This commit is contained in:
Yevhenii Poliakov 2023-05-14 21:17:30 +02:00
parent c3c751076e
commit 2d8d1d999e

View File

@ -7,27 +7,28 @@ 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')
data = pd.read_csv('data.csv')
# Drop a specific row
data = data.drop(index=5059)
# Prepare the data
X = data[['movie title', 'User Rating', 'Director', 'Top 5 Casts', 'Writer', 'year']]
X = data[['movie title', 'User Rating', 'Director', 'Top 5 Casts', 'Writer']]
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()
X_genres = pd.DataFrame(mlb_genres.fit_transform(data['Generes']), columns=mlb_genres.classes_)
mlb_keywords = MultiLabelBinarizer()
X_keywords = mlb_keywords.fit_transform(data['Plot Kyeword'])
X.loc[:, 'Plot Kyeword'] = X_keywords.tolist()
X_keywords = pd.DataFrame(mlb_keywords.fit_transform(data['Plot Kyeword']), columns=mlb_keywords.classes_)
mlb_casts = MultiLabelBinarizer()
X_casts = mlb_casts.fit_transform(data['Top 5 Casts'].astype(str))
X.loc[:, 'Top 5 Casts'] = X_casts.tolist()
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)