from sklearn import datasets
from sklearn.cross_validation import train_test_split, KFold
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.svm import SVC

# 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_fraction=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', precision_score),
    ('recall', recall_score),
]

for score_name, score_func in scores:
    print "# Tuning hyper-parameters for %s" % score_name
    print

#modified to produce error
    clf = GridSearchCV(SVC(C=1), tuned_parameters, score_func=score_func,cv=KFold(n=len(X_train),k=10))
    clf.fit(X_train.tolist(), y_train) #happens only for lists

#modification end
    print "Best parameters set found on development set:"
    print
    print clf.best_estimator_
    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.tolist())
    print classification_report(y_true, y_pred)
    print