rnp.seed(3056)
########################################
from io_helper import IOHelper
from data_helper import DataHelper
from config_helper import ConfigHelper
from metrics_helper import MetricsHelper
if __name__ == "__main__":
train_data = IOHelper.read_dataset("train")
train_X, train_y = DataHelper.extract_feature_labels(train_data)
predef = ConfigHelper.use_predefined_cols
DataHelper.add_nan_indication_cols(train_X)
DataHelper.remove_high_nan_rate_cols(train_X, predef)
DataHelper.remove_small_variance_cols(train_X, predef)
train_y = DataHelper.remove_high_nan_rate_rows(train_X, train_y)
DataHelper.fill_missing_data(train_X, is_train=True)
train_X = DataHelper.split_categorical_cols(train_X, is_train=True)
DataHelper.scale_continuous_cols(train_X, is_train=True)
train_X = DataHelper.select_best_features(train_X,
None,
train_y,
ConfigHelper.max_nb_features,
is_train=True)
test_X = IOHelper.read_dataset("test")
import time
from io_helper import IOHelper
from data_helper import DataHelper
from config_helper import ConfigHelper
from metrics_helper import MetricsHelper
if __name__ == "__main__":
data = IOHelper.read_dataset("train")
feats, labels = DataHelper.extract_feature_labels(data)
predef = ConfigHelper.use_predefined_cols
DataHelper.add_nan_indication_cols(feats)
DataHelper.remove_high_nan_rate_cols(feats, predef)
DataHelper.remove_small_variance_cols(feats, predef)
for e in xrange(ConfigHelper.nb_executions):
print "Execution: " + str(e + 1)
MetricsHelper.reset_metrics()
for f, (train_idxs,
val_idxs) in enumerate(ConfigHelper.k_fold_cv(labels)):
start_time = time.time()
print "Fold: " + str(f + 1)
DataHelper.reset_scaler()
