import pandas as pd
import numpy as np
import tensorflow as tf
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Step 1: Load the dataset
data = pd.read_csv('25k_movies.csv.shuf')


# Step 2: Preprocess the data
features = ['Total Run Time', 'User Rating', 'Genres', 'Director Name', 'Writer Name']
target = 'Movie Rating'
data = data[features + [target]]

# Handle missing values if any
data = data.dropna()

# Filter out rows with a different number of columns
try:
    data = data[data.apply(lambda x: len(x) == 12, axis=1)]
except pd.errors.ParserError as e:
    print(f"Error occurred while parsing the dataset: {e}")
    print("Dropping rows with inconsistent number of columns...")
    data = data[~data.apply(lambda x: len(x) != 12, axis=1)]

# Convert categorical variables to numerical representations
data = pd.get_dummies(data, columns=['Genres', 'Director Name', 'Writer Name'])

# Split the data into features and target variables
X = data.drop(target, axis=1)
y = data[target]

# 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)

# Standardize the feature data
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Step 3: Build and train the neural network model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(1)
])

model.compile(optimizer='adam', loss='mean_squared_error')

model.fit(X_train, y_train, epochs=10, batch_size=32)

# Step 4: Evaluate the model
y_pred = model.predict(X_test)
mse = np.mean((y_pred - y_test)**2)

print(f"Mean Squared Error (MSE): {mse}")