我正在使用 tpotClassifier() 并将以下管道作为我的最佳管道。我附上了我得到的管道代码。有人可以解释管道流程和顺序吗?
import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFwe, f_classif
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
from tpot.builtins import StackingEstimator
from sklearn.preprocessing import FunctionTransformer
from copy import copy
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)
features = tpot_data.drop('target', axis=1)
training_features, testing_features, training_target, testing_target = \
train_test_split(features, tpot_data['target'], random_state=None)
exported_pipeline = make_pipeline(
make_union(
FunctionTransformer(copy),
make_union(
FunctionTransformer(copy),
make_union(
FunctionTransformer(copy),
make_union(
FunctionTransformer(copy),
FunctionTransformer(copy)
)
)
)
),
SelectFwe(score_func=f_classif, alpha=0.049),
ExtraTreesClassifier(bootstrap=False, criterion="entropy", max_features=1.0, min_samples_leaf=2, min_samples_split=5, n_estimators=100)
)
exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)