Add application

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+tmp/
+
+gradio_cached_examples/

app.py

@@ -0,0 +1,86 @@
+from dataclasses import dataclass
+from operator import add, sub
+
+import gradio as gr
+
+import numpy as np
+from datasets import load_dataset
+from sklearn.metrics.pairwise import cosine_similarity
+
+from pyparsing import Word, alphas, Char, ParseException
+
+term = Word(alphas)
+operator = Char("+ -")
+
+expression = term + (operator + term)[...]
+operations = {"+": add, "-": sub}
+
+
+def parse_expression(input):
+    try:
+        return expression.parseString(input)
+    except ParseException as pe:
+        raise gr.Error(f"Syntax error at {pe.loc}: {pe.msg}")
+
+
+def evaluate_expression(input):
+    # Skip every other item
+    words = input[::2]
+    operators = input[1::2]
+
+    result = word_to_vectors(words[0])
+
+    for operator, word in zip(operators, words[1:]):
+        result = operations[operator](result, word_to_vectors(word))
+
+    return result
+
+
+dataset = load_dataset("karmiq/glove", split="train")
+df = dataset.to_pandas()
+
+all_words = df["word"].to_numpy()
+all_vectors = np.array(df["embeddings"].to_list())
+
+
+def word_to_vectors(word):
+    return df.loc[df["word"] == word].embeddings.to_numpy()[0]
+
+
+def expression_to_vectors(input):
+    return evaluate_expression(parse_expression(input))
+
+
+def get_results(expression):
+    vectors = expression_to_vectors(expression)
+    similarity_scores = cosine_similarity([vectors], all_vectors)[0]
+    top_indices = np.argsort(similarity_scores)[::-1]
+    return dict(
+        [
+            (all_words[i], similarity_scores[i])
+            for i in top_indices
+            if not all_words[i] in expression.split()
+        ][:10]
+    )
+
+
+examples = [
+    "king - man + woman",
+    "berlin - germany + france",
+]
+
+with gr.Blocks() as app:
+    with gr.Row():
+        with gr.Column():
+            input = gr.Textbox(value=examples[0], label="Expression")
+            with gr.Row():
+                btn = gr.Button("Run")
+            with gr.Row():
+                gr.Examples(examples, inputs=input)
+
+        with gr.Column():
+            output = gr.Label(label="Closest words")
+
+    btn.click(fn=get_results, inputs=input, outputs=output)
+
+app.launch()

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+
+datasets
+numpy
+scikit-learn
+
+pyparsing