def _main():
X, y = data_preprocessing.import_dataset('Salary_Data.csv', slice(0, -1),
1)
X_train, X_test, y_train, y_test = data_preprocessing.split_train_test(
X, y, 1 / 3)
regressor = LinearRegression()
regressor.fit(X_train, y_train)
visualize_performance_on_training(regressor, X_train, y_train)
visualize_performance_on_test(regressor, X_test, y_test)
def _main():
features, labels = data_preprocessing.import_dataset('50_Startups.csv', slice(0, 4), 4)
features, _ = data_preprocessing.one_hot_encode_categorical_features(features, [3])
features_train, features_test, labels_train, labels_test = \
data_preprocessing.split_train_test(features, labels, test_size=0.2)
regressor = LinearRegression()
regressor.fit(features_train, labels_train)
labels_test_pred = regressor.predict(features_test)
features_opt_idxs = backward_elimination(features, labels)
from data_preprocessing import data_preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from plots.classification_result_visualizer import visualize_two_feature_classification
features, labels = data_preprocessing.import_dataset(
'datasets/Social_Network_Ads.csv', [2, 3], 4)
feature_scaler = StandardScaler()
features = feature_scaler.fit_transform(features)
features_train, features_test, labels_train, labels_test = \
data_preprocessing.split_train_test(features, labels, test_size = 0.25)
classifier = LogisticRegression(random_state=0, solver='liblinear')
classifier.fit(features, labels)
visualize_two_feature_classification(features_train, labels_train, classifier,
xlabel='Age', ylabel='Estimated salary')