Create app.py

app.py

@@ -0,0 +1,54 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import linear_kernel
+import gradio as gr
+
+# Load the MovieLens dataset
+movies = pd.read_csv('https://files.grouplens.org/datasets/movielens/ml-latest-small.zip', compression='zip')
+
+# Define a TF-IDF Vectorizer Object. Remove all english stop words such as 'the', 'a'
+tfidf = TfidfVectorizer(stop_words='english')
+
+# Replace NaN with an empty string
+movies['genres'] = movies['genres'].fillna('')
+
+# Construct the required TF-IDF matrix by fitting and transforming the data
+tfidf_matrix = tfidf.fit_transform(movies['genres'])
+
+# Compute the cosine similarity matrix
+cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
+
+# Construct a reverse map of indices and movie titles
+indices = pd.Series(movies.index, index=movies['title']).drop_duplicates()
+
+# Function that takes in movie title as input and outputs most similar movies
+def get_recommendations(title, cosine_sim=cosine_sim):
+    # Get the index of the movie that matches the title
+    idx = indices[title]
+
+    # Get the pairwise similarity scores of all movies with that movie
+    sim_scores = list(enumerate(cosine_sim[idx]))
+
+    # Sort the movies based on the similarity scores
+    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
+
+    # Get the scores of the 10 most similar movies
+    sim_scores = sim_scores[1:11]
+
+    # Get the movie indices
+    movie_indices = [i[0] for i in sim_scores]
+
+    # Return the top 10 most similar movies
+    return movies['title'].iloc[movie_indices]
+
+# Gradio interface
+def recommend_movies(movie):
+    recommendations = get_recommendations(movie)
+    return recommendations.tolist()
+
+# Create the Gradio interface
+movie_list = movies['title'].tolist()
+iface = gr.Interface(fn=recommend_movies, inputs=gr.inputs.Dropdown(movie_list), outputs="text", title="Movie Recommender", description="Select a movie to get recommendations based on content filtering.")
+
+# Launch the app
+iface.launch()