-
Notifications
You must be signed in to change notification settings - Fork 0
/
cycl0.00711368615815Fin1.py
24 lines (20 loc) · 1.12 KB
/
cycl0.00711368615815Fin1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.decomposition import RandomizedPCA
from sklearn.ensemble import AdaBoostClassifier, VotingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.pipeline import make_pipeline, make_union
from sklearn.preprocessing import FunctionTransformer, RobustScaler
# NOTE: Make sure that the class is labeled 'class' in the data file
tpot_data = np.recfromcsv('PATH/TO/DATA/FILE', delimiter='COLUMN_SEPARATOR', dtype=np.float64)
features = np.delete(tpot_data.view(np.float64).reshape(tpot_data.size, -1), tpot_data.dtype.names.index('class'), axis=1)
training_features, testing_features, training_classes, testing_classes = \
train_test_split(features, tpot_data['class'], random_state=42)
exported_pipeline = make_pipeline(
RobustScaler(),
RandomizedPCA(iterated_power=10),
make_union(VotingClassifier([("est", GaussianNB())]), FunctionTransformer(lambda X: X)),
AdaBoostClassifier(learning_rate=0.0001, n_estimators=500)
)
exported_pipeline.fit(training_features, training_classes)
results = exported_pipeline.predict(testing_features)