from auto_machine_learning.hyperparameter_optimization.hpo_methods import *
from auto_machine_learning.data_preprocessing.preprocessing import dataset_split
from auto_machine_learning.utils import check
from auto_machine_learning.datasets.load_dataset import load_dataset
from sklearn.linear_model import LinearRegression, Ridge, Lasso, LogisticRegression
from sklearn.ensemble import RandomForestClassifier
import warnings
warnings.filterwarnings('ignore')
boston_dataset, boston_label = load_dataset('boston')
diabetes_dataset, diabetes_label = load_dataset('diabetes')
boston_X_train, boston_X_test, boston_y_train, boston_y_test = dataset_split(
boston_dataset, boston_label)
diabetes_X_train, diabetes_X_test, diabetes_y_train, diabetes_y_test = dataset_split(
diabetes_dataset, diabetes_label)
def test_grid_search():
for model in [LinearRegression, Lasso, Ridge]:
# grid_search(boston_dataset, boston_label, model)
assert check(grid_search, model, boston_X_train, boston_y_train)
for model in [LogisticRegression, RandomForestClassifier]:
assert check(grid_search, model, diabetes_X_train, diabetes_y_train)
def test_random_search():
for model in [LinearRegression, Lasso, Ridge]:
assert check(random_search, model, boston_X_train, boston_y_train)
for model in [LogisticRegression, RandomForestClassifier]:
assert check(random_search, model, diabetes_X_train, diabetes_y_train)
from auto_machine_learning.data_preprocessing.preprocessing import *
from auto_machine_learning.utils import check
from auto_machine_learning.datasets.load_dataset import load_dataset
boston_dataset, boston_label = load_dataset('boston')
titanic_dataset, titanic_label = load_dataset('titanic')
def test_preprocess_data():
assert check(preprocess_data, boston_dataset, boston_label, 'regression')
assert check(preprocess_data, boston_dataset, boston_label,
'classification') == False
def test_remove_null():
assert check(remove_null, boston_dataset, boston_label)
assert check(remove_null, titanic_dataset, titanic_label)
def test_label_encode():
assert check(label_encode, titanic_dataset, titanic_label)
def test_oversampling():
assert check(oversampling, boston_dataset, boston_label) == False
assert check(oversampling, titanic_dataset, titanic_label)
def test_dataset_split():
assert check(dataset_split, boston_dataset, boston_label, test_size=0.3)
split_datasets = dataset_split(boston_dataset, boston_label, test_size=0.3)
from sklearn.linear_model import LinearRegression
import pandas as pd
from auto_machine_learning.feature_engineering.anova import anova_regressor
import warnings
from auto_machine_learning.data_preprocessing.preprocessing import *
from auto_machine_learning.datasets.load_dataset import load_dataset
from auto_machine_learning.visualization.plot_2d import *
warnings.filterwarnings('ignore')
models = list(map_model.keys())
# models = models[9:]
# print(models)
# models = ['LogisticRegression', 'RandomForestClassifier']
#models = ['BaggingRegressor']
#dataset = pd.read_csv('http://54.196.8.61:3000/uploads/titanic/Boston.csv')
dataset, label = load_dataset('titanic')
#print('dataset downloaded')
# dataset.drop(['Unnamed: 0'],axis=1,inplace=True)
# dataset = anova_regressor(dataset, label, LinearRegression)
# X_train, X_test, Y_train, Y_test = dataset_split(dataset, label)
# print('here',X_train.shape)
# params = {'fit_intercept': True, 'n_jobs': 1, 'normalize': True}
# base_model = LinearRegression(**params)
# base_model.fit(X_train, Y_train)
# print('Accuracy for base model:',base_model.score(dataset[get_features(dataset,label)], dataset[label]))
#stats,model =automl_run(dataset, label,base_layer_models=['Lasso','Ridge'], meta_layer_models=['LinearRegression'], task='prediction',excel_file='1',sortby='r2')
model, stats, f = automl_run(dataset,
label,
base_layer_models=['LogisticRegression'],
from auto_machine_learning.AutoML.auto_model_trainer import *
from auto_machine_learning.utils import check
from auto_machine_learning.datasets.load_dataset import load_dataset
from auto_machine_learning.data_preprocessing.preprocessing import dataset_split
import warnings
warnings.filterwarnings('ignore')
boston_dataset, boston_label = load_dataset('carprice')
diabetes_dataset, diabetes_label = load_dataset('diabetes')
# check function will return False because bayesian_gp doesn't work
def test_auto_trainer():
for model in ['LinearRegression']:
# auto_trainer(boston_dataset, boston_label, models=[model] ,task='prediction', anova_estimator=model)
assert check(auto_trainer,
boston_dataset,
boston_label,
models=[model],
task='prediction',
anova_estimator=model)
for model in ['LogisticRegression']:
assert check(auto_trainer,
diabetes_dataset,
diabetes_label,
models=[model],
task='classification',
anova_estimator=model)
