def optimal_svm(optimal_c):
"""
This function is to calculate AUC for optimal C chose from model selection
"""
#load datasets
train_X, train_y = load_data('train_X.csv', 'train_y.csv')
test_X, test_y = load_data('test_X.csv', 'test_y.csv')
train_X_pca = data_pca(0.95, train_X, train_X)
test_X_pca = data_pca(0.95, train_X, test_X)
train_y = np.array(train_y).ravel()
test_y = np.array(test_y).ravel()
#set up model with the optimal C
my_svm = svm.SVC(kernel='linear', C=optimal_c, class_weight='auto')
predicted_y = my_svm.fit(train_X_pca,train_y).decision_function(test_X_pca)
fpr, tpr, tr = roc_curve(test_y, predicted_y)
print auc(fpr, tpr)
def main():
#load datasets
train_X, train_Y = load_data('train_X.csv', 'train_y.csv')
train_X_pca = data_pca(0.95, train_X, train_X)
train = train_X_pca
train['Y'] = train_Y
#set a list of hyperparameter C
c = [10**i for i in range(-9,2)]
#conduct X cross validation and return AUCs in each sample for each C
aucs=xValSVM(train, 'Y', 5, c)
#calculate the average and standard error of AUC for each C
avg, stderr = avg_stderr(aucs, c)
#plot the results of cross validation
plotxValSVM(avg, stderr, c)
def main():
train_X, train_Y = load_data("train_X.csv", "train_y.csv")
train_x, validation_x, train_y, validation_y = split_data(train_X, train_Y, 0.2)
train_x_pca_df = data_pca(0.95, train_X, train_x)
validation_x_pca_df = data_pca(0.95, train_X, validation_x)
svm_model(train_x_pca_df, train_y, validation_x_pca_df, validation_y)
