add csv data and endpoints to show user track history from it

.gitignore

@@ -0,0 +1,2 @@
+.idea
+__pycache__

data/music_info.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d930430f811ba3c77f217b3f456f2b6271c238b828d6d9ad76e889b5d725f187
+size 14985870

data/user_listening_history_10k.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a82d52ec512f00bf1a3416ecbf153aaa478266e87f6d3c0c4bff85ce4e1d4a
+size 620427

recommender.py

@@ -0,0 +1,16 @@
+from fastai.learner import Learner
+import pandas as pd
+
+def get_recommendations_for_user(learn: Learner, user_id: str, limit: int = 5):
+    # TODO: Fetch list of not listened songs as entries
+    not_listened_songs = ["Revelry, Kings of Leon, 2008", "Gears, Miss May I, 2010", "Sexy Bitch, David Guetta, 2009"]
+    input_dataframe = pd.DataFrame({'user_id': ["440abe26940ae9d9268157222a4a3d5735d44ed8"] * len(not_listened_songs), 'entry': not_listened_songs})
+    test_dl = learn.dls.test_dl(input_dataframe)
+    predictions = learn.get_preds(dl=test_dl)
+
+    # TODO: Return recommendations in track format
+    return {
+        "user_id": user_id,
+        "limit": limit,
+        "recommendations": predictions[0].numpy().tolist()
+    }

server.py

@@ -1,12 +1,14 @@
 from fastai.collab import load_learner
 from fastapi import FastAPI, Query
 from fastapi.middleware.cors import CORSMiddleware
-from custom_models import DotProductBias 
+from custom_models import DotProductBias
 import asyncio
 import uvicorn
-import pandas as pd
 import os
 
+from tracks import get_top_tracks_for_user, get_users_with_track_interactions
+from recommender import get_recommendations_for_user
+
 # FastAPI app
 app = FastAPI()
 
@@ -35,28 +37,18 @@ async def startup_event():
     tasks = [asyncio.ensure_future(setup_learner())]  # assign some task
     learn = (await asyncio.gather(*tasks))[0]
 
-@app.get('/user/{user_id}/history')
-async def get_user_track_history(user_id: str):
-    return {
-        "user_id": user_id,
-        "history": [
-            {"track_id": "1", "genre": "Rock", "year": "2008", "artist": "Kings of Leon", "name": "Revelry"},
-            {"track_id": "2", "genre": "Metalcore", "year": "2010", "artist": "Miss May I", "name": "Gears"},
-            {"track_id": "3", "genre": "Electro", "year": "2009", "artist": "David Guetta", "name": "Sexy Bitch"}
-        ]
-    }
+@app.get("/users")
+async def get_users(limit: int = Query(10)):
+    return get_users_with_track_interactions(limit=limit)
+
+@app.get('/users/{user_id}')
+async def get_user_track_history(user_id: str, limit:int = Query(5)):
+    user_history = get_top_tracks_for_user(user_id, limit)
+    return {"user_id": user_id, "history": user_history}
 
 @app.get("/recommend/{user_id}")
-async def get_recommendations_for_user(user_id: str, num_recommendations: int = Query(5)):
-    print(num_recommendations)
-    print(user_id)
-    not_listened_songs = ["Revelry, Kings of Leon, 2008", "Gears, Miss May I, 2010", "Sexy Bitch, David Guetta, 2009"]
-    input_dataframe = pd.DataFrame({'user_id': ["440abe26940ae9d9268157222a4a3d5735d44ed8"] * len(not_listened_songs), 'entry': not_listened_songs})
-    test_dl = learn.dls.test_dl(input_dataframe)
-    predictions = learn.get_preds(dl=test_dl)
-    print(predictions)
-    #pred = learn.predict(file)
-    return {"result": predictions[0].numpy().tolist()}
+async def get_recommendations(user_id: str, num_recommendations: int = Query(5)):
+    return get_recommendations_for_user(learn, user_id, num_recommendations)
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", 7860)))

tracks.py

@@ -0,0 +1,40 @@
+import pandas as pd
+
+# Read the CSV files
+print("Reading music info csv ...")
+tracks_df = pd.read_csv('data/music_info.csv')
+
+print("Reading user listening history ...")
+track_interactions_df = pd.read_csv('data/user_listening_history_10k.csv', nrows=1000)
+
+# Merge the dataframes on 'track_id'
+dataframe = pd.merge(tracks_df, track_interactions_df, on='track_id', how='left')
+
+# Convert all NaN values to empty strings and all columns to string type
+dataframe.fillna('', inplace=True)
+dataframe = dataframe.astype(str)
+
+# Group by 'user_id' and then create a list of dictionaries for each group
+lookup_table = {user_id: group.drop('user_id', axis=1).to_dict('records')
+                for user_id, group in dataframe.groupby('user_id')}
+
+def get_users_with_track_interactions(ascending=False, limit=10):
+    # Count the number of rows for each 'user_id'
+    playcount_summary = track_interactions_df.groupby('user_id').size().reset_index(name='track_interactions')
+    # Sort the DataFrame based on 'track_interactions', either ascending or descending
+    playcount_summary.sort_values(by='track_interactions', ascending=ascending, inplace=True)
+    # Limit the results if limit is specified
+    if limit is not None:
+        playcount_summary = playcount_summary.head(limit)
+    # Convert the DataFrame to a list of dictionaries
+    return playcount_summary.to_dict(orient='records')
+
+def get_top_tracks_for_user(user_id: str, limit=20):
+    # Retrieve the user's track list from the lookup table or an empty list if not found
+    track_list = lookup_table.get(user_id, [])
+    # Sort the track list by 'playcount' in descending order (assuming 'playcount' is stored as a string)
+    sorted_tracks = sorted(track_list, key=lambda x: int(x['playcount']) if 'playcount' in x and x['playcount'].isdigit() else 0, reverse=True)
+    # Apply the limit if specified
+    if limit is not None:
+        sorted_tracks = sorted_tracks[:limit]
+    return sorted_tracks