def fit(self, X, y=None):
return self
def transform(self, X):
return X.astype(self.dtype)
if __name__ == '__main__':
config = get_config()
target = config['target']
categorical_predictors = config['cat_predictors']
numerical_predictors = config['num_predictors']
diw_path = os.path.join(project_directory(), config['diw_path'], 'diw.txt')
diw_df = pd.read_csv(diw_path, sep=config['data_sep'])
num_pipeline = Pipeline([('selector',
DataFrameSelector(numerical_predictors)),
('imputer', Imputer()),
('scaler', MinMaxScaler())])
# The cat vars we have now don't require imputing
cat_pipeline = Pipeline([('selector',
DataFrameSelector(categorical_predictors)),
('label_encoder', MultiColumnLabelEncoder()),
('one_hot_encoder', OneHotEncoder(sparse=False))])
target_pipeline = Pipeline([
('selector', DataFrameSelector(target)),
('dtype_transform', DataTypeTransformer(np.int8)),
import keras
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.metrics import classification_report, auc, roc_curve
import numpy as np
import pandas as pd
from dirutil import project_directory
from configfile import get_config
from transformer import clean_nulls, SamplerFactory
if __name__ == '__main__':
sample_method = 'under'
project_path = project_directory()
config = get_config('standard_model')
train_pct = .9
performance_data_path = os.path.join(project_path, config['diw_path'],
'diw.txt')
performance_data = pd.read_csv(performance_data_path,
sep=config['data_sep'])
target = config['target']
predictors = config['predictors']
# Pull out the predictors & target
model_data = performance_data[predictors + [target]]
def get_config(filename='default'):
config_file = filename + '.json'
config_path = os.path.join(project_directory(), 'config', config_file)
with open(config_path, 'r') as cfg_file:
config = json.loads(cfg_file.read())
return config