Initial commit

app.py

@@ -0,0 +1,38 @@
+import streamlit as st
+from transformers import pipeline
+from sklearn.cluster import KMeans
+import numpy as np
+
+# Mock data
+mock_words = [
+    "apple", "banana", "cherry", "date",      # Fruits
+    "car", "truck", "bus", "bicycle",         # Vehicles
+    "red", "blue", "green", "yellow",         # Colors
+    "cat", "dog", "rabbit", "hamster"         # Pets
+]
+
+# Embedding model
+embedder = pipeline('feature-extraction', model='distilbert-base-uncased')
+
+def embed_words(words):
+    embeddings = embedder(words)
+    return np.array([np.mean(embedding[0], axis=0) for embedding in embeddings])
+
+def cluster_words(words):
+    embeddings = embed_words(words)
+    kmeans = KMeans(n_clusters=4, random_state=0).fit(embeddings)
+    clusters = {i: [] for i in range(4)}
+    for word, label in zip(words, kmeans.labels_):
+        clusters[label].append(word)
+    return clusters
+
+def main():
+    st.title("NYT Connections Solver")
+    
+    if st.button("Generate Clusters"):
+        clusters = cluster_words(mock_words)
+        for i, words in clusters.items():
+            st.write(f"Group {i+1}: {', '.join(words)}")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+scikit-learn
+streamlit