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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
"""
=================================================================
Displaying Pipelines
=================================================================
The default configuration for displaying a pipeline in a Jupyter Notebook is
`'diagram'` where `set_config(display='diagram')`. To deactivate HTML representation,
use `set_config(display='text')`.
To see more detailed steps in the visualization of the pipeline, click on the
steps in the pipeline.
"""
# %%
# Displaying a Pipeline with a Preprocessing Step and Classifier
################################################################################
# This section constructs a :class:`~sklearn.pipeline.Pipeline` with a preprocessing
# step, :class:`~sklearn.preprocessing.StandardScaler`, and classifier,
# :class:`~sklearn.linear_model.LogisticRegression`, and displays its visual
# representation.
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn import set_config
steps = [
("preprocessing", StandardScaler()),
("classifier", LogisticRegression()),
]
pipe = Pipeline(steps)
# %%
# To visualize the diagram, the default is `display='diagram'`.
set_config(display="diagram")
pipe # click on the diagram below to see the details of each step
# %%
# To view the text pipeline, change to `display='text'`.
set_config(display="text")
pipe
# %%
# Put back the default display
set_config(display="diagram")
# %%
# Displaying a Pipeline Chaining Multiple Preprocessing Steps & Classifier
################################################################################
# This section constructs a :class:`~sklearn.pipeline.Pipeline` with multiple
# preprocessing steps, :class:`~sklearn.preprocessing.PolynomialFeatures` and
# :class:`~sklearn.preprocessing.StandardScaler`, and a classifier step,
# :class:`~sklearn.linear_model.LogisticRegression`, and displays its visual
# representation.
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, PolynomialFeatures
from sklearn.linear_model import LogisticRegression
steps = [
("standard_scaler", StandardScaler()),
("polynomial", PolynomialFeatures(degree=3)),
("classifier", LogisticRegression(C=2.0)),
]
pipe = Pipeline(steps)
pipe # click on the diagram below to see the details of each step
# %%
# Displaying a Pipeline and Dimensionality Reduction and Classifier
################################################################################
# This section constructs a :class:`~sklearn.pipeline.Pipeline` with a
# dimensionality reduction step, :class:`~sklearn.decomposition.PCA`,
# a classifier, :class:`~sklearn.svm.SVC`, and displays its visual
# representation.
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC
from sklearn.decomposition import PCA
steps = [("reduce_dim", PCA(n_components=4)), ("classifier", SVC(kernel="linear"))]
pipe = Pipeline(steps)
pipe # click on the diagram below to see the details of each step
# %%
# Displaying a Complex Pipeline Chaining a Column Transformer
################################################################################
# This section constructs a complex :class:`~sklearn.pipeline.Pipeline` with a
# :class:`~sklearn.compose.ColumnTransformer` and a classifier,
# :class:`~sklearn.linear_model.LogisticRegression`, and displays its visual
# representation.
import numpy as np
from sklearn.pipeline import make_pipeline
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.linear_model import LogisticRegression
numeric_preprocessor = Pipeline(
steps=[
("imputation_mean", SimpleImputer(missing_values=np.nan, strategy="mean")),
("scaler", StandardScaler()),
]
)
categorical_preprocessor = Pipeline(
steps=[
(
"imputation_constant",
SimpleImputer(fill_value="missing", strategy="constant"),
),
("onehot", OneHotEncoder(handle_unknown="ignore")),
]
)
preprocessor = ColumnTransformer(
[
("categorical", categorical_preprocessor, ["state", "gender"]),
("numerical", numeric_preprocessor, ["age", "weight"]),
]
)
pipe = make_pipeline(preprocessor, LogisticRegression(max_iter=500))
pipe # click on the diagram below to see the details of each step
# %%
# Displaying a Grid Search over a Pipeline with a Classifier
################################################################################
# This section constructs a :class:`~sklearn.model_selection.GridSearchCV`
# over a :class:`~sklearn.pipeline.Pipeline` with
# :class:`~sklearn.ensemble.RandomForestClassifier` and displays its visual
# representation.
import numpy as np
from sklearn.pipeline import make_pipeline
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
numeric_preprocessor = Pipeline(
steps=[
("imputation_mean", SimpleImputer(missing_values=np.nan, strategy="mean")),
("scaler", StandardScaler()),
]
)
categorical_preprocessor = Pipeline(
steps=[
(
"imputation_constant",
SimpleImputer(fill_value="missing", strategy="constant"),
),
("onehot", OneHotEncoder(handle_unknown="ignore")),
]
)
preprocessor = ColumnTransformer(
[
("categorical", categorical_preprocessor, ["state", "gender"]),
("numerical", numeric_preprocessor, ["age", "weight"]),
]
)
pipe = Pipeline(
steps=[("preprocessor", preprocessor), ("classifier", RandomForestClassifier())]
)
param_grid = {
"classifier__n_estimators": [200, 500],
"classifier__max_features": ["auto", "sqrt", "log2"],
"classifier__max_depth": [4, 5, 6, 7, 8],
"classifier__criterion": ["gini", "entropy"],
}
grid_search = GridSearchCV(pipe, param_grid=param_grid, n_jobs=1)
grid_search # click on the diagram below to see the details of each step
|
