def train_xgboost(train_X,
train_y,
valid_X,
valid_y,
test_X,
test_y,
learning_rate=None,
mask=None):
learning_rate = 0.01
n_estimators = 350
subsample = 0.3
if mask:
train_X = mask_columns(train_X, mask)
valid_X = mask_columns(valid_X, mask)
test_X = mask_columns(test_X, mask)
xgb_model = xgb.XGBClassifier(objective="binary:logistic",
tree_method='gpu_hist',
predictor='gpu_predictor')
xgb_model.learning_rate = learning_rate
xgb_model.n_estimators = n_estimators
xgb_model.subsample = subsample
xgb_model.fit(train_X, train_y.values.ravel())
train_pred = xgb_model.predict(train_X)
valid_pred = xgb_model.predict(valid_X)
test_pred = xgb_model.predict(test_X)
return (get_metrics(train_y, train_pred, verbose=True),
get_metrics(valid_y, valid_pred, verbose=True),
get_metrics(test_y, test_pred, verbose=True))
def __call__(self, chrom):
train_X = mask_columns(self.train_X, chrom.genes)
test_X = mask_columns(self.test_X, chrom.genes)
classifier = svm.SVC(kernel=self.kernel, class_weight=None)
classifier.fit(train_X, self.train_y.values.ravel())
pred_y = classifier.predict(test_X)
chrom.fitness = metrics.accuracy_score(self.test_y, pred_y)
return chrom.fitness
def __call__(self, chrom):
train_X = mask_columns(self.train_X, chrom.genes)
test_X = mask_columns(self.test_X, chrom.genes)
classifier = xgboost.XGBClassifier(objective="binary:logistic",
tree_method='gpu_hist',
predictor='gpu_predictor')
classifier.learning_rate = 0.01
classifier.n_estimators = 350
classifier.subsample = 0.3
classifier.fit(train_X, self.train_y.values.ravel())
pred_y = classifier.predict(test_X)
chrom.fitness = metrics.accuracy_score(self.test_y, pred_y)
return chrom.fitness
def __call__(self,
master_chrom: Chromosome,
train_chrom: Chromosome,
valid_chrom: Chromosome):
train_X = mask_columns(self.train_X, master_chrom.genes)
valid_X = mask_columns(self.valid_X, master_chrom.genes)
train_X = mask_rows(train_X, train_chrom.genes)
train_y = mask_rows(self.train_y, train_chrom.genes)
valid_X = mask_rows(valid_X, valid_chrom.genes)
valid_y = mask_rows(self.valid_y, valid_chrom.genes)
classifier = svm.SVC(kernel=self.kernel)
classifier.fit(train_X, train_y.values.ravel())
pred_y = classifier.predict(valid_X)
fitness = metrics.accuracy_score(valid_y, pred_y)
# print(fitness)
return fitness
def train_cumulative_voting(train_X,
train_y,
valid_X,
valid_y,
test_X,
test_y,
threshold=0.5,
mask=None):
if mask:
train_X = mask_columns(train_X, mask)
valid_X = mask_columns(valid_X, mask)
test_X = mask_columns(test_X, mask)
model = CumulativeVoting(threshold)
train_pred = model.predict(train_X)
valid_pred = model.predict(valid_X)
test_pred = model.predict(test_X)
return (get_metrics(train_y, train_pred, verbose=True),
get_metrics(valid_y, valid_pred, verbose=True),
get_metrics(test_y, test_pred, verbose=True))
def train_svm(kernel,
train_X,
train_y,
valid_X,
valid_y,
test_X,
test_y,
mask=None):
if mask:
train_X = mask_columns(train_X, mask)
valid_X = mask_columns(valid_X, mask)
test_X = mask_columns(test_X, mask)
classifier = svm.SVC(kernel=kernel)
classifier.fit(train_X, train_y.values.ravel())
train_pred = classifier.predict(train_X)
valid_pred = classifier.predict(valid_X)
test_pred = classifier.predict(test_X)
return (get_metrics(train_y, train_pred, verbose=True),
get_metrics(valid_y, valid_pred, verbose=True),
get_metrics(test_y, test_pred, verbose=True))
def train_majority_voting(train_X,
train_y,
valid_X,
valid_y,
test_X,
test_y,
vote_threshold=0.5,
count_threshold=0.5,
mask=None):
if mask:
train_X = mask_columns(train_X, mask)
valid_X = mask_columns(valid_X, mask)
test_X = mask_columns(test_X, mask)
model = MajorityVoting(vote_threshold, count_threshold)
train_pred = model.predict(train_X)
valid_pred = model.predict(valid_X)
test_pred = model.predict(test_X)
return (get_metrics(train_y, train_pred, verbose=True),
get_metrics(valid_y, valid_pred, verbose=True),
get_metrics(test_y, test_pred, verbose=True))
def train_xgboost_gridsearch(train_X,
train_y,
valid_X,
valid_y,
test_X,
test_y,
learning_rate=None,
mask=None):
if mask:
train_X = mask_columns(train_X, mask)
valid_X = mask_columns(valid_X, mask)
test_X = mask_columns(test_X, mask)
param_grid_gb = {
'learning_rate': [0.01],
'n_estimators': [350],
'subsample': [0.3]
}
# Regressor Instantiation
gb = xgb.XGBClassifier()
mse_grid = GridSearchCV(estimator=gb,
param_grid=param_grid_gb,
scoring='neg_mean_squared_error',
cv=4,
verbose=2)
# xgb_model = xgb.XGBClassifier(objective="binary:logistic")
mse_grid.fit(train_X, train_y.values.ravel())
train_pred = mse_grid.predict(train_X)
valid_pred = mse_grid.predict(valid_X)
test_pred = mse_grid.predict(test_X)
print("Best parameters:", mse_grid.best_params_)
return (get_metrics(train_y, train_pred, verbose=True),
get_metrics(valid_y, valid_pred, verbose=True),
get_metrics(test_y, test_pred, verbose=True))
def __call__(self, chrom):
test_X = mask_columns(self.test_X, chrom.genes)
classifier = CumulativeVoting()
pred_y = classifier.predict(test_X)
chrom.fitness = metrics.accuracy_score(self.test_y, pred_y)
return chrom.fitness