# Append classifier to preprocessing pipeline.
# Now we have a full prediction pipeline.
clf = Pipeline(steps=[('preprocessor',
preprocessor), ('classifier', LogisticRegression())])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
clf.fit(X_train, y_train)
print("model score: %.3f" % clf.score(X_test, y_test))
###############################################################################
# Using the prediction pipeline in a grid search
###############################################################################
# Grid search can also be performed on the different preprocessing steps
# defined in the ``ColumnTransformer`` object, together with the classifier's
# hyperparameters as part of the ``Pipeline``.
# We will search for both the imputer strategy of the numeric preprocessing
# and the regularization parameter of the logistic regression using
# :class:`mrex.model_selection.GridSearchCV`.
param_grid = {
'preprocessor__num__imputer__strategy': ['mean', 'median'],
'classifier__C': [0.1, 1.0, 10, 100],
}
grid_search = GridSearchCV(clf, param_grid, cv=10)
grid_search.fit(X_train, y_train)
print(("best logistic regression from grid search: %.3f" %
grid_search.score(X_test, y_test)))
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,
edgecolors='k')
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
# iterate over classifiers
for est_idx, (name, (estimator, param_grid)) in \
enumerate(zip(names, classifiers)):
ax = axes[ds_cnt, est_idx + 1]
clf = GridSearchCV(estimator=estimator, param_grid=param_grid)
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print('%s: %.2f' % (name, score))
# plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]*[y_min, y_max].
if hasattr(clf, "decision_function"):
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
else:
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
# put the result into a color plot
Z = Z.reshape(xx.shape)
ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
# plot the training points
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,