def log06(x_train, y_train, x_test, folds, max_round, n_splits=5):
clf = LogisticRegression(
penalty='l2',
dual=False,
tol=0.0001,
C=0.005,
fit_intercept=True,
intercept_scaling=1,
class_weight='balanced',
random_state=None,
solver='sag',
max_iter=200,
multi_class='ovr',
verbose=0,
warm_start=False,
n_jobs=4,
)
# Additional processing of data
x_train, x_test = feature_engineering_6(x_train, x_test, y_train)
# Cross Validate
cv = Cross_Validate(log06.__name__, n_splits, x_train.shape[0],
x_test.shape[0], clf, -1, -1)
cv.cross_validate(x_train, y_train, x_test, folds, verbose_eval=True)
return cv.trn_gini, cv.y_trn, cv.y_tst, cv.fscore
def rgf04(x_train, y_train, x_test, folds, max_round, n_splits=5):
clf = RGFClassifier(
max_leaf=1000,
algorithm="RGF",
loss="Log",
l2=0.01,
sl2=0.01,
normalize=False,
min_samples_leaf=7, # 10,
n_iter=None,
opt_interval=100,
learning_rate=.45, # .3,
calc_prob="sigmoid",
n_jobs=-2,
memory_policy="generous",
verbose=0)
# Additional processing of data
x_train, x_test = feature_engineering_4(x_train, x_test, y_train)
# Cross Validate
cv = Cross_Validate(rgf04.__name__, n_splits, x_train.shape[0],
x_test.shape[0], clf, -1, -1)
cv.cross_validate(x_train, y_train, x_test, folds, verbose_eval=True)
return cv.trn_gini, cv.y_trn, cv.y_tst, cv.fscore
def etc07(x_train, y_train, x_test, folds, max_round, n_splits=5):
clf = ExtraTreesClassifier(
n_estimators = 800,
criterion = 'gini',
max_depth = 5,
min_samples_split = 100,
min_samples_leaf = 100,
max_features ='auto',
min_impurity_decrease = 0.0,
n_jobs = 4,
verbose = 0,
)
# Additional processing of data
x_train, x_test = feature_engineering_7(x_train, x_test, y_train)
# Cross Validate
cv = Cross_Validate(etc07.__name__, n_splits, x_train.shape[0], x_test.shape[0], clf, -1, -1)
cv.cross_validate(x_train, y_train, x_test, folds, verbose_eval=True)
return cv.trn_gini, cv.y_trn, cv.y_tst, cv.fscore
def cat05(x_train, y_train, x_test, folds, max_round, n_splits=5):
clf = CatBoostClassifier(
iterations=900,
learning_rate=0.057,
depth=5,
l2_leaf_reg=23,
leaf_estimation_method='Newton',
loss_function='Logloss',
thread_count=7,
random_seed=177,
one_hot_max_size=10,
allow_writing_files=False,
)
# Additional processing of data
x_train, x_test = feature_engineering_5(x_train, x_test, y_train)
# Cross Validate
cv = Cross_Validate(cat05.__name__, n_splits, x_train.shape[0],
x_test.shape[0], clf, -1, -1)
cv.cross_validate(x_train, y_train, x_test, folds, verbose_eval=True)
return cv.trn_gini, cv.y_trn, cv.y_tst, cv.fscore