from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.naive_bayes import GaussianNB, BernoulliNB
from sklearn.pipeline import make_pipeline
from sklearn.tree import DecisionTreeClassifier
from tpot.builtins import StackingEstimator
from tools import prepare_dataset, load_test
y, x = prepare_dataset()
x_train = x[:614]
y_train = y[:614].reshape(-1, )
x_valid = x[614:]
y_valid = y[614:].reshape(-1, )
# Average CV score on the training set was:0.8469063987308303
exported_pipeline = make_pipeline(
StackingEstimator(estimator=DecisionTreeClassifier(criterion="gini", max_depth=4, min_samples_leaf=15, min_samples_split=11)),
StackingEstimator(estimator=BernoulliNB(alpha=0.01, fit_prior=False)),
StackingEstimator(estimator=RandomForestClassifier(bootstrap=False, criterion="entropy", max_features=0.45, min_samples_leaf=3, min_samples_split=9, n_estimators=100)),
StackingEstimator(estimator=ExtraTreesClassifier(bootstrap=False, criterion="gini", max_features=0.9000000000000001, min_samples_leaf=12, min_samples_split=16, n_estimators=100)),
GaussianNB()
)
exported_pipeline.fit(x_train, y_train)
ids, x = load_test()
predictions = exported_pipeline.predict(x)
for index, id_number in enumerate(ids):
print(str(int(id_number[0])) + "," + str(int(predictions[index])))
import analitics as a
import numpy as np
if __name__ == '__main__':
normal = t.Data(conf.path, conf.data_set_type)
normal.add_dataset_from_file('r2/normal/', 'normal', 'csv')
timeout = t.Data(conf.path, conf.data_set_type)
timeout.add_dataset_from_file('r2/normal/', 'timeout', 'csv')
ds_sizes = 5000
ds_pos = 0
ds_power = []
ds_power = np.append(
ds_power,
t.prepare_dataset(normal.ods['Power'], ds_pos, ds_sizes, 'cut'))
ds_power = np.append(
ds_power,
t.prepare_dataset(timeout.ods['Power'], ds_pos, ds_sizes, 'cut'))
ds_temperature = []
ds_temperature = np.append(
ds_temperature,
t.prepare_dataset(normal.ods['Temp'], ds_pos, ds_sizes, 'diff'))
ds_temperature = np.append(
ds_temperature,
t.prepare_dataset(timeout.ods['Temp'], ds_pos, ds_sizes, 'diff'))
# t.plot_series(ds_power, 0, len(ds_power))
# t.plot_series(ds_temperature, 0, len(ds_temperature))
#