1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
|
"""
Feature engineering pipeline for categorical data
=================================================
The script showcases how to keep the categorical data encoding consistent across
training and inference. There are many ways to attain the same goal, this script can be
used as a starting point.
See Also
--------
- :doc:`Tutorial </tutorials/categorical>`
- :ref:`sphx_glr_python_examples_categorical.py`
- :ref:`sphx_glr_python_examples_cat_in_the_dat.py`
"""
from typing import List, Tuple
import numpy as np
import pandas as pd
from sklearn.compose import make_column_selector, make_column_transformer
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import OrdinalEncoder
import xgboost as xgb
def make_example_data() -> Tuple[pd.DataFrame, pd.Series, List[str]]:
"""Generate data for demo."""
n_samples = 2048
rng = np.random.default_rng(1994)
# We have three categorical features, while the rest are numerical.
categorical_features = ["brand_id", "retailer_id", "category_id"]
df = pd.DataFrame(
np.random.randint(32, 96, size=(n_samples, 3)),
columns=categorical_features,
)
df["price"] = rng.integers(100, 200, size=(n_samples,))
df["stock_status"] = rng.choice([True, False], n_samples)
df["on_sale"] = rng.choice([True, False], n_samples)
df["label"] = rng.normal(loc=0.0, scale=1.0, size=n_samples)
X = df.drop(["label"], axis=1)
y = df["label"]
return X, y, categorical_features
def native() -> None:
"""Using the native XGBoost interface."""
X, y, cat_feats = make_example_data()
X_train, X_test, y_train, y_test = train_test_split(
X, y, random_state=1994, test_size=0.2
)
# Create an encoder based on training data.
enc = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=np.nan)
enc.set_output(transform="pandas")
enc = enc.fit(X_train[cat_feats])
def enc_transform(X: pd.DataFrame) -> pd.DataFrame:
# don't make change inplace so that we can have demonstrations for encoding
X = X.copy()
cat_cols = enc.transform(X[cat_feats])
for i, name in enumerate(cat_feats):
# create pd.Series based on the encoder
cat_cols[name] = pd.Categorical.from_codes(
codes=cat_cols[name].astype(np.int32), categories=enc.categories_[i]
)
X[cat_feats] = cat_cols
return X
# Encode the data based on fitted encoder.
X_train_enc = enc_transform(X_train)
X_test_enc = enc_transform(X_test)
# Train XGBoost model using the native interface.
Xy_train = xgb.QuantileDMatrix(X_train_enc, y_train, enable_categorical=True)
Xy_test = xgb.QuantileDMatrix(
X_test_enc, y_test, enable_categorical=True, ref=Xy_train
)
booster = xgb.train({}, Xy_train)
booster.predict(Xy_test)
# Following shows that data are encoded consistently.
# We first obtain result from newly encoded data
predt0 = booster.inplace_predict(enc_transform(X_train.head(16)))
# then we obtain result from already encoded data from training.
predt1 = booster.inplace_predict(X_train_enc.head(16))
np.testing.assert_allclose(predt0, predt1)
def pipeline() -> None:
"""Using the sklearn pipeline."""
X, y, cat_feats = make_example_data()
X_train, X_test, y_train, y_test = train_test_split(
X, y, random_state=3, test_size=0.2
)
enc = make_column_transformer(
(
OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=np.nan),
# all categorical feature names end with "_id"
make_column_selector(pattern=".*_id"),
),
remainder="passthrough",
verbose_feature_names_out=False,
)
# No need to set pandas output, we use `feature_types` to indicate the type of
# features.
# enc.set_output(transform="pandas")
feature_types = ["c" if fn in cat_feats else "q" for fn in X_train.columns]
reg = xgb.XGBRegressor(
feature_types=feature_types, enable_categorical=True, n_estimators=10
)
p = make_pipeline(enc, reg)
p.fit(X_train, y_train)
# check XGBoost is using the feature type correctly.
model_types = reg.get_booster().feature_types
assert model_types is not None
for a, b in zip(model_types, feature_types):
assert a == b
# Following shows that data are encoded consistently.
# We first create a slice of data that doesn't contain all the categories
predt0 = p.predict(X_train.iloc[:16, :])
# Then we use the dataframe that contains all the categories
predt1 = p.predict(X_train)[:16]
# The resulting encoding is the same
np.testing.assert_allclose(predt0, predt1)
if __name__ == "__main__":
pipeline()
native()
|
