Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,3 +1,21 @@
+from recommendation_utils import (
+    load_nn_model, load_svd_model, load_trainset,
+    recommend_with_nn, recommend_with_svd
+)
+
+import pickle
+from keras.models import load_model
+
+# Nur einmal laden
+@st.cache_resource
+def load_models():
+    nn_model = load_nn_model("recommender_model.keras")
+    svd_model = load_svd_model("svd_model.pkl")
+    trainset = load_trainset("trainset.pkl")
+    return nn_model, svd_model, trainset
+
+nn_model, svd_model, trainset = load_models()
+
 import streamlit as st
 import pandas as pd
 import random
@@ -487,4 +505,38 @@ else:
         worst = merged[merged["rating"] <= 2].sort_values(["rating", "timestamp"], ascending=[True, False])
         show_table(worst, "😞 Worst Rated", checkbox_key="worst_rated")
 
+        st.subheader("🎯 Recommended For You")
+
+        user_ratings_dict = {r["movie_id"]: r["rating"] for r in all_ratings_data}
+
+        if user_ratings_dict:
+            if st.session_state["model_selection"] == "Neural Network":
+                available_movies = movie_df["movieId"].tolist()
+                recommendations = recommend_with_nn(user_ratings_dict, nn_model, available_movies, top_n=10)
+            else:
+                ratings_full = pd.DataFrame(all_ratings_data)
+                ratings_full["userId"] = 999999  # Dummy user
+                ratings_full["rating"] = ratings_full["rating"].astype(float)
+                recommendations = recommend_with_svd(svd_model, trainset, ratings_full, user_ratings_dict, top_n=10)
+
+            recommended_df = pd.merge(recommendations, movie_df, on="movieId", how="left")
+
+            for _, movie in recommended_df.iterrows():
+                poster_url, _ = get_tmdb_data(movie["clean_title"], movie["year"])
+                st.markdown(f"""
+                <div style="margin-bottom:1em;padding:1em;border:1px solid #333;border-radius:10px;background:#1a1a1a;">
+                    <div style="display:flex;gap:20px;">
+                        <div>
+                            <img src="{poster_url}" width="100" style="border-radius:5px;" />
+                        </div>
+                        <div>
+                            <a href='/?movie_id={movie["movieId"]}' style="font-size:18px;color:#e63946;font-weight:bold;">{movie['clean_title']}</a><br>
+                            <span style="color:#ccc;">{movie['genres']} · {movie['year']}</span><br>
+                            <span style="color:#d4af37;">Predicted Rating: {round(movie['rating'], 2)}</span>
+                        </div>
+                    </div>
+                </div>
+                """, unsafe_allow_html=True)
+        else:
+            st.info("Rate a few movies to get recommendations.")