def q3(): # Got points off b/c I have 89 accuracy instead of 92
""" Logistic Regression """
data = utils.load_and_normalize_polluted_spam_data()
k = 10
k_folds = hw3u.partition_folds(data, k)
train_acc = []
test_acc = []
hw2_train_acc = []
hw2_test_acc = []
for ki in range(k):
grouped_fold = hw5u.group_fold(k_folds, ki)
y, X = utils.split_truth_from_data(grouped_fold)
y_truth, X_test = utils.split_truth_from_data(k_folds[ki])
clf = lm.LogisticRegression() #penalty="l1")
ridge_clf = hw5u.Ridge()
#clf = lm.Lasso(alpha=.5)
#clf = lm.RidgeClassifier(alpha=.1)
clf.fit(X, y)
ridge_clf.fit(X, y)
y_train = [1 if p >= .5 else 0 for p in clf.predict(X)]
y_test = [1 if p >= .5 else 0 for p in clf.predict(X_test)]
yhat_ridge_train = [1 if p >= .5 else 0 for p in ridge_clf.predict(X)]
yhat_ridge_test = [1 if p >= .5 else 0 for p in ridge_clf.predict(X_test)]
train_acc.append(accuracy_score(y, y_train))
test_acc.append(accuracy_score(y_truth, y_test))
hw2_train_acc.append(accuracy_score(y, yhat_ridge_train))
hw2_test_acc.append(accuracy_score(y_truth, yhat_ridge_test))
print 'Fold {} train acc: {} test acc: {} HW2 ridge train: {} HW2 ridge test: {}'.format(ki+1, train_acc[-1], test_acc[-1], hw2_train_acc[-1], hw2_test_acc[-1])
print 'Average acc - Train: {} Test: {} HW2 ridge: {}'.format(np.mean(train_acc), np.mean(test_acc), np.mean(hw2_train_acc), np.mean(hw2_test_acc))
def GaussianNB(X, num_features=None):
model_type = 1
train_acc_sum = 0
test_acc_sum = 0
k = 10
nb_models = []
if num_features is not None:
y, X = utils.split_truth_from_data(X)
q4_slct = SelectKBest(k=num_features).fit(X, y)
X = q4_slct.transform(X)
X = utils.add_row(X, y)
k_folds = hw3u.partition_folds(X, k)
for ki in range(k):
grouped_fold = hw5u.group_fold(k_folds, ki)
alpha = .001 if model_type==0 else 0
mask_cols = check_cols(grouped_fold)
#nb_model = nb.NaiveBayes(model_type, alpha=alpha, ignore_cols=mask_cols)
nb_model = BernoulliNB()
print 'len of kfolds {}'.format(len(grouped_fold))
#truth_rows, data_rows, data_mus, y_mu = hw3u.get_data_and_mus(grouped_fold)
truth_rows, data_rows = utils.split_truth_from_data(grouped_fold)
print 'len of data {}'.format(len(data_rows))
#nb_model.train(data_rows, truth_rows)
nb_model.fit(data_rows, truth_rows)
predict = nb_model.predict(data_rows)
#print predict
accuracy = hw3u.get_accuracy(predict, truth_rows)
train_acc_sum += accuracy
print_output(ki, accuracy)
nb_models.append(nb_model)
truth_rows, data_rows = utils.split_truth_from_data(k_folds[ki])
test_predict = nb_model.predict(data_rows)
test_accuracy = hw3u.get_accuracy(test_predict, truth_rows)
test_acc_sum += test_accuracy
print_output(ki, test_accuracy, 'test')
print_test_output(float(train_acc_sum)/k, float(test_acc_sum)/k)
