Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import gensim.downloader as api
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.manifold import TSNE
+import pandas as pd
+import plotly.express as px
+
+# Load pre-trained Word2Vec model
+@st.cache_resource
+def load_model():
+    return api.load("word2vec-google-news-300")
+
+model = load_model()
+
+# Streamlit UI
+st.title("🔍 Word Embedding Visualization")
+st.write("Enter words to visualize their embeddings using t-SNE.")
+
+# User input
+words = st.text_input("Enter words (comma-separated)", "king, queen, man, woman, dog, cat")
+
+# Process input
+words = [word.strip() for word in words.split(",") if word.strip() in model]
+
+if len(words) < 2:
+    st.warning("Please enter at least two valid words from the Word2Vec model.")
+else:
+    # Get embeddings
+    vectors = np.array([model[word] for word in words])
+
+    # Reduce to 2D using t-SNE
+    tsne = TSNE(n_components=2, perplexity=5, random_state=42)
+    vectors_2d = tsne.fit_transform(vectors)
+
+    # Plot using Matplotlib
+    fig, ax = plt.subplots(figsize=(8, 6))
+    ax.scatter(vectors_2d[:, 0], vectors_2d[:, 1])
+
+    for i, word in enumerate(words):
+        ax.text(vectors_2d[i, 0] + 0.01, vectors_2d[i, 1] + 0.01, word, fontsize=12)
+
+    st.pyplot(fig)
+
+    # 3D Visualization with Plotly
+    tsne_3d = TSNE(n_components=3, perplexity=5, random_state=42)
+    vectors_3d = tsne_3d.fit_transform(vectors)
+
+    df = pd.DataFrame(vectors_3d, columns=["x", "y", "z"])
+    df["word"] = words
+
+    fig3d = px.scatter_3d(df, x="x", y="y", z="z", text="word", title="3D t-SNE Word Embeddings")
+    st.plotly_chart(fig3d)