update script4
This commit is contained in:
parent
c3282144cd
commit
bd09cb0dd1
@ -5,8 +5,7 @@ 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')
|
||||
# Replace 'path_to_dataset.csv' with the actual path to your dataset file
|
||||
data = pd.read_csv('25k_movies.csv.shuf', error_bad_lines=False)
|
||||
|
||||
# Step 2: Preprocess the data
|
||||
features = ['Total Run Time', 'User Rating', 'Genres', 'Director Name', 'Writer Name']
|
||||
@ -16,6 +15,9 @@ data = data[features + [target]]
|
||||
# Handle missing values if any
|
||||
data = data.dropna()
|
||||
|
||||
# Filter out rows with a different 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'])
|
||||
|
||||
@ -46,4 +48,4 @@ model.fit(X_train, y_train, epochs=10, batch_size=32)
|
||||
y_pred = model.predict(X_test)
|
||||
mse = np.mean((y_pred - y_test)**2)
|
||||
|
||||
print(f"Mean Squared Error (MSE): {mse}")
|
||||
print(f"Mean Squared Error (MSE): {mse}")
|
||||
|
Loading…
Reference in New Issue
Block a user