import numpy as np
from sklearn.ensemble import RandomForestRegressor
from preprocessing.to_onehot import to_labels
from gini_normalized import normalized_gini
# joined = pd.read_csv('../data/joined.csv')
#
# train = joined[joined['Hazard'] != -1]
# test = joined[joined['Hazard'] == -1]
train = pd.read_csv('../data/train_new.csv')
hold = pd.read_csv('../data/hold_new.csv')
test = pd.read_csv('../data/test.csv')
# hold = pd.read_csv('../data/hold_new.csv')
train, hold = to_labels((train, hold))
y = train['Hazard']
X = train.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_hold = hold.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_test = hold.drop(['Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
random_state = 42
ind = 1
if ind == 1:
rs = ShuffleSplit(len(y), n_iter=10, test_size=0.5, random_state=random_state)
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from preprocessing.to_onehot import to_labels
from gini_normalized import normalized_gini
# joined = pd.read_csv('../data/joined.csv')
#
# train = joined[joined['Hazard'] != -1]
# test = joined[joined['Hazard'] == -1]
train = pd.read_csv('../data/train_new.csv')
hold = pd.read_csv('../data/hold_new.csv')
test = pd.read_csv('../data/test.csv')
# hold = pd.read_csv('../data/hold_new.csv')
train, hold = to_labels((train, hold))
y = train['Hazard']
X = train.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_hold = hold.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_test = hold.drop(['Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
random_state = 42
ind = 1
if ind == 1:
rs = ShuffleSplit(len(y),
n_iter=10,
test_size=0.5,
joined = pd.read_csv('../data/joined.csv')
train = joined[joined['Hazard'] != -1]
test = joined[joined['Hazard'] == -1]
y_train = train['Hazard']
X_train = train.drop(['Hazard', 'Id'], 1)
X_test = test.drop(['Hazard', 'Id'], 1)
train = pd.read_csv('../data/train_new.csv')
hold = pd.read_csv('../data/hold_new.csv')
test = pd.read_csv('../data/test.csv')
# hold = pd.read_csv('../data/hold_new.csv')
train, hold, test = to_labels((train, hold, test))
y = train['Hazard']
X = train.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_hold = hold.drop(['Hazard', 'Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
X_test = hold.drop(['Id', 'T2_V10', 'T2_V7', 'T1_V13', 'T1_V10'], 1)
net1 = NeuralNet(
layers=[ # three layers: one hidden layer
('input', layers.InputLayer),
# ('dropout1', DropoutLayer),
('hidden0', layers.DenseLayer),
# ('dropout2', DropoutLayer),
# ('hidden1', layers.DenseLayer),
('output', layers.DenseLayer),
