Create app.py

app.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# -----------------------
+# 1. Load and prepare data
+# -----------------------
+@st.cache_data
+def load_data():
+    # Replace with your file path or relative path
+    df1 = pd.read_csv("tmdb_5000_credits.csv")
+    df2 = pd.read_csv("tmdb_5000_movies.csv")
+    df = pd.merge(df1, df2, left_on="movie_id", right_on="id")
+    df["overview"] = df["overview"].fillna(" ")
+    return df, df2
+
+df, df2 = load_data()
+
+# -----------------------
+# 2. Build TF-IDF and cosine similarity
+# -----------------------
+@st.cache_resource
+def build_model(df):
+    tfidf = TfidfVectorizer(stop_words="english")
+    tfidf_matrix = tfidf.fit_transform(df["overview"])
+    cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
+    return cosine_sim
+
+cosine_sim = build_model(df)
+
+# -----------------------
+# 3. Build reverse index mapping (title -> index)
+# -----------------------
+indices = pd.Series(df2.index, index=df2["title"]).drop_duplicates()
+
+# -----------------------
+# 4. Recommendation function
+# -----------------------
+def get_recommendations(title, cosine_sim=cosine_sim):
+    if title not in indices:
+        return []
+    idx = indices[title]
+    sim_scores = list(enumerate(cosine_sim[idx]))
+    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
+    sim_scores = sim_scores[1:11]  # skip the movie itself
+    movie_indices = [i[0] for i in sim_scores]
+    return df2["title"].iloc[movie_indices]
+
+# -----------------------
+# 5. Streamlit App UI
+# -----------------------
+st.title("🎬 Movie Recommendation Engine")
+st.markdown("Get recommendations based on similar movie plots!")
+
+movie_list = df2["title"].values
+selected_movie = st.selectbox("Choose a movie to get recommendations", movie_list)
+
+if st.button("Recommend"):
+    recommendations = get_recommendations(selected_movie)
+    if len(recommendations) == 0:
+        st.warning("Movie not found in the database.")
+    else:
+        st.success("You might also like:")
+        for rec in recommendations:
+            st.write(f"- {rec}")