Upload 2 files

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+from joblib import load
+import h5py
+
+# Load the model and data once at startup
+with h5py.File('complete_artist_data.hdf5', 'r') as f:
+    # Deserialize the vectorizer
+    vectorizer_bytes = f['vectorizer'][()].tobytes()
+    vectorizer_buffer = BytesIO(vectorizer_bytes)
+    vectorizer = load(vectorizer_buffer)
+    
+    # Load X_artist
+    X_artist = f['X_artist'][:]
+    
+    # Load artist names and decode to strings
+    artist_names = [name.decode() for name in f['artist_names'][:]]
+
+def find_similar_artists(new_tags_string):
+    new_image_tags = [tag.strip() for tag in new_tags_string.split(",")]
+    unseen_tags = set(new_image_tags) - set(vectorizer.vocabulary_.keys())
+    unseen_tags_str = f'Unseen Tags: {", ".join(unseen_tags)}' if unseen_tags else 'No unseen tags.'
+    
+    X_new_image = vectorizer.transform([','.join(new_image_tags)])
+    similarities = cosine_similarity(X_new_image, X_artist)[0]
+    
+    top_n = 20
+    top_artist_indices = np.argsort(similarities)[-top_n:][::-1]
+    bottom_artist_indices = np.argsort(similarities)[:top_n]
+    
+    top_artists = [(artist_names[i], similarities[i]) for i in top_artist_indices]
+    bottom_artists = [(artist_names[i], similarities[i]) for i in bottom_artist_indices]
+    
+    top_artists_str = "\n".join([f"{rank+1}. {artist} - similarity score: {score:.4f}" for rank, (artist, score) in enumerate(top_artists)])
+    bottom_artists_str = "\n".join([f"{rank+1}. {artist} - similarity score: {score:.4f}" for rank, (artist, score) in enumerate(bottom_artists)])
+    
+    output_str = f"{unseen_tags_str}\n\nTop 10 artists:\n{top_artists_str}\n\nBottom 10 artists:\n{bottom_artists_str}"
+    return output_str
+
+iface = gr.Interface(
+    fn=find_similar_artists,
+    inputs="text",
+    outputs="text",
+    title="Artist Similarity Finder",
+    description="Enter image tags to find similar artists based on learned similarities."
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio==3.41.2
+numpy==1.25.1
+scikit-learn==1.2.2
+h5py==3.8.0
+joblib==1.2.0
+