-
Notifications
You must be signed in to change notification settings - Fork 0
/
574_house_16H_pipeline.py
23 lines (20 loc) · 1.05 KB
/
574_house_16H_pipeline.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
import numpy as np
import pandas as pd
from sklearn.linear_model import LassoLarsCV, RidgeCV
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
from sklearn.tree import DecisionTreeRegressor
from tpot.builtins import StackingEstimator
# NOTE: Make sure that the class is labeled 'target' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1).values
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'].values, random_state=42)
# Score on the training set was:-1355809532.5819757
exported_pipeline = make_pipeline(
StackingEstimator(estimator=LassoLarsCV(normalize=True)),
StackingEstimator(estimator=RidgeCV()),
DecisionTreeRegressor(max_depth=10, min_samples_leaf=19, min_samples_split=12)
)
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)