def smoter(df):
IDs = df.Quote_ID
target = df.QuoteConversion_Flag
data = df.drop(['QuoteConversion_Flag'], axis=1).values
print("Before SMOTE: ", sorted(Counter(target).items()))
####
# ENN
####
enn = ENN(sampling_strategy="not majority",
kind_sel="mode",
n_neighbors=5,
n_jobs=-1,
random_state=RANDOM_STATE)
smote_enn = SMOTEENN(enn=enn, random_state=RANDOM_STATE)
X_resampled, y_resampled = smote_enn.fit_resample(data, target)
print("SMOTE ENN: ", sorted(Counter(y_resampled).items()))
####
# Tomeks
####
# smote_tomek = SMOTETomek(random_state=0)
# X_resampled, y_resampled = smote_tomek.fit_resample(data, target)
# print("Using SMOTE: ", sorted(Counter(y_resampled).items()))
data = pd.DataFrame(data=X_resampled, columns=FIELDS)
target = pd.DataFrame(data=y_resampled, columns=['QuoteConversion_Flag'])
return data, target
def balance_smote(features, target):
#only balancing training data so test data doesn't overfit
oversample = SMOTE(sampling_strategy=0.3,
k_neighbors=5,
random_state=config.RANDOM_STATE)
undersample = ENN(n_neighbors=5)
pipeline = make_pipeline(oversample, undersample)
features, target = pipeline.fit_resample(features, target)
return features, target
def renn_sampling(X,Y):
enn = ENN(return_indices=True)
nsamples, nx, ny = X.shape
print(X.shape)
X = X.reshape((nsamples, nx*ny))
X, Y, idx_resampled = enn.fit_sample(X,Y)
nsamples, ny = X.shape
print(X.shape)
X = X.reshape((nsamples, nx, ny/nx))
Y = Y.reshape((nsamples, 1))
return X, Y
def test_pipeline_fit_then_sample_of_three_samplers_with_sampler_last_estimator():
X, y = make_classification(n_classes=2, class_sep=2, weights=[0.1, 0.9],
n_informative=3, n_redundant=1, flip_y=0,
n_features=20, n_clusters_per_class=1,
n_samples=50000, random_state=0)
rus = RandomUnderSampler(random_state=42)
enn = ENN()
pipeline = make_pipeline(rus, enn, rus)
X_fit_sample_resampled, y_fit_sample_resampled = pipeline.fit_sample(X,y)
pipeline = make_pipeline(rus, enn, rus)
pipeline.fit(X,y)
X_fit_then_sample_resampled, y_fit_then_sample_resampled = pipeline.sample(X,y)
assert_array_equal(X_fit_sample_resampled, X_fit_then_sample_resampled)
assert_array_equal(y_fit_sample_resampled, y_fit_then_sample_resampled)
def fit_resample(self, X, y):
"""
Resample the dataset.
First standardize X, then perform SMOTEENN, then de-standardize
to return results in the same "units" as input.
Parameters
----------
X : ndarray
Dense, feature matrix where rows are observations.
y : ndarray
1-D array of responses.
Returns
-------
X_resample, y_resampled : ndarray, ndarray
Resampled X and y in the original "units" of X.
"""
ss = StandardScaler()
X_std = ss.fit_transform(X)
sm = SMOTEENN(
sampling_strategy=self.sampling_strategy_smoteenn,
random_state=self.random_state,
smote=SMOTE(
random_state=self.random_state,
k_neighbors=self.k_smote,
sampling_strategy=self.sampling_strategy_smote,
),
enn=ENN(
sampling_strategy=self.sampling_strategy_enn,
n_neighbors=self.k_enn,
kind_sel=self.kind_sel_enn,
),
)
X_res, y_res = sm.fit_resample(X_std, y)
return ss.inverse_transform(X_res), y_res
print(classification_report(Y_test,predictions))
print("Balanced Accuracy:",balanced_accuracy_score(Y_test, predictions))
# print("best parameters Random Forest",model_rf.best_params_)f
t1 = pl.time.time() - t0
print("Time taken: {:.0f} min {:.0f} secs".format(*divmod(t1, 60)))
print("best parameters:",GB_model.best_params_)
plot_confusion_matrix(confusion_matrix(Y_test,predictions),['Dolphin','Non-Dolphin'])
#13th Test----------------------MLP-------------------------------- simple
from sklearn.neural_network import MLPClassifier
from imblearn.under_sampling import TomekLinks
from imblearn.under_sampling import EditedNearestNeighbours as ENN
from imblearn.combine import SMOTETomek
param={"activation": ['identity', 'logistic', 'tanh', 'relu'], "alpha": [0.0001, 0.001, 0.01, 0.1,1], "learning_rate_init": [0.0001, 0.001, 0.01, 0.1,1] , "solver":['lbfgs', 'sgd', 'adam']}
t0 = pl.time.time()
sample=SMOTETomek(random_state=49, sampling_strategy='minority')
sample= ENN()
Xtrain_sample, Ytrain_sample= sample.fit_sample(X_train, Y_train)
mlp_model = GridSearchCV(MLPClassifier(random_state=49, max_iter=5000, hidden_layer_sizes=(5,2), activation='identity', alpha=0.0001, learning_rate_init=0.0001, solver='lbfgs'),param,cv=3)
mlp_model= MLPClassifier(random_state=49, max_iter=5000, hidden_layer_sizes=(6,4), activation='relu', alpha=0.0001, solver='lbfgs')
mlp_model.fit(Xtrain_sample, Ytrain_sample.values.ravel())
predictions = mlp_model.predict(X_test)
from sklearn.metrics import classification_report, confusion_matrix, balanced_accuracy_score
print(confusion_matrix(Y_test,predictions))
print(classification_report(Y_test,predictions))
print("Balanced Accuracy:",balanced_accuracy_score(Y_test, predictions))
# print("best parameters MLP",mlp_model.best_params_)
t1 = pl.time.time() - t0
print("Time taken: {:.0f} min {:.0f} secs".format(*divmod(t1, 60)))
plot_confusion_matrix(confusion_matrix(Y_test,predictions),['Dolphin','Non-Dolphin'])
