def test_bootstrap_samples():
# Test that bootstrapping samples generate non-perfect base estimators.
X, y = make_imbalance(iris.data, iris.target, ratio={0: 20, 1: 25, 2: 50},
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
random_state=0)
base_estimator = DecisionTreeClassifier().fit(X_train, y_train)
# without bootstrap, all trees are perfect on the training set
# disable the resampling by passing an empty dictionary.
ensemble = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
max_samples=1.0,
bootstrap=False,
n_estimators=10,
ratio={},
random_state=0).fit(X_train, y_train)
assert (ensemble.score(X_train, y_train) ==
base_estimator.score(X_train, y_train))
# with bootstrap, trees are no longer perfect on the training set
ensemble = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
max_samples=1.0,
bootstrap=True,
random_state=0).fit(X_train, y_train)
assert (ensemble.score(X_train, y_train) <
base_estimator.score(X_train, y_train))
def test_bootstrap_samples():
# Test that bootstrapping samples generate non-perfect base estimators.
X, y = make_imbalance(iris.data, iris.target, ratio={0: 20, 1: 25, 2: 50},
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
random_state=0)
base_estimator = DecisionTreeClassifier().fit(X_train, y_train)
# without bootstrap, all trees are perfect on the training set
# disable the resampling by passing an empty dictionary.
ensemble = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
max_samples=1.0,
bootstrap=False,
n_estimators=10,
ratio={},
random_state=0).fit(X_train, y_train)
assert (ensemble.score(X_train, y_train) ==
base_estimator.score(X_train, y_train))
# with bootstrap, trees are no longer perfect on the training set
ensemble = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
max_samples=1.0,
bootstrap=True,
random_state=0).fit(X_train, y_train)
assert (ensemble.score(X_train, y_train) <
base_estimator.score(X_train, y_train))
def test_oob_score_classification():
# Check that oob prediction is a good estimation of the generalization
# error.
X, y = make_imbalance(iris.data,
iris.target,
sampling_strategy={
0: 20,
1: 25,
2: 50
},
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
for base_estimator in [DecisionTreeClassifier(), SVC(gamma='scale')]:
clf = BalancedBaggingClassifier(base_estimator=base_estimator,
n_estimators=100,
bootstrap=True,
oob_score=True,
random_state=0).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert abs(test_score - clf.oob_score_) < 0.1
# Test with few estimators
assert_warns(
UserWarning,
BalancedBaggingClassifier(base_estimator=base_estimator,
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=0).fit, X_train, y_train)
def test_oob_score_classification():
# Check that oob prediction is a good estimation of the generalization
# error.
X, y = make_imbalance(iris.data, iris.target, ratio={0: 20, 1: 25, 2: 50},
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y,
random_state=0)
for base_estimator in [DecisionTreeClassifier(), SVC()]:
clf = BalancedBaggingClassifier(
base_estimator=base_estimator,
n_estimators=100,
bootstrap=True,
oob_score=True,
random_state=0).fit(X_train, y_train)
test_score = clf.score(X_test, y_test)
assert abs(test_score - clf.oob_score_) < 0.1
# Test with few estimators
assert_warns(UserWarning,
BalancedBaggingClassifier(
base_estimator=base_estimator,
n_estimators=1,
bootstrap=True,
oob_score=True,
random_state=0).fit,
X_train,
y_train)
print('Validation Results')
print(clf_rf.score(x_val, y_val))
print(recall_score(y_val, clf_rf.predict(x_val)))
print(precision_score(y_val, clf_rf.predict(x_val)))
print('\nTest Results')
print(clf_rf.score(data_features_test, data_labels_test))
print(recall_score(data_labels_test, clf_rf.predict(data_features_test)))
print(precision_score(data_labels_test, clf_rf.predict(data_features_test)))
print("END")
bbc = BalancedBaggingClassifier(random_state=12)
bbc.fit(x_train, np.array(y_train.iloc[:, 0]))
print('Validation Results')
print(bbc.score(x_val, y_val))
print(recall_score(y_val, bbc.predict(x_val)))
print(precision_score(y_val, bbc.predict(x_val)))
print('\nTest Results')
print(bbc.score(data_features_test, data_labels_test))
print(recall_score(data_labels_test, bbc.predict(data_features_test)))
print(precision_score(data_labels_test, bbc.predict(data_features_test)))
clf_xg = GradientBoostingClassifier(learning_rate=0.15,
n_estimators=70,
min_samples_split=0.5,
min_samples_leaf=45,
max_depth=8,
max_features='sqrt',
subsample=0.8)
clf_xg.fit(x_train_res, y_train_res)
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
import pandas as pd
from src.evaluation_methods import *
from imblearn.under_sampling import RandomUnderSampler
if __name__ == '__main__':
df = pd.read_excel('../../data_base/excel/datasetV2.xlsx', sheet_name='Casos Dengue')
x, y = df.iloc[:, :-1].values, df.iloc[:, -1:].values
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0, stratify=y)
under_sampler = RandomUnderSampler()
x_train, y_train = under_sampler.fit_resample(x_train, y_train)
#us = NearMiss(n_neighbors=3, version=2)
#X_train_res, y_train_res = us.fit_sample(x_train, y_train)
print("Distribution before resampling {}".format(y_train.shape))
bbc = BalancedBaggingClassifier(base_estimator=DecisionTreeClassifier(),
sampling_strategy='auto',
replacement=False,
random_state=0)
# Train the classifier.
bbc.fit(x_train, y_train)
pred_y = bbc.predict(x_test)
y_predict = bbc.predict(x_test)
print('Test Accuracy: %.3f' % bbc.score(x_test, y_test))
confusionMatrix(y_test, y_predict)
