forest 4-->tr: 0.866979504134,val: 0.572140934661,cost 108
forest 5-->tr: 0.865444728731,val: 0.565962549302,cost 105
forest 6-->tr: 0.847071811478,val: 0.550088494652,cost 105
forest 7-->tr: 0.867795690777,val: 0.55928161695,cost 110
forest 8-->tr: 0.849556952293,val: 0.54308323331,cost 111
forest 9-->tr: 0.852024718779,val: 0.558287108709,cost 105
'''
#%%
'''
validating on training dataset
'''
forest_2nd = []
for forest_idx in range(0, 10, 1):
model = read_variable('final/2nd_level_models/' + str(forest_idx))
forest_2nd.append(model)
val_Y_sum = np.zeros(val_Y.shape[0])
for model in forest_2nd:
val_Y_pred = model.predict(val_votes)
print('mcc:', matthews_corrcoef(val_Y, val_Y_pred))
val_Y_sum += val_Y_pred
#%%
'''
mcc: 0.572089121234
mcc: 0.584374265357
mcc: 0.574731321479
mcc: 0.561043527534
mcc: 0.56279640286
mcc: 0.568082925197
from sklearn.cross_validation import train_test_split
i = 0
from imblearn.over_sampling.smote import SMOTE
sm = SMOTE()
pd_tf_np = ss.fit_transform(pd_tf_np)
out = np.ones(shape=(250, 9))
rfc = []
for i in range(9):
rfc.append(RandomForestClassifier(n_estimators=400))
res = []
for i in range(9):
#x_train,x_test,y_train,y_test = train_test_split(pd_tf_np,y_vals.iloc[:,i].values)
x_train, x_test = pd_tf_np[250:, :], pd_tf_np[:250, :]
y_train, y_test = y_vals.iloc[:,
i].values[250:], y_vals.iloc[:,
i].values[:250]
#ss = StandardScaler()