Initial commit: Add Streamlit app for movie recommendation

app.py

@@ -0,0 +1,88 @@
+import os
+import gdown
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import ipywidgets as widgets
+from IPython.display import display
+
+# Google Drive file IDs
+movies_file_id = "1HWlVK-nXM5JG4GfSDHyR-x8T1AlfQQYw"
+ratings_file_id = "1V2s1rpu4Gfjbt8z2a1Xml9IJr5KSozK1"
+
+# Download the files if they don't exist
+def download_file_from_google_drive(file_id, output):
+    url = f"https://drive.google.com/uc?id={file_id}"
+    gdown.download(url, output, quiet=False)
+
+if not os.path.exists("movies.csv"):
+    download_file_from_google_drive(movies_file_id, "movies.csv")
+
+if not os.path.exists("ratings.csv"):
+    download_file_from_google_drive(ratings_file_id, "ratings.csv")
+
+# Load the data
+movies = pd.read_csv("movies.csv")
+ratings = pd.read_csv("ratings.csv")
+
+# Clean movie titles
+import re
+def clean_title(title):
+    title = re.sub("[^a-zA-Z0-9 ]", "", title)
+    return title
+
+movies["clean_title"] = movies["title"].apply(clean_title)
+
+# Vectorize the titles
+vectorizer = TfidfVectorizer(ngram_range=(1, 2))
+tfidf = vectorizer.fit_transform(movies["clean_title"])
+
+# Function to search for movies
+def search(title):
+    title = clean_title(title)
+    query_vec = vectorizer.transform([title])
+    similarity = cosine_similarity(query_vec, tfidf).flatten()
+    indices = np.argpartition(similarity, -5)[-5:]
+    results = movies.iloc[indices].iloc[::-1]
+
+    return results
+
+# Function to find similar movies
+def find_similar_movies(movie_id):
+    similar_users = ratings[(ratings["movieId"] == movie_id) & (ratings["rating"] > 4)]["userId"].unique()
+    similar_user_recs = ratings[(ratings["userId"].isin(similar_users)) & (ratings["rating"] > 4)]["movieId"]
+    similar_user_recs = similar_user_recs.value_counts() / len(similar_users)
+
+    similar_user_recs = similar_user_recs[similar_user_recs > .10]
+    all_users = ratings[(ratings["movieId"].isin(similar_user_recs.index)) & (ratings["rating"] > 4)]
+    all_user_recs = all_users["movieId"].value_counts() / len(all_users["userId"].unique())
+    rec_percentages = pd.concat([similar_user_recs, all_user_recs], axis=1)
+    rec_percentages.columns = ["similar", "all"]
+
+    rec_percentages["score"] = rec_percentages["similar"] / rec_percentages["all"]
+    rec_percentages = rec_percentages.sort_values("score", ascending=False)
+    return rec_percentages.head(10).merge(movies, left_index=True, right_on="movieId")[["score", "title", "genres"]]
+
+
+# Widgets for the UI
+movie_name_input = widgets.Text(
+    value='Toy Story',
+    description='Movie Title:',
+    disabled=False
+)
+recommendation_list = widgets.Output()
+
+def on_type(data):
+    with recommendation_list:
+        recommendation_list.clear_output()
+        title = data["new"]
+        if len(title) > 5:
+            results = search(title)
+            movie_id = results.iloc[0]["movieId"]
+            display(find_similar_movies(movie_id))
+
+movie_name_input.observe(on_type, names='value')
+
+# Display the widgets
+display(movie_name_input, recommendation_list)

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+scikit-learn
+numpy
+gdown