def cv(theme, percentage, current_svm): [dataset, features] = parse_theme(theme) [known_dataset, known_targets, unk] = split_dataset(dataset, targets) known_targets = np.asarray(known_targets) # cv_features = features_cross_validation(known_dataset, known_targets, features, current_svm) # selected_features = select_final_features_from_cv(cv_features, percentage) selected_features = select_features(percentage, theme) sf = SelectedFeatures(known_dataset, known_targets, selected_features, features) combined_dataset = sf.extract_data_from_selected_features() std = StandardizedData(known_targets, combined_dataset) known_dataset_scaled, known_targets = std.split_and_standardize_dataset() print '####### FEATURES ####### %d \n %s' % (len(selected_features), str(selected_features)) return cross_validation(np.array(known_dataset_scaled), known_targets, ids, current_svm)
return np.ma.masked_array(np.interp(value, x, y))
if __name__ == "__main__":
spreadsheet = Spreadsheet(project_data_file)
data = Data(spreadsheet)
targets = data.targets
ids = data.ids
theme = raw_input("Theme.\n")
percentage = float(raw_input("Percentage as float.\n"))
[dataset, features] = parse_theme(theme)
[known_dataset, known_targets, unk] = split_dataset(dataset, targets)
known_targets = np.asarray(known_targets)
selected_features = select_features(percentage, theme)
sf = SelectedFeatures(known_dataset, known_targets, selected_features, features)
dataset = sf.extract_data_from_selected_features()
dataset = preprocessing.scale(dataset)
C_range = np.arange(0.1, 9, 0.1)
gamma_range = np.arange(0.1, 9, 0.1)
param_grid = dict(gamma=gamma_range, C=C_range)
# cv = StratifiedShuffleSplit(known_targets, random_state=42)
cv = StratifiedKFold(known_targets, n_folds=10)
grid = GridSearchCV(SVC(class_weight='auto'), param_grid=param_grid, cv=cv, scoring='f1')
grid.fit(dataset, known_targets)
print("The best parameters are %s with a score of %0.2f" % (grid.best_params_, grid.best_score_))
classifiers = []