"RANSAC",
"K-Neighbors",
"Radius Neighbors",
"MLP",
"Decision Tree",
"Extra Tree",
"SVR"
]
classifiers = [
RandomForestRegressor(n_estimators=200, n_jobs=5,
random_state=randomstate),
ExtraTreesRegressor(n_estimators=200, n_jobs=5, random_state=randomstate),
# GradientBoostingRegressor(random_state=randomstate), # learning_rate is a hyper-parameter in the range (0.0, 1.0]
# HistGradientBoostingClassifier(random_state=randomstate), # learning_rate is a hyper-parameter in the range (0.0, 1.0]
AdaBoostRegressor(n_estimators=200, random_state=randomstate),
GaussianProcessRegressor(normalize_y=True),
ARDRegression(),
# HuberRegressor(), # epsilon: greater than 1.0, default 1.35
LinearRegression(n_jobs=5),
PassiveAggressiveRegressor(
random_state=randomstate), # C: 0.25, 0.5, 1, 5, 10
SGDRegressor(random_state=randomstate),
TheilSenRegressor(n_jobs=5, random_state=randomstate),
RANSACRegressor(random_state=randomstate),
KNeighborsRegressor(
weights='distance'), # n_neighbors: 3, 6, 9, 12, 15, 20
RadiusNeighborsRegressor(weights='distance'), # radius: 1, 2, 5, 10, 15
MLPRegressor(max_iter=10000000, random_state=randomstate),
DecisionTreeRegressor(
random_state=randomstate), # max_depth = 2, 3, 4, 6, 8
(Ridge(), ['predict'], create_regression_problem_1()),
(RidgeCV(), ['predict'], create_regression_problem_1()),
(SGDRegressor(), ['predict'], create_regression_problem_1()),
(Lasso(), ['predict'], create_regression_problem_1()),
(Pipeline([('earth', Earth()), ('logistic', LogisticRegression())]),
['predict', 'predict_proba'], create_weird_classification_problem_1()),
(FeatureUnion([('earth', Earth()), ('earth2', Earth(max_degree=2))],
transformer_weights={
'earth': 1,
'earth2': 2
}), ['transform'], create_weird_classification_problem_1()),
(RandomForestRegressor(), ['predict'], create_regression_problem_1()),
(CalibratedClassifierCV(LogisticRegression(),
'isotonic'), ['predict_proba'],
create_weird_classification_problem_1()),
(AdaBoostRegressor(), ['predict'], create_regression_problem_1()),
(BaggingRegressor(), ['predict'], create_regression_problem_1()),
(BaggingClassifier(), ['predict_proba'],
create_weird_classification_problem_1()),
(GradientBoostingRegressor(verbose=True), ['predict'],
create_regression_problem_1(m=100000, n=200)),
(XGBRegressor(), ['predict'], create_regression_problem_for_xgb_1())
]
# Create tests for numpy_flat language
def create_case_numpy_flat(estimator, methods, fit_data, predict_data,
export_predict_data):
def test_case(self):
model = clone(estimator)
model.fit(**fit_data)
from sklearn.preprocessing.data import MinMaxScaler
boston = datasets.load_boston()
X = MinMaxScaler().fit_transform(boston.data)
y = boston.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
models = []
models.append(RandomForestRegressor())
models.append(RandomForestRegressor(n_estimators=100))
models.append(GradientBoostingRegressor())
models.append(GradientBoostingRegressor(n_estimators=300))
models.append(AdaBoostRegressor())
def evaluation():
for model in models:
score = cross_val_score(estimator=model, X=X, y=y, cv=KFold(10), scoring='r2')
print(score.mean(), score.std())
def visualization():
for model in models:
model.fit(X_train, y_train)
y_predict = model.predict(X_test)
x_axis = range(0, len(y_test))
plt.plot(x_axis, y_test, 'r', label='test')
plt.plot(x_axis, y_predict, 'b', label='predict')
from sklearn.cluster.spectral import SpectralClustering
from sklearn.cluster.bicluster import SpectralCoclustering
from sklearn.manifold.spectral_embedding_ import SpectralEmbedding
from sklearn.preprocessing.data import StandardScaler
from sklearn.manifold.t_sne import TSNE
from sklearn.linear_model.theil_sen import TheilSenRegressor
from sklearn.mixture.dpgmm import VBGMM
from sklearn.feature_selection.variance_threshold import VarianceThreshold
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
clf_dict = {'ARDRegression':ARDRegression(),
'AdaBoostClassifier':AdaBoostClassifier(),
'AdaBoostRegressor':AdaBoostRegressor(),
'AdditiveChi2Sampler':AdditiveChi2Sampler(),
'AffinityPropagation':AffinityPropagation(),
'AgglomerativeClustering':AgglomerativeClustering(),
'BaggingClassifier':BaggingClassifier(),
'BaggingRegressor':BaggingRegressor(),
'BayesianGaussianMixture':BayesianGaussianMixture(),
'BayesianRidge':BayesianRidge(),
'BernoulliNB':BernoulliNB(),
'BernoulliRBM':BernoulliRBM(),
'Binarizer':Binarizer(),
'Birch':Birch(),
'CCA':CCA(),
'CalibratedClassifierCV':CalibratedClassifierCV(),
'DBSCAN':DBSCAN(),
'DPGMM':DPGMM(),
from sklearn.ensemble.weight_boosting import AdaBoostRegressor
from sklearn.model_selection._split import train_test_split
tl = TrendLine(data_type='train')
data_df = tl.get()
train_set, test_set = train_test_split(data_df,
test_size=0.2,
random_state=np.random.randint(1, 1000))
y_train = train_set['time_to_failure']
x_train_seg = train_set['segment_id']
x_train = train_set.drop(['time_to_failure', 'segment_id'], axis=1)
y_test = test_set['time_to_failure']
x_test_seg = test_set['segment_id']
x_test = test_set.drop(['time_to_failure', 'segment_id'], axis=1)
adbReg = AdaBoostRegressor(n_estimators=50,
learning_rate=1.0,
loss='linear',
random_state=42)
adbReg.fit(x_train, y_train)
y_pred = adbReg.predict(x_test)
# y_pred = x_train.mean(axis=1)
print('MAE Score for acerage ', mean_absolute_error(y_test, y_pred))