def FriedmanDataset_2():
d_train = datasets.make_friedman2(240, random_state=0)
d_test = datasets.make_friedman2(1000, random_state=0)
features_train = d_train[0]
for i in range(240):
features_train[i] += np.random.normal(0, features_train[i] / 3)
target_train = d_train[1]
features_test = d_test[0]
target_test = d_test[1]
return features_train, target_train, features_test, target_test
def test_make_friedman2():
X, y = make_friedman2(n_samples=5, noise=0.0, random_state=0)
assert_equal(X.shape, (5, 4), "X shape mismatch")
assert_equal(y.shape, (5,), "y shape mismatch")
assert_array_almost_equal(y, (X[:, 0] ** 2 + (X[:, 1] * X[:, 2] - 1 / (X[:, 1] * X[:, 3])) ** 2) ** 0.5)
def friedman2(n_samples=100,
noise=0.0,
random_state=None):
return datasets.make_friedman2(n_samples=n_samples,
noise=noise,
random_state=random_state)
def test_regression_synthetic():
"""Test on synthetic regression datasets used in Leo Breiman,
`Bagging Predictors?. Machine Learning 24(2): 123-140 (1996). """
random_state = check_random_state(1)
regression_params = {'n_estimators': 100, 'max_depth': 4,
'min_samples_split': 1, 'learning_rate': 0.1,
'loss': 'ls'}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200,
random_state=random_state, noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor()
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 5.0, "Failed on Friedman1 with mse = %.4f" % mse
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 1700.0, "Failed on Friedman2 with mse = %.4f" % mse
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 0.015, "Failed on Friedman3 with mse = %.4f" % mse
def test_regression_synthetic():
"""Test on synthetic regression datasets used in Leo Breiman,
`Bagging Predictors?. Machine Learning 24(2): 123-140 (1996). """
random_state = check_random_state(1)
regression_params = {'n_estimators': 100, 'max_depth': 4,
'min_samples_split': 1, 'learning_rate': 0.1,
'loss': 'ls'}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200,
random_state=random_state, noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor()
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 5.0, "Failed on Friedman1 with mse = %.4f" % mse
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 1700.0, "Failed on Friedman2 with mse = %.4f" % mse
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 0.015, "Failed on Friedman3 with mse = %.4f" % mse
def test_make_friedman2():
X, y = make_friedman2(n_samples=5, noise=0.0, random_state=0)
assert X.shape == (5, 4), "X shape mismatch"
assert y.shape == (5, ), "y shape mismatch"
assert_array_almost_equal(y, (X[:, 0]**2 + (X[:, 1] * X[:, 2] - 1 /
(X[:, 1] * X[:, 3]))**2)**0.5)
def friedman_2(n, noise):
"""Generate the friedman_2 data set
Args:
n (int): number of data samples
noise (float): added noise
Returns:
Friedman 2 data set
"""
return make_friedman2(n_samples=n, noise=noise)
def generateDatas(N, F, choice):
if (choice == 'f1'):
X, Y = datasets.make_friedman1(N, F, noise=1)
elif (choice == 'f2'):
X, Y = datasets.make_friedman2(N, F)
elif (choice == 'f3'):
X, Y == datasets.make_friedman3(N, F)
elif (choice == 'boston'):
boston = datasets.load_boston()
X, Y = boston.data, boston.target
return X, Y
def genFriedman(self, i=1, N=240, D=10):
if i not in range(1, 4):
raise Exception('not a correct dataset')
if i == 1:
X, Y = datasets.make_friedman1(N, D)
if i == 2:
X, Y = datasets.make_friedman2(N, D)
if i == 3:
X, Y = datasets.make_friedman3(N, D)
return X, Y
def genFriedman(self, i=1, N=240, D=10):
if i not in range(1,4):
raise Exception('not a correct dataset')
if i == 1:
X, Y = datasets.make_friedman1(N, D )
if i == 2:
X, Y = datasets.make_friedman2(N, D)
if i == 3:
X, Y = datasets.make_friedman3(N, D)
return X, Y
def define_tested_reg_datasets():
gDatasets = {};
gDatasets["diabetes"] = datasets.load_diabetes()
gDatasets["boston"] = datasets.load_boston()
gDatasets["freidman1"] = datasets.make_friedman1(random_state=1960)
gDatasets["freidman2"] = datasets.make_friedman2(random_state=1960)
gDatasets["freidman3"] = datasets.make_friedman3(random_state=1960)
gDatasets["RandomReg_10"] = datasets.make_regression(n_features=10, random_state=1960);
gDatasets["RandomReg_100"] = datasets.make_regression(n_features=100, random_state=1960);
gDatasets["RandomReg_500"] = datasets.make_regression(n_features=500, random_state=1960);
return gDatasets;
def generate_Dataset(name_dataset):
# default
ind = f(name_dataset)
if ind == 1:
x,y = datasets.make_friedman1(n_samples=100, n_features=10, noise=0.0, random_state=None)
elif ind == 2:
x,y = datasets.make_friedman2(n_samples=100, noise=0.0, random_state=None)
elif ind == 3:
x,y = datasets.make_friedman3(n_samples=100, noise=0.0, random_state=None)
else :
x, y = datasets.load_boston(return_X_y=True)
x = x.tolist()
return x,y
def test_regression_synthetic():
# Test on synthetic regression datasets used in Leo Breiman,
# `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996).
random_state = check_random_state(1)
regression_params = {
'n_estimators': 100,
'max_depth': 4,
'min_samples_split': 2,
'learning_rate': 0.1,
'loss': 'ls'
}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200,
random_state=random_state,
noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
clf = GradientBoostingRegressor(presort=presort)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 5.0)
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 1700.0)
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 0.015)
def test_regression_synthetic():
# Test on synthetic regression datasets used in Leo Breiman,
# `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996).
random_state = check_random_state(1)
regression_params = {'n_estimators': 100, 'max_depth': 4,
'min_samples_split': 2, 'learning_rate': 0.1,
'loss': 'ls'}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200,
random_state=random_state,
noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
clf = GradientBoostingRegressor(presort=presort)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 5.0)
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 1700.0)
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
for presort in True, False:
regression_params['presort'] = presort
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert_less(mse, 0.015)
def main():
X, y = make_friedman2(
n_samples=500, noise=0,
random_state=0) # This is the test data we are fitting
print(type(X))
print(np.shape(X)) # 500 samples each with 4 variables
print(type(y))
print(np.shape(y)) # 500 outputs
kernel = DotProduct() + WhiteKernel()
gpr = GaussianProcessRegressor(kernel=kernel,
optimizer='fmin_l_bfgs_b',
random_state=0).fit(X, y)
gpr_score = gpr.score(X, y) # R2 of the prediction
print('Prediction of R^2: %f' % gpr_score)
print("Shape of thing ", np.shape(X[:2, :]))
print("Thing ", X[:2, :])
gpr_predict = gpr.predict(X[:2, :], return_std=True)
print(gpr_predict)
def test_regression_synthetic():
# Test on synthetic regression datasets used in Leo Breiman,
# `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996).
random_state = check_random_state(1)
regression_params = {
"n_estimators": 100,
"max_depth": 4,
"min_samples_split": 2,
"learning_rate": 0.1,
"loss": "squared_error",
}
# Friedman1
X, y = datasets.make_friedman1(n_samples=1200, random_state=random_state, noise=1.0)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor()
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 5.0
# Friedman2
X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 1700.0
# Friedman3
X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingRegressor(**regression_params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
assert mse < 0.015
def test_all_regressors():
x, y = make_friedman2(10000)
x_train, y_train, x_test, y_test = test_helpers.split_dataset(x,y)
#print y_test[:100]
ols = LinearRegression()
ols.fit(x_train, y_train)
ols_pred = ols.predict(x_test)
#print ols_pred[:100]
ols_mse = mean_square_error(y_test, ols_pred)
for fn in regressors:
print fn
model = fn(x_train,y_train)
print model
pred = model.predict(x_test)
#print pred[:100]
mse = mean_square_error(y_test, pred)
print "OLS MSE:", ols_mse, " Current MSE:", mse
print "Ratio:", mse / ols_mse
assert ols_mse > 1.1*mse
def test_all_regressors():
x, y = make_friedman2(10000)
x_train, y_train, x_test, y_test = test_helpers.split_dataset(x, y)
#print y_test[:100]
ols = LinearRegression()
ols.fit(x_train, y_train)
ols_pred = ols.predict(x_test)
#print ols_pred[:100]
ols_mse = mean_square_error(y_test, ols_pred)
for fn in regressors:
print fn
model = fn(x_train, y_train)
print model
pred = model.predict(x_test)
#print pred[:100]
mse = mean_square_error(y_test, pred)
print "OLS MSE:", ols_mse, " Current MSE:", mse
print "Ratio:", mse / ols_mse
assert ols_mse > 1.1 * mse
def friedman2(n_samples=20000):
""" Generated data """
(data, target) = datasets.make_friedman2(n_samples=n_samples)
return DatasetFactory.Dataset(data=data, target=target)
def uniform_dataset(args):
X = np.random.random(size=(args.num_examples, args.num_features))
y = np.random.choice([-1, 1], size=args.num_examples)
return (X, y)
DATASETS = {
"uniform":
uniform_dataset,
"hastie":
lambda args: datasets.make_hastie_10_2(n_samples=args.num_examples),
"friedman1":
lambda args: datasets.make_friedman1(n_samples=args.num_examples,
n_features=args.num_features),
"friedman2":
lambda args: datasets.make_friedman2(n_samples=args.num_examples,
noise=args.noise),
"friedman3":
lambda args: datasets.make_friedman3(n_samples=args.num_examples,
noise=args.noise),
"make_regression":
lambda args: datasets.make_regression(n_samples=args.num_examples,
n_features=args.num_features,
n_informative=args.num_informative)
}
ENSEMBLE_REGRESSORS = [
("GB-D1", with_depth(ensemble.GradientBoostingRegressor, 1)),
("GB-D3", with_depth(ensemble.GradientBoostingRegressor, 3)),
("GB-B10", with_best_first(ensemble.GradientBoostingRegressor, 10)),
("RF-D1", with_depth(ensemble.RandomForestRegressor, 1)),
("RF-D3", with_depth(ensemble.RandomForestRegressor, 3)),
# filename = input('Введите путь файла для записи: ')
# Define the color maps for plots
color_map = plt.cm.get_cmap('RdYlBu')
color_map_discrete = matplotlib.colors.LinearSegmentedColormap.from_list(
"", ["red", "cyan", "magenta", "blue"])
fig = plt.figure(figsize=(18, 5))
x, y = dt.make_friedman1(n_samples=1000, n_features=5, random_state=rand_state)
dataset_x1 = x
dataset_y1 = y
ax = fig.add_subplot(131, projection='3d')
my_scatter_plot = ax.scatter(x[:, 0], x[:, 1], x[:, 2], c=y, cmap=color_map)
fig.colorbar(my_scatter_plot)
plt.title('make_friedman1')
x, y = dt.make_friedman2(n_samples=1000, random_state=rand_state)
dataset_x2 = x
dataset_y2 = y
ax = fig.add_subplot(132, projection='3d')
my_scatter_plot = ax.scatter(x[:, 0], x[:, 1], x[:, 2], c=y, cmap=color_map)
fig.colorbar(my_scatter_plot)
plt.title('make_friedman2')
x, y = dt.make_friedman3(n_samples=1000, random_state=rand_state)
dataset_x3 = x
dataset_y3 = y
ax = fig.add_subplot(133, projection='3d')
my_scatter_plot = ax.scatter(x[:, 0], x[:, 1], x[:, 2], c=y, cmap=color_map)
fig.colorbar(my_scatter_plot)
plt.suptitle('make_friedman?() for Non-Linear Data', fontsize=20)
plt.title('make_friedman3')
'''Friedman #2 data example'''
import rvm
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import mean_squared_error
from sklearn.datasets import make_friedman2
from sklearn.datasets import make_friedman3
print('Friedman data set')
np.random.seed(2)
n_exp = 1
rel_vec = 0
RMSE = 0
for i in range(n_exp):
train_x, train_y = make_friedman2(240, noise=0)
cl = rvm.RVMRegression(kernel="rbf", gamma=0.00001)
cl.fit(np.matrix(train_x), np.matrix(train_y.reshape(240, 1)))
rel_vec += len(cl.rel_ind)
valid_x, valid_y = make_friedman2(240)
pred_y = cl.predict(valid_x)
RMSE += mean_squared_error(valid_y, pred_y) ** 0.5
print("Vectors: ", rel_vec / n_exp)
print("Root mean square = ", RMSE / n_exp)
def getSKData(style='timeseries', n_samples=1, **kwargs):
if isinstance(style, str):
style = Style(style.lower())
if style == Style.REGRESSION:
return make_regression(
n_samples, kwargs.get('n_features', RegressionArgs.n_features),
kwargs.get('n_informative', RegressionArgs.n_informative),
kwargs.get('n_targets', RegressionArgs.n_targets),
kwargs.get('bias', RegressionArgs.bias),
kwargs.get('effective_rank', RegressionArgs.effective_rank),
kwargs.get('tail_strength', RegressionArgs.tail_strength),
kwargs.get('noise', RegressionArgs.noise),
kwargs.get('shuffle', RegressionArgs.shuffle),
kwargs.get('coef', RegressionArgs.coef),
kwargs.get('random_state', RegressionArgs.random_state))
elif style == Style.BLOBS:
return make_blobs(n_samples,
kwargs.get('n_features', BlobsArgs.n_features),
kwargs.get('centers', BlobsArgs.centers),
kwargs.get('cluster_std', BlobsArgs.cluster_std),
kwargs.get('center_box', BlobsArgs.center_box),
kwargs.get('shuffle', BlobsArgs.shuffle),
kwargs.get('random_state', BlobsArgs.random_state))
elif style == Style.CLASSIFICATION:
return make_classification(
n_samples, kwargs.get('n_features', ClassificationArgs.n_features),
kwargs.get('n_informative', ClassificationArgs.n_informative),
kwargs.get('n_redundant', ClassificationArgs.n_redundant),
kwargs.get('n_repeated', ClassificationArgs.n_repeated),
kwargs.get('n_classes', ClassificationArgs.n_classes),
kwargs.get('n_clusters_per_class',
ClassificationArgs.n_clusters_per_class),
kwargs.get('weights', ClassificationArgs.weights),
kwargs.get('flip_y', ClassificationArgs.flip_y),
kwargs.get('class_sep', ClassificationArgs.class_sep),
kwargs.get('hypercube', ClassificationArgs.hypercube),
kwargs.get('shift', ClassificationArgs.shift),
kwargs.get('scale', ClassificationArgs.scale),
kwargs.get('shuffle', ClassificationArgs.shuffle),
kwargs.get('random_state', ClassificationArgs.random_state))
elif style == Style.MULTILABEL:
return make_multilabel_classification(
n_samples,
kwargs.get('n_features', MultilabelClassificationArgs.n_features),
kwargs.get('n_classes', MultilabelClassificationArgs.n_classes),
kwargs.get('n_labels', MultilabelClassificationArgs.n_labels),
kwargs.get('length', MultilabelClassificationArgs.length),
kwargs.get('allow_unlabeled',
MultilabelClassificationArgs.allow_unlabeled),
kwargs.get('sparse', MultilabelClassificationArgs.sparse),
kwargs.get('return_indicator',
MultilabelClassificationArgs.return_indicator),
kwargs.get('return_distributions',
MultilabelClassificationArgs.return_distributions),
kwargs.get('random_state',
MultilabelClassificationArgs.random_state))
elif style == Style.GAUSSIAN:
return make_gaussian_quantiles(
n_samples=n_samples,
n_features=kwargs.get('n_features', GaussianArgs.n_features),
mean=kwargs.get('mean', GaussianArgs.mean),
cov=kwargs.get('cov', GaussianArgs.cov),
n_classes=kwargs.get('n_classes', GaussianArgs.n_classes),
shuffle=kwargs.get('shuffle', GaussianArgs.shuffle),
random_state=kwargs.get('random_state', GaussianArgs.random_state))
elif style == Style.HASTIE:
return make_hastie_10_2(n_samples,
random_state=kwargs.get(
'random_state', HastieArgs.random_state))
elif style == Style.CIRCLES:
return make_circles(
n_samples, kwargs.get('shuffle', CirclesArgs.shuffle),
kwargs.get('noise', CirclesArgs.noise),
kwargs.get('random_state', CirclesArgs.random_state),
kwargs.get('factor', CirclesArgs.factor))
elif style == Style.MOONS:
return make_moons(n_samples, kwargs.get('shuffle', MoonsArgs.shuffle),
kwargs.get('noise', MoonsArgs.noise),
kwargs.get('random_state', MoonsArgs.random_state))
elif style == Style.BICLUSTERS:
return make_biclusters(
kwargs.get('shape', BiclusterArgs.shape),
kwargs.get('n_clusters', BiclusterArgs.n_clusters),
kwargs.get('noise', BiclusterArgs.noise),
kwargs.get('minval', BiclusterArgs.minval),
kwargs.get('maxval', BiclusterArgs.maxval),
kwargs.get('shuffle', BiclusterArgs.shuffle),
kwargs.get('random_state', BiclusterArgs.random_state))
elif style == Style.SCURVE:
return make_s_curve(
n_samples, kwargs.get('noise', SCurveArgs.noise),
kwargs.get('random_state', SCurveArgs.random_state))
elif style == Style.CHECKER:
return make_checkerboard(
kwargs.get('shape', CheckerArgs.shape),
kwargs.get('n_clusters', CheckerArgs.n_clusters),
kwargs.get('noise', CheckerArgs.noise),
kwargs.get('minval', CheckerArgs.minval),
kwargs.get('maxval', CheckerArgs.maxval),
kwargs.get('shuffle', CheckerArgs.shuffle),
kwargs.get('random_state', CheckerArgs.random_state))
elif style == Style.FRIEDMAN:
return make_friedman1(
n_samples, kwargs.get('n_features', FriedmanArgs.n_features),
kwargs.get('noise', FriedmanArgs.noise),
kwargs.get('random_state', FriedmanArgs.random_state))
elif style == Style.FRIEDMAN2:
return make_friedman2(
n_samples, kwargs.get('noise', Friedman2Args.noise),
kwargs.get('random_state', Friedman2Args.random_state))
elif style == Style.FRIEDMAN3:
return make_friedman3(
n_samples, kwargs.get('noise', Friedman3Args.noise),
kwargs.get('random_state', Friedman3Args.random_state))
def prep_data_sklearn(dataset_name, test_size=0.2, model_class='realkd', downsample_size=None, norm_mean=False,
random_seed=None, pos_class=None):
target_name, without = dataset_signature(dataset_name)
if dataset_name == 'tic-tac-toe':
bunch = ds.fetch_openml(dataset_name)
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
df.rename(lambda s: s[:-7], axis='columns', inplace=True)
df.replace(0, 'b', inplace=True)
df.replace(1, 'o', inplace=True)
df.replace(2, 'x', inplace=True)
data_rf = pd.get_dummies(df)
target = pd.Series(where(bunch.target == 'positive', 1, -1))
elif dataset_name == 'kr - vs - kp':
bunch = ds.fetch_openml(data_id=3)
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
data_rf = pd.get_dummies(df)
target = pd.Series(where(bunch.target == 'won', 1, -1))
elif dataset_name == 'breast_cancer':
bunch = ds.load_breast_cancer()
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
data_rf = pd.get_dummies(df)
target = pd.Series(where(bunch.target == 1, 1, -1))
elif dataset_name == 'iris':
bunch = ds.load_iris()
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
data_rf = pd.get_dummies(df)
target = pd.Series(where(bunch.target == 1, 1, -1))
elif dataset_name == 'make_friedman1':
global_friedman_cols =10
data, target = ds.make_friedman1(n_samples=2000, n_features=10, noise=0.1, random_state=random_seed) # 1
no_cols = np.size(data, 1)
col_names = ['X' + str(i+1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(target)
elif dataset_name == 'make_friedman2':
data, target = ds.make_friedman2(n_samples=2000, noise=0.1, random_state=random_seed) # 1
no_cols = np.size(data, 1)
col_names = ['X' + str(i+1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(target)
elif dataset_name == 'make_friedman3':
data, target = ds.make_friedman3(n_samples=2000, noise=0.1, random_state=random_seed)
no_cols = np.size(data, 1)
col_names = ['X' + str(i+1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(target)
elif dataset_name == 'make_classification2':
data, target = ds.make_classification(n_samples=2000, n_features=8, n_classes=2,
hypercube=True, n_clusters_per_class=3,
n_informative=3, n_redundant=3, n_repeated=0,
random_state=random_seed)
no_cols = np.size(data, 1)
col_names = ['X' + str(i+1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(where(target == 1, 1, -1))
elif dataset_name == 'make_classification3':
data, target = ds.make_classification(n_samples=2000, n_features=15, n_classes=3,
hypercube=True, n_clusters_per_class=3,
n_informative=5, n_redundant=5, n_repeated=0,
random_state=random_seed)
no_cols = np.size(data, 1)
col_names = ['X' + str(i + 1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(where(target == 1, 1, -1))
elif dataset_name == 'load_wine':
bunch = ds.load_wine()
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
data_rf = pd.get_dummies(df)
target = pd.Series(where(bunch.target == 1, 1, -1))
elif dataset_name == 'make_hastie_10_2':
data, target = ds.make_hastie_10_2(n_samples=12000, random_state=random_seed)
no_cols = np.size(data, 1)
col_names = ['X' + str(i+1) for i in range(no_cols)]
data_rf = pd.DataFrame(data, columns=col_names)
target = pd.Series(where(target == 1, 1, -1))
elif dataset_name == 'load_diabetes':
bunch = ds.load_diabetes()
df = pd.DataFrame(bunch.data, columns=bunch.feature_names)
data_rf = pd.get_dummies(df)
target = pd.Series(bunch.target)
elif dataset_name[:-1] == 'noisy_pairity_':
d = int(dataset_name[-1])
data, target_name, random_seed = prep_noisy_pairity(d=d, random_seed=random_seed)
return data, target_name, random_seed
elif dataset_name == 'digits5':
data_rf, target = prep_digits()
x_train, x_test, y_train, y_test = train_test_split(data_rf, target, test_size=test_size, random_state=random_seed)
if downsample_size != None:
x_train[target_name] = y_train
sampled_train = x_train.sample(n=min(downsample_size, len(y_train)), random_state=random_seed)
x_train.reset_index(inplace=True, drop=True) # this may be unncessesary
y_train = sampled_train[target_name]
x_train = sampled_train.drop([target_name], axis='columns')
if norm_mean: # scikitlearn transformer.
target_train_mean = sum(y_train) / len(y_train)
y_train -= target_train_mean
y_test -= target_train_mean
y_train = [y_train, target_train_mean]
y_test = [y_test, target_train_mean]
data = [x_train, y_train, x_test, y_test]
n = (len(y_train), len(y_test))
return data, target_name, random_seed
from sklearn.gaussian_process import GaussianProcessClassifier from sklearn.datasets import make_friedman2 import matplotlib.pyplot as plt from sklearn.gaussian_process.kernels import Matern import numpy as np N = 10000 addns = 2 X, _ = make_friedman2(n_samples=N, noise=0, random_state=0) Xtrain = X[:int(0.7 * N)] Xpool = X[int(0.7 * N):int(0.8 * N)] Xtest = X[int(0.8 * N):] Xtrain = (Xtrain - np.mean(Xtrain)) / np.std(Xtrain) Xtest = (Xtest - np.mean(Xtest)) / np.std(Xtest) y = np.random.randint(2, size=N) ytrain = y[:int(0.7 * N)] ypool = X[int(0.7 * N):int(0.8 * N)] ytest = y[int(0.7 * N):] model = GaussianProcessClassifier() gp = model.fit(Xtrain, ytrain) preds = gp.predict_proba(Xtrain) preds = np.max(preds, axis=1) newXs = (1 - preds).argsort()[-addns:][::-1]
@logger.catch
def predict_proba(self, X, **kwargs):
prediction = self.model.predict_proba(X, **kwargs)
return prediction
@logger.catch
def partial_fit(self, X, y, **kwargs):
self.changed = True
self.model.partial_fit(X, y, **kwargs)
def fit(self, X, y, **kwargs):
self.changed = True
self.model.fit(X, y, **kwargs)
class CustomSklearnGaussianProcedure(SklearnProcedure):
def __init__(self, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)
kernel = DotProduct() + WhiteKernel()
gpr = GaussianProcessRegressor(kernel=kernel, random_state=0)
self.dictionary.model = gpr
if __name__ == "__main__":
general_procedure = CustomSklearnGaussianProcedure()
X, y = make_friedman2(n_samples=500, noise=0, random_state=0)
general_procedure.fit(X, y)
print(general_procedure.predict(X[:2, :], return_std=True))
# print(general_procedure.get_params())
print(general_procedure.extract())
import numpy as np import sklearn.datasets as Datasets import seaborn as sn import matplotlib.pyplot as plt X, y = Datasets.make_friedman2(200, 0.3) index = np.random.choice(range(len(X)), 3) center = X[index, :] print(center)
print("the output of load_wine() :: ", datasets.load_wine())
#make_blobs() excuted
print("the output of make_blobs() :: ", datasets.make_blobs())
#make_circles() executed
print("the output of make_circles() :: ", datasets.make_circles())
#make_classification() executed
print("the output of make_classification() :: ",
datasets.make_classification())
#make_friedman1() executed
print("the output of make_friedman1() :: ", datasets.make_friedman1())
#make_friedman2() executed
print("the output of make_friedman2() :: ", datasets.make_friedman2())
#make_friedman3() executed
print("the output of make_friedman3() :: ", datasets.make_friedman3())
#make_gaussian_quantiles() executed
print("the output of make_gaussian_quantiles() :: ",
datasets.make_gaussian_quantiles())
#make_hastie_10_2() executed
print("the output of make_hastie_10_2() :: ", datasets.make_hastie_10_2())
#make_moons() executed
print("the output of make_moons() :: ", datasets.make_moons())
#make_multilabel_classification() executed
from sklearn import datasets import matplotlib.pyplot as plt # make_friedman2 data X, y = datasets.make_friedman2(n_samples=100, noise=0.0, random_state=None) print(X) print(y)
try:
reload # Python 2.7
except NameError:
try:
from importlib import reload # Python 3.4+
except ImportError:
from imp import reload # Python 3.0 - 3.3
NNC = reload(NNC)
import tensorflow as tf
boston = sdata.load_boston()
diabetes = sdata.load_diabetes()
mf1 = sdata.make_friedman1(n_samples=2500)
mf2 = sdata.make_friedman2(n_samples=2500)
datas =\
[ [boston.data, boston.target, "boston"],
[diabetes.data, diabetes.target, "diabetes"],
[mf1[0], mf1[1], "friedman1"],
[mf2[0], mf2[1], "friedman2"],
]
dict_layers = lambda x,size :\
{ "I" : x,\
"N1" : size,\
"N2" : size,\
"N3" : size,\
"N4" : size,\
"N5" : size,\
def getSKData(style='timeseries', as_dataframe=False, n_samples=10, **kwargs):
if style == 'regression':
return make_regression(n_samples,
kwargs.get('n_features', RegressionArgs.n_features),
kwargs.get('n_informative', RegressionArgs.n_informative),
kwargs.get('n_targets', RegressionArgs.n_targets),
kwargs.get('bias', RegressionArgs.bias),
kwargs.get('effective_rank', RegressionArgs.effective_rank),
kwargs.get('tail_strength', RegressionArgs.tail_strength),
kwargs.get('noise', RegressionArgs.noise),
kwargs.get('shuffle', RegressionArgs.shuffle),
kwargs.get('coef', RegressionArgs.coef),
kwargs.get('random_state', RegressionArgs.random_state))
elif style == 'blobs':
return make_blobs(n_samples,
kwargs.get('n_features', BlobsArgs.n_features),
kwargs.get('centers', BlobsArgs.centers),
kwargs.get('cluster_std', BlobsArgs.cluster_std),
kwargs.get('center_box', BlobsArgs.center_box),
kwargs.get('shuffle', BlobsArgs.shuffle),
kwargs.get('random_state', BlobsArgs.random_state))
elif style == 'classification':
return make_classification(n_samples,
kwargs.get('n_features', ClassificationArgs.n_features),
kwargs.get('n_informative', ClassificationArgs.n_informative),
kwargs.get('n_redundant', ClassificationArgs.n_redundant),
kwargs.get('n_repeated', ClassificationArgs.n_repeated),
kwargs.get('n_classes', ClassificationArgs.n_classes),
kwargs.get('n_clusters_per_class', ClassificationArgs.n_clusters_per_class),
kwargs.get('weights', ClassificationArgs.weights),
kwargs.get('flip_y', ClassificationArgs.flip_y),
kwargs.get('class_sep', ClassificationArgs.class_sep),
kwargs.get('hypercube', ClassificationArgs.hypercube),
kwargs.get('shift', ClassificationArgs.shift),
kwargs.get('scale', ClassificationArgs.scale),
kwargs.get('shuffle', ClassificationArgs.shuffle),
kwargs.get('random_state', ClassificationArgs.random_state))
elif style == 'multilabel':
return make_multilabel_classification(n_samples,
kwargs.get('n_features', MultilabelClassificationArgs.n_features),
kwargs.get('n_classes', MultilabelClassificationArgs.n_classes),
kwargs.get('n_labels', MultilabelClassificationArgs.n_labels),
kwargs.get('length', MultilabelClassificationArgs.length),
kwargs.get('allow_unlabeled', MultilabelClassificationArgs.allow_unlabeled),
kwargs.get('sparse', MultilabelClassificationArgs.sparse),
kwargs.get('return_indicator', MultilabelClassificationArgs.return_indicator),
kwargs.get('return_distributions', MultilabelClassificationArgs.return_distributions),
kwargs.get('random_state', MultilabelClassificationArgs.random_state))
elif style == 'gaussian':
return make_gaussian_quantiles(n_samples=n_samples,
n_features=kwargs.get('n_features', GaussianArgs.n_features),
mean=kwargs.get('mean', GaussianArgs.mean),
cov=kwargs.get('cov', GaussianArgs.cov),
n_classes=kwargs.get('n_classes', GaussianArgs.n_classes),
shuffle=kwargs.get('shuffle', GaussianArgs.shuffle),
random_state=kwargs.get('random_state', GaussianArgs.random_state))
elif style == 'hastie':
return make_hastie_10_2(n_samples,
random_state=kwargs.get('random_state', HastieArgs.random_state))
elif style == 'circles':
return make_circles(n_samples,
kwargs.get('shuffle', CirclesArgs.shuffle),
kwargs.get('noise', CirclesArgs.noise),
kwargs.get('random_state', CirclesArgs.random_state),
kwargs.get('factor', CirclesArgs.factor))
elif style == 'moons':
return make_moons(n_samples,
kwargs.get('shuffle', MoonsArgs.shuffle),
kwargs.get('noise', MoonsArgs.noise),
kwargs.get('random_state', MoonsArgs.random_state))
elif style == 'biclusters':
x = make_biclusters(kwargs.get('shape', BiclusterArgs.shape),
kwargs.get('n_clusters', BiclusterArgs.n_clusters),
kwargs.get('noise', BiclusterArgs.noise),
kwargs.get('minval', BiclusterArgs.minval),
kwargs.get('maxval', BiclusterArgs.maxval),
kwargs.get('shuffle', BiclusterArgs.shuffle),
kwargs.get('random_state', BiclusterArgs.random_state))
if as_dataframe:
return pd.concat([pd.DataFrame(x[0]), pd.DataFrame(x[1].T)], axis=1)
else:
return x
elif style == 'scurve':
return make_s_curve(n_samples,
kwargs.get('noise', SCurveArgs.noise),
kwargs.get('random_state', SCurveArgs.random_state))
elif style == 'checker':
return make_checkerboard(kwargs.get('shape', CheckerArgs.shape),
kwargs.get('n_clusters', CheckerArgs.n_clusters),
kwargs.get('noise', CheckerArgs.noise),
kwargs.get('minval', CheckerArgs.minval),
kwargs.get('maxval', CheckerArgs.maxval),
kwargs.get('shuffle', CheckerArgs.shuffle),
kwargs.get('random_state', CheckerArgs.random_state))
elif style == 'friedman':
return make_friedman1(n_samples,
kwargs.get('n_features', FriedmanArgs.n_features),
kwargs.get('noise', FriedmanArgs.noise),
kwargs.get('random_state', FriedmanArgs.random_state))
elif style == 'friedman2':
return make_friedman2(n_samples,
kwargs.get('noise', Friedman2Args.noise),
kwargs.get('random_state', Friedman2Args.random_state))
elif style == 'friedman3':
return make_friedman3(n_samples,
kwargs.get('noise', Friedman3Args.noise),
kwargs.get('random_state', Friedman3Args.random_state))
def with_best_first(cls, max_leaf_nodes):
return partial(cls, max_leaf_nodes=max_leaf_nodes)
def uniform_dataset(args):
X = np.random.random(size=(args.num_examples, args.num_features))
y = np.random.choice([-1, 1], size=args.num_examples)
return (X, y)
DATASETS = {
"uniform": uniform_dataset,
"hastie": lambda args: datasets.make_hastie_10_2(
n_samples=args.num_examples),
"friedman1": lambda args: datasets.make_friedman1(
n_samples=args.num_examples, n_features=args.num_features),
"friedman2": lambda args: datasets.make_friedman2(
n_samples=args.num_examples, noise=args.noise),
"friedman3": lambda args: datasets.make_friedman3(
n_samples=args.num_examples, noise=args.noise),
"make_regression": lambda args: datasets.make_regression(
n_samples=args.num_examples,
n_features=args.num_features,
n_informative=args.num_informative)
}
ENSEMBLE_REGRESSORS = [
("GB-D1", with_depth(ensemble.GradientBoostingRegressor, 1)),
("GB-D3", with_depth(ensemble.GradientBoostingRegressor, 3)),
("GB-B10", with_best_first(ensemble.GradientBoostingRegressor, 10)),
("RF-D1", with_depth(ensemble.RandomForestRegressor, 1)),
("RF-D3", with_depth(ensemble.RandomForestRegressor, 3)),
("RF-D5", with_depth(ensemble.RandomForestRegressor, 5)),
