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
|
"""
Getting started with categorical data
=====================================
Experimental support for categorical data.
In before, users need to run an encoder themselves before passing the data into XGBoost,
which creates a sparse matrix and potentially increase memory usage. This demo
showcases the experimental categorical data support, more advanced features are planned.
.. versionadded:: 1.5.0
See Also
--------
- :doc:`Tutorial </tutorials/categorical>`
- :ref:`sphx_glr_python_examples_cat_in_the_dat.py`
- :ref:`sphx_glr_python_examples_cat_pipeline.py`
"""
from typing import Tuple
import numpy as np
import pandas as pd
import xgboost as xgb
def make_categorical(
n_samples: int, n_features: int, n_categories: int, onehot: bool
) -> Tuple[pd.DataFrame, pd.Series]:
"""Make some random data for demo."""
rng = np.random.RandomState(1994)
pd_dict = {}
for i in range(n_features + 1):
c = rng.randint(low=0, high=n_categories, size=n_samples)
pd_dict[str(i)] = pd.Series(c, dtype=np.int64)
df = pd.DataFrame(pd_dict)
label = df.iloc[:, 0]
df = df.iloc[:, 1:]
for i in range(0, n_features):
label += df.iloc[:, i]
label += 1
df = df.astype("category")
categories = np.arange(0, n_categories)
for col in df.columns:
df[col] = df[col].cat.set_categories(categories)
if onehot:
return pd.get_dummies(df), label
return df, label
def main() -> None:
# Use builtin categorical data support
# For scikit-learn interface, the input data should be pandas DataFrame or cudf
# DataFrame with categorical features. If an numpy/cupy array is used instead, the
# `feature_types` for `XGBRegressor` should be set accordingly.
X, y = make_categorical(100, 10, 4, False)
# Specify `enable_categorical` to True, also we use onehot-encoding-based split here
# for demonstration. For details see the document of `max_cat_to_onehot`.
reg = xgb.XGBRegressor(
tree_method="hist", enable_categorical=True, max_cat_to_onehot=5, device="cuda"
)
reg.fit(X, y, eval_set=[(X, y)])
# Pass in already encoded data
X_enc, y_enc = make_categorical(100, 10, 4, True)
reg_enc = xgb.XGBRegressor(tree_method="hist", device="cuda")
reg_enc.fit(X_enc, y_enc, eval_set=[(X_enc, y_enc)])
reg_results = np.array(reg.evals_result()["validation_0"]["rmse"])
reg_enc_results = np.array(reg_enc.evals_result()["validation_0"]["rmse"])
# Check that they have same results
np.testing.assert_allclose(reg_results, reg_enc_results)
# Convert to DMatrix for SHAP value
booster: xgb.Booster = reg.get_booster()
m = xgb.DMatrix(X, enable_categorical=True) # specify categorical data support.
SHAP = booster.predict(m, pred_contribs=True)
margin = booster.predict(m, output_margin=True)
np.testing.assert_allclose(
np.sum(SHAP, axis=len(SHAP.shape) - 1), margin, rtol=1e-3
)
if __name__ == "__main__":
main()
|
