Update src/recommendation_utils.py

src/recommendation_utils.py

@@ -1,20 +1,23 @@
 import numpy as np
 import pandas as pd
 import pickle
-from keras.models import load_model
 from keras.models import model_from_json
 from keras.optimizers import Adam
 
+# ─────────────────────────────────────────────────────────────────────────────
+# Neural Network Model Laden (aus JSON + Weights)
+# ─────────────────────────────────────────────────────────────────────────────
 def load_nn_model(config_path, weights_path):
     with open(config_path, "r") as f:
         model_json = f.read()
     model = model_from_json(model_json)
     model.load_weights(weights_path)
-
-    # same config as used in training
     model.compile(optimizer=Adam(), loss="mse", metrics=["mse", "mae"])
     return model
 
+# ─────────────────────────────────────────────────────────────────────────────
+# SVD Model & Trainset Laden
+# ─────────────────────────────────────────────────────────────────────────────
 def load_svd_model(path):
     with open(path, "rb") as f:
         return pickle.load(f)
@@ -23,10 +26,16 @@ def load_trainset(path):
     with open(path, "rb") as f:
         return pickle.load(f)
 
+# ─────────────────────────────────────────────────────────────────────────────
+# Encodings (dict mit user/movie Encodings) laden
+# ─────────────────────────────────────────────────────────────────────────────
 def load_encodings(path="encodings.pkl"):
     with open(path, "rb") as f:
         return pickle.load(f)
 
+# ─────────────────────────────────────────────────────────────────────────────
+# SVD Recommendation
+# ─────────────────────────────────────────────────────────────────────────────
 def fold_in_new_user(model, trainset, user_ratings, reg=5):
     n_factors = model.n_factors
     A = np.zeros((n_factors, n_factors))
@@ -64,10 +73,26 @@ def recommend_with_svd(model, trainset, ratings_df, user_ratings, top_n=10):
     df = pd.DataFrame(movie_predictions).sort_values("rating", ascending=False).head(top_n)
     return df
 
+# ─────────────────────────────────────────────────────────────────────────────
+# Neural Network Recommendation
+# ─────────────────────────────────────────────────────────────────────────────
 def recommend_with_nn(user_ratings, model, available_movies, top_n=10):
-    user_id = max(user_ratings.keys(), default=0) + 100000  # Dummy user ID
+    """
+    Args:
+        user_ratings: dict of movieId → rating
+        model: compiled Keras model
+        available_movies: list of movieIds
+        top_n: number of recommendations
+    Returns:
+        DataFrame with movieId and predicted rating
+    """
+    if not available_movies:
+        return pd.DataFrame(columns=["movieId", "rating"])
+
+    user_id = max(user_ratings.keys(), default=0) + 100000  # Dummy new user
     user_vector = np.array([user_id] * len(available_movies))
     movie_vector = np.array(available_movies)
+
     predictions = model.predict([user_vector, movie_vector], verbose=0)
     df = pd.DataFrame({
         'movieId': available_movies,