import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MultiLabelBinarizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Embedding, Flatten
from tensorflow.keras.optimizers import Adam

# Load the dataset from the CSV file
data = pd.read_csv('data.csv', on_bad_lines='skip', engine='python')


# Prepare the data
X = data[['movie title', 'User Rating', 'Generes', 'Plot Kyeword', 'Director', 'Top 5 Casts', 'Writer', 'year']]
y = data['Rating']

# Preprocess the data
# Convert the categorical columns into numerical representations
mlb = MultiLabelBinarizer()
X['Generes'] = mlb.fit_transform(X['Generes']).tolist()
X['Plot Kyeword'] = mlb.fit_transform(X['Plot Kyeword']).tolist()
X['Top 5 Casts'] = mlb.fit_transform(X['Top 5 Casts'].astype(str)).tolist()

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create the neural network model
model = Sequential()
model.add(Embedding(input_dim=len(mlb.classes_), output_dim=10, input_length=X.shape[1]))
model.add(Flatten())
model.add(Dense(32, activation='relu'))
model.add(Dense(1))

# Compile the model
model.compile(optimizer=Adam(), loss='mse')

# Train the model
model.fit(X_train, y_train, batch_size=64, epochs=10, validation_data=(X_test, y_test))

# Evaluate the model
mse = model.evaluate(X_test, y_test)
print("Mean Squared Error:", mse)