scikit-learn/examples/model_selection/plot_grid_search_digits.py

69 lines
2.4 KiB
Python

"""
============================================================
Parameter estimation using grid search with cross-validation
============================================================
This examples shows how a classifier is optimized by cross-validation,
which is done using the :class:`~sklearn.model_selection.GridSearchCV` object
on a development set that comprises only half of the available labeled data.
The performance of the selected hyper-parameters and trained model is
then measured on a dedicated evaluation set that was not used during
the model selection step.
More details on tools available for model selection can be found in the
sections on :ref:`cross_validation` and :ref:`grid_search`.
"""
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.svm import SVC
# Loading the Digits dataset
X, y = datasets.load_digits(return_X_y=True)
# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)
# Set the parameters by cross-validation
tuned_parameters = [
{"kernel": ["rbf"], "gamma": [1e-3, 1e-4], "C": [1, 10, 100, 1000]},
{"kernel": ["linear"], "C": [1, 10, 100, 1000]},
]
scores = ["precision", "recall"]
for score in scores:
print("# Tuning hyper-parameters for %s" % score)
print()
clf = GridSearchCV(SVC(), tuned_parameters, scoring="%s_macro" % score)
clf.fit(X_train, y_train)
print("Best parameters set found on development set:")
print()
print(clf.best_params_)
print()
print("Grid scores on development set:")
print()
means = clf.cv_results_["mean_test_score"]
stds = clf.cv_results_["std_test_score"]
for mean, std, params in zip(means, stds, clf.cv_results_["params"]):
print("%0.3f (+/-%0.03f) for %r" % (mean, std * 2, params))
print()
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
y_true, y_pred = y_test, clf.predict(X_test)
print(classification_report(y_true, y_pred))
print()
# Note the problem is too easy: the hyperparameter plateau is too flat and the
# output model is the same for precision and recall with ties in quality.