Create app.py

app.py

@@ -0,0 +1,158 @@
+import pandas as pd
+import numpy as np
+from zipfile import ZipFile
+import tensorflow as tf
+from tensorflow import keras
+from pathlib import Path
+import matplotlib.pyplot as plt
+import gradio as gr
+from huggingface_hub import from_pretrained_keras
+
+# Download the actual data from http://files.grouplens.org/datasets/movielens/ml-latest-small.zip"
+# Use the ratings.csv file
+movielens_data_file_url = (
+    "http://files.grouplens.org/datasets/movielens/ml-latest-small.zip"
+)
+movielens_zipped_file = keras.utils.get_file(
+    "ml-latest-small.zip", movielens_data_file_url, extract=False
+)
+keras_datasets_path = Path(movielens_zipped_file).parents[0]
+movielens_dir = keras_datasets_path / "ml-latest-small"
+
+# Only extract the data the first time the script is run.
+if not movielens_dir.exists():
+    with ZipFile(movielens_zipped_file, "r") as zip:
+        # Extract files
+        print("Extracting all the files now...")
+        zip.extractall(path=keras_datasets_path)
+        print("Done!")
+
+ratings_file = movielens_dir / "ratings.csv"
+df = pd.read_csv(ratings_file)
+
+# Make all the encodings
+user_ids = df["userId"].unique().tolist()
+user2user_encoded = {x: i for i, x in enumerate(user_ids)}
+userencoded2user = {i: x for i, x in enumerate(user_ids)}
+movie_ids = df["movieId"].unique().tolist()
+movie2movie_encoded = {x: i for i, x in enumerate(movie_ids)}
+movie_encoded2movie = {i: x for i, x in enumerate(movie_ids)}
+df["user"] = df["userId"].map(user2user_encoded)
+df["movie"] = df["movieId"].map(movie2movie_encoded)
+
+num_users = len(user2user_encoded)
+num_movies = len(movie_encoded2movie)
+df["rating"] = df["rating"].values.astype(np.float32)
+# min and max ratings will be used to normalize the ratings later
+min_rating = min(df["rating"])
+max_rating = max(df["rating"])
+
+# Load model
+model = from_pretrained_keras('mindwrapped/collaborative-filtering-movielens')
+movie_df = pd.read_csv(movielens_dir / "movies.csv")
+
+
+def update_user(id):
+  return get_top_rated_from_user(id), get_recommendations(id)
+  
+
+def get_top_rated_from_user(id):
+  decoded_id = userencoded2user.get(id)
+  movies_watched_by_user = df[df.userId == decoded_id]
+
+  # Get the top rated movies by this user
+  top_movies_user = (
+      movies_watched_by_user.sort_values(by="rating", ascending=False)
+      .head(5)
+      .movieId.values
+  )
+  movie_df_rows = movie_df[movie_df["movieId"].isin(top_movies_user)]
+  movie_df_rows = movie_df_rows.drop('movieId', axis=1)
+  return movie_df_rows
+
+
+def random_user():
+  return update_user(np.random.randint(0, num_users))
+
+
+def get_recommendations(id):
+  decoded_id = userencoded2user.get(id)
+  movies_watched_by_user = df[df.userId == decoded_id]
+
+  # Get the top 10 recommended movies for this user
+  movies_not_watched = movie_df[
+      ~movie_df["movieId"].isin(movies_watched_by_user.movieId.values)
+  ]["movieId"]
+  movies_not_watched = list(
+      set(movies_not_watched).intersection(set(movie2movie_encoded.keys()))
+  )
+  movies_not_watched = [[movie2movie_encoded.get(x)] for x in movies_not_watched]
+
+  # Encode user
+  user_encoder = id
+
+  # Create data [[user_id, movie_id],...]
+  user_movie_array = np.hstack(
+      ([[user_encoder]] * len(movies_not_watched), movies_not_watched)
+  )
+
+  # Predict ratings for movies not watched
+  ratings = model.predict(user_movie_array).flatten()
+
+  # Get indices of top ten movies
+  top_ratings_indices = ratings.argsort()[-10:][::-1]
+
+  # Decode each movie
+  recommended_movie_ids = [
+      movie_encoded2movie.get(movies_not_watched[x][0]) for x in top_ratings_indices
+  ]
+  recommended_movies = movie_df[movie_df["movieId"].isin(recommended_movie_ids)]
+  recommended_movies = recommended_movies.drop('movieId', axis=1)
+
+  return recommended_movies
+
+demo = gr.Blocks()
+
+with demo:
+  with gr.Box():
+    gr.Markdown(
+    """
+    ## Input
+    #### Select a user to get recommendations for.
+    """)
+
+    inp1 = gr.Slider(0, num_users, value=0, label='User')
+    # btn1 = gr.Button('Random User')
+
+    # top_rated_from_user = get_top_rated_from_user(0)
+
+    gr.Markdown(
+    """
+    #### Movies with the Highest Ratings from this user
+    """)
+    df1 = gr.DataFrame(interactive=False)
+
+  with gr.Box():
+    gr.Markdown('## Output')
+    # recommendations = get_recommendations(0)
+    gr.Markdown(
+    """
+    #### Top 10 movie recommendations
+    """)
+    df2 = gr.DataFrame(interactive=False)
+
+  gr.HTML("""
+  <p style='text-align: center; color: #C7C7C7'>
+      <a href='https://keras.io/examples/structured_data/collaborative_filtering_movielens/' target='_blank' style='text-decoration: underline'>Keras Example by Siddhartha Banerjee</a>
+      <br>
+      Space by Scott Krstyen (mindwrapped)
+      </p>
+  """)
+  
+  
+  inp1.change(fn=update_user,
+              inputs=inp1,
+              outputs=[df1, df2])
+  
+
+demo.launch()