529_pollen_tpotregressor_pipeline.py

import numpy as np
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.linear_model import RidgeCV
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline, make_union
from sklearn.preprocessing import MinMaxScaler, Normalizer
from sklearn.tree import DecisionTreeRegressor
from tpot.builtins import StackingEstimator, ZeroCount
from sklearn.preprocessing import FunctionTransformer
from copy import copy

# 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:-2.0465041165861417
exported_pipeline = make_pipeline(
    make_union(
        make_pipeline(
            StackingEstimator(estimator=DecisionTreeRegressor(max_depth=2, min_samples_leaf=4, min_samples_split=15)),
            PCA(iterated_power=3, svd_solver="randomized"),
            ZeroCount(),
            Normalizer(norm="l2"),
            MinMaxScaler()
        ),
        FunctionTransformer(copy)
    ),
    RidgeCV()
)

exported_pipeline.fit(training_features, training_target)
results = exported_pipeline.predict(testing_features)