clf = None
metric = 'logloss' if CLASSIFIER == 'xgb' else 'binary_logloss'
if CLASSIFIER == 'xgb':
clf = xgb.XGBClassifier(**PARAMS)
else:
par = PARAMS.copy()
par['num_leaves'] = 2**par['max_depth']
del par['gamma']
del par['max_depth']
clf = lgb.LGBMClassifier(**par)
if MODE == 'cv':
utils.perform_cv(X_train,
y_train,
clf,
MODEL_NAME + '-' + CLASSIFIER,
fit_params={'eval_metric': metric},
stratify_labels=utils.load_stratify_labels())
elif MODE == 'out':
utils.VJUH(X_train,
X_test,
y_train,
clf,
MODEL_NAME,
'out',
fit_params={'eval_metric': metric},
seed_name='seed',
runs=RUNS,
stratify_labels=utils.load_stratify_labels())
else:
print('Unsupported mode')
def predict_proba(self, X):
X1, X2, idx1, idx2 = self._split_data(X)
preds = self.models1[0].predict_proba(X1)
preds[idx2] = self.models2[0].predict_proba(X2.loc[idx2])
for i in range(1, self.num_runs):
preds[idx1] += self.models1[i].predict_proba(X1.loc[idx1])
preds[idx2] += self.models2[i].predict_proba(X2.loc[idx2])
return preds / self.num_runs
def _split_data(self, X):
idx_1 = (X['upd_start_level'] <= START_LEVEL_THRESHOLD).values
idx_2 = (X['upd_start_level'] > START_LEVEL_THRESHOLD).values
X1 = X.loc[:, self.x1_columns]
X2 = X.loc[:, self.x2_columns]
return X1, X2, idx_1, idx_2
if __name__ == '__main__':
np.random.seed(2707)
X_train, X_test, y_train = utils.load_data(data_name='extended')
clf = XGBoostSplit(num_runs=NUM_RUNS, base=CLASSIFIER)
if MODE == 'cv':
utils.perform_cv(X_train, y_train, clf, MODEL_NAME + '-' + CLASSIFIER,
stratify_labels=utils.load_stratify_labels())
elif MODE == 'ensemble':
utils.VJUH(X_train, X_test, y_train, clf, MODEL_NAME, 'ensemble', stratify_labels=utils.load_stratify_labels())
else:
print('Unsupported# mode')
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)
X_train, X_test, y_train = utils.load_data('log_flipped')
scaler = StandardScaler()
scaler.fit(pd.concat((X_train, X_test), axis=0, ignore_index=True))
X_train = pd.DataFrame(scaler.transform(X_train), columns=X_train.columns)
X_test = pd.DataFrame(scaler.transform(X_test), columns=X_test.columns)
encoder = LabelEncoder()
y_train = encoder.fit_transform(y_train).astype(np.int32)
num_classes = len(encoder.classes_)
X_train = np.array(X_train).astype(np.float32)
X_test = np.array(X_test).astype(np.float32)
num_features = X_train.shape[1]
clf = NeuralNet(input_shape=(None, num_features), output_num_units=num_classes, **PARAMS)
if MODE == 'cv':
utils.perform_cv(X_train, y_train, clf, MODEL_NAME, stratify_labels=utils.load_stratify_labels())
elif MODE == 'ensemble':
utils.VJUH(X_train, X_test, y_train, clf, MODEL_NAME, 'ensemble',
lasagne=True,
runs=RUNS,
stratify_labels=utils.load_stratify_labels()
)
else:
print('Unsupported mode')