Update model.py

model.py

@@ -2,15 +2,19 @@ import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder
-from sklearn.metrics.pairwise import cosine_similarity
-import matplotlib.pyplot as plt
 from tensorflow.keras.models import Model
 from tensorflow.keras.layers import Input, Embedding, Flatten, concatenate, Dense
 from tensorflow.keras.optimizers import Adam
+from sklearn.metrics.pairwise import cosine_similarity
+import tensorflow as tf
+
+# Check if GPU is available
+gpu_available = tf.config.list_physical_devices('GPU')
+print(gpu_available)
 
 # Load datasets
-books = pd.read_csv("../data/dataset/books.csv")
-ratings = pd.read_csv("../data/dataset/ratings.csv")
+books = pd.read_csv("../data/datasets/books.csv")
+ratings = pd.read_csv("../data/datasets/ratings.csv")
 
 # Preprocess data
 user_encoder = LabelEncoder()
@@ -19,32 +23,25 @@ book_encoder = LabelEncoder()
 ratings["user_id"] = user_encoder.fit_transform(ratings["user_id"])
 ratings["book_id"] = book_encoder.fit_transform(ratings["book_id"])
 
-# Split the data into training and testing sets
-train, test = train_test_split(ratings, test_size=0.2, random_state=42)
-
+# Ensure all book IDs are included
+all_books = np.arange(len(books))
 
 # Define the neural network model
 def build_model(num_users, num_books, embedding_size=50):
     """
     Build a recommendation model.
-
     Args:
         num_users (int): The number of users in the dataset.
         num_books (int): The number of books in the dataset.
         embedding_size (int, optional): The size of the embedding vectors. Defaults to 50.
-
     Returns:
         keras.Model: The compiled recommendation model.
     """
     user_input = Input(shape=(1,))
     book_input = Input(shape=(1,))
 
-    user_embedding = Embedding(input_dim=num_users, output_dim=embedding_size)(
-        user_input
-    )
-    book_embedding = Embedding(input_dim=num_books, output_dim=embedding_size)(
-        book_input
-    )
+    user_embedding = Embedding(input_dim=num_users, output_dim=embedding_size)(user_input)
+    book_embedding = Embedding(input_dim=num_books, output_dim=embedding_size)(book_input)
 
     user_flat = Flatten()(user_embedding)
     book_flat = Flatten()(book_embedding)
@@ -58,32 +55,33 @@ def build_model(num_users, num_books, embedding_size=50):
 
     return model
 
+# Train the collaborative filtering model
+with tf.device('/GPU:0') if gpu_available else tf.device('/CPU:0'):
+    model_cf = build_model(num_users=len(ratings["user_id"].unique()),
+                           num_books=len(books))
+    model_cf.summary()  # Display model summary
+    history = model_cf.fit([ratings["user_id"], ratings["book_id"]],
+                           ratings["rating"],
+                           epochs=5,
+                           batch_size=128,
+                           validation_split=0.1)
+
+# Save the collaborative filtering model
+model_cf.save("recommendation_model.keras")
+
+# Evaluate the collaborative filtering model
+test_loss = model_cf.evaluate([ratings["user_id"], ratings["book_id"]], ratings["rating"])
+print(f"Collaborative Filtering Test Loss: {test_loss}")
+
+# Test the recommendation functions
+user_id = 0  # Example user ID
+book_name = "The Great Gatsby"  # Example book name
+
+print("Content-Based Recommendation:")
+print(content_based_recommendation(book_name, books))
+
+print("\nModel-Recommended History-Based Recommendation:")
+print(history_based_recommendation(user_id, model_cf, ratings))
 
-# Train the model
-model = build_model(
-    num_users=len(ratings["user_id"].unique()),
-    num_books=len(ratings["book_id"].unique()),
-)
-history = model.fit(
-    [train["user_id"], train["book_id"]],
-    train["rating"],
-    epochs=5,
-    batch_size=128,
-    validation_split=0.1,
-)
-
-# Plot training and validation loss
-plt.figure(figsize=(12, 6))
-plt.plot(history.history["loss"], label="Training Loss")
-plt.plot(history.history["val_loss"], label="Validation Loss")
-plt.xlabel("Epoch")
-plt.ylabel("Loss")
-plt.legend()
-plt.show()
-
-# Save the model
-model.save("recommendation_model.h5")
-
-# Evaluate the model
-test_loss = model.evaluate([test["user_id"], test["book_id"]], test["rating"])
-print(f"Test Loss: {test_loss}")
+print("\nHybrid Recommendation:")
+print(hybrid_recommendation(user_id, book_name, model_cf, books, ratings))