50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
|
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
|
||
|
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', 'Director', 'Top 5 Casts', 'Writer', 'year']]
|
||
|
y = data['Rating']
|
||
|
|
||
|
# Preprocess the data
|
||
|
# Convert the categorical columns into numerical representations
|
||
|
mlb_genres = MultiLabelBinarizer()
|
||
|
X_genres = mlb_genres.fit_transform(data['Generes'])
|
||
|
X.loc[:, 'Generes'] = X_genres.tolist()
|
||
|
|
||
|
mlb_keywords = MultiLabelBinarizer()
|
||
|
X_keywords = mlb_keywords.fit_transform(data['Plot Kyeword'])
|
||
|
X.loc[:, 'Plot Kyeword'] = X_keywords.tolist()
|
||
|
|
||
|
mlb_casts = MultiLabelBinarizer()
|
||
|
X_casts = mlb_casts.fit_transform(data['Top 5 Casts'].astype(str))
|
||
|
X.loc[:, 'Top 5 Casts'] = X_casts.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(Dense(32, activation='relu', input_dim=X.shape[1]))
|
||
|
model.add(Dense(16, 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)
|