from sklearn.datasets import load_svmlight_file
from sklearn.cross_validation import train_test_split
from sklearn import preprocessing
from sklearn.neural_network import BernoulliRBM
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report, confusion_matrix
import numpy as np

#load dataset in svmlib format
X, y = load_svmlight_file("dataset1.txt")

#X is scipy.sparse CSR matrix, we need to convert it to numpy array
X = X.toarray()

#scaling to [0,1]
min_max_scaler = preprocessing.MinMaxScaler()
X_scaled = min_max_scaler.fit_transform(X)

#split train-testing
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.3) #30% test

# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['sigmoid'], 'gamma': [1e-3, 1e-4],
                     'C': [1, 10, 100, 1000]},
                    {'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]

scores = ['precision', 'recall']

# Finding the best hyper-parameters that optimize the score of
# precision and 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(confusion_matrix(y_true, y_pred))

# modified from http://scikit-learn.org/stable/auto_examples/model_selection/grid_search_digits.html#example-model-selection-grid-search-digits-py