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 Pipeline with a preprocessing step, StandardScaler, and classifier, 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

Pipeline(steps=[('preprocessing', StandardScaler()),
                ('classifier', LogisticRegression())])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

To view the text pipeline, change to display='text'.

set_config(display="text")
pipe

Pipeline(steps=[('preprocessing', StandardScaler()),
                ('classifier', LogisticRegression())])

Put back the default display

set_config(display="diagram")

Displaying a Pipeline Chaining Multiple Preprocessing Steps & Classifier

This section constructs a Pipeline with multiple preprocessing steps, PolynomialFeatures and StandardScaler, and a classifier step, 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

Pipeline(steps=[('standard_scaler', StandardScaler()),
                ('polynomial', PolynomialFeatures(degree=3)),
                ('classifier', LogisticRegression(C=2.0))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Displaying a Pipeline and Dimensionality Reduction and Classifier

This section constructs a Pipeline with a dimensionality reduction step, PCA, a classifier, 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

Pipeline(steps=[('reduce_dim', PCA(n_components=4)),
                ('classifier', SVC(kernel='linear'))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Displaying a Complex Pipeline Chaining a Column Transformer

This section constructs a complex Pipeline with a ColumnTransformer and a classifier, 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

Pipeline(steps=[('columntransformer',
                 ColumnTransformer(transformers=[('categorical',
                                                  Pipeline(steps=[('imputation_constant',
                                                                   SimpleImputer(fill_value='missing',
                                                                                 strategy='constant')),
                                                                  ('onehot',
                                                                   OneHotEncoder(handle_unknown='ignore'))]),
                                                  ['state', 'gender']),
                                                 ('numerical',
                                                  Pipeline(steps=[('imputation_mean',
                                                                   SimpleImputer()),
                                                                  ('scaler',
                                                                   StandardScaler())]),
                                                  ['age', 'weight'])])),
                ('logisticregression', LogisticRegression(max_iter=500))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Displaying a Grid Search over a Pipeline with a Classifier

This section constructs a GridSearchCV over a Pipeline with 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

GridSearchCV(estimator=Pipeline(steps=[('preprocessor',
                                        ColumnTransformer(transformers=[('categorical',
                                                                         Pipeline(steps=[('imputation_constant',
                                                                                          SimpleImputer(fill_value='missing',
                                                                                                        strategy='constant')),
                                                                                         ('onehot',
                                                                                          OneHotEncoder(handle_unknown='ignore'))]),
                                                                         ['state',
                                                                          'gender']),
                                                                        ('numerical',
                                                                         Pipeline(steps=[('imputation_mean',
                                                                                          SimpleImputer()),
                                                                                         ('scaler',
                                                                                          StandardScaler())]),
                                                                         ['age',
                                                                          'weight'])])),
                                       ('classifier',
                                        RandomForestClassifier())]),
             n_jobs=1,
             param_grid={'classifier__criterion': ['gini', 'entropy'],
                         'classifier__max_depth': [4, 5, 6, 7, 8],
                         'classifier__max_features': ['auto', 'sqrt', 'log2'],
                         'classifier__n_estimators': [200, 500]})

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.