Upload 6 files

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import pandas as pd
+import zipfile
+import requests
+import io
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Function to download and load data
+def load_data():
+    url = "https://files.grouplens.org/datasets/movielens/ml-latest-small.zip"
+    response = requests.get(url)
+    zip_file = zipfile.ZipFile(io.BytesIO(response.content))
+    
+    ratings = pd.read_csv(zip_file.open('ml-latest-small/ratings.csv'))
+    movies = pd.read_csv(zip_file.open('ml-latest-small/movies.csv'))
+    
+    data = pd.merge(ratings, movies, on='movieId')
+    return data
+
+# Function to build user-item matrix and similarity matrix
+def build_matrices(data):
+    user_item_matrix = data.pivot_table(index='userId', columns='title', values='rating').fillna(0)
+    user_similarity = cosine_similarity(user_item_matrix)
+    user_similarity_df = pd.DataFrame(user_similarity, index=user_item_matrix.index, columns=user_item_matrix.index)
+    return user_item_matrix, user_similarity_df
+
+# Function to get recommendations
+def get_recommendations(user_id, user_item_matrix, user_similarity_df, num_recommendations=5):
+    user_sim_scores = user_similarity_df[user_id]
+    similar_users = user_sim_scores.sort_values(ascending=False)
+    similar_users_ratings = user_item_matrix.loc[similar_users.index]
+    weighted_ratings = similar_users_ratings.T.dot(similar_users)
+    weighted_ratings = weighted_ratings / similar_users.sum()
+    recommendations = weighted_ratings.sort_values(ascending=False).head(num_recommendations)
+    return recommendations
+
+# Load data and build matrices
+data = load_data()
+user_item_matrix, user_similarity_df = build_matrices(data)
+
+# Streamlit app
+st.title("Collaborative Filtering Recommendation System")
+
+user_id = st.number_input("Enter User ID", min_value=1, max_value=user_similarity_df.index.max(), step=1)
+
+if st.button("Get Recommendations"):
+    if user_id in user_similarity_df.index:
+        recommendations = get_recommendations(user_id, user_item_matrix, user_similarity_df)
+        st.write("Top Recommendations:")
+        for movie, score in recommendations.items():
+            st.write(f"{movie}: {score:.2f}")
+    else:
+        st.write("User ID not found.")

requirements.txt

@@ -0,0 +1,3 @@
+streamlit 
+pandas 
+scikit-learn