Create app.py

app.py

@@ -0,0 +1,66 @@
+import gensim.downloader 
+import gradio as gr
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from sklearn.manifold import TSNE
+model = gensim.downloader.load("glove-wiki-gigaword-50")
+
+# Function to reduce dimensions
+def reduce_dimensions(data, method='PCA'):
+    if method == 'PCA':
+        model = PCA(n_components=2)
+    elif method == 'TSNE':
+        model = TSNE(n_components=2, learning_rate='auto', init='random', perplexity=3)
+    return model.fit_transform(data)
+
+description = """
+### Word Embedding Demo App
+Universidade Federal de São Paulo - Escola Paulista de Medicina
+
+The output is Word3 + (Word2 - Word1)
+
+Credits:  
+* Gensim
+* Glove
+"""
+
+Word1 = gr.Textbox()
+Word2 = gr.Textbox()
+Word3 = gr.Textbox()
+label = gr.Label(show_label=True, label="Word4")
+sp = gr.ScatterPlot(x="x", y="y", color="color")
+
+
+def inference(word1, word2, word3):
+    output = model.similar_by_vector(model[word3] + model[word2] - model[word1])
+    word_list = [word1, word2, word3]
+    word_list.expand([x for x,y in output[:4]])
+    words = {key: model[key] for key in word_list}
+    data = np.concatenate([x[np.newaxis, :] for x in words.values()], axis=0)
+    labels = words.keys()
+    reduced_data_pca = reduce_dimensions(data, method='PCA')
+    df = pd.DataFrame({
+        "x": reduced_data[:, 0], 
+        "y": reduced_data[:, 1],
+        "color": ["b", "b", "b", "r", "g", "g", "g"]
+    })
+
+    return df
+
+examples = [
+    ["woman", "man", "aunt"],  
+    ["woman", "man", "girl"],
+    ["woman", "man", "granddaughter"],
+]
+
+iface = gr.Interface(
+    fn=inference,
+    inputs=[Word1, Word2, Word3],
+    outputs=sp,
+    description=description,
+    examples=examples
+    )
+
+iface.launch()