrete categories. One
axis of the plot shows the specific categories being compared, and the
other axis represents a measured value.
| 52 | 12 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def bar(self, x=None, y=None, **kwargs) -> PlotAccessor:
return self(kind="bar", x=x, y=y, **kwargs)
```
###Assistant :
Vertical bar plot.
A bar plot is a plot that presents categorical data with
rectangular bars with lengths proportional to the values that they
represent. A bar plot shows comparisons among discrete categories. One
axis of the plot shows the specific categories being compared, and the
other axis represents a measured value.
|
238 | def ctc_decode(y_pred, input_length, greedy=True, beam_width=100, top_paths=1):
input_shape = shape(y_pred)
num_samples, num_steps = input_shape[0], input_shape[1]
y_pred = tf.math.log(
tf.compat.v1.transpose(y_pred, perm=[1, 0, 2]) + epsilon()
)
input_length = tf.cast(input_length, tf.int32)
if greedy:
(decoded, log_prob) = tf.nn.ctc_greedy_decoder(
inputs=y_pred, sequence_length=input_length
)
else:
(decoded, log_prob) = tf.compat.v1.nn.ctc_beam_search_decoder(
inputs=y_pred,
sequence_length=input_length,
beam_width=beam_width,
top_paths=top_paths,
)
decoded_dense = []
for st in decoded:
st = tf.SparseTensor(st.indices, st.values, (num_samples, num_steps))
decoded_dense.append(tf.sparse.to_dense(sp_input=st, default_value=-1))
return (decoded_dense, log_prob)
# HIGH ORDER FUNCTIONS
@keras_export("keras.backend.map_fn")
@doc_controls.do_not_generate_docs | Decodes the output of a softmax.
Can use either greedy search (also known as best path)
or a constrained dictionary search.
Args:
y_pred: tensor `(samples, time_steps, num_categories)`
containing the prediction, or output of the softmax.
input_length: tensor `(samples, )` containing the sequence length for
each batch item in `y_pred`.
greedy: perform much faster best-path search if `true`.
This does not use a dictionary.
beam_width: if `greedy` is `false`: a beam search decoder will be used
with a beam of this width.
top_paths: if `greedy` is `false`,
how many of the most probable paths will be returned.
Returns:
Tuple:
List: if `greedy` is `true`, returns a list of one element that
contains the decoded sequence.
If `false`, returns the `top_paths` most probable
decoded sequences.
Each decoded sequence has shape (samples, time_steps).
Important: blank labels are returned as `-1`.
Tensor `(top_paths, )` that contains
the log probability of each decoded sequence.
| 149 | 71 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def ctc_decode(y_pred, input_length, greedy=True, beam_width=100, top_paths=1):
input_shape = shape(y_pred)
num_samples, num_steps = input_shape[0], input_shape[1]
y_pred = tf.math.log(
tf.compat.v1.transpose(y_pred, perm=[1, 0, 2]) + epsilon()
)
input_length = tf.cast(input_length, tf.int32)
if greedy:
(decoded, log_prob) = tf.nn.ctc_greedy_decoder(
inputs=y_pred, sequence_length=input_length
)
else:
(decoded, log_prob) = tf.compat.v1.nn.ctc_beam_search_decoder(
inputs=y_pred,
sequence_length=input_length,
beam_width=beam_width,
top_paths=top_paths,
)
decoded_dense = []
for st in decoded:
st = tf.SparseTensor(st.indices, st.values, (num_samples, num_steps))
decoded_dense.append(tf.sparse.to_dense(sp_input=st, default_value=-1))
return (decoded_dense, log_prob)
# HIGH ORDER FUNCTIONS
@keras_export("keras.backend.map_fn")
@doc_controls.do_not_generate_docs
```
###Assistant : Decodes the output of a softmax.
Can use either greedy search (also known as best path)
or a constrained dictionary search.
Args:
y_pred: tensor `(samples, time_steps, num_categories)`
containing the prediction, or output of the softmax.
input_length: tensor `(samples, )` containing the sequence length for
each batch item in `y_pred`.
greedy: perform much faster best-path search if `true`.
This does not use a dictionary.
beam_width: if `greedy` is `false`: a beam search decoder will be used
with a beam of this width.
top_paths: if `greedy` is `false`,
how many of the most probable paths will be returned.
Returns:
Tuple:
List: if `greedy` is `true`, returns a list of one element that
contains the decoded sequence.
If `false`, returns the `top_paths` most probable
decoded sequences.
Each decoded sequence has shape (samples, time_steps).
Important: blank labels are returned as `-1`.
Tensor `(top_paths, )` that contains
the log probability of each decoded sequence.
|
239 | def display_time_updates(bar):
threading.Thread(target=_show_time_updates, args=(bar,)).start()
|
Start displaying the progress `bar` in a notebook.
Parameters
----------
bar : tqdm.tqdm
The progress bar wrapper to display in a notebook cell.
| 23 | 4 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def display_time_updates(bar):
threading.Thread(target=_show_time_updates, args=(bar,)).start()
```
###Assistant :
Start displaying the progress `bar` in a notebook.
Parameters
----------
bar : tqdm.tqdm
The progress bar wrapper to display in a notebook cell.
|
240 | def remove(name=None, pkgs=None, **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)
errors = []
# Get a list of the currently installed pkgs.
old = list_pkgs()
# Remove the fileset or rpm package(s)
for target in targets:
try:
named, versionpkg, rpmpkg = _check_pkg(target)
except CommandExecutionError as exc:
if exc.info:
errors.append(exc.info["errors"])
continue
if rpmpkg:
# assume use dnf or yum
cmdflags = " -y remove "
if pathlib.Path("/opt/freeware/bin/dnf").is_file():
cmdexe = "/opt/freeware/bin/dnf"
elif pathlib.Path("/opt/freeware/bin/yum").is_file():
cmdexe = "/opt/freeware/bin/yum"
elif pathlib.Path("/usr/bin/yum").is_file():
cmdexe = "/usr/bin/yum"
else:
cmdexe = "/usr/bin/rpm"
cmdflags = " -e "
cmd = [cmdexe, cmdflags, named]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
else:
cmd = ["/usr/sbin/installp", "-u", named]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
# 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 removing filesets(s)/package(s)",
info={"changes": ret, "errors": errors},
)
return ret
|
Remove specified fileset(s)/rpm package(s).
name
The name of the fileset or rpm package to be deleted.
.. 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
Multiple Package Options:
pkgs
A list of filesets and/or rpm packages to delete.
Must be passed as a python list. The ``name`` parameter will be
ignored if this option is passed.
Returns a list containing the removed packages.
CLI Example:
.. code-block:: bash
salt '*' pkg.remove <fileset/rpm package name>
salt '*' pkg.remove tcsh
salt '*' pkg.remove xlC.rte
salt '*' pkg.remove Firefox.base.adt
salt '*' pkg.remove pkgs='["foo", "bar"]'
| 101 | 157 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def remove(name=None, pkgs=None, **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)
errors = []
# Get a list of the currently installed pkgs.
old = list_pkgs()
# Remove the fileset or rpm package(s)
for target in targets:
try:
named, versionpkg, rpmpkg = _check_pkg(target)
except CommandExecutionError as exc:
if exc.info:
errors.append(exc.info["errors"])
continue
if rpmpkg:
# assume use dnf or yum
cmdflags = " -y remove "
if pathlib.Path("/opt/freeware/bin/dnf").is_file():
cmdexe = "/opt/freeware/bin/dnf"
elif pathlib.Path("/opt/freeware/bin/yum").is_file():
cmdexe = "/opt/freeware/bin/yum"
elif pathlib.Path("/usr/bin/yum").is_file():
cmdexe = "/usr/bin/yum"
else:
cmdexe = "/usr/bin/rpm"
cmdflags = " -e "
cmd = [cmdexe, cmdflags, named]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
else:
cmd = ["/usr/sbin/installp", "-u", named]
out = __salt__["cmd.run_all"](cmd, python_shell=False)
# 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 removing filesets(s)/package(s)",
info={"changes": ret, "errors": errors},
)
return ret
```
###Assistant :
Remove specified fileset(s)/rpm package(s).
name
The name of the fileset or rpm package to be deleted.
.. 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
Multiple Package Options:
pkgs
A list of filesets and/or rpm packages to delete.
Must be passed as a python list. The ``name`` parameter will be
ignored if this option is passed.
Returns a list containing the removed packages.
CLI Example:
.. code-block:: bash
salt '*' pkg.remove <fileset/rpm package name>
salt '*' pkg.remove tcsh
salt '*' pkg.remove xlC.rte
salt '*' pkg.remove Firefox.base.adt
salt '*' pkg.remove pkgs='["foo", "bar"]'
|
241 | def _from_ordinalf(x, tz=None):
tz = _get_tzinfo(tz)
dt = (np.datetime64(get_epoch()) +
np.timedelta64(int(np.round(x * MUSECONDS_PER_DAY)), 'us'))
if dt < np.datetime64('0001-01-01') or dt >= np.datetime64('10000-01-01'):
raise ValueError(f'Date ordinal {x} converts to {dt} (using '
f'epoch {get_epoch()}), but Matplotlib dates must be '
'between year 0001 and 9999.')
# convert from datetime64 to datetime:
dt = dt.tolist()
# datetime64 is always UTC:
dt = dt.replace(tzinfo=dateutil.tz.gettz('UTC'))
# but maybe we are working in a different timezone so move.
dt = dt.astimezone(tz)
# fix round off errors
if np.abs(x) > 70 * 365:
# if x is big, round off to nearest twenty microseconds.
# This avoids floating point roundoff error
ms = round(dt.microsecond / 20) * 20
if ms == 1000000:
dt = dt.replace(microsecond=0) + datetime.timedelta(seconds=1)
else:
dt = dt.replace(microsecond=ms)
return dt
# a version of _from_ordinalf that can operate on numpy arrays
_from_ordinalf_np_vectorized = np.vectorize(_from_ordinalf, otypes="O")
# a version of dateutil.parser.parse that can operate on numpy arrays
_dateutil_parser_parse_np_vectorized = np.vectorize(dateutil.parser.parse)
|
Convert Gregorian float of the date, preserving hours, minutes,
seconds and microseconds. Return value is a `.datetime`.
The input date *x* is a float in ordinal days at UTC, and the output will
be the specified `.datetime` object corresponding to that time in
timezone *tz*, or if *tz* is ``None``, in the timezone specified in
:rc:`timezone`.
| 56 | 156 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _from_ordinalf(x, tz=None):
tz = _get_tzinfo(tz)
dt = (np.datetime64(get_epoch()) +
np.timedelta64(int(np.round(x * MUSECONDS_PER_DAY)), 'us'))
if dt < np.datetime64('0001-01-01') or dt >= np.datetime64('10000-01-01'):
raise ValueError(f'Date ordinal {x} converts to {dt} (using '
f'epoch {get_epoch()}), but Matplotlib dates must be '
'between year 0001 and 9999.')
# convert from datetime64 to datetime:
dt = dt.tolist()
# datetime64 is always UTC:
dt = dt.replace(tzinfo=dateutil.tz.gettz('UTC'))
# but maybe we are working in a different timezone so move.
dt = dt.astimezone(tz)
# fix round off errors
if np.abs(x) > 70 * 365:
# if x is big, round off to nearest twenty microseconds.
# This avoids floating point roundoff error
ms = round(dt.microsecond / 20) * 20
if ms == 1000000:
dt = dt.replace(microsecond=0) + datetime.timedelta(seconds=1)
else:
dt = dt.replace(microsecond=ms)
return dt
# a version of _from_ordinalf that can operate on numpy arrays
_from_ordinalf_np_vectorized = np.vectorize(_from_ordinalf, otypes="O")
# a version of dateutil.parser.parse that can operate on numpy arrays
_dateutil_parser_parse_np_vectorized = np.vectorize(dateutil.parser.parse)
```
###Assistant :
Convert Gregorian float of the date, preserving hours, minutes,
seconds and microseconds. Return value is a `.datetime`.
The input date *x* is a float in ordinal days at UTC, and the output will
be the specified `.datetime` object corresponding to that time in
timezone *tz*, or if *tz* is ``None``, in the timezone specified in
:rc:`timezone`.
|
242 | def getdoc(object):
try:
doc = object.__doc__
except AttributeError:
return None
if doc is None:
try:
doc = _finddoc(object)
except (AttributeError, TypeError):
return None
if not isinstance(doc, str):
return None
return cleandoc(doc)
| Get the documentation string for an object.
All tabs are expanded to spaces. To clean up docstrings that are
indented to line up with blocks of code, any whitespace than can be
uniformly removed from the second line onwards is removed. | 41 | 31 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def getdoc(object):
try:
doc = object.__doc__
except AttributeError:
return None
if doc is None:
try:
doc = _finddoc(object)
except (AttributeError, TypeError):
return None
if not isinstance(doc, str):
return None
return cleandoc(doc)
```
###Assistant : Get the documentation string for an object.
All tabs are expanded to spaces. To clean up docstrings that are
indented to line up with blocks of code, any whitespace than can be
uniformly removed from the second line onwards is removed.
|
243 | def load_config_with_kwargs(cls, kwargs):
assert_is_a_marshmallow_class(cls)
schema = cls.Schema()
fields = schema.fields.keys()
return load_config(cls, **{k: v for k, v in kwargs.items() if k in fields}), {
k: v for k, v in kwargs.items() if k not in fields
}
| Takes a marshmallow class and dict of parameter values and appropriately instantiantes the schema. | 14 | 37 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def load_config_with_kwargs(cls, kwargs):
assert_is_a_marshmallow_class(cls)
schema = cls.Schema()
fields = schema.fields.keys()
return load_config(cls, **{k: v for k, v in kwargs.items() if k in fields}), {
k: v for k, v in kwargs.items() if k not in fields
}
```
###Assistant : Takes a marshmallow class and dict of parameter values and appropriately instantiantes the schema.
|
244 | def test_payment_refund_or_void_refund_called_txn_exist(refund_mock, payment):
# given
payment.charge_status = ChargeStatus.FULLY_CHARGED
payment.save(update_fields=["charge_status"])
assert payment.can_refund() is True
payment.captured_amount = payment.total
payment.save(update_fields=["captured_amount"])
txn = payment.transactions.create(
is_success=True,
action_required=False,
kind=TransactionKind.REFUND_ONGOING,
amount=payment.captured_amount / 2,
currency=payment.currency,
token="test",
gateway_response={},
)
# when
gateway.payment_refund_or_void(
payment, get_plugins_manager(), None, transaction_id=txn.token
)
# then
assert refund_mock.called_once()
@patch("saleor.payment.gateway.refund") | Ensure that the refund method is called when the refund process
is already ongoing but not covered full payment captured amount. | 21 | 43 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_payment_refund_or_void_refund_called_txn_exist(refund_mock, payment):
# given
payment.charge_status = ChargeStatus.FULLY_CHARGED
payment.save(update_fields=["charge_status"])
assert payment.can_refund() is True
payment.captured_amount = payment.total
payment.save(update_fields=["captured_amount"])
txn = payment.transactions.create(
is_success=True,
action_required=False,
kind=TransactionKind.REFUND_ONGOING,
amount=payment.captured_amount / 2,
currency=payment.currency,
token="test",
gateway_response={},
)
# when
gateway.payment_refund_or_void(
payment, get_plugins_manager(), None, transaction_id=txn.token
)
# then
assert refund_mock.called_once()
@patch("saleor.payment.gateway.refund")
```
###Assistant : Ensure that the refund method is called when the refund process
is already ongoing but not covered full payment captured amount.
|
245 | def _all(self):
groups = super(Deprecated, self).values()
return EntryPoints(itertools.chain.from_iterable(groups))
|
Reconstruct a list of all entrypoints from the groups.
| 9 | 8 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _all(self):
groups = super(Deprecated, self).values()
return EntryPoints(itertools.chain.from_iterable(groups))
```
###Assistant :
Reconstruct a list of all entrypoints from the groups.
|
246 | def readlines(self, sizehint=None, keepends=True):
data = self.read()
return data.splitlines(keepends)
| Read all lines available on the input stream
and return them as a list.
Line breaks are implemented using the codec's decoder
method and are included in the list entries.
sizehint, if given, is ignored since there is no efficient
way to finding the true end-of-line.
| 46 | 9 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def readlines(self, sizehint=None, keepends=True):
data = self.read()
return data.splitlines(keepends)
```
###Assistant : Read all lines available on the input stream
and return them as a list.
Line breaks are implemented using the codec's decoder
method and are included in the list entries.
sizehint, if given, is ignored since there is no efficient
way to finding the true end-of-line.
|
247 | async def notify_clients(cls) -> None:
while not cls.STOP:
await asyncio.sleep(cls.UPDATE_INTERVALS)
if cls.EVENT_QUEUE:
await cls.broadcast_estimations()
|
Notify clients about events statuses in the queue periodically.
| 9 | 14 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
async def notify_clients(cls) -> None:
while not cls.STOP:
await asyncio.sleep(cls.UPDATE_INTERVALS)
if cls.EVENT_QUEUE:
await cls.broadcast_estimations()
```
###Assistant :
Notify clients about events statuses in the queue periodically.
|
248 | def _readPyPIFile(self):
# Complex stuff, pylint: disable=too-many-branches,too-many-statements
if self.used_modules is None:
pyi_filename = self.getPyIFilename()
if os.path.exists(pyi_filename):
pyi_deps = OrderedSet()
# Flag signalling multiline import handling
in_import = False
in_import_part = ""
for line in getFileContentByLine(pyi_filename):
line = line.strip()
if not in_import:
if line.startswith("import "):
imported = line[7:]
pyi_deps.add(imported)
elif line.startswith("from "):
parts = line.split(None, 3)
assert parts[0] == "from"
assert parts[2] == "import"
origin_name = parts[1]
if origin_name == "typing":
continue
if origin_name == ".":
origin_name = self.getFullName()
else:
dot_count = 0
while origin_name.startswith("."):
origin_name = origin_name[1:]
dot_count += 1
if dot_count > 0:
if origin_name:
origin_name = (
self.getFullName()
.getRelativePackageName(level=dot_count + 1)
.getChildNamed(origin_name)
)
else:
origin_name = (
self.getFullName().getRelativePackageName(
level=dot_count + 1
)
)
if origin_name != self.getFullName():
pyi_deps.add(origin_name)
imported = parts[3]
if imported.startswith("("):
# Handle multiline imports
if not imported.endswith(")"):
in_import = True
imported = imported[1:]
in_import_part = origin_name
assert in_import_part, (
"Multiline part in file %s cannot be empty"
% pyi_filename
)
else:
in_import = False
imported = imported[1:-1]
assert imported
if imported == "*":
continue
for name in imported.split(","):
if name:
name = name.strip()
pyi_deps.add(origin_name + "." + name)
else: # In import
imported = line
if imported.endswith(")"):
imported = imported[0:-1]
in_import = False
for name in imported.split(","):
name = name.strip()
if name:
pyi_deps.add(in_import_part + "." + name)
if "typing" in pyi_deps:
pyi_deps.discard("typing")
if "__future__" in pyi_deps:
pyi_deps.discard("__future__")
if self.getFullName() in pyi_deps:
pyi_deps.discard(self.getFullName())
if self.getFullName().getPackageName() in pyi_deps:
pyi_deps.discard(self.getFullName().getPackageName())
self.used_modules = tuple((pyi_dep, None) for pyi_dep in pyi_deps)
else:
self.used_modules = ()
| Read the .pyi file if present and scan for dependencies. | 10 | 244 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _readPyPIFile(self):
# Complex stuff, pylint: disable=too-many-branches,too-many-statements
if self.used_modules is None:
pyi_filename = self.getPyIFilename()
if os.path.exists(pyi_filename):
pyi_deps = OrderedSet()
# Flag signalling multiline import handling
in_import = False
in_import_part = ""
for line in getFileContentByLine(pyi_filename):
line = line.strip()
if not in_import:
if line.startswith("import "):
imported = line[7:]
pyi_deps.add(imported)
elif line.startswith("from "):
parts = line.split(None, 3)
assert parts[0] == "from"
assert parts[2] == "import"
origin_name = parts[1]
if origin_name == "typing":
continue
if origin_name == ".":
origin_name = self.getFullName()
else:
dot_count = 0
while origin_name.startswith("."):
origin_name = origin_name[1:]
dot_count += 1
if dot_count > 0:
if origin_name:
origin_name = (
self.getFullName()
.getRelativePackageName(level=dot_count + 1)
.getChildNamed(origin_name)
)
else:
origin_name = (
self.getFullName().getRelativePackageName(
level=dot_count + 1
)
)
if origin_name != self.getFullName():
pyi_deps.add(origin_name)
imported = parts[3]
if imported.startswith("("):
# Handle multiline imports
if not imported.endswith(")"):
in_import = True
imported = imported[1:]
in_import_part = origin_name
assert in_import_part, (
"Multiline part in file %s cannot be empty"
% pyi_filename
)
else:
in_import = False
imported = imported[1:-1]
assert imported
if imported == "*":
continue
for name in imported.split(","):
if name:
name = name.strip()
pyi_deps.add(origin_name + "." + name)
else: # In import
imported = line
if imported.endswith(")"):
imported = imported[0:-1]
in_import = False
for name in imported.split(","):
name = name.strip()
if name:
pyi_deps.add(in_import_part + "." + name)
if "typing" in pyi_deps:
pyi_deps.discard("typing")
if "__future__" in pyi_deps:
pyi_deps.discard("__future__")
if self.getFullName() in pyi_deps:
pyi_deps.discard(self.getFullName())
if self.getFullName().getPackageName() in pyi_deps:
pyi_deps.discard(self.getFullName().getPackageName())
self.used_modules = tuple((pyi_dep, None) for pyi_dep in pyi_deps)
else:
self.used_modules = ()
```
###Assistant : Read the .pyi file if present and scan for dependencies.
|
249 | def topological_sort(self):
result = []
# Make a shallow copy of the adjacency list
alist = {}
for k, v in self.adjacency_list.items():
alist[k] = v[:]
while True:
# See what we can remove in this run
to_remove = []
for k, v in list(alist.items())[:]:
if not v:
to_remove.append(k)
del alist[k]
if not to_remove:
# What's left in alist (if anything) is a cycle.
break
# Remove from the adjacency list of others
for k, v in alist.items():
alist[k] = [(d, r) for d, r in v if d not in to_remove]
logger.debug('Moving to result: %s',
['%s (%s)' % (d.name, d.version) for d in to_remove])
result.extend(to_remove)
return result, list(alist.keys())
|
Perform a topological sort of the graph.
:return: A tuple, the first element of which is a topologically sorted
list of distributions, and the second element of which is a
list of distributions that cannot be sorted because they have
circular dependencies and so form a cycle.
| 47 | 108 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def topological_sort(self):
result = []
# Make a shallow copy of the adjacency list
alist = {}
for k, v in self.adjacency_list.items():
alist[k] = v[:]
while True:
# See what we can remove in this run
to_remove = []
for k, v in list(alist.items())[:]:
if not v:
to_remove.append(k)
del alist[k]
if not to_remove:
# What's left in alist (if anything) is a cycle.
break
# Remove from the adjacency list of others
for k, v in alist.items():
alist[k] = [(d, r) for d, r in v if d not in to_remove]
logger.debug('Moving to result: %s',
['%s (%s)' % (d.name, d.version) for d in to_remove])
result.extend(to_remove)
return result, list(alist.keys())
```
###Assistant :
Perform a topological sort of the graph.
:return: A tuple, the first element of which is a topologically sorted
list of distributions, and the second element of which is a
list of distributions that cannot be sorted because they have
circular dependencies and so form a cycle.
|
250 | def soft_reset(self) -> None:
self.length = 0
self.episode_id = random.randrange(int(2e9))
self.total_reward = 0.0
self.agent_rewards = defaultdict(float)
self._agent_reward_history = defaultdict(list)
| Clears rewards and metrics, but retains RNN and other state.
This is used to carry state across multiple logical episodes in the
same env (i.e., if `soft_horizon` is set).
| 29 | 19 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def soft_reset(self) -> None:
self.length = 0
self.episode_id = random.randrange(int(2e9))
self.total_reward = 0.0
self.agent_rewards = defaultdict(float)
self._agent_reward_history = defaultdict(list)
```
###Assistant : Clears rewards and metrics, but retains RNN and other state.
This is used to carry state across multiple logical episodes in the
same env (i.e., if `soft_horizon` is set).
|
251 | def get_ordering_field(self, field_name):
try:
field = self.opts.get_field(field_name)
return field.name
except FieldDoesNotExist:
# See whether field_name is a name of a non-field
# that allows sorting.
if callable(field_name):
attr = field_name
elif hasattr(self.model_admin, field_name):
attr = getattr(self.model_admin, field_name)
else:
attr = getattr(self.model, field_name)
return getattr(attr, "admin_order_field", None)
|
Returns the proper model field name corresponding to the given
field_name to use for ordering. field_name may either be the name of a
proper model field or the name of a method (on the admin or model) or a
callable with the 'admin_order_field' attribute. Returns None if no
proper model field name can be matched.
| 55 | 46 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_ordering_field(self, field_name):
try:
field = self.opts.get_field(field_name)
return field.name
except FieldDoesNotExist:
# See whether field_name is a name of a non-field
# that allows sorting.
if callable(field_name):
attr = field_name
elif hasattr(self.model_admin, field_name):
attr = getattr(self.model_admin, field_name)
else:
attr = getattr(self.model, field_name)
return getattr(attr, "admin_order_field", None)
```
###Assistant :
Returns the proper model field name corresponding to the given
field_name to use for ordering. field_name may either be the name of a
proper model field or the name of a method (on the admin or model) or a
callable with the 'admin_order_field' attribute. Returns None if no
proper model field name can be matched.
|
252 | def _check_ordering(self, obj):
# ordering = None
if obj.ordering is None: # The default value is None
return []
elif not isinstance(obj.ordering, (list, tuple)):
return must_be(
"a list or tuple", option="ordering", obj=obj, id="admin.E031"
)
else:
return list(
chain.from_iterable(
self._check_ordering_item(obj, field_name, "ordering[%d]" % index)
for index, field_name in enumerate(obj.ordering)
)
)
| Check that ordering refers to existing fields or is random. | 10 | 50 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _check_ordering(self, obj):
# ordering = None
if obj.ordering is None: # The default value is None
return []
elif not isinstance(obj.ordering, (list, tuple)):
return must_be(
"a list or tuple", option="ordering", obj=obj, id="admin.E031"
)
else:
return list(
chain.from_iterable(
self._check_ordering_item(obj, field_name, "ordering[%d]" % index)
for index, field_name in enumerate(obj.ordering)
)
)
```
###Assistant : Check that ordering refers to existing fields or is random.
|
253 | def parsing_hooks(cls) -> Tuple[Type["Block"], Type["Sentence"], Type["Statements"]]:
return Block, Sentence, Statements
| Returns object types that this class should be able to `parse` recusrively.
The order of the objects indicates the order in which the parser should
try to parse each subitem.
:returns: A list of Parsable classes.
:rtype list:
| 38 | 10 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def parsing_hooks(cls) -> Tuple[Type["Block"], Type["Sentence"], Type["Statements"]]:
return Block, Sentence, Statements
```
###Assistant : Returns object types that this class should be able to `parse` recusrively.
The order of the objects indicates the order in which the parser should
try to parse each subitem.
:returns: A list of Parsable classes.
:rtype list:
|
254 | def _cast_inplace(terms, acceptable_dtypes, dtype) -> None:
dt = np.dtype(dtype)
for term in terms:
if term.type in acceptable_dtypes:
continue
try:
new_value = term.value.astype(dt)
except AttributeError:
new_value = dt.type(term.value)
term.update(new_value)
|
Cast an expression inplace.
Parameters
----------
terms : Op
The expression that should cast.
acceptable_dtypes : list of acceptable numpy.dtype
Will not cast if term's dtype in this list.
dtype : str or numpy.dtype
The dtype to cast to.
| 39 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _cast_inplace(terms, acceptable_dtypes, dtype) -> None:
dt = np.dtype(dtype)
for term in terms:
if term.type in acceptable_dtypes:
continue
try:
new_value = term.value.astype(dt)
except AttributeError:
new_value = dt.type(term.value)
term.update(new_value)
```
###Assistant :
Cast an expression inplace.
Parameters
----------
terms : Op
The expression that should cast.
acceptable_dtypes : list of acceptable numpy.dtype
Will not cast if term's dtype in this list.
dtype : str or numpy.dtype
The dtype to cast to.
|
255 | def _deployment_created(self, external_id, request):
payload = request.data["payload"]
vercel_project_id = (
payload["projectId"] if payload.get("projectId") else payload["project"]["id"]
)
# Only create releases for production deploys for now
if payload["target"] != "production":
logger.info(
f"Ignoring deployment for environment: {payload['target']}",
extra={"external_id": external_id, "vercel_project_id": vercel_project_id},
)
return self.respond(status=204)
logging_params = {"external_id": external_id, "vercel_project_id": vercel_project_id}
org_integrations = OrganizationIntegration.objects.select_related("organization").filter(
integration__external_id=external_id, integration__provider=self.provider
)
if not org_integrations:
logger.info("Integration not found", extra=logging_params)
return self.respond({"detail": "Integration not found"}, status=404)
# for each org integration, search the configs to find one that matches the vercel project of the webhook
for org_integration in org_integrations:
project_mappings = org_integration.config.get("project_mappings") or []
matched_mappings = list(filter(lambda x: x[1] == vercel_project_id, project_mappings))
if matched_mappings:
organization = org_integration.organization
sentry_project_id = matched_mappings[0][0]
logging_params["organization_id"] = organization.id
logging_params["project_id"] = sentry_project_id
try:
release_payload, token = get_payload_and_token(
payload, organization.id, sentry_project_id
)
except Project.DoesNotExist:
logger.info("Project not found", extra=logging_params)
return self.respond({"detail": "Project not found"}, status=404)
except SentryAppInstallationForProvider.DoesNotExist:
logger.info("Installation not found", extra=logging_params)
return self.respond({"detail": "Installation not found"}, status=404)
except SentryAppInstallationToken.DoesNotExist:
logger.info("Token not found", extra=logging_params)
return self.respond({"detail": "Token not found"}, status=404)
except NoCommitFoundError:
logger.info("No commit found", extra=logging_params)
return self.respond({"detail": "No commit found"}, status=404)
except MissingRepositoryError:
logger.info("Could not determine repository", extra=logging_params)
return self.respond({"detail": "Could not determine repository"}, status=400)
url = absolute_uri(f"/api/0/organizations/{organization.slug}/releases/")
headers = {
"Accept": "application/json",
"Authorization": f"Bearer {token}",
"User-Agent": f"sentry_vercel/{VERSION}",
}
json_error = None
# create the basic release payload without refs
no_ref_payload = release_payload.copy()
del no_ref_payload["refs"]
with http.build_session() as session:
try:
resp = session.post(url, json=no_ref_payload, headers=headers)
json_error = safe_json_parse(resp)
resp.raise_for_status()
except RequestException as e:
# errors here should be uncommon but we should be aware of them
logger.error(
f"Error creating release: {e} - {json_error}",
extra=logging_params,
exc_info=True,
)
# 400 probably isn't the right status code but oh well
return self.respond({"detail": f"Error creating release: {e}"}, status=400)
# set the refs
try:
resp = session.post(
url,
json=release_payload,
headers=headers,
)
json_error = safe_json_parse(resp)
resp.raise_for_status()
except RequestException as e:
# errors will probably be common if the user doesn't have repos set up
logger.info(
f"Error setting refs: {e} - {json_error}",
extra=logging_params,
exc_info=True,
)
# 400 probably isn't the right status code but oh well
return self.respond({"detail": f"Error setting refs: {e}"}, status=400)
# we are going to quit after the first project match as there shouldn't be multiple matches
return self.respond(status=201)
return self.respond(status=204)
|
Steps:
1. Find all org integrations that match the external id
2. Search the configs to find one that matches the vercel project of the webhook
3. Look up the Sentry project that matches
4. Look up the connected internal integration
5. Find the token associated with that installation
6. Determine the commit sha and repo based on what provider is used
7. Create the release using the token WITHOUT refs
8. Update the release with refs
| 77 | 360 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _deployment_created(self, external_id, request):
payload = request.data["payload"]
vercel_project_id = (
payload["projectId"] if payload.get("projectId") else payload["project"]["id"]
)
# Only create releases for production deploys for now
if payload["target"] != "production":
logger.info(
f"Ignoring deployment for environment: {payload['target']}",
extra={"external_id": external_id, "vercel_project_id": vercel_project_id},
)
return self.respond(status=204)
logging_params = {"external_id": external_id, "vercel_project_id": vercel_project_id}
org_integrations = OrganizationIntegration.objects.select_related("organization").filter(
integration__external_id=external_id, integration__provider=self.provider
)
if not org_integrations:
logger.info("Integration not found", extra=logging_params)
return self.respond({"detail": "Integration not found"}, status=404)
# for each org integration, search the configs to find one that matches the vercel project of the webhook
for org_integration in org_integrations:
project_mappings = org_integration.config.get("project_mappings") or []
matched_mappings = list(filter(lambda x: x[1] == vercel_project_id, project_mappings))
if matched_mappings:
organization = org_integration.organization
sentry_project_id = matched_mappings[0][0]
logging_params["organization_id"] = organization.id
logging_params["project_id"] = sentry_project_id
try:
release_payload, token = get_payload_and_token(
payload, organization.id, sentry_project_id
)
except Project.DoesNotExist:
logger.info("Project not found", extra=logging_params)
return self.respond({"detail": "Project not found"}, status=404)
except SentryAppInstallationForProvider.DoesNotExist:
logger.info("Installation not found", extra=logging_params)
return self.respond({"detail": "Installation not found"}, status=404)
except SentryAppInstallationToken.DoesNotExist:
logger.info("Token not found", extra=logging_params)
return self.respond({"detail": "Token not found"}, status=404)
except NoCommitFoundError:
logger.info("No commit found", extra=logging_params)
return self.respond({"detail": "No commit found"}, status=404)
except MissingRepositoryError:
logger.info("Could not determine repository", extra=logging_params)
return self.respond({"detail": "Could not determine repository"}, status=400)
url = absolute_uri(f"/api/0/organizations/{organization.slug}/releases/")
headers = {
"Accept": "application/json",
"Authorization": f"Bearer {token}",
"User-Agent": f"sentry_vercel/{VERSION}",
}
json_error = None
# create the basic release payload without refs
no_ref_payload = release_payload.copy()
del no_ref_payload["refs"]
with http.build_session() as session:
try:
resp = session.post(url, json=no_ref_payload, headers=headers)
json_error = safe_json_parse(resp)
resp.raise_for_status()
except RequestException as e:
# errors here should be uncommon but we should be aware of them
logger.error(
f"Error creating release: {e} - {json_error}",
extra=logging_params,
exc_info=True,
)
# 400 probably isn't the right status code but oh well
return self.respond({"detail": f"Error creating release: {e}"}, status=400)
# set the refs
try:
resp = session.post(
url,
json=release_payload,
headers=headers,
)
json_error = safe_json_parse(resp)
resp.raise_for_status()
except RequestException as e:
# errors will probably be common if the user doesn't have repos set up
logger.info(
f"Error setting refs: {e} - {json_error}",
extra=logging_params,
exc_info=True,
)
# 400 probably isn't the right status code but oh well
return self.respond({"detail": f"Error setting refs: {e}"}, status=400)
# we are going to quit after the first project match as there shouldn't be multiple matches
return self.respond(status=201)
return self.respond(status=204)
```
###Assistant :
Steps:
1. Find all org integrations that match the external id
2. Search the configs to find one that matches the vercel project of the webhook
3. Look up the Sentry project that matches
4. Look up the connected internal integration
5. Find the token associated with that installation
6. Determine the commit sha and repo based on what provider is used
7. Create the release using the token WITHOUT refs
8. Update the release with refs
|
256 | def _app_user(self) -> User | None:
return self.user if isinstance(self.user, User) else None
| The user, if they are represented persistently in our app. | 10 | 13 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _app_user(self) -> User | None:
return self.user if isinstance(self.user, User) else None
```
###Assistant : The user, if they are represented persistently in our app.
|
257 | def new_locator(self, nx, nx1=None):
return AxesLocator(self, nx, 0, nx1 if nx1 is not None else nx + 1, 1)
|
Create a new `.AxesLocator` for the specified cell.
Parameters
----------
nx, nx1 : int
Integers specifying the column-position of the
cell. When *nx1* is None, a single *nx*-th column is
specified. Otherwise, location of columns spanning between *nx*
to *nx1* (but excluding *nx1*-th column) is specified.
| 46 | 19 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def new_locator(self, nx, nx1=None):
return AxesLocator(self, nx, 0, nx1 if nx1 is not None else nx + 1, 1)
```
###Assistant :
Create a new `.AxesLocator` for the specified cell.
Parameters
----------
nx, nx1 : int
Integers specifying the column-position of the
cell. When *nx1* is None, a single *nx*-th column is
specified. Otherwise, location of columns spanning between *nx*
to *nx1* (but excluding *nx1*-th column) is specified.
|
258 | def test_edit_cases(self) -> None:
self.login("hamlet")
hamlet = self.example_user("hamlet")
msg_id = self.send_stream_message(
self.example_user("hamlet"), "Denmark", topic_name="topic 1", content="content 1"
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 2",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 1")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(
set(history[0].keys()),
{
"timestamp",
"prev_content",
"user_id",
"prev_rendered_content",
"prev_rendered_content_version",
},
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"topic": "topic 2",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 1")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(set(history[0].keys()), {"timestamp", LEGACY_PREV_TOPIC, "user_id"})
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 3",
"topic": "topic 3",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 2")
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 2")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(
set(history[0].keys()),
{
"timestamp",
LEGACY_PREV_TOPIC,
"prev_content",
"user_id",
"prev_rendered_content",
"prev_rendered_content_version",
},
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 4",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 3")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.login("iago")
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"topic": "topic 4",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 3")
self.assertEqual(history[0]["user_id"], self.example_user("iago").id)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 3")
self.assertEqual(history[2][LEGACY_PREV_TOPIC], "topic 2")
self.assertEqual(history[3][LEGACY_PREV_TOPIC], "topic 1")
self.assertEqual(history[1]["prev_content"], "content 3")
self.assertEqual(history[2]["prev_content"], "content 2")
self.assertEqual(history[4]["prev_content"], "content 1")
# Now, we verify that the edit history data sent back has the
# correct filled-out fields
message_edit_history = self.client_get(f"/json/messages/{msg_id}/history")
json_response = orjson.loads(message_edit_history.content)
# We reverse the message history view output so that the IDs line up with the above.
message_history = list(reversed(json_response["message_history"]))
i = 0
for entry in message_history:
expected_entries = {"content", "rendered_content", "topic", "timestamp", "user_id"}
if i in {0, 2, 3}:
expected_entries.add("prev_topic")
if i in {1, 2, 4}:
expected_entries.add("prev_content")
expected_entries.add("prev_rendered_content")
expected_entries.add("content_html_diff")
i += 1
self.assertEqual(expected_entries, set(entry.keys()))
self.assert_length(message_history, 6)
self.assertEqual(message_history[0]["prev_topic"], "topic 3")
self.assertEqual(message_history[0]["topic"], "topic 4")
self.assertEqual(message_history[1]["topic"], "topic 3")
self.assertEqual(message_history[2]["topic"], "topic 3")
self.assertEqual(message_history[2]["prev_topic"], "topic 2")
self.assertEqual(message_history[3]["topic"], "topic 2")
self.assertEqual(message_history[3]["prev_topic"], "topic 1")
self.assertEqual(message_history[4]["topic"], "topic 1")
self.assertEqual(message_history[0]["content"], "content 4")
self.assertEqual(message_history[1]["content"], "content 4")
self.assertEqual(message_history[1]["prev_content"], "content 3")
self.assertEqual(message_history[2]["content"], "content 3")
self.assertEqual(message_history[2]["prev_content"], "content 2")
self.assertEqual(message_history[3]["content"], "content 2")
self.assertEqual(message_history[4]["content"], "content 2")
self.assertEqual(message_history[4]["prev_content"], "content 1")
self.assertEqual(message_history[5]["content"], "content 1")
self.assertEqual(message_history[5]["topic"], "topic 1")
| This test verifies the accuracy of construction of Zulip's edit
history data structures. | 13 | 310 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_edit_cases(self) -> None:
self.login("hamlet")
hamlet = self.example_user("hamlet")
msg_id = self.send_stream_message(
self.example_user("hamlet"), "Denmark", topic_name="topic 1", content="content 1"
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 2",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 1")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(
set(history[0].keys()),
{
"timestamp",
"prev_content",
"user_id",
"prev_rendered_content",
"prev_rendered_content_version",
},
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"topic": "topic 2",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 1")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(set(history[0].keys()), {"timestamp", LEGACY_PREV_TOPIC, "user_id"})
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 3",
"topic": "topic 3",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 2")
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 2")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.assertEqual(
set(history[0].keys()),
{
"timestamp",
LEGACY_PREV_TOPIC,
"prev_content",
"user_id",
"prev_rendered_content",
"prev_rendered_content_version",
},
)
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"content": "content 4",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0]["prev_content"], "content 3")
self.assertEqual(history[0]["user_id"], hamlet.id)
self.login("iago")
result = self.client_patch(
f"/json/messages/{msg_id}",
{
"message_id": msg_id,
"topic": "topic 4",
},
)
self.assert_json_success(result)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 3")
self.assertEqual(history[0]["user_id"], self.example_user("iago").id)
history = orjson.loads(Message.objects.get(id=msg_id).edit_history)
self.assertEqual(history[0][LEGACY_PREV_TOPIC], "topic 3")
self.assertEqual(history[2][LEGACY_PREV_TOPIC], "topic 2")
self.assertEqual(history[3][LEGACY_PREV_TOPIC], "topic 1")
self.assertEqual(history[1]["prev_content"], "content 3")
self.assertEqual(history[2]["prev_content"], "content 2")
self.assertEqual(history[4]["prev_content"], "content 1")
# Now, we verify that the edit history data sent back has the
# correct filled-out fields
message_edit_history = self.client_get(f"/json/messages/{msg_id}/history")
json_response = orjson.loads(message_edit_history.content)
# We reverse the message history view output so that the IDs line up with the above.
message_history = list(reversed(json_response["message_history"]))
i = 0
for entry in message_history:
expected_entries = {"content", "rendered_content", "topic", "timestamp", "user_id"}
if i in {0, 2, 3}:
expected_entries.add("prev_topic")
if i in {1, 2, 4}:
expected_entries.add("prev_content")
expected_entries.add("prev_rendered_content")
expected_entries.add("content_html_diff")
i += 1
self.assertEqual(expected_entries, set(entry.keys()))
self.assert_length(message_history, 6)
self.assertEqual(message_history[0]["prev_topic"], "topic 3")
self.assertEqual(message_history[0]["topic"], "topic 4")
self.assertEqual(message_history[1]["topic"], "topic 3")
self.assertEqual(message_history[2]["topic"], "topic 3")
self.assertEqual(message_history[2]["prev_topic"], "topic 2")
self.assertEqual(message_history[3]["topic"], "topic 2")
self.assertEqual(message_history[3]["prev_topic"], "topic 1")
self.assertEqual(message_history[4]["topic"], "topic 1")
self.assertEqual(message_history[0]["content"], "content 4")
self.assertEqual(message_history[1]["content"], "content 4")
self.assertEqual(message_history[1]["prev_content"], "content 3")
self.assertEqual(message_history[2]["content"], "content 3")
self.assertEqual(message_history[2]["prev_content"], "content 2")
self.assertEqual(message_history[3]["content"], "content 2")
self.assertEqual(message_history[4]["content"], "content 2")
self.assertEqual(message_history[4]["prev_content"], "content 1")
self.assertEqual(message_history[5]["content"], "content 1")
self.assertEqual(message_history[5]["topic"], "topic 1")
```
###Assistant : This test verifies the accuracy of construction of Zulip's edit
history data structures.
|
259 | def get_project_name(doctype, txt, searchfield, start, page_len, filters):
doctype = "Project"
cond = ""
if filters and filters.get("customer"):
cond = % (
frappe.db.escape(filters.get("customer"))
)
fields = get_fields(doctype, ["name", "project_name"])
searchfields = frappe.get_meta(doctype).get_search_fields()
searchfields = " or ".join(["`tabProject`." + field + " like %(txt)s" for field in searchfields])
return frappe.db.sql(
.format(
fields=", ".join(["`tabProject`.{0}".format(f) for f in fields]),
cond=cond,
scond=searchfields,
match_cond=get_match_cond(doctype),
start=start,
page_len=page_len,
),
{"txt": "%{0}%".format(txt), "_txt": txt.replace("%", "")},
)
@frappe.whitelist()
@frappe.validate_and_sanitize_search_inputs | (`tabProject`.customer = %s or
ifnull(`tabProject`.customer,"")="") andselect {fields} from `tabProject`
where
`tabProject`.status not in ('Completed', 'Cancelled')
and {cond} {scond} {match_cond}
order by
(case when locate(%(_txt)s, `tabProject`.name) > 0 then locate(%(_txt)s, `tabProject`.name) else 99999 end),
`tabProject`.idx desc,
`tabProject`.name asc
limit {page_len} offset {start} | 41 | 69 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_project_name(doctype, txt, searchfield, start, page_len, filters):
doctype = "Project"
cond = ""
if filters and filters.get("customer"):
cond = % (
frappe.db.escape(filters.get("customer"))
)
fields = get_fields(doctype, ["name", "project_name"])
searchfields = frappe.get_meta(doctype).get_search_fields()
searchfields = " or ".join(["`tabProject`." + field + " like %(txt)s" for field in searchfields])
return frappe.db.sql(
.format(
fields=", ".join(["`tabProject`.{0}".format(f) for f in fields]),
cond=cond,
scond=searchfields,
match_cond=get_match_cond(doctype),
start=start,
page_len=page_len,
),
{"txt": "%{0}%".format(txt), "_txt": txt.replace("%", "")},
)
@frappe.whitelist()
@frappe.validate_and_sanitize_search_inputs
```
###Assistant : (`tabProject`.customer = %s or
ifnull(`tabProject`.customer,"")="") andselect {fields} from `tabProject`
where
`tabProject`.status not in ('Completed', 'Cancelled')
and {cond} {scond} {match_cond}
order by
(case when locate(%(_txt)s, `tabProject`.name) > 0 then locate(%(_txt)s, `tabProject`.name) else 99999 end),
`tabProject`.idx desc,
`tabProject`.name asc
limit {page_len} offset {start}
|
260 | def test_autosuggest_at_EOL(text, cursor, suggestion, called):
event = make_event(text, cursor, suggestion)
event.current_buffer.insert_text = Mock()
_apply_autosuggest(event)
if called:
event.current_buffer.insert_text.assert_called()
else:
event.current_buffer.insert_text.assert_not_called()
# event.current_buffer.document.get_end_of_line_position.assert_called()
|
test that autosuggest is only applied at end of line.
| 10 | 21 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_autosuggest_at_EOL(text, cursor, suggestion, called):
event = make_event(text, cursor, suggestion)
event.current_buffer.insert_text = Mock()
_apply_autosuggest(event)
if called:
event.current_buffer.insert_text.assert_called()
else:
event.current_buffer.insert_text.assert_not_called()
# event.current_buffer.document.get_end_of_line_position.assert_called()
```
###Assistant :
test that autosuggest is only applied at end of line.
|
261 | def stack3(x, filters, blocks, stride1=2, groups=32, name=None):
x = block3(x, filters, stride=stride1, groups=groups, name=name + "_block1")
for i in range(2, blocks + 1):
x = block3(
x,
filters,
groups=groups,
conv_shortcut=False,
name=name + "_block" + str(i),
)
return x
@keras_export(
"keras.applications.resnet50.ResNet50",
"keras.applications.resnet.ResNet50",
"keras.applications.ResNet50",
) | A set of stacked residual blocks.
Args:
x: input tensor.
filters: integer, filters of the bottleneck layer in a block.
blocks: integer, blocks in the stacked blocks.
stride1: default 2, stride of the first layer in the first block.
groups: default 32, group size for grouped convolution.
name: string, stack label.
Returns:
Output tensor for the stacked blocks.
| 58 | 43 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def stack3(x, filters, blocks, stride1=2, groups=32, name=None):
x = block3(x, filters, stride=stride1, groups=groups, name=name + "_block1")
for i in range(2, blocks + 1):
x = block3(
x,
filters,
groups=groups,
conv_shortcut=False,
name=name + "_block" + str(i),
)
return x
@keras_export(
"keras.applications.resnet50.ResNet50",
"keras.applications.resnet.ResNet50",
"keras.applications.ResNet50",
)
```
###Assistant : A set of stacked residual blocks.
Args:
x: input tensor.
filters: integer, filters of the bottleneck layer in a block.
blocks: integer, blocks in the stacked blocks.
stride1: default 2, stride of the first layer in the first block.
groups: default 32, group size for grouped convolution.
name: string, stack label.
Returns:
Output tensor for the stacked blocks.
|
262 | def is_mixed(self) -> bool:
warnings.warn(
"Index.is_mixed is deprecated and will be removed in a future version. "
"Check index.inferred_type directly instead.",
FutureWarning,
stacklevel=find_stack_level(inspect.currentframe()),
)
return self.inferred_type in ["mixed"]
|
Check if the Index holds data with mixed data types.
Returns
-------
bool
Whether or not the Index holds data with mixed data types.
See Also
--------
is_boolean : Check if the Index only consists of booleans.
is_integer : Check if the Index only consists of integers.
is_floating : Check if the Index is a floating type.
is_numeric : Check if the Index only consists of numeric data.
is_object : Check if the Index is of the object dtype.
is_categorical : Check if the Index holds categorical data.
is_interval : Check if the Index holds Interval objects.
Examples
--------
>>> idx = pd.Index(['a', np.nan, 'b'])
>>> idx.is_mixed()
True
>>> idx = pd.Index([1.0, 2.0, 3.0, 5.0])
>>> idx.is_mixed()
False
| 118 | 28 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def is_mixed(self) -> bool:
warnings.warn(
"Index.is_mixed is deprecated and will be removed in a future version. "
"Check index.inferred_type directly instead.",
FutureWarning,
stacklevel=find_stack_level(inspect.currentframe()),
)
return self.inferred_type in ["mixed"]
```
###Assistant :
Check if the Index holds data with mixed data types.
Returns
-------
bool
Whether or not the Index holds data with mixed data types.
See Also
--------
is_boolean : Check if the Index only consists of booleans.
is_integer : Check if the Index only consists of integers.
is_floating : Check if the Index is a floating type.
is_numeric : Check if the Index only consists of numeric data.
is_object : Check if the Index is of the object dtype.
is_categorical : Check if the Index holds categorical data.
is_interval : Check if the Index holds Interval objects.
Examples
--------
>>> idx = pd.Index(['a', np.nan, 'b'])
>>> idx.is_mixed()
True
>>> idx = pd.Index([1.0, 2.0, 3.0, 5.0])
>>> idx.is_mixed()
False
|
263 | def responder(request):
# Find an available port
with socket.socket() as sock:
sock.bind(("localhost", 0))
port = sock.getsockname()[1]
server_process = multiprocessing.Process(
target=process_server, args=(request.param, port)
)
server_process.start()
yield port
server_process.join(10)
server_process.terminate()
kill_time = 5
wait_time = 0
while server_process.is_alive():
if wait_time > kill_time:
server_process.kill()
break
else:
wait_time += 0.1
time.sleep(0.1)
server_process.close()
@pytest.mark.parametrize(
"responder, read_method, parquet_engine",
[
(CSVUserAgentResponder, pd.read_csv, None),
(JSONUserAgentResponder, pd.read_json, None),
(ParquetPyArrowUserAgentResponder, pd.read_parquet, "pyarrow"),
pytest.param(
ParquetFastParquetUserAgentResponder,
pd.read_parquet,
"fastparquet",
# TODO(ArrayManager) fastparquet
marks=[
td.skip_array_manager_not_yet_implemented,
pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10"),
],
),
(PickleUserAgentResponder, pd.read_pickle, None),
(StataUserAgentResponder, pd.read_stata, None),
(GzippedCSVUserAgentResponder, pd.read_csv, None),
(GzippedJSONUserAgentResponder, pd.read_json, None),
],
indirect=["responder"],
) |
Fixture that starts a local http server in a separate process on localhost
and returns the port.
Running in a separate process instead of a thread to allow termination/killing
of http server upon cleanup.
| 34 | 93 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def responder(request):
# Find an available port
with socket.socket() as sock:
sock.bind(("localhost", 0))
port = sock.getsockname()[1]
server_process = multiprocessing.Process(
target=process_server, args=(request.param, port)
)
server_process.start()
yield port
server_process.join(10)
server_process.terminate()
kill_time = 5
wait_time = 0
while server_process.is_alive():
if wait_time > kill_time:
server_process.kill()
break
else:
wait_time += 0.1
time.sleep(0.1)
server_process.close()
@pytest.mark.parametrize(
"responder, read_method, parquet_engine",
[
(CSVUserAgentResponder, pd.read_csv, None),
(JSONUserAgentResponder, pd.read_json, None),
(ParquetPyArrowUserAgentResponder, pd.read_parquet, "pyarrow"),
pytest.param(
ParquetFastParquetUserAgentResponder,
pd.read_parquet,
"fastparquet",
# TODO(ArrayManager) fastparquet
marks=[
td.skip_array_manager_not_yet_implemented,
pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10"),
],
),
(PickleUserAgentResponder, pd.read_pickle, None),
(StataUserAgentResponder, pd.read_stata, None),
(GzippedCSVUserAgentResponder, pd.read_csv, None),
(GzippedJSONUserAgentResponder, pd.read_json, None),
],
indirect=["responder"],
)
```
###Assistant :
Fixture that starts a local http server in a separate process on localhost
and returns the port.
Running in a separate process instead of a thread to allow termination/killing
of http server upon cleanup.
|
264 | def _pre_setup(self):
super()._pre_setup()
if self.available_apps is not None:
apps.set_available_apps(self.available_apps)
setting_changed.send(
sender=settings._wrapped.__class__,
setting="INSTALLED_APPS",
value=self.available_apps,
enter=True,
)
for db_name in self._databases_names(include_mirrors=False):
emit_post_migrate_signal(verbosity=0, interactive=False, db=db_name)
try:
self._fixture_setup()
except Exception:
if self.available_apps is not None:
apps.unset_available_apps()
setting_changed.send(
sender=settings._wrapped.__class__,
setting="INSTALLED_APPS",
value=settings.INSTALLED_APPS,
enter=False,
)
raise
# Clear the queries_log so that it's less likely to overflow (a single
# test probably won't execute 9K queries). If queries_log overflows,
# then assertNumQueries() doesn't work.
for db_name in self._databases_names(include_mirrors=False):
connections[db_name].queries_log.clear()
|
Perform pre-test setup:
* If the class has an 'available_apps' attribute, restrict the app
registry to these applications, then fire the post_migrate signal --
it must run with the correct set of applications for the test case.
* If the class has a 'fixtures' attribute, install those fixtures.
| 48 | 72 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _pre_setup(self):
super()._pre_setup()
if self.available_apps is not None:
apps.set_available_apps(self.available_apps)
setting_changed.send(
sender=settings._wrapped.__class__,
setting="INSTALLED_APPS",
value=self.available_apps,
enter=True,
)
for db_name in self._databases_names(include_mirrors=False):
emit_post_migrate_signal(verbosity=0, interactive=False, db=db_name)
try:
self._fixture_setup()
except Exception:
if self.available_apps is not None:
apps.unset_available_apps()
setting_changed.send(
sender=settings._wrapped.__class__,
setting="INSTALLED_APPS",
value=settings.INSTALLED_APPS,
enter=False,
)
raise
# Clear the queries_log so that it's less likely to overflow (a single
# test probably won't execute 9K queries). If queries_log overflows,
# then assertNumQueries() doesn't work.
for db_name in self._databases_names(include_mirrors=False):
connections[db_name].queries_log.clear()
```
###Assistant :
Perform pre-test setup:
* If the class has an 'available_apps' attribute, restrict the app
registry to these applications, then fire the post_migrate signal --
it must run with the correct set of applications for the test case.
* If the class has a 'fixtures' attribute, install those fixtures.
|
265 | def test_multiple_actions_form(self):
action_data = {
ACTION_CHECKBOX_NAME: [self.s1.pk],
# Two different actions selected on the two forms...
"action": ["external_mail", "delete_selected"],
# ...but "go" was clicked on the top form.
"index": 0,
}
self.client.post(
reverse("admin:admin_views_externalsubscriber_changelist"), action_data
)
# The action sends mail rather than deletes.
self.assertEqual(len(mail.outbox), 1)
self.assertEqual(mail.outbox[0].subject, "Greetings from a function action")
|
Actions come from the form whose submit button was pressed (#10618).
| 11 | 51 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_multiple_actions_form(self):
action_data = {
ACTION_CHECKBOX_NAME: [self.s1.pk],
# Two different actions selected on the two forms...
"action": ["external_mail", "delete_selected"],
# ...but "go" was clicked on the top form.
"index": 0,
}
self.client.post(
reverse("admin:admin_views_externalsubscriber_changelist"), action_data
)
# The action sends mail rather than deletes.
self.assertEqual(len(mail.outbox), 1)
self.assertEqual(mail.outbox[0].subject, "Greetings from a function action")
```
###Assistant :
Actions come from the form whose submit button was pressed (#10618).
|
266 | def test_empty_message(self) -> None:
self.login("hamlet")
othello = self.example_user("othello")
result = self.client_post(
"/json/messages",
{"type": "private", "content": " ", "to": othello.email},
)
self.assert_json_error(result, "Message must not be empty")
|
Sending a message that is empty or only whitespace should fail
| 11 | 26 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_empty_message(self) -> None:
self.login("hamlet")
othello = self.example_user("othello")
result = self.client_post(
"/json/messages",
{"type": "private", "content": " ", "to": othello.email},
)
self.assert_json_error(result, "Message must not be empty")
```
###Assistant :
Sending a message that is empty or only whitespace should fail
|
267 | def freqai_feature_engineering_generic(self, dataframe, **kwargs):
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
return dataframe
|
This optional function will be called for all include_timeframes (including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
:param df: strategy dataframe which will receive the features
dataframe["%-pct-change"] = dataframe["close"].pct_change()
| 38 | 15 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def freqai_feature_engineering_generic(self, dataframe, **kwargs):
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
return dataframe
```
###Assistant :
This optional function will be called for all include_timeframes (including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
:param df: strategy dataframe which will receive the features
dataframe["%-pct-change"] = dataframe["close"].pct_change()
|
268 | def next_sample(uid):
return next(_SHARED_SEQUENCES[uid])
@keras_export("keras.utils.GeneratorEnqueuer") | Gets the next value from the generator `uid`.
To allow multiple generators to be used at the same time, we use `uid` to
get a specific one. A single generator would cause the validation to
overwrite the training generator.
Args:
uid: int, generator identifier
Returns:
The next value of generator `uid`.
| 51 | 5 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def next_sample(uid):
return next(_SHARED_SEQUENCES[uid])
@keras_export("keras.utils.GeneratorEnqueuer")
```
###Assistant : Gets the next value from the generator `uid`.
To allow multiple generators to be used at the same time, we use `uid` to
get a specific one. A single generator would cause the validation to
overwrite the training generator.
Args:
uid: int, generator identifier
Returns:
The next value of generator `uid`.
|
269 | def check_settings(base_url=None):
if base_url is None:
base_url = settings.STATIC_URL
if not base_url:
raise ImproperlyConfigured(
"You're using the staticfiles app "
"without having set the required STATIC_URL setting.")
if settings.MEDIA_URL == base_url:
raise ImproperlyConfigured(
"The MEDIA_URL and STATIC_URL settings must have different values"
)
if (settings.DEBUG and settings.MEDIA_URL and settings.STATIC_URL and
settings.MEDIA_URL.startswith(settings.STATIC_URL)):
raise ImproperlyConfigured(
"runserver can't serve media if MEDIA_URL is within STATIC_URL."
)
if ((settings.MEDIA_ROOT and settings.STATIC_ROOT) and
(settings.MEDIA_ROOT == settings.STATIC_ROOT)):
raise ImproperlyConfigured(
"The MEDIA_ROOT and STATIC_ROOT settings must have different values"
)
|
Check if the staticfiles settings have sane values.
| 8 | 83 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def check_settings(base_url=None):
if base_url is None:
base_url = settings.STATIC_URL
if not base_url:
raise ImproperlyConfigured(
"You're using the staticfiles app "
"without having set the required STATIC_URL setting.")
if settings.MEDIA_URL == base_url:
raise ImproperlyConfigured(
"The MEDIA_URL and STATIC_URL settings must have different values"
)
if (settings.DEBUG and settings.MEDIA_URL and settings.STATIC_URL and
settings.MEDIA_URL.startswith(settings.STATIC_URL)):
raise ImproperlyConfigured(
"runserver can't serve media if MEDIA_URL is within STATIC_URL."
)
if ((settings.MEDIA_ROOT and settings.STATIC_ROOT) and
(settings.MEDIA_ROOT == settings.STATIC_ROOT)):
raise ImproperlyConfigured(
"The MEDIA_ROOT and STATIC_ROOT settings must have different values"
)
```
###Assistant :
Check if the staticfiles settings have sane values.
|
270 | def kubernetes_dict(self, **kwargs) -> Dict:
config = self.dict(**kwargs)
for idx, deployment in enumerate(config["deployments"]):
if isinstance(deployment.get("ray_actor_options"), dict):
# JSON-serialize ray_actor_options' resources dictionary
if isinstance(deployment["ray_actor_options"].get("resources"), dict):
deployment["ray_actor_options"]["resources"] = json.dumps(
deployment["ray_actor_options"]["resources"]
)
# JSON-serialize ray_actor_options' runtime_env dictionary
if isinstance(deployment["ray_actor_options"].get("runtime_env"), dict):
deployment["ray_actor_options"]["runtime_env"] = json.dumps(
deployment["ray_actor_options"]["runtime_env"]
)
# Convert ray_actor_options' keys
deployment["ray_actor_options"] = dict_keys_snake_to_camel_case(
deployment["ray_actor_options"]
)
# JSON-serialize user_config dictionary
if isinstance(deployment.get("user_config"), dict):
deployment["user_config"] = json.dumps(deployment["user_config"])
# Convert deployment's keys
config["deployments"][idx] = dict_keys_snake_to_camel_case(deployment)
# Convert top-level runtime_env
if isinstance(config.get("runtime_env"), dict):
config["runtime_env"] = json.dumps(config["runtime_env"])
# Convert top-level option's keys
config = dict_keys_snake_to_camel_case(config)
return config
@PublicAPI(stability="beta") | Returns dictionary in Kubernetes format.
Dictionary can be yaml-dumped to a Serve config file directly and then
copy-pasted into a RayService Kubernetes config.
Args: all kwargs are passed directly into schema's dict() function.
| 33 | 89 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def kubernetes_dict(self, **kwargs) -> Dict:
config = self.dict(**kwargs)
for idx, deployment in enumerate(config["deployments"]):
if isinstance(deployment.get("ray_actor_options"), dict):
# JSON-serialize ray_actor_options' resources dictionary
if isinstance(deployment["ray_actor_options"].get("resources"), dict):
deployment["ray_actor_options"]["resources"] = json.dumps(
deployment["ray_actor_options"]["resources"]
)
# JSON-serialize ray_actor_options' runtime_env dictionary
if isinstance(deployment["ray_actor_options"].get("runtime_env"), dict):
deployment["ray_actor_options"]["runtime_env"] = json.dumps(
deployment["ray_actor_options"]["runtime_env"]
)
# Convert ray_actor_options' keys
deployment["ray_actor_options"] = dict_keys_snake_to_camel_case(
deployment["ray_actor_options"]
)
# JSON-serialize user_config dictionary
if isinstance(deployment.get("user_config"), dict):
deployment["user_config"] = json.dumps(deployment["user_config"])
# Convert deployment's keys
config["deployments"][idx] = dict_keys_snake_to_camel_case(deployment)
# Convert top-level runtime_env
if isinstance(config.get("runtime_env"), dict):
config["runtime_env"] = json.dumps(config["runtime_env"])
# Convert top-level option's keys
config = dict_keys_snake_to_camel_case(config)
return config
@PublicAPI(stability="beta")
```
###Assistant : Returns dictionary in Kubernetes format.
Dictionary can be yaml-dumped to a Serve config file directly and then
copy-pasted into a RayService Kubernetes config.
Args: all kwargs are passed directly into schema's dict() function.
|
271 | def reload_images(self, group_method, img_list):
logger.info("Preparing to group...")
if group_method == 'group_blur':
filename_list, image_list = self._get_images()
blurs = [self.estimate_blur(img) for img in image_list]
temp_list = list(zip(filename_list, blurs))
elif group_method == 'group_blur_fft':
filename_list, image_list = self._get_images()
fft_blurs = [self.estimate_blur_fft(img) for img in image_list]
temp_list = list(zip(filename_list, fft_blurs))
elif group_method == 'group_face_cnn':
filename_list, image_list, landmarks = self._get_landmarks()
temp_list = list(zip(filename_list, landmarks))
elif group_method == 'group_face_yaw':
filename_list, image_list, landmarks = self._get_landmarks()
yaws = [self.calc_landmarks_face_yaw(mark) for mark in landmarks]
temp_list = list(zip(filename_list, yaws))
elif group_method == 'group_hist':
filename_list, image_list = self._get_images()
histograms = [cv2.calcHist([img], [0], None, [256], [0, 256]) for img in image_list]
temp_list = list(zip(filename_list, histograms))
elif group_method == 'group_black_pixels':
filename_list, image_list = self._get_images()
black_pixels = [np.ndarray.all(img == [0, 0, 0], axis=2).sum()/img.size*100*3
for img in image_list]
temp_list = list(zip(filename_list, black_pixels))
else:
raise ValueError(f"{group_method} group_method not found.")
return self.splice_lists(img_list, temp_list)
|
Reloads the image list by replacing the comparative values with those
that the chosen grouping method expects.
:param group_method: str name of the grouping method that will be used.
:param img_list: image list that has been sorted by one of the sort
methods.
:return: img_list but with the comparative values that the chosen
grouping method expects.
| 56 | 135 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def reload_images(self, group_method, img_list):
logger.info("Preparing to group...")
if group_method == 'group_blur':
filename_list, image_list = self._get_images()
blurs = [self.estimate_blur(img) for img in image_list]
temp_list = list(zip(filename_list, blurs))
elif group_method == 'group_blur_fft':
filename_list, image_list = self._get_images()
fft_blurs = [self.estimate_blur_fft(img) for img in image_list]
temp_list = list(zip(filename_list, fft_blurs))
elif group_method == 'group_face_cnn':
filename_list, image_list, landmarks = self._get_landmarks()
temp_list = list(zip(filename_list, landmarks))
elif group_method == 'group_face_yaw':
filename_list, image_list, landmarks = self._get_landmarks()
yaws = [self.calc_landmarks_face_yaw(mark) for mark in landmarks]
temp_list = list(zip(filename_list, yaws))
elif group_method == 'group_hist':
filename_list, image_list = self._get_images()
histograms = [cv2.calcHist([img], [0], None, [256], [0, 256]) for img in image_list]
temp_list = list(zip(filename_list, histograms))
elif group_method == 'group_black_pixels':
filename_list, image_list = self._get_images()
black_pixels = [np.ndarray.all(img == [0, 0, 0], axis=2).sum()/img.size*100*3
for img in image_list]
temp_list = list(zip(filename_list, black_pixels))
else:
raise ValueError(f"{group_method} group_method not found.")
return self.splice_lists(img_list, temp_list)
```
###Assistant :
Reloads the image list by replacing the comparative values with those
that the chosen grouping method expects.
:param group_method: str name of the grouping method that will be used.
:param img_list: image list that has been sorted by one of the sort
methods.
:return: img_list but with the comparative values that the chosen
grouping method expects.
|
272 | def get_sales_orders(quotations):
if not quotations:
return []
quotation_names = [q.name for q in quotations]
return frappe.db.sql(
.format(
", ".join(["%s"] * len(quotation_names))
),
tuple(quotation_names),
as_dict=1,
) # nosec
|
SELECT so.`name`, so.`base_grand_total`, soi.prevdoc_docname as quotation
FROM `tabSales Order` so, `tabSales Order Item` soi
WHERE so.docstatus=1 AND so.name = soi.parent AND soi.prevdoc_docname in ({0})
| 24 | 27 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_sales_orders(quotations):
if not quotations:
return []
quotation_names = [q.name for q in quotations]
return frappe.db.sql(
.format(
", ".join(["%s"] * len(quotation_names))
),
tuple(quotation_names),
as_dict=1,
) # nosec
```
###Assistant :
SELECT so.`name`, so.`base_grand_total`, soi.prevdoc_docname as quotation
FROM `tabSales Order` so, `tabSales Order Item` soi
WHERE so.docstatus=1 AND so.name = soi.parent AND soi.prevdoc_docname in ({0})
|
273 | def download_extract(name, folder=None):
fname = download(name)
base_dir = os.path.dirname(fname)
data_dir, ext = os.path.splitext(fname)
if ext == '.zip':
fp = zipfile.ZipFile(fname, 'r')
elif ext in ('.tar', '.gz'):
fp = tarfile.open(fname, 'r')
else:
assert False, 'Only zip/tar files can be extracted.'
fp.extractall(base_dir)
return os.path.join(base_dir, folder) if folder else data_dir
| Download and extract a zip/tar file.
Defined in :numref:`sec_utils` | 9 | 47 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def download_extract(name, folder=None):
fname = download(name)
base_dir = os.path.dirname(fname)
data_dir, ext = os.path.splitext(fname)
if ext == '.zip':
fp = zipfile.ZipFile(fname, 'r')
elif ext in ('.tar', '.gz'):
fp = tarfile.open(fname, 'r')
else:
assert False, 'Only zip/tar files can be extracted.'
fp.extractall(base_dir)
return os.path.join(base_dir, folder) if folder else data_dir
```
###Assistant : Download and extract a zip/tar file.
Defined in :numref:`sec_utils`
|
274 | def sample_weights_mismatch(self):
# If there is a mismatch between sample weight mode and the placeholders
# created, then recompile the sub-graphs that depend on sample weights.
return (
self.sample_weight_mode is not None and self.sample_weight is None
) or (
self.sample_weight_mode is None and self.sample_weight is not None
)
| Check if the sample weight and the mode match or not. | 11 | 48 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def sample_weights_mismatch(self):
# If there is a mismatch between sample weight mode and the placeholders
# created, then recompile the sub-graphs that depend on sample weights.
return (
self.sample_weight_mode is not None and self.sample_weight is None
) or (
self.sample_weight_mode is None and self.sample_weight is not None
)
```
###Assistant : Check if the sample weight and the mode match or not.
|
275 | def shebang(self, line, cell):
# Create the event loop in which to run script magics
# this operates on a background thread
if self.event_loop is None:
if sys.platform == "win32":
# don't override the current policy,
# just create an event loop
event_loop = asyncio.WindowsProactorEventLoopPolicy().new_event_loop()
else:
event_loop = asyncio.new_event_loop()
self.event_loop = event_loop
# start the loop in a background thread
asyncio_thread = Thread(target=event_loop.run_forever, daemon=True)
asyncio_thread.start()
else:
event_loop = self.event_loop
| Run a cell via a shell command
The `%%script` line is like the #! line of script,
specifying a program (bash, perl, ruby, etc.) with which to run.
The rest of the cell is run by that program.
Examples
--------
::
In [1]: %%script bash
...: for i in 1 2 3; do
...: echo $i
...: done
1
2
3
| 61 | 69 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def shebang(self, line, cell):
# Create the event loop in which to run script magics
# this operates on a background thread
if self.event_loop is None:
if sys.platform == "win32":
# don't override the current policy,
# just create an event loop
event_loop = asyncio.WindowsProactorEventLoopPolicy().new_event_loop()
else:
event_loop = asyncio.new_event_loop()
self.event_loop = event_loop
# start the loop in a background thread
asyncio_thread = Thread(target=event_loop.run_forever, daemon=True)
asyncio_thread.start()
else:
event_loop = self.event_loop
```
###Assistant : Run a cell via a shell command
The `%%script` line is like the #! line of script,
specifying a program (bash, perl, ruby, etc.) with which to run.
The rest of the cell is run by that program.
Examples
--------
::
In [1]: %%script bash
...: for i in 1 2 3; do
...: echo $i
...: done
1
2
3
|
276 | def statistics(self):
try:
return self._local.statistics
except AttributeError:
self._local.statistics = {}
return self._local.statistics
| Return a dictionary of runtime statistics.
This dictionary will be empty when the controller has never been
ran. When it is running or has ran previously it should have (but
may not) have useful and/or informational keys and values when
running is underway and/or completed.
.. warning:: The keys in this dictionary **should** be some what
stable (not changing), but there existence **may**
change between major releases as new statistics are
gathered or removed so before accessing keys ensure that
they actually exist and handle when they do not.
.. note:: The values in this dictionary are local to the thread
running call (so if multiple threads share the same retrying
object - either directly or indirectly) they will each have
there own view of statistics they have collected (in the
future we may provide a way to aggregate the various
statistics from each thread).
| 145 | 12 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def statistics(self):
try:
return self._local.statistics
except AttributeError:
self._local.statistics = {}
return self._local.statistics
```
###Assistant : Return a dictionary of runtime statistics.
This dictionary will be empty when the controller has never been
ran. When it is running or has ran previously it should have (but
may not) have useful and/or informational keys and values when
running is underway and/or completed.
.. warning:: The keys in this dictionary **should** be some what
stable (not changing), but there existence **may**
change between major releases as new statistics are
gathered or removed so before accessing keys ensure that
they actually exist and handle when they do not.
.. note:: The values in this dictionary are local to the thread
running call (so if multiple threads share the same retrying
object - either directly or indirectly) they will each have
there own view of statistics they have collected (in the
future we may provide a way to aggregate the various
statistics from each thread).
|
277 | def send(self, sender, **named):
if (
not self.receivers
or self.sender_receivers_cache.get(sender) is NO_RECEIVERS
):
return []
return [
(receiver, receiver(signal=self, sender=sender, **named))
for receiver in self._live_receivers(sender)
]
|
Send signal from sender to all connected receivers.
If any receiver raises an error, the error propagates back through send,
terminating the dispatch loop. So it's possible that all receivers
won't be called if an error is raised.
Arguments:
sender
The sender of the signal. Either a specific object or None.
named
Named arguments which will be passed to receivers.
Return a list of tuple pairs [(receiver, response), ... ].
| 70 | 26 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def send(self, sender, **named):
if (
not self.receivers
or self.sender_receivers_cache.get(sender) is NO_RECEIVERS
):
return []
return [
(receiver, receiver(signal=self, sender=sender, **named))
for receiver in self._live_receivers(sender)
]
```
###Assistant :
Send signal from sender to all connected receivers.
If any receiver raises an error, the error propagates back through send,
terminating the dispatch loop. So it's possible that all receivers
won't be called if an error is raised.
Arguments:
sender
The sender of the signal. Either a specific object or None.
named
Named arguments which will be passed to receivers.
Return a list of tuple pairs [(receiver, response), ... ].
|
278 | def deploy_ray_func(func, *args): # pragma: no cover
result = func(*args)
ip = get_node_ip_address()
if isinstance(result, pandas.DataFrame):
return result, len(result), len(result.columns), ip
elif all(isinstance(r, pandas.DataFrame) for r in result):
return [i for r in result for i in [r, len(r), len(r.columns), ip]]
else:
return [i for r in result for i in [r, None, None, ip]]
|
Execute a function on an axis partition in a worker process.
Parameters
----------
func : callable
Function to be executed on an axis partition.
*args : iterable
Additional arguments that need to passed in ``func``.
Returns
-------
list
The result of the function ``func`` and metadata for it.
Notes
-----
Ray functions are not detected by codecov (thus pragma: no cover).
| 61 | 55 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def deploy_ray_func(func, *args): # pragma: no cover
result = func(*args)
ip = get_node_ip_address()
if isinstance(result, pandas.DataFrame):
return result, len(result), len(result.columns), ip
elif all(isinstance(r, pandas.DataFrame) for r in result):
return [i for r in result for i in [r, len(r), len(r.columns), ip]]
else:
return [i for r in result for i in [r, None, None, ip]]
```
###Assistant :
Execute a function on an axis partition in a worker process.
Parameters
----------
func : callable
Function to be executed on an axis partition.
*args : iterable
Additional arguments that need to passed in ``func``.
Returns
-------
list
The result of the function ``func`` and metadata for it.
Notes
-----
Ray functions are not detected by codecov (thus pragma: no cover).
|
279 | def _set_gradient_checkpointing(self, module, value=False):
if isinstance(module, ViltEncoder):
module.gradient_checkpointing = value
VILT_START_DOCSTRING = r
VILT_INPUTS_DOCSTRING = r
VILT_IMAGES_AND_TEXT_CLASSIFICATION_INPUTS_DOCSTRING = r
@add_start_docstrings(
"The bare ViLT Model transformer outputting raw hidden-states without any specific head on top.",
VILT_START_DOCSTRING,
) |
This model is a PyTorch `torch.nn.Module <https://pytorch.org/docs/stable/nn.html#torch.nn.Module>`_ subclass. Use
it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and
behavior.
Parameters:
config ([`ViltConfig`]): Model configuration class with all the parameters of the model.
Initializing with a config file does not load the weights associated with the model, only the
configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
1]`:
- 0 corresponds to a *sentence A* token,
- 1 corresponds to a *sentence B* token.
[What are token type IDs?](../glossary#token-type-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`ViltFeatureExtractor`]. See
[`ViltFeatureExtractor.__call__`] for details.
pixel_mask (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*):
Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`:
- 1 for pixels that are real (i.e. **not masked**),
- 0 for pixels that are padding (i.e. **masked**).
`What are attention masks? <../glossary.html#attention-mask>`__
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
image_embeds (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*):
Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation.
This is useful if you want more control over how to convert `pixel_values` into patch embeddings.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~file_utils.ModelOutput`] instead of a plain tuple.
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
1]`:
- 0 corresponds to a *sentence A* token,
- 1 corresponds to a *sentence B* token.
[What are token type IDs?](../glossary#token-type-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_images, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`ViltFeatureExtractor`]. See
[`ViltFeatureExtractor.__call__`] for details.
pixel_mask (`torch.LongTensor` of shape `(batch_size, num_images, height, width)`, *optional*):
Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`:
- 1 for pixels that are real (i.e. **not masked**),
- 0 for pixels that are padding (i.e. **masked**).
`What are attention masks? <../glossary.html#attention-mask>`__
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
image_embeds (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*):
Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation.
This is useful if you want more control over how to convert `pixel_values` into patch embeddings.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~file_utils.ModelOutput`] instead of a plain tuple.
| 802 | 36 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _set_gradient_checkpointing(self, module, value=False):
if isinstance(module, ViltEncoder):
module.gradient_checkpointing = value
VILT_START_DOCSTRING = r
VILT_INPUTS_DOCSTRING = r
VILT_IMAGES_AND_TEXT_CLASSIFICATION_INPUTS_DOCSTRING = r
@add_start_docstrings(
"The bare ViLT Model transformer outputting raw hidden-states without any specific head on top.",
VILT_START_DOCSTRING,
)
```
###Assistant :
This model is a PyTorch `torch.nn.Module <https://pytorch.org/docs/stable/nn.html#torch.nn.Module>`_ subclass. Use
it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and
behavior.
Parameters:
config ([`ViltConfig`]): Model configuration class with all the parameters of the model.
Initializing with a config file does not load the weights associated with the model, only the
configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
1]`:
- 0 corresponds to a *sentence A* token,
- 1 corresponds to a *sentence B* token.
[What are token type IDs?](../glossary#token-type-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`ViltFeatureExtractor`]. See
[`ViltFeatureExtractor.__call__`] for details.
pixel_mask (`torch.LongTensor` of shape `(batch_size, height, width)`, *optional*):
Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`:
- 1 for pixels that are real (i.e. **not masked**),
- 0 for pixels that are padding (i.e. **masked**).
`What are attention masks? <../glossary.html#attention-mask>`__
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
image_embeds (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*):
Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation.
This is useful if you want more control over how to convert `pixel_values` into patch embeddings.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~file_utils.ModelOutput`] instead of a plain tuple.
Args:
input_ids (`torch.LongTensor` of shape `({0})`):
Indices of input sequence tokens in the vocabulary. Indices can be obtained using [`BertTokenizer`]. See
[`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input
IDs?](../glossary#input-ids)
attention_mask (`torch.FloatTensor` of shape `({0})`, *optional*):
Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
- 1 for tokens that are **not masked**,
- 0 for tokens that are **masked**.
[What are attention masks?](../glossary#attention-mask)
token_type_ids (`torch.LongTensor` of shape `({0})`, *optional*):
Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
1]`:
- 0 corresponds to a *sentence A* token,
- 1 corresponds to a *sentence B* token.
[What are token type IDs?](../glossary#token-type-ids)
pixel_values (`torch.FloatTensor` of shape `(batch_size, num_images, num_channels, height, width)`):
Pixel values. Pixel values can be obtained using [`ViltFeatureExtractor`]. See
[`ViltFeatureExtractor.__call__`] for details.
pixel_mask (`torch.LongTensor` of shape `(batch_size, num_images, height, width)`, *optional*):
Mask to avoid performing attention on padding pixel values. Mask values selected in `[0, 1]`:
- 1 for pixels that are real (i.e. **not masked**),
- 0 for pixels that are padding (i.e. **masked**).
`What are attention masks? <../glossary.html#attention-mask>`__
head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
- 1 indicates the head is **not masked**,
- 0 indicates the head is **masked**.
inputs_embeds (`torch.FloatTensor` of shape `({0}, hidden_size)`, *optional*):
Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
model's internal embedding lookup matrix.
image_embeds (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`, *optional*):
Optionally, instead of passing `pixel_values`, you can choose to directly pass an embedded representation.
This is useful if you want more control over how to convert `pixel_values` into patch embeddings.
output_attentions (`bool`, *optional*):
Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
tensors for more detail.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~file_utils.ModelOutput`] instead of a plain tuple.
|
280 | def needs_document_end_workaround(self):
if objects.backend == usertypes.Backend.QtWebKit:
return False
assert objects.backend == usertypes.Backend.QtWebEngine, objects.backend
broken_scripts = [
('http://userstyles.org', None),
('https://github.com/ParticleCore', 'Iridium'),
]
return any(self._matches_id(namespace=namespace, name=name)
for namespace, name in broken_scripts)
| Check whether to force @run-at document-end.
This needs to be done on QtWebEngine for known-broken scripts.
On Qt 5.12, accessing the DOM isn't possible with "@run-at
document-start". It was documented to be impossible before, but seems
to work fine.
However, some scripts do DOM access with "@run-at document-start". Fix
those by forcing them to use document-end instead.
| 57 | 29 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def needs_document_end_workaround(self):
if objects.backend == usertypes.Backend.QtWebKit:
return False
assert objects.backend == usertypes.Backend.QtWebEngine, objects.backend
broken_scripts = [
('http://userstyles.org', None),
('https://github.com/ParticleCore', 'Iridium'),
]
return any(self._matches_id(namespace=namespace, name=name)
for namespace, name in broken_scripts)
```
###Assistant : Check whether to force @run-at document-end.
This needs to be done on QtWebEngine for known-broken scripts.
On Qt 5.12, accessing the DOM isn't possible with "@run-at
document-start". It was documented to be impossible before, but seems
to work fine.
However, some scripts do DOM access with "@run-at document-start". Fix
those by forcing them to use document-end instead.
|
281 | def _temperature_unit(self) -> str:
if (
weather_option_temperature_unit := self._weather_option_temperature_unit
) is not None:
return weather_option_temperature_unit
return self._default_temperature_unit
| Return the converted unit of measurement for temperature.
Should not be set by integrations.
| 14 | 17 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _temperature_unit(self) -> str:
if (
weather_option_temperature_unit := self._weather_option_temperature_unit
) is not None:
return weather_option_temperature_unit
return self._default_temperature_unit
```
###Assistant : Return the converted unit of measurement for temperature.
Should not be set by integrations.
|
282 | def fontName(self, fontprop):
if isinstance(fontprop, str):
filenames = [fontprop]
elif mpl.rcParams['pdf.use14corefonts']:
filenames = _fontManager._find_fonts_by_props(
fontprop, fontext='afm', directory=RendererPdf._afm_font_dir
)
else:
filenames = _fontManager._find_fonts_by_props(fontprop)
first_Fx = None
for fname in filenames:
Fx = self.fontNames.get(fname)
if not first_Fx:
first_Fx = Fx
if Fx is None:
Fx = next(self._internal_font_seq)
self.fontNames[fname] = Fx
_log.debug('Assigning font %s = %r', Fx, fname)
if not first_Fx:
first_Fx = Fx
# find_fontsprop's first value always adheres to
# findfont's value, so technically no behaviour change
return first_Fx
|
Select a font based on fontprop and return a name suitable for
Op.selectfont. If fontprop is a string, it will be interpreted
as the filename of the font.
| 28 | 78 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def fontName(self, fontprop):
if isinstance(fontprop, str):
filenames = [fontprop]
elif mpl.rcParams['pdf.use14corefonts']:
filenames = _fontManager._find_fonts_by_props(
fontprop, fontext='afm', directory=RendererPdf._afm_font_dir
)
else:
filenames = _fontManager._find_fonts_by_props(fontprop)
first_Fx = None
for fname in filenames:
Fx = self.fontNames.get(fname)
if not first_Fx:
first_Fx = Fx
if Fx is None:
Fx = next(self._internal_font_seq)
self.fontNames[fname] = Fx
_log.debug('Assigning font %s = %r', Fx, fname)
if not first_Fx:
first_Fx = Fx
# find_fontsprop's first value always adheres to
# findfont's value, so technically no behaviour change
return first_Fx
```
###Assistant :
Select a font based on fontprop and return a name suitable for
Op.selectfont. If fontprop is a string, it will be interpreted
as the filename of the font.
|
283 | def center_to_corners_format(x):
x_center, y_center, width, height = x.unbind(-1)
boxes = [(x_center - 0.5 * width), (y_center - 0.5 * height), (x_center + 0.5 * width), (y_center + 0.5 * height)]
return torch.stack(boxes, dim=-1)
|
Converts a PyTorch tensor of bounding boxes of center format (center_x, center_y, width, height) to corners format
(left, top, right, bottom).
| 21 | 33 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def center_to_corners_format(x):
x_center, y_center, width, height = x.unbind(-1)
boxes = [(x_center - 0.5 * width), (y_center - 0.5 * height), (x_center + 0.5 * width), (y_center + 0.5 * height)]
return torch.stack(boxes, dim=-1)
```
###Assistant :
Converts a PyTorch tensor of bounding boxes of center format (center_x, center_y, width, height) to corners format
(left, top, right, bottom).
|
284 | def add(self, key, value, timeout=DEFAULT_TIMEOUT, version=None):
raise NotImplementedError(
"subclasses of BaseCache must provide an add() method"
)
|
Set a value in the cache if the key does not already exist. If
timeout is given, use that timeout for the key; otherwise use the
default cache timeout.
Return True if the value was stored, False otherwise.
| 38 | 17 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def add(self, key, value, timeout=DEFAULT_TIMEOUT, version=None):
raise NotImplementedError(
"subclasses of BaseCache must provide an add() method"
)
```
###Assistant :
Set a value in the cache if the key does not already exist. If
timeout is given, use that timeout for the key; otherwise use the
default cache timeout.
Return True if the value was stored, False otherwise.
|
285 | def normalized_laplacian_matrix(G, nodelist=None, weight="weight"):
r
import numpy as np
import scipy as sp
import scipy.sparse # call as sp.sparse
if nodelist is None:
nodelist = list(G)
A = nx.to_scipy_sparse_array(G, nodelist=nodelist, weight=weight, format="csr")
n, m = A.shape
diags = A.sum(axis=1)
# TODO: rm csr_array wrapper when spdiags can produce arrays
D = sp.sparse.csr_array(sp.sparse.spdiags(diags, 0, m, n, format="csr"))
L = D - A
with sp.errstate(divide="ignore"):
diags_sqrt = 1.0 / np.sqrt(diags)
diags_sqrt[np.isinf(diags_sqrt)] = 0
# TODO: rm csr_array wrapper when spdiags can produce arrays
DH = sp.sparse.csr_array(sp.sparse.spdiags(diags_sqrt, 0, m, n, format="csr"))
return DH @ (L @ DH)
| Returns the normalized Laplacian matrix of G.
The normalized graph Laplacian is the matrix
.. math::
N = D^{-1/2} L D^{-1/2}
where `L` is the graph Laplacian and `D` is the diagonal matrix of
node degrees [1]_.
Parameters
----------
G : graph
A NetworkX graph
nodelist : list, optional
The rows and columns are ordered according to the nodes in nodelist.
If nodelist is None, then the ordering is produced by G.nodes().
weight : string or None, optional (default='weight')
The edge data key used to compute each value in the matrix.
If None, then each edge has weight 1.
Returns
-------
N : SciPy sparse array
The normalized Laplacian matrix of G.
Notes
-----
For MultiGraph, the edges weights are summed.
See :func:`to_numpy_array` for other options.
If the Graph contains selfloops, D is defined as ``diag(sum(A, 1))``, where A is
the adjacency matrix [2]_.
See Also
--------
laplacian_matrix
normalized_laplacian_spectrum
References
----------
.. [1] Fan Chung-Graham, Spectral Graph Theory,
CBMS Regional Conference Series in Mathematics, Number 92, 1997.
.. [2] Steve Butler, Interlacing For Weighted Graphs Using The Normalized
Laplacian, Electronic Journal of Linear Algebra, Volume 16, pp. 90-98,
March 2007.
| 190 | 94 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def normalized_laplacian_matrix(G, nodelist=None, weight="weight"):
r
import numpy as np
import scipy as sp
import scipy.sparse # call as sp.sparse
if nodelist is None:
nodelist = list(G)
A = nx.to_scipy_sparse_array(G, nodelist=nodelist, weight=weight, format="csr")
n, m = A.shape
diags = A.sum(axis=1)
# TODO: rm csr_array wrapper when spdiags can produce arrays
D = sp.sparse.csr_array(sp.sparse.spdiags(diags, 0, m, n, format="csr"))
L = D - A
with sp.errstate(divide="ignore"):
diags_sqrt = 1.0 / np.sqrt(diags)
diags_sqrt[np.isinf(diags_sqrt)] = 0
# TODO: rm csr_array wrapper when spdiags can produce arrays
DH = sp.sparse.csr_array(sp.sparse.spdiags(diags_sqrt, 0, m, n, format="csr"))
return DH @ (L @ DH)
```
###Assistant : Returns the normalized Laplacian matrix of G.
The normalized graph Laplacian is the matrix
.. math::
N = D^{-1/2} L D^{-1/2}
where `L` is the graph Laplacian and `D` is the diagonal matrix of
node degrees [1]_.
Parameters
----------
G : graph
A NetworkX graph
nodelist : list, optional
The rows and columns are ordered according to the nodes in nodelist.
If nodelist is None, then the ordering is produced by G.nodes().
weight : string or None, optional (default='weight')
The edge data key used to compute each value in the matrix.
If None, then each edge has weight 1.
Returns
-------
N : SciPy sparse array
The normalized Laplacian matrix of G.
Notes
-----
For MultiGraph, the edges weights are summed.
See :func:`to_numpy_array` for other options.
If the Graph contains selfloops, D is defined as ``diag(sum(A, 1))``, where A is
the adjacency matrix [2]_.
See Also
--------
laplacian_matrix
normalized_laplacian_spectrum
References
----------
.. [1] Fan Chung-Graham, Spectral Graph Theory,
CBMS Regional Conference Series in Mathematics, Number 92, 1997.
.. [2] Steve Butler, Interlacing For Weighted Graphs Using The Normalized
Laplacian, Electronic Journal of Linear Algebra, Volume 16, pp. 90-98,
March 2007.
|
286 | def extract_patches_2d(image, patch_size, *, max_patches=None, random_state=None):
i_h, i_w = image.shape[:2]
p_h, p_w = patch_size
if p_h > i_h:
raise ValueError(
"Height of the patch should be less than the height of the image."
)
if p_w > i_w:
raise ValueError(
"Width of the patch should be less than the width of the image."
)
image = check_array(image, allow_nd=True)
image = image.reshape((i_h, i_w, -1))
n_colors = image.shape[-1]
extracted_patches = _extract_patches(
image, patch_shape=(p_h, p_w, n_colors), extraction_step=1
)
n_patches = _compute_n_patches(i_h, i_w, p_h, p_w, max_patches)
if max_patches:
rng = check_random_state(random_state)
i_s = rng.randint(i_h - p_h + 1, size=n_patches)
j_s = rng.randint(i_w - p_w + 1, size=n_patches)
patches = extracted_patches[i_s, j_s, 0]
else:
patches = extracted_patches
patches = patches.reshape(-1, p_h, p_w, n_colors)
# remove the color dimension if useless
if patches.shape[-1] == 1:
return patches.reshape((n_patches, p_h, p_w))
else:
return patches
| Reshape a 2D image into a collection of patches.
The resulting patches are allocated in a dedicated array.
Read more in the :ref:`User Guide <image_feature_extraction>`.
Parameters
----------
image : ndarray of shape (image_height, image_width) or \
(image_height, image_width, n_channels)
The original image data. For color images, the last dimension specifies
the channel: a RGB image would have `n_channels=3`.
patch_size : tuple of int (patch_height, patch_width)
The dimensions of one patch.
max_patches : int or float, default=None
The maximum number of patches to extract. If `max_patches` is a float
between 0 and 1, it is taken to be a proportion of the total number
of patches.
random_state : int, RandomState instance, default=None
Determines the random number generator used for random sampling when
`max_patches` is not None. Use an int to make the randomness
deterministic.
See :term:`Glossary <random_state>`.
Returns
-------
patches : array of shape (n_patches, patch_height, patch_width) or \
(n_patches, patch_height, patch_width, n_channels)
The collection of patches extracted from the image, where `n_patches`
is either `max_patches` or the total number of patches that can be
extracted.
Examples
--------
>>> from sklearn.datasets import load_sample_image
>>> from sklearn.feature_extraction import image
>>> # Use the array data from the first image in this dataset:
>>> one_image = load_sample_image("china.jpg")
>>> print('Image shape: {}'.format(one_image.shape))
Image shape: (427, 640, 3)
>>> patches = image.extract_patches_2d(one_image, (2, 2))
>>> print('Patches shape: {}'.format(patches.shape))
Patches shape: (272214, 2, 2, 3)
>>> # Here are just two of these patches:
>>> print(patches[1])
[[[174 201 231]
[174 201 231]]
[[173 200 230]
[173 200 230]]]
>>> print(patches[800])
[[[187 214 243]
[188 215 244]]
[[187 214 243]
[188 215 244]]]
| 266 | 136 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def extract_patches_2d(image, patch_size, *, max_patches=None, random_state=None):
i_h, i_w = image.shape[:2]
p_h, p_w = patch_size
if p_h > i_h:
raise ValueError(
"Height of the patch should be less than the height of the image."
)
if p_w > i_w:
raise ValueError(
"Width of the patch should be less than the width of the image."
)
image = check_array(image, allow_nd=True)
image = image.reshape((i_h, i_w, -1))
n_colors = image.shape[-1]
extracted_patches = _extract_patches(
image, patch_shape=(p_h, p_w, n_colors), extraction_step=1
)
n_patches = _compute_n_patches(i_h, i_w, p_h, p_w, max_patches)
if max_patches:
rng = check_random_state(random_state)
i_s = rng.randint(i_h - p_h + 1, size=n_patches)
j_s = rng.randint(i_w - p_w + 1, size=n_patches)
patches = extracted_patches[i_s, j_s, 0]
else:
patches = extracted_patches
patches = patches.reshape(-1, p_h, p_w, n_colors)
# remove the color dimension if useless
if patches.shape[-1] == 1:
return patches.reshape((n_patches, p_h, p_w))
else:
return patches
```
###Assistant : Reshape a 2D image into a collection of patches.
The resulting patches are allocated in a dedicated array.
Read more in the :ref:`User Guide <image_feature_extraction>`.
Parameters
----------
image : ndarray of shape (image_height, image_width) or \
(image_height, image_width, n_channels)
The original image data. For color images, the last dimension specifies
the channel: a RGB image would have `n_channels=3`.
patch_size : tuple of int (patch_height, patch_width)
The dimensions of one patch.
max_patches : int or float, default=None
The maximum number of patches to extract. If `max_patches` is a float
between 0 and 1, it is taken to be a proportion of the total number
of patches.
random_state : int, RandomState instance, default=None
Determines the random number generator used for random sampling when
`max_patches` is not None. Use an int to make the randomness
deterministic.
See :term:`Glossary <random_state>`.
Returns
-------
patches : array of shape (n_patches, patch_height, patch_width) or \
(n_patches, patch_height, patch_width, n_channels)
The collection of patches extracted from the image, where `n_patches`
is either `max_patches` or the total number of patches that can be
extracted.
Examples
--------
>>> from sklearn.datasets import load_sample_image
>>> from sklearn.feature_extraction import image
>>> # Use the array data from the first image in this dataset:
>>> one_image = load_sample_image("china.jpg")
>>> print('Image shape: {}'.format(one_image.shape))
Image shape: (427, 640, 3)
>>> patches = image.extract_patches_2d(one_image, (2, 2))
>>> print('Patches shape: {}'.format(patches.shape))
Patches shape: (272214, 2, 2, 3)
>>> # Here are just two of these patches:
>>> print(patches[1])
[[[174 201 231]
[174 201 231]]
[[173 200 230]
[173 200 230]]]
>>> print(patches[800])
[[[187 214 243]
[188 215 244]]
[[187 214 243]
[188 215 244]]]
|
287 | def refresh_from_db(self, using=None, fields=None):
if fields is None:
self._prefetched_objects_cache = {}
else:
prefetched_objects_cache = getattr(self, "_prefetched_objects_cache", ())
for field in fields:
if field in prefetched_objects_cache:
del prefetched_objects_cache[field]
fields.remove(field)
if not fields:
return
if any(LOOKUP_SEP in f for f in fields):
raise ValueError(
'Found "%s" in fields argument. Relations and transforms '
"are not allowed in fields." % LOOKUP_SEP
)
hints = {"instance": self}
db_instance_qs = self.__class__._base_manager.db_manager(
using, hints=hints
).filter(pk=self.pk)
# Use provided fields, if not set then reload all non-deferred fields.
deferred_fields = self.get_deferred_fields()
if fields is not None:
fields = list(fields)
db_instance_qs = db_instance_qs.only(*fields)
elif deferred_fields:
fields = [
f.attname
for f in self._meta.concrete_fields
if f.attname not in deferred_fields
]
db_instance_qs = db_instance_qs.only(*fields)
db_instance = db_instance_qs.get()
non_loaded_fields = db_instance.get_deferred_fields()
for field in self._meta.concrete_fields:
if field.attname in non_loaded_fields:
# This field wasn't refreshed - skip ahead.
continue
setattr(self, field.attname, getattr(db_instance, field.attname))
# Clear cached foreign keys.
if field.is_relation and field.is_cached(self):
field.delete_cached_value(self)
# Clear cached relations.
for field in self._meta.related_objects:
if field.is_cached(self):
field.delete_cached_value(self)
self._state.db = db_instance._state.db
|
Reload field values from the database.
By default, the reloading happens from the database this instance was
loaded from, or by the read router if this instance wasn't loaded from
any database. The using parameter will override the default.
Fields can be used to specify which fields to reload. The fields
should be an iterable of field attnames. If fields is None, then
all non-deferred fields are reloaded.
When accessing deferred fields of an instance, the deferred loading
of the field will call this method.
| 85 | 165 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def refresh_from_db(self, using=None, fields=None):
if fields is None:
self._prefetched_objects_cache = {}
else:
prefetched_objects_cache = getattr(self, "_prefetched_objects_cache", ())
for field in fields:
if field in prefetched_objects_cache:
del prefetched_objects_cache[field]
fields.remove(field)
if not fields:
return
if any(LOOKUP_SEP in f for f in fields):
raise ValueError(
'Found "%s" in fields argument. Relations and transforms '
"are not allowed in fields." % LOOKUP_SEP
)
hints = {"instance": self}
db_instance_qs = self.__class__._base_manager.db_manager(
using, hints=hints
).filter(pk=self.pk)
# Use provided fields, if not set then reload all non-deferred fields.
deferred_fields = self.get_deferred_fields()
if fields is not None:
fields = list(fields)
db_instance_qs = db_instance_qs.only(*fields)
elif deferred_fields:
fields = [
f.attname
for f in self._meta.concrete_fields
if f.attname not in deferred_fields
]
db_instance_qs = db_instance_qs.only(*fields)
db_instance = db_instance_qs.get()
non_loaded_fields = db_instance.get_deferred_fields()
for field in self._meta.concrete_fields:
if field.attname in non_loaded_fields:
# This field wasn't refreshed - skip ahead.
continue
setattr(self, field.attname, getattr(db_instance, field.attname))
# Clear cached foreign keys.
if field.is_relation and field.is_cached(self):
field.delete_cached_value(self)
# Clear cached relations.
for field in self._meta.related_objects:
if field.is_cached(self):
field.delete_cached_value(self)
self._state.db = db_instance._state.db
```
###Assistant :
Reload field values from the database.
By default, the reloading happens from the database this instance was
loaded from, or by the read router if this instance wasn't loaded from
any database. The using parameter will override the default.
Fields can be used to specify which fields to reload. The fields
should be an iterable of field attnames. If fields is None, then
all non-deferred fields are reloaded.
When accessing deferred fields of an instance, the deferred loading
of the field will call this method.
|
288 | def set_tunnel(self, host, port=None, headers=None):
if self.sock:
raise RuntimeError("Can't set up tunnel for established connection")
self._tunnel_host, self._tunnel_port = self._get_hostport(host, port)
if headers:
self._tunnel_headers = headers
else:
self._tunnel_headers.clear()
| Set up host and port for HTTP CONNECT tunnelling.
In a connection that uses HTTP CONNECT tunneling, the host passed to the
constructor is used as a proxy server that relays all communication to
the endpoint passed to `set_tunnel`. This done by sending an HTTP
CONNECT request to the proxy server when the connection is established.
This method must be called before the HTTP connection has been
established.
The headers argument should be a mapping of extra HTTP headers to send
with the CONNECT request.
| 85 | 27 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def set_tunnel(self, host, port=None, headers=None):
if self.sock:
raise RuntimeError("Can't set up tunnel for established connection")
self._tunnel_host, self._tunnel_port = self._get_hostport(host, port)
if headers:
self._tunnel_headers = headers
else:
self._tunnel_headers.clear()
```
###Assistant : Set up host and port for HTTP CONNECT tunnelling.
In a connection that uses HTTP CONNECT tunneling, the host passed to the
constructor is used as a proxy server that relays all communication to
the endpoint passed to `set_tunnel`. This done by sending an HTTP
CONNECT request to the proxy server when the connection is established.
This method must be called before the HTTP connection has been
established.
The headers argument should be a mapping of extra HTTP headers to send
with the CONNECT request.
|
289 | def explicit_device_get_scope() -> Iterator[None]:
state = transfer_guard_lib.thread_local_state()
prev = state.explicit_device_get
state.explicit_device_get = True
try:
yield
finally:
state.explicit_device_get = prev
| Indicates that the current context is an explicit device_get() call. | 10 | 19 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def explicit_device_get_scope() -> Iterator[None]:
state = transfer_guard_lib.thread_local_state()
prev = state.explicit_device_get
state.explicit_device_get = True
try:
yield
finally:
state.explicit_device_get = prev
```
###Assistant : Indicates that the current context is an explicit device_get() call.
|
290 | def accessory_info(self) -> Service:
return self.accessory.services.first(
service_type=ServicesTypes.ACCESSORY_INFORMATION
)
| Information about the make and model of an accessory. | 9 | 8 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def accessory_info(self) -> Service:
return self.accessory.services.first(
service_type=ServicesTypes.ACCESSORY_INFORMATION
)
```
###Assistant : Information about the make and model of an accessory.
|
291 | def _always_object(classes):
if object not in classes:
return classes + (object,)
return classes
|
Ensure object appears in the mro even
for old-style classes.
| 10 | 13 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _always_object(classes):
if object not in classes:
return classes + (object,)
return classes
```
###Assistant :
Ensure object appears in the mro even
for old-style classes.
|
292 | def addIncludedDataFilesFromFileOptions():
for included_datafile in _addIncludedDataFilesFromFileOptions():
addIncludedDataFile(included_datafile)
| Early data files, from user options that work with file system. | 11 | 7 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def addIncludedDataFilesFromFileOptions():
for included_datafile in _addIncludedDataFilesFromFileOptions():
addIncludedDataFile(included_datafile)
```
###Assistant : Early data files, from user options that work with file system.
|
293 | def _attributes(**kwargs) -> dict[str, str]:
return {key: str(value) for key, value in kwargs.items() if value is not None}
| Return the given kwargs as a dictionary with values converted to strings. Items with a value of None will be omitted. | 21 | 18 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _attributes(**kwargs) -> dict[str, str]:
return {key: str(value) for key, value in kwargs.items() if value is not None}
```
###Assistant : Return the given kwargs as a dictionary with values converted to strings. Items with a value of None will be omitted.
|
294 | def test_charpp(self):
dll = CDLL(_ctypes_test.__file__)
func = dll._testfunc_c_p_p
func.restype = c_char_p
argv = (c_char_p * 2)()
argc = c_int( 2 )
argv[0] = b'hello'
argv[1] = b'world'
result = func( byref(argc), argv )
self.assertEqual(result, b'world')
| Test that a character pointer-to-pointer is correctly passed | 8 | 35 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_charpp(self):
dll = CDLL(_ctypes_test.__file__)
func = dll._testfunc_c_p_p
func.restype = c_char_p
argv = (c_char_p * 2)()
argc = c_int( 2 )
argv[0] = b'hello'
argv[1] = b'world'
result = func( byref(argc), argv )
self.assertEqual(result, b'world')
```
###Assistant : Test that a character pointer-to-pointer is correctly passed
|
295 | def test_error_message_unsigned(self):
# Ensure to test for potential overflow in the case of:
# x - y
# and
# y - x
x = np.asarray([0, 1, 8], dtype='uint8')
y = np.asarray([4, 4, 4], dtype='uint8')
with pytest.raises(AssertionError) as exc_info:
assert_allclose(x, y, atol=3)
msgs = str(exc_info.value).split('\n')
assert_equal(msgs[4], 'Max absolute difference: 4')
| Check the the message is formatted correctly when overflow can occur
(gh21768) | 12 | 50 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def test_error_message_unsigned(self):
# Ensure to test for potential overflow in the case of:
# x - y
# and
# y - x
x = np.asarray([0, 1, 8], dtype='uint8')
y = np.asarray([4, 4, 4], dtype='uint8')
with pytest.raises(AssertionError) as exc_info:
assert_allclose(x, y, atol=3)
msgs = str(exc_info.value).split('\n')
assert_equal(msgs[4], 'Max absolute difference: 4')
```
###Assistant : Check the the message is formatted correctly when overflow can occur
(gh21768)
|
296 | def _join_or_get_room(self, room_id_or_alias):
rooms = self._client.get_rooms()
if room_id_or_alias in rooms:
_LOGGER.debug("Already in room %s", room_id_or_alias)
return rooms[room_id_or_alias]
for room in rooms.values():
if room.room_id not in self._aliases_fetched_for:
room.update_aliases()
self._aliases_fetched_for.add(room.room_id)
if (
room_id_or_alias in room.aliases
or room_id_or_alias == room.canonical_alias
):
_LOGGER.debug(
"Already in room %s (known as %s)", room.room_id, room_id_or_alias
)
return room
room = self._client.join_room(room_id_or_alias)
_LOGGER.info("Joined room %s (known as %s)", room.room_id, room_id_or_alias)
return room
| Join a room or get it, if we are already in the room.
We can't just always call join_room(), since that seems to crash
the client if we're already in the room.
| 32 | 64 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _join_or_get_room(self, room_id_or_alias):
rooms = self._client.get_rooms()
if room_id_or_alias in rooms:
_LOGGER.debug("Already in room %s", room_id_or_alias)
return rooms[room_id_or_alias]
for room in rooms.values():
if room.room_id not in self._aliases_fetched_for:
room.update_aliases()
self._aliases_fetched_for.add(room.room_id)
if (
room_id_or_alias in room.aliases
or room_id_or_alias == room.canonical_alias
):
_LOGGER.debug(
"Already in room %s (known as %s)", room.room_id, room_id_or_alias
)
return room
room = self._client.join_room(room_id_or_alias)
_LOGGER.info("Joined room %s (known as %s)", room.room_id, room_id_or_alias)
return room
```
###Assistant : Join a room or get it, if we are already in the room.
We can't just always call join_room(), since that seems to crash
the client if we're already in the room.
|
297 | def _is_function_class_equation(func_class, f, symbol):
if f.is_Mul or f.is_Add:
return all(_is_function_class_equation(func_class, arg, symbol)
for arg in f.args)
if f.is_Pow:
if not f.exp.has(symbol):
return _is_function_class_equation(func_class, f.base, symbol)
else:
return False
if not f.has(symbol):
return True
if isinstance(f, func_class):
try:
g = Poly(f.args[0], symbol)
return g.degree() <= 1
except PolynomialError:
return False
else:
return False
| Tests whether the equation is an equation of the given function class.
The given equation belongs to the given function class if it is
comprised of functions of the function class which are multiplied by
or added to expressions independent of the symbol. In addition, the
arguments of all such functions must be linear in the symbol as well.
Examples
========
>>> from sympy.solvers.solveset import _is_function_class_equation
>>> from sympy import tan, sin, tanh, sinh, exp
>>> from sympy.abc import x
>>> from sympy.functions.elementary.trigonometric import TrigonometricFunction
>>> from sympy.functions.elementary.hyperbolic import HyperbolicFunction
>>> _is_function_class_equation(TrigonometricFunction, exp(x) + tan(x), x)
False
>>> _is_function_class_equation(TrigonometricFunction, tan(x) + sin(x), x)
True
>>> _is_function_class_equation(TrigonometricFunction, tan(x**2), x)
False
>>> _is_function_class_equation(TrigonometricFunction, tan(x + 2), x)
True
>>> _is_function_class_equation(HyperbolicFunction, tanh(x) + sinh(x), x)
True
| 123 | 52 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def _is_function_class_equation(func_class, f, symbol):
if f.is_Mul or f.is_Add:
return all(_is_function_class_equation(func_class, arg, symbol)
for arg in f.args)
if f.is_Pow:
if not f.exp.has(symbol):
return _is_function_class_equation(func_class, f.base, symbol)
else:
return False
if not f.has(symbol):
return True
if isinstance(f, func_class):
try:
g = Poly(f.args[0], symbol)
return g.degree() <= 1
except PolynomialError:
return False
else:
return False
```
###Assistant : Tests whether the equation is an equation of the given function class.
The given equation belongs to the given function class if it is
comprised of functions of the function class which are multiplied by
or added to expressions independent of the symbol. In addition, the
arguments of all such functions must be linear in the symbol as well.
Examples
========
>>> from sympy.solvers.solveset import _is_function_class_equation
>>> from sympy import tan, sin, tanh, sinh, exp
>>> from sympy.abc import x
>>> from sympy.functions.elementary.trigonometric import TrigonometricFunction
>>> from sympy.functions.elementary.hyperbolic import HyperbolicFunction
>>> _is_function_class_equation(TrigonometricFunction, exp(x) + tan(x), x)
False
>>> _is_function_class_equation(TrigonometricFunction, tan(x) + sin(x), x)
True
>>> _is_function_class_equation(TrigonometricFunction, tan(x**2), x)
False
>>> _is_function_class_equation(TrigonometricFunction, tan(x + 2), x)
True
>>> _is_function_class_equation(HyperbolicFunction, tanh(x) + sinh(x), x)
True
|
298 | def get_feature_names_out(self, input_features=None):
class_name = self.__class__.__name__.lower()
return np.asarray([f"{class_name}0"], dtype=object)
| Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Ignored.
Returns
-------
feature_names_out : ndarray of str objects
An ndarray with one string i.e. ["isotonicregression0"].
| 32 | 9 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_feature_names_out(self, input_features=None):
class_name = self.__class__.__name__.lower()
return np.asarray([f"{class_name}0"], dtype=object)
```
###Assistant : Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Ignored.
Returns
-------
feature_names_out : ndarray of str objects
An ndarray with one string i.e. ["isotonicregression0"].
|
299 | def get_distance(self, f, dist_val, lookup_type):
# Getting the distance parameter
value = dist_val[0]
# Shorthand boolean flags.
geodetic = f.geodetic(self.connection)
geography = f.geography
if isinstance(value, Distance):
if geography:
dist_param = value.m
elif geodetic:
if lookup_type == "dwithin":
raise ValueError(
"Only numeric values of degree units are "
"allowed on geographic DWithin queries."
)
dist_param = value.m
else:
dist_param = getattr(
value, Distance.unit_attname(f.units_name(self.connection))
)
else:
# Assuming the distance is in the units of the field.
dist_param = value
return [dist_param]
|
Retrieve the distance parameters for the given geometry field,
distance lookup value, and the distance lookup type.
This is the most complex implementation of the spatial backends due to
what is supported on geodetic geometry columns vs. what's available on
projected geometry columns. In addition, it has to take into account
the geography column type.
| 55 | 80 | Python |
###User : Below is a Python method which does a task. Create a documentation for the below code :
```Python
def get_distance(self, f, dist_val, lookup_type):
# Getting the distance parameter
value = dist_val[0]
# Shorthand boolean flags.
geodetic = f.geodetic(self.connection)
geography = f.geography
if isinstance(value, Distance):
if geography:
dist_param = value.m
elif geodetic:
if lookup_type == "dwithin":
raise ValueError(
"Only numeric values of degree units are "
"allowed on geographic DWithin queries."
)
dist_param = value.m
else:
dist_param = getattr(
value, Distance.unit_attname(f.units_name(self.connection))
)
else:
# Assuming the distance is in the units of the field.
dist_param = value
return [dist_param]
```
###Assistant :
Retrieve the distance parameters for the given geometry field,
distance lookup value, and the distance lookup type.
This is the most complex implementation of the spatial backends due to
what is supported on geodetic geometry columns vs. what's available on
projected geometry columns. In addition, it has to take into account
the geography column type.
|