In [1]:

    

from __future__ import print_function

from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.svm import SVC

print(__doc__)

# Loading the Digits dataset
digits = datasets.load_digits()

# To apply an classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.images)
X = digits.images.reshape((n_samples, -1))
y = digits.target

# 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(C=1), tuned_parameters, cv=5,
                       scoring='%s_weighted' % 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()
    for params, mean_score, scores in clf.grid_scores_:
        print("%0.3f (+/-%0.03f) for %r"
              % (mean_score, scores.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()


    

    




Automatically created module for IPython interactive environment
# Tuning hyper-parameters for precision

Best parameters set found on development set:

{'kernel': 'rbf', 'C': 10, 'gamma': 0.001}

Grid scores on development set:

0.987 (+/-0.018) for {'kernel': 'rbf', 'C': 1, 'gamma': 0.001}
0.959 (+/-0.030) for {'kernel': 'rbf', 'C': 1, 'gamma': 0.0001}
0.988 (+/-0.018) for {'kernel': 'rbf', 'C': 10, 'gamma': 0.001}
0.982 (+/-0.027) for {'kernel': 'rbf', 'C': 10, 'gamma': 0.0001}
0.988 (+/-0.018) for {'kernel': 'rbf', 'C': 100, 'gamma': 0.001}
0.982 (+/-0.026) for {'kernel': 'rbf', 'C': 100, 'gamma': 0.0001}
0.988 (+/-0.018) for {'kernel': 'rbf', 'C': 1000, 'gamma': 0.001}
0.982 (+/-0.026) for {'kernel': 'rbf', 'C': 1000, 'gamma': 0.0001}
0.974 (+/-0.014) for {'kernel': 'linear', 'C': 1}
0.974 (+/-0.014) for {'kernel': 'linear', 'C': 10}
0.974 (+/-0.014) for {'kernel': 'linear', 'C': 100}
0.974 (+/-0.014) for {'kernel': 'linear', 'C': 1000}

Detailed classification report:

The model is trained on the full development set.
The scores are computed on the full evaluation set.

             precision    recall  f1-score   support

          0       1.00      1.00      1.00        89
          1       0.97      1.00      0.98        90
          2       0.99      0.98      0.98        92
          3       1.00      0.99      0.99        93
          4       1.00      1.00      1.00        76
          5       0.99      0.98      0.99       108
          6       0.99      1.00      0.99        89
          7       0.99      1.00      0.99        78
          8       1.00      0.98      0.99        92
          9       0.99      0.99      0.99        92

avg / total       0.99      0.99      0.99       899


# Tuning hyper-parameters for recall

Best parameters set found on development set:

{'kernel': 'rbf', 'C': 10, 'gamma': 0.001}

Grid scores on development set:

0.986 (+/-0.021) for {'kernel': 'rbf', 'C': 1, 'gamma': 0.001}
0.958 (+/-0.029) for {'kernel': 'rbf', 'C': 1, 'gamma': 0.0001}
0.987 (+/-0.021) for {'kernel': 'rbf', 'C': 10, 'gamma': 0.001}
0.981 (+/-0.029) for {'kernel': 'rbf', 'C': 10, 'gamma': 0.0001}
0.987 (+/-0.021) for {'kernel': 'rbf', 'C': 100, 'gamma': 0.001}
0.981 (+/-0.027) for {'kernel': 'rbf', 'C': 100, 'gamma': 0.0001}
0.987 (+/-0.021) for {'kernel': 'rbf', 'C': 1000, 'gamma': 0.001}
0.981 (+/-0.027) for {'kernel': 'rbf', 'C': 1000, 'gamma': 0.0001}
0.973 (+/-0.015) for {'kernel': 'linear', 'C': 1}
0.973 (+/-0.015) for {'kernel': 'linear', 'C': 10}
0.973 (+/-0.015) for {'kernel': 'linear', 'C': 100}
0.973 (+/-0.015) for {'kernel': 'linear', 'C': 1000}

Detailed classification report:

The model is trained on the full development set.
The scores are computed on the full evaluation set.

             precision    recall  f1-score   support

          0       1.00      1.00      1.00        89
          1       0.97      1.00      0.98        90
          2       0.99      0.98      0.98        92
          3       1.00      0.99      0.99        93
          4       1.00      1.00      1.00        76
          5       0.99      0.98      0.99       108
          6       0.99      1.00      0.99        89
          7       0.99      1.00      0.99        78
          8       1.00      0.98      0.99        92
          9       0.99      0.99      0.99        92

avg / total       0.99      0.99      0.99       899