Update app.py

app.py

@@ -1,82 +1,26 @@
-import pandas as pd
-import streamlit as st
-from surprise import Dataset, Reader, SVD
-from surprise.model_selection import train_test_split
-from collections import defaultdict
 import kagglehub
-
-# Step 1: Download the latest version of the dataset and get the path
-path = kagglehub.download_dataset("ashpalsingh1525/imdb-movies-dataset")
-
-# Step 2: Define the dataset folder path
-dataset_folder = "/home/user/.cache/kagglehub/datasets/ashpalsingh1525/imdb-movies-dataset/versions/1"
-
-# Step 3: Define the CSV file path (Update if the filename is different)
-dataset_path = f"{dataset_folder}/imdb_movies.csv"
-
-# Load the dataset
-df = pd.read_csv(dataset_path)
-
-# Ensure all categorical columns are strings
-categorical_columns = ['genre', 'orig_title', 'orig_lang', 'country', 'crew']
-
-for col in categorical_columns:
-    df[col] = df[col].astype(str)  # Convert to string explicitly
-
-# Check unique values in genre column (to ensure it's not numerical)
-if df['genre'].str.isnumeric().all():
-    print("Warning: Genre column is numeric. Mapping needed.")
-    genre_mapping = {i: f"Genre_{i}" for i in df['genre'].unique()}
-    df['genre'] = df['genre'].map(genre_mapping)
-
-# Prepare dataset for Surprise
-reader = Reader(rating_scale=(df['score'].min(), df['score'].max()))
-data = Dataset.load_from_df(df[['orig_title', 'orig_lang', 'score']], reader)
-
-# Train collaborative filtering model
-trainset, testset = train_test_split(data, test_size=0.2, random_state=42)
-model = SVD(n_factors=50, random_state=42)
-model.fit(trainset)
-
-# Function to get movie recommendations
-def get_recommendations(selected_movies, genre):
-    if not selected_movies:
-        return ["Please select at least one movie."]
-
-    # Filter dataset by genre
-    filtered_movies = df[df['genre'] == genre]
-
-    # Store average scores of all movies
-    movie_scores = defaultdict(float)
-
-    # Predict ratings for all movies in the filtered dataset
-    for movie in filtered_movies['orig_title'].unique():
-        est_score = model.predict(uid='user', iid=movie).est
-        movie_scores[movie] = est_score
-
-    # Sort movies by predicted score (descending)
-    recommended_movies = sorted(movie_scores.items(), key=lambda x: x[1], reverse=True)
-
-    # Exclude already selected movies
-    recommended_movies = [movie for movie, _ in recommended_movies if movie not in selected_movies]
-
-    return recommended_movies[:5]  # Return top 5 recommendations
-
-# Streamlit UI
-st.title("🎬 Movie Recommendation System")
-
-# Genre selection
-selected_genre = st.selectbox("Select a Genre", sorted(df['genre'].unique().tolist()))
-
-# Get available movies for the selected genre
-movies_in_genre = df[df['genre'] == selected_genre]['orig_title'].unique().tolist()
-
-# Movie selection
-selected_movies = st.multiselect("Select Up to 3 Movies", movies_in_genre, max_selections=3)
-
-# Recommendation button
-if st.button("Get Recommendations"):
-    recommendations = get_recommendations(selected_movies, selected_genre)
-    st.subheader("Recommended Movies:")
-    for movie in recommendations:
-        st.write(f"- {movie}")
+import os
+import random
+from PIL import Image
+
+# Step 1: Download the latest version of the dataset
+path = kagglehub.dataset_download("imreallyjohn/cartoonset10k")
+
+print("Path to dataset files:", path)
+
+# Step 2: List all image files in the dataset directory
+images_folder = os.path.join(path, "/content/CartoonAvatar/CartoonAvatar")  # Adjust the subdirectory if needed
+image_files = [f for f in os.listdir(images_folder) if f.endswith('.png')]  # Filter for .png files
+
+if image_files:
+    # Step 3: Select a random available image
+    random_image_filename = random.choice(image_files)  # Select a random image
+    image_path = os.path.join(images_folder, random_image_filename)
+
+    # Step 4: Load and display the selected image
+    selected_image = Image.open(image_path)
+    selected_image.show()
+    print(f"Displayed image: {random_image_filename}")
+    display(selected_image)
+else:
+    print("No available images to display.")