from sklearn.neighbors.classification import KNeighborsClassifier
from sklearn.datasets import make_classification
from sklearnext.tools import BinaryExperiment
from sklearnext.over_sampling import SMOTE, GeometricSMOTE
# Generate datasets
datasets = [
('A', make_classification(random_state=1, weights=[0.80, 0.20], n_features=10)),
('B', make_classification(random_state=1, weights=[0.85, 0.15], n_features=10)),
('C', make_classification(random_state=1, weights=[0.90, 0.10], n_features=10))
]
# Oversamplers and classifiers
oversamplers = [
('NO OVERSAMPLING', None),
('SMOTE', SMOTE(random_state=0), {'k_neighbors':[3, 4]}),
('G-SMOTE', GeometricSMOTE(random_state=0), {
'k_neighbors':[3, 4],
'deformation_factor': [0.25, 0.50, 0.75],
'truncation_factor': [-0.5, 0.0, 0.5]
}
)
]
classifiers = [
('DT', DecisionTreeClassifier(), {'max_depth': [3, 4, 5]}),
('KNN', KNeighborsClassifier(), {'n_neighbors':[3, 5]}),
]
# Define experiment
experiment = BinaryExperiment(
name='example',
from sklearn.neighbors.classification import KNeighborsClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearnext.over_sampling import RandomOverSampler, SMOTE, GeometricSMOTE, DensityDistributor
from sklearnext.cluster import SOM
from sklearnext.tools import evaluate_binary_imbalanced_experiments, read_csv_dir, summarize_binary_datasets
# Paths
datasets_path = join(dirname(__file__), '..', '..', 'data',
'binary-numerical-imbalanced')
results_path = join(dirname(__file__), '..', '..', 'data', 'results', 'gsomo')
# Oversamplers and classifiers
oversamplers = [
('NO OVERSAMPLING', None),
('RANDOM OVERSAMPLING', RandomOverSampler(random_state=0)),
('SMOTE', SMOTE(random_state=1), {
'k_neighbors': [3, 5]
}),
('G-SOMO',
GeometricSMOTE(clusterer=SOM(),
distributor=DensityDistributor(distances_exponent=2,
filtering_threshold=1.0),
random_state=3), {
'k_neighbors': [3, 5],
'truncation_factor': [-1.0, 0.0, 0.25, 1.0],
'deformation_factor': [0.0, 0.5, 1.0],
'clusterer__n_clusters': [0.2, 0.5],
'distributor__distribution_ratio': [0.75, 1.0]
})
]
classifiers = [('LR', LogisticRegression()),
from imblearn.pipeline import Pipeline
from sklearnext.cluster import KMeans
from sklearnext.model_selection import ModelSearchCV
from sklearnext.over_sampling import SMOTE
from sklearnext.over_sampling.base import DensityDistributor
from sklearnext.tools import report_model_search_results
# Load data
X, y = make_classification(n_informative=15,
n_clusters_per_class=3,
weights=[0.9, 0.1])
# Define estimators
estimators = [('GBC', GradientBoostingClassifier()),
('SMOTE+GBC',
Pipeline([('smote', SMOTE()),
('gbc', GradientBoostingClassifier())])),
('KMeanSMOTE+GBC',
Pipeline([('smote',
SMOTE(clusterer=KMeans(n_init=1),
distributor=DensityDistributor())),
('gbc', GradientBoostingClassifier())]))]
# Define parameters grid
param_grids = [{
'SMOTE+GBC__smote__k_neighbors': [2, 3, 4, 5],
'SMOTE+GBC__gbc__max_depth': [2, 4]
}, {
'KMeanSMOTE+GBC__smote__k_neighbors': [2, 3, 4, 5],
'KMeanSMOTE+GBC__smote__clusterer__n_clusters':
[0.1, 0.3, 0.5, 0.7, 0.9, 1.0],
def generate_oversamplers(oversamplers_names):
"Generate oversamplers."
oversamplers = [
('NO OVERSAMPLING', None, {}),
('RANDOM OVERSAMPLING', RandomOverSampler(), {}),
('SMOTE', SMOTE(), {
'k_neighbors': [3, 5]
}), ('BORDERLINE SMOTE', BorderlineSMOTE(), {
'k_neighbors': [3, 5]
}), ('ADASYN', ADASYN(), {
'n_neighbors': [2, 3]
}),
('G-SMOTE', GeometricSMOTE(), {
'k_neighbors': [3, 5],
'selection_strategy': ['combined', 'minority', 'majority'],
'truncation_factor': [-1.0, -0.5, .0, 0.25, 0.5, 0.75, 1.0],
'deformation_factor': [.0, 0.2, 0.4, 0.5, 0.6, 0.8, 1.0]
}),
('K-MEANS RANDOM OVERSAMPLING',
RandomOverSampler(clusterer=KMeans(),
distributor=DensityDistributor()),
{
'k_neighbors': [3,
5],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0]
}),
('K-MEANS SMOTE',
SMOTE(clusterer=KMeans(), distributor=DensityDistributor()), {
'k_neighbors': [3, 5],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0]
}),
('K-MEANS BORDERLINE SMOTE',
BorderlineSMOTE(clusterer=KMeans(), distributor=DensityDistributor()),
{
'k_neighbors': [3, 5],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0]
}),
('K-MEANS G-SMOTE',
GeometricSMOTE(clusterer=KMeans(), distributor=DensityDistributor()),
{
'k_neighbors':
[3, 5],
'selection_strategy': ['combined', 'minority', 'majority'],
'truncation_factor': [-1.0, -0.5, .0, 0.25, 0.5, 0.75, 1.0],
'deformation_factor': [.0, 0.2, 0.4, 0.5, 0.6, 0.8, 1.0],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0]
}),
('SOMO', SMOTE(clusterer=SOM(), distributor=DensityDistributor()), {
'k_neighbors': [3, 5],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0],
'distributor__distribution_ratio': [0.0, 0.25, 0.5, 0.75, 1.0]
}),
('G-SOMO',
GeometricSMOTE(clusterer=SOM(), distributor=DensityDistributor()), {
'k_neighbors': [3, 5],
'selection_strategy': ['combined', 'minority', 'majority'],
'truncation_factor': [-1.0, -0.5, .0, 0.25, 0.5, 0.75, 1.0],
'deformation_factor': [.0, 0.2, 0.4, 0.5, 0.6, 0.8, 1.0],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0],
'distributor__distribution_ratio': [0.0, 0.25, 0.5, 0.75, 1.0]
})
]
if oversamplers_names in ('basic', 'scaled', 'undersampled'):
oversamplers = select_pipelines(
oversamplers, ('NO OVERSAMPLING', 'RANDOM OVERSAMPLING', 'SMOTE',
'BORDERLINE SMOTE', 'ADASYN', 'G-SMOTE'))
if oversamplers_names == 'scaled':
oversamplers = append_transformer(MinMaxScaler(), oversamplers)
elif oversamplers_names == 'undersampled':
oversamplers = set_sampling_strategy(
lambda y: generate_sampling_strategy(y, 1 / 3), oversamplers)
oversamplers = append_transformer(
RandomUnderSampler(
sampling_strategy=lambda y: generate_sampling_strategy(y, 3)),
oversamplers)
return oversamplers
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors.classification import KNeighborsClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearnext.cluster import KMeans
from sklearnext.tools import evaluate_binary_imbalanced_experiments, read_csv_dir, summarize_binary_datasets
from sklearnext.over_sampling import SMOTE, DensityDistributor
# Paths
datasets_path = join(dirname(__file__), '..', '..', 'data',
'binary-numerical-imbalanced')
results_path = join(dirname(__file__), '..', '..', 'data', 'results',
'kmeans-oversampling', 'smote')
# Oversamplers and classifiers
oversamplers = [('NO OVERSAMPLING', None),
('SMOTE', SMOTE(random_state=0), {
'k_neighbors': [3, 5]
}),
('K-MEANS SMOTE',
SMOTE(clusterer=KMeans(random_state=1, n_init=1),
distributor=DensityDistributor(),
random_state=0), {
'k_neighbors': [3, 5],
'clusterer__n_clusters':
[0.0, 0.25, 0.5, 0.75, 1.0],
'distributor__distances_exponent': [0, 1, 2],
'distributor__filtering_threshold': [0.5, 1.0]
})]
classifiers = [('LR', LogisticRegression()),
('KNN', KNeighborsClassifier(), {
'n_neighbors': [3, 5]
from sklearn.neighbors.classification import KNeighborsClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearnext.cluster import KMeans, SOM, AgglomerativeClustering, Birch, SpectralClustering
from sklearnext.tools import evaluate_binary_imbalanced_experiments, read_csv_dir, summarize_binary_datasets
from sklearnext.over_sampling import SMOTE, DensityDistributor
# Paths
datasets_path = join(dirname(__file__), '..', '..', 'data',
'binary-numerical-imbalanced')
results_path = join(dirname(__file__), '..', '..', 'data', 'results',
'clustering-smote')
# Oversamplers and classifiers
oversamplers = [
('NO OVERSAMPLING', None),
('SMOTE', SMOTE(random_state=0), {
'k_neighbors': [3, 4, 5]
}),
('K-MEANS SMOTE',
SMOTE(clusterer=KMeans(random_state=1),
distributor=DensityDistributor(),
random_state=0), {
'k_neighbors': [3, 4, 5],
'clusterer__n_clusters':
[0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0],
'distributor__distances_exponent': [0, 1, 2, 5],
'distributor__filtering_threshold': [0.0, 0.5, 1.0, 2.0]
}),
('SOMO',
SMOTE(clusterer=SOM(), distributor=DensityDistributor(),
random_state=0), {
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors.classification import KNeighborsClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearnext.cluster import KMeans
from sklearnext.tools import evaluate_binary_imbalanced_experiments, read_csv_dir, summarize_binary_datasets
from sklearnext.over_sampling import SMOTE, DensityDistributor
# Paths
datasets_path = join(dirname(__file__), '..', '..', 'data', 'binary-numerical-imbalanced')
results_path = join(dirname(__file__), '..', '..', 'data', 'results', 'kmeans-oversampling', 'borderline-smote')
# Oversamplers and classifiers
oversamplers = [
('NO OVERSAMPLING', None),
('BORDERLINE-SMOTE', SMOTE(random_state=0, kind='borderline1'), {'k_neighbors': [3, 5]}),
('K-MEANS BORDERLINE-SMOTE', SMOTE(clusterer=KMeans(random_state=1, n_init=1), distributor=DensityDistributor(), random_state=0, kind='borderline1'), {
'k_neighbors': [3, 5],
'clusterer__n_clusters': [0.0, 0.25, 0.5, 0.75, 1.0],
'distributor__distances_exponent': [0, 1, 2],
'distributor__filtering_threshold': [0.5, 1.0]
}
)
]
classifiers = [
('LR', LogisticRegression()),
('KNN', KNeighborsClassifier(), {'n_neighbors': [3, 5]}),
('DT', DecisionTreeClassifier(random_state=2), {'max_depth': [3, 6]}),
('GBC', GradientBoostingClassifier(random_state=3), {'max_depth':[3, 6], 'n_estimators': [50, 100]})
]