Update app.py

app.py

@@ -1,51 +1,182 @@
+import requests
+import pandas as pd
+import spacy
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from textblob import TextBlob
 import streamlit as st
-import google.generativeai as genai
-import os
-
-# Securely retrieve API key from environment variables
-GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
-
-# Ensure the API key is set before configuring Gemini
-if GOOGLE_API_KEY:
-    genai.configure(api_key=GOOGLE_API_KEY)
-else:
-    st.error("❌ API Key is missing! Please set it in Hugging Face Secrets.")
-
-# Function to generate a funny story
-def get_funny_story(query, style, length):
-    prompt = (
-        f"Write a funny short story based on this query: '{query}'. "
-        f"Make it {length} sentences long and style it as {style}. "
-        "The story should be humorous and entertaining."
-    )
-
-    try:
-        model = genai.GenerativeModel("gemini-2.0-pro-exp-02-05")
-        response = model.generate_content(prompt)
-        return response.text
-    except Exception as e:
-        return f"Error generating story: {e}"
-
-# Streamlit UI
-st.title("😂 Funny Story Generator")
-
-# User Input: Query
-query = st.text_input("Enter a topic or query for your funny story:")
-
-# User Input: Story Style (Dropdown)
-style = st.selectbox(
-    "Select a storytelling style:",
-    ["Witty and Sarcastic", "Goofy and Childish", "Epic and Dramatic", "Absurd and Nonsensical"]
+
+# 🔹 Replace this with your TMDB API Key
+API_KEY = "bbb69cf69be036e363d9ab8996f7f4ee"
+BASE_URL = "https://api.themoviedb.org/3"
+
+# 🔹 TMDB Image Base URL for posters
+IMAGE_BASE_URL = "https://image.tmdb.org/t/p/w500"
+
+# Load Spacy English NLP model
+nlp = spacy.load("en_core_web_sm")
+
+
+# ===========================
+#  STEP 1: FETCH MOVIE DATA
+# ===========================
+def fetch_movies(num_pages=2):
+    """Fetch popular movies from TMDB API."""
+    all_movies = []
+
+    for page in range(1, num_pages + 1):
+        url = f"{BASE_URL}/discover/movie?api_key={API_KEY}&language=en-US&sort_by=popularity.desc&page={page}"
+        response = requests.get(url)
+        data = response.json()
+
+        if "results" in data:
+            for movie in data["results"]:
+                all_movies.append({
+                    "id": movie["id"],
+                    "title": movie["title"],
+                    "overview": movie["overview"],
+                    "vote_average": movie["vote_average"],
+                    "release_date": movie["release_date"]
+                })
+
+    return pd.DataFrame(all_movies)
+
+
+# ===========================
+#  STEP 2: FETCH ADDITIONAL DETAILS (GENRES, CAST, DIRECTOR)
+# ===========================
+def fetch_genres():
+    """Retrieve genre names from TMDB API and return a dictionary mapping genre IDs to names."""
+    url = f"{BASE_URL}/genre/movie/list?api_key={API_KEY}&language=en-US"
+    response = requests.get(url)
+    data = response.json()
+
+    return {genre["id"]: genre["name"] for genre in data["genres"]}
+
+
+def fetch_movie_details(movie_id):
+    """Fetch top 3 cast members and director for a given movie."""
+    url = f"{BASE_URL}/movie/{movie_id}/credits?api_key={API_KEY}"
+    response = requests.get(url)
+    data = requests.get(url).json()
+
+    # Get top 3 cast members
+    cast = ", ".join([member["name"] for member in data.get("cast", [])[:3]])
+
+    # Get director
+    director = next((crew["name"] for crew in data.get("crew", []) if crew["job"] == "Director"), "Unknown")
+
+    return cast, director
+
+
+# ===========================
+#  STEP 3: ENRICH MOVIE DATA WITH GENRES, CAST, DIRECTOR
+# ===========================
+def enhance_movie_data(movies_df):
+    """Add genres, top cast, and director information to the movie dataset."""
+    genre_dict = fetch_genres()
+
+    movies_df["cast"], movies_df["director"] = zip(*movies_df["id"].apply(fetch_movie_details))
+    return movies_df
+
+
+# ===========================
+#  STEP 4: FEATURE ENGINEERING (KEYWORDS & SENTIMENT)
+# ===========================
+def extract_keywords(text, num_keywords=5):
+    """Extract top keywords from text using TF-IDF."""
+    vectorizer = TfidfVectorizer(stop_words="english", max_features=50)
+    tfidf_matrix = vectorizer.fit_transform([text])
+    feature_names = vectorizer.get_feature_names_out()
+
+    sorted_indices = tfidf_matrix.toarray().argsort()[0][-num_keywords:]
+    return ", ".join(feature_names[i] for i in sorted_indices)
+
+
+def get_sentiment(text):
+    """Analyze sentiment (-1 to 1) from movie description using TextBlob."""
+    return TextBlob(text).sentiment.polarity
+
+
+# ===========================
+#  STEP 5: BUILD RECOMMENDER SYSTEM (CONTENT-BASED FILTERING)
+# ===========================
+def recommend_movies(movie_title, num_recommendations=5):
+    """Recommend similar movies based on content similarity."""
+    if movie_title not in movies_df["title"].values:
+        return "Movie not found in dataset!"
+
+    # Get index of the selected movie
+    movie_index = movies_df[movies_df["title"] == movie_title].index[0]
+
+    # Compute similarity scores and sort them
+    similarity_scores = list(enumerate(cosine_sim[movie_index]))
+    similarity_scores = sorted(similarity_scores, key=lambda x: x[1], reverse=True)[1:num_recommendations + 1]
+
+    # Get recommended movie titles
+    return [movies_df.iloc[i[0]]["title"] for i in similarity_scores]
+
+
+# ===========================
+#  STEP 6: FETCH MOVIE POSTER
+# ===========================
+def get_movie_poster(movie_title):
+    """Fetch movie poster from TMDB API."""
+    movie = movies_df[movies_df["title"] == movie_title]
+    if not movie.empty:
+        movie_id = movie.iloc[0]["id"]
+        url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API_KEY}"
+        response = requests.get(url).json()
+        return IMAGE_BASE_URL + response.get("poster_path", "")
+    return None
+
+
+# ===========================
+#  STEP 7: LOAD & PROCESS MOVIE DATA
+# ===========================
+movies_df = fetch_movies(num_pages=2)  # Fetch movie data
+movies_df = enhance_movie_data(movies_df)  # Add cast, director info
+
+# Apply feature extraction
+movies_df["keywords"] = movies_df["overview"].apply(lambda x: extract_keywords(str(x)))
+movies_df["sentiment"] = movies_df["overview"].apply(lambda x: get_sentiment(str(x)))
+
+# Combine relevant text features for recommendation
+movies_df["combined_features"] = (
+        movies_df["overview"].fillna("") + " " +
+        movies_df["keywords"].fillna("")
 )
 
-# User Input: Story Length (Slider)
-length = st.slider("Select story length (in sentences)", min_value=3, max_value=15, value=7)
+# Convert text into numerical vectors using TF-IDF
+tfidf_vectorizer = TfidfVectorizer(stop_words="english")
+tfidf_matrix = tfidf_vectorizer.fit_transform(movies_df["combined_features"])
+
+# Compute similarity scores between movies
+cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
+
+# ===========================
+#  STEP 8: STREAMLIT APP UI
+# ===========================
+st.title("🎬 Movie Recommendation System")
+
+# Dropdown to select a movie
+selected_movie = st.selectbox("Select a Movie", movies_df["title"].values)
+
+# Recommend button
+if st.button("Recommend"):
+    recommendations = recommend_movies(selected_movie)
+
+    if isinstance(recommendations, list):
+        st.subheader(f"Movies similar to {selected_movie}:")
+
+        # Display recommended movies in a horizontal layout
+        cols = st.columns(len(recommendations))
 
-# Generate Story Button
-if st.button("Generate Funny Story"):
-    if query.strip():
-        story = get_funny_story(query, style, length)
-        st.subheader("📖 Your Funny Story:")
-        st.write(story)
+        for i, movie in enumerate(recommendations):
+            poster_url = get_movie_poster(movie)
+            with cols[i]:
+                if poster_url:
+                    st.image(poster_url, width=150)
+                st.write(f"**{movie}**")
     else:
-        st.warning("Please enter a query for your story.")
+        st.error("No recommendations found.")