def run(train_df, test_df):
encoder = None
encoder = Encoder(train_df)
lr = modelDict["GBM"](need_scale=False)
encoder.transform(train_df)
n_train_df = pd.get_dummies(train_df)
lr.train(n_train_df)
encoder.transform(test_df)
n_test_df = pd.get_dummies(test_df)
y = lr.test(n_test_df)
save(test_df, y, encoder)
def run_ensemble(train_df):
encoder = None
encoder = Encoder(train_df)
encoder.transform(train_df)
estimators = []
scores = []
labels = []
nums = list(range(1, 5, 1)) + list(range(5, 60, 5)) + list(
range(60, 100, 10)) + list(range(100, 500, 50))
for n in nums:
lr = modelDict["GBM"](n_estimators=n)
n_train_df = pd.get_dummies(train_df)
train_score, val_score = lr.train(n_train_df)
scores += [train_score, val_score]
estimators += [n, n]
labels += ['train', 'val']
return scores, labels, estimators