89 lines
3.1 KiB
Python
89 lines
3.1 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')
|
|
|
|
|
|
|
|
# Prepare the data
|
|
X = data[['movie title', 'User Rating', 'Director', 'Top 5 Casts', 'Writer']]
|
|
#y = data['Rating'].apply(lambda x: float(x) if isinstance(x, (int, float)) else np.nan) # Convert 'Rating' column to float data type
|
|
#y = pd.Series(data['Rating'], dtype=float)
|
|
y = data['Rating'].astype('float64')
|
|
#y = y.fillna(y.mean())
|
|
#y = np.array(y)
|
|
|
|
print("Unique values in 'Rating' column:", data['Rating'].unique())
|
|
print("Data type of 'Rating' column:", y.dtype)
|
|
|
|
mean_rating = data['Rating'].mean()
|
|
data['Rating'].fillna(mean_rating, inplace=True)
|
|
|
|
# Preprocess the data
|
|
# Convert the categorical columns into numerical representations
|
|
mlb_genres = MultiLabelBinarizer()
|
|
X_genres = pd.DataFrame(mlb_genres.fit_transform(data['Generes']), columns=mlb_genres.classes_)
|
|
|
|
mlb_keywords = MultiLabelBinarizer()
|
|
X_keywords = pd.DataFrame(mlb_keywords.fit_transform(data['Plot Kyeword']), columns=mlb_keywords.classes_)
|
|
|
|
mlb_casts = MultiLabelBinarizer()
|
|
X_casts = pd.DataFrame(mlb_casts.fit_transform(data['Top 5 Casts'].astype(str)), columns=mlb_casts.classes_)
|
|
|
|
# Concatenate the transformed columns with the remaining columns
|
|
X = pd.concat([X, X_genres, X_keywords, X_casts], axis=1)
|
|
|
|
# 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)
|
|
|
|
# Convert the modified 'Rating' column to a numpy array
|
|
y_train_updated = data['Rating'].to_numpy()
|
|
y_train_updated = pd.Series(y_train_updated[:len(X_train)])
|
|
|
|
# Update the 'y_train' array with the modified values
|
|
y_train.loc[X_train.index] = y_train_updated
|
|
|
|
# Fill NaN values with the mean of non-missing values
|
|
y_train.fillna(y_train.mean(), inplace=True)
|
|
|
|
# Convert the 'y_train' series to a NumPy array
|
|
y_train = y_train.values
|
|
|
|
# Filter out non-numeric and NaN values from y_train
|
|
y_train = y_train.astype(float)
|
|
y_train = y_train[np.isfinite(y_train)]
|
|
|
|
non_numeric_values = [value for value in y_train if not np.issubdtype(type(value), np.number)]
|
|
print("Non-numeric values in y_train:", non_numeric_values)
|
|
|
|
# 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')
|
|
|
|
print("Data type of 'Rating' column:", y_train.dtype)
|
|
|
|
print("First few rows of 'y_train':", y_train[:10])
|
|
|
|
print("Data type of 'X_train':", X_train.dtypes)
|
|
print("Shape of 'X_train':", X_train.shape)
|
|
print("Data type of 'y_train':", y_train.dtypes)
|
|
print("Shape of 'y_train':", y_train.shape)
|
|
|
|
# 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)
|