def smote_data(data_train, target_train):
y = np.bincount(target_train)
ratio = 1.5 # float(y[2] + y[1]) / float(y[0])
# smote = SMOTE(ratio=ratio, verbose=True, kind='regular')
# smox, smoy = smote.fit_transform(data_train, target_train)
OS = OverSampler(ratio=ratio, verbose=True)
osx, osy = OS.fit_transform(data_train, target_train)
return osx, osy
def oversample_data(X_t, y_t, ratio):
x_columns = X_t.columns
X_t = X_t.reset_index(drop=True).as_matrix()
y_t = y_t.reset_index(drop=True).as_matrix()
smote = OverSampler(ratio=ratio, verbose=False)
smox, smoy = smote.fit_transform(X_t, y_t)
X_t = pd.DataFrame(smox, columns=x_columns)
y_t = pd.Series(smoy)
return X_t, y_t
def split(self, x_data, y_data):
Xt, Yt, Xv, Yv = super(OverUnderSplitter, self).split(x_data, y_data)
Xt_smote, Yt_smote = OverSampler(
ratio=self._over_sample).fit_transform(Xt.as_matrix(),
Yt.as_matrix())
Xt_smote, Yt_smote = UnderSampler(
ratio=self._under_sample).fit_transform(Xt_smote, Yt_smote)
return Xt_smote, Yt_smote, Xv, Yv
def test_rest(x, y):
print('Random under-sampling')
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
print('Tomek links')
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
print('NearMiss-1')
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
print('NearMiss-2')
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
print('NearMiss-3')
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(verbose=verbose)
ncrx, ncry = NCR.fit_transform(x, y)
print('Random over-sampling')
OS = OverSampler(verbose=verbose)
ox, oy = OS.fit_transform(x, y)
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose)
sennx, senny = SENN.fit_transform(x, y)
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(x, y)
def sampling():
verbose = False
y = np.bincount(target_train1)
print y
ratio = float(y[2]) / float(y[1])
# 'Random over-sampling'
OS = OverSampler(ratio=ratio, verbose=verbose)
osx, osy = OS.fit_transform(data_train1, target_train1)
random_methods(osx,osy)
# 'SMOTE'
smote = SMOTE(ratio=ratio, verbose=verbose, kind='regular')
smox, smoy = smote.fit_transform(data_train1, target_train1)
random_methods(smox,smoy)
# 'SMOTE bordeline 1'
bsmote1 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline1')
bs1x, bs1y = bsmote1.fit_transform(data_train, target_train)
random_methods(bs1x,bs1y)
# 'SMOTE bordeline 2'
bsmote2 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline2')
bs2x, bs2y = bsmote2.fit_transform(data_train1, target_train1)
random_methods(bs2x,bs2y)
# 'SMOTE SVM'
svm_args={'class_weight' : 'auto'}
svmsmote = SMOTE(ratio=ratio, verbose=verbose, kind='svm', **svm_args)
svsx, svsy = svmsmote.fit_transform(data_train1, target_train1)
random_methods(svsx,svsy)
# 'SMOTE Tomek links'
STK = SMOTETomek(ratio=ratio, verbose=verbose)
stkx, stky = STK.fit_transform(data_train1, target_train1)
random_methods(stkx,stky)
# 'SMOTE ENN'
SENN = SMOTEENN(ratio=ratio, verbose=verbose)
ennx, enny = SENN.fit_transform(data_train1, target_train1)
random_methods(ennx,enny)
# 'EasyEnsemble'
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(data_train1, target_train1)
random_methods(eex,eey)
# 'BalanceCascade'
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(data_train1, target_train1)
random_methods(bsx,bsy)
def _parallel_build_trees(tree, forest, X, y):
if forest.sampling is None:
sampler = BootstrapSampler(random_state=tree.random_state)
elif forest.sampling == 'up':
sampler = OverSampler(random_state=tree.random_state, verbose=False)
elif forest.sampling == 'down':
sampler = UnderSampler(random_state=tree.random_state, verbose=False)
X_sample, y_sample = sampler.fit_transform(X, y)
tree.fit(X_sample, y_sample, check_input=False)
return tree
def _sample_values(X, y, method=None, ratio=1, verbose=False):
"""Perform any kind of sampling(over and under).
Parameters
----------
X : array, shape = [n_samples, n_features]
Data.
y : array, shape = [n_samples]
Target.
method : str, optional default: None
Over or under smapling method.
ratio: float
Unbalanced class ratio.
Returns
-------
X, y : tuple
Sampled X and y.
"""
if method == 'SMOTE':
sampler = SMOTE(ratio=ratio, verbose=verbose)
elif method == 'SMOTEENN':
ratio = ratio * 0.3
sampler = SMOTEENN(ratio=ratio, verbose=verbose)
elif method == 'random_over_sample':
sampler = OverSampler(ratio=ratio, verbose=verbose)
elif method == 'random_under_sample':
sampler = UnderSampler(verbose=verbose)
elif method == 'TomekLinks':
sampler = TomekLinks(verbose=verbose)
return sampler.fit_transform(X, y)
def random_over_sampling(self):
OS = OverSampler(ratio=self._ratio, verbose=self.verbose)
osx, osy = OS.fit_transform(self.x, self.y)
return osx, osy
def apply_sampling(X_data, Y_data, sampling, n_states, maxlen):
ratio = float(np.count_nonzero(Y_data == 1)) / \
float(np.count_nonzero(Y_data == 0))
X_data = np.reshape(X_data, (len(X_data), n_states * maxlen))
# 'Random over-sampling'
if sampling == 'OverSampler':
OS = OverSampler(ratio=ratio, verbose=True)
# 'Random under-sampling'
elif sampling == 'UnderSampler':
OS = UnderSampler(verbose=True)
# 'Tomek under-sampling'
elif sampling == 'TomekLinks':
OS = TomekLinks(verbose=True)
# Oversampling
elif sampling == 'SMOTE':
OS = SMOTE(ratio=1, verbose=True, kind='regular')
# Oversampling - Undersampling
elif sampling == 'SMOTETomek':
OS = SMOTETomek(ratio=ratio, verbose=True)
# Undersampling
elif sampling == 'OneSidedSelection':
OS = OneSidedSelection(verbose=True)
# Undersampling
elif sampling == 'CondensedNearestNeighbour':
OS = CondensedNearestNeighbour(verbose=True)
# Undersampling
elif sampling == 'NearMiss':
OS = NearMiss(version=1, verbose=True)
# Undersampling
elif sampling == 'NeighbourhoodCleaningRule':
OS = NeighbourhoodCleaningRule(verbose=True)
# ERROR: WRONG SAMPLER, TERMINATE
else:
print('Wrong sampling variable you have set... Exiting...')
sys.exit()
# print('shape ' + str(X.shape))
X_data, Y_data = OS.fit_transform(X_data, Y_data)
return X_data, Y_data
del df['ID']
id = df_test['ID']
del df_test['ID']
from src.transfomations import remove_correlated
_, to_remove = remove_correlated(df, 0.99)
df_test.drop(to_remove, axis=1, inplace=True)
variance_threshold = VarianceThreshold(threshold=0.001)
df = variance_threshold.fit_transform(df)
ratio = float(sum(target)) / float(len(target) - sum(target))
print(ratio)
smote = OverSampler(ratio=ratio * 2, verbose=True)
print(type(target))
# df, target = smote.fit_transform(df.as_matrix(), target.as_matrix())
df_test = variance_threshold.fit(df_test)
gbc = GradientBoostingClassifier()
gbc.fit(df, target)
# best = randomizedSearch.best_estimator_
# print(randomizedSearch.best_params_)
scores = cross_validation.cross_val_score(gbc,
df,
target,
cv=5,
scoring='roc_auc',
edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
axes[2, 1].set_title('One-sided selection', fontsize=fs)
# Neighboorhood cleaning rule
axes[2, 2].scatter(ncrx_vis[ncry==0, 0], ncrx_vis[ncry==0, 1], label="Class #0", alpha=0.5,
edgecolor=almost_black, facecolor=palette[0], linewidth=0.15)
axes[2, 2].scatter(ncrx_vis[ncry==1, 0], ncrx_vis[ncry==1, 1], label="Class #1", alpha=0.5,
edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
axes[2, 2].set_title('Neighboorhood cleaning rule', fontsize=fs)
plt.show()
# Generate the new dataset using under-sampling method
verbose = False
ratio = float(np.count_nonzero(y==1)) / float(np.count_nonzero(y==0))
# 'Random over-sampling'
OS = OverSampler(ratio=ratio, verbose=verbose)
osx, osy = OS.fit_transform(x, y)
# 'SMOTE'
smote = SMOTE(ratio=ratio, verbose=verbose, kind='regular')
smox, smoy = smote.fit_transform(x, y)
# 'SMOTE bordeline 1'
bsmote1 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline1')
bs1x, bs1y = bsmote1.fit_transform(x, y)
# 'SMOTE bordeline 2'
bsmote2 = SMOTE(ratio=ratio, verbose=verbose, kind='borderline2')
bs2x, bs2y = bsmote2.fit_transform(x, y)
# 'SMOTE SVM'
svm_args={'class_weight' : 'auto'}
svmsmote = SMOTE(ratio=ratio, verbose=verbose, kind='svm', **svm_args)
svsx, svsy = svmsmote.fit_transform(x, y)
# 'SMOTE Tomek links'
y = pd.read_csv(tain_path,
header=None,
index_col=False,
names=colnames,
skiprows=[0],
usecols=[8])
y = y['violation'].values
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.333, random_state=0)
main_x = X.values
main_y = y
verbose = False
ratio = float(np.count_nonzero(y == 1)) / float(np.count_nonzero(y == 0))
# 'Random over-sampling'
OS = OverSampler(ratio=ratio, verbose=verbose)
x, y = OS.fit_transform(main_x, main_y)
X_train, X_test, y_train, y_test = train_test_split(x,
y,
test_size=.333,
random_state=0)
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import cross_val_score
clf = RandomForestClassifier(n_estimators=10)
scores = cross_val_score(clf, X_test, y_test)
y_pred = clf.fit(X_train, y_train).predict(X_test)
y_score = clf.fit(X_train, y_train).predict_proba(X_test)[:, 1]