def q1():
""" feature analysis with Adaboost """
#spamData = hw3u.pandas_to_data(hw3u.load_and_normalize_spambase())
spamData = utils.load_and_normalize_polluted_spam_data()
k = 10
all_folds = hw3u.partition_folds(spamData, k)
col_errs = []
kf_train, kf_test = dl.get_train_and_test(all_folds, 0)
y, X = hw4u.split_truth_from_data(kf_train)
y_test, X_test = hw4u.split_truth_from_data(kf_test)
# We're not actually cross-validating anything -- we just want feature weights
#X = np.concatenate([X, X_test], axis=0)
#y = np.concatenate([y, y_test], axis=0)
#adaboost = adac.AdaboostOptimal(max_rounds=100, do_fast=False, learner=lambda: DecisionTreeClassifier(max_depth=1, splitter='random'))
adaboost = adac.AdaboostOptimal(max_rounds=100, do_fast=False, learner=lambda: DecisionTreeClassifier(max_depth=1, splitter='best'))
#adaboost = adac.AdaboostOptimal(max_rounds=10, do_fast=False, learner=hw4u.TreeOptimal)
adaboost.fit(X, y)
margin_fractions = get_margin_fractions(adaboost, X[0])
#margin_fractions_v = hw5u.get_margin_fractions_validate(adaboost, X, y)
#print col_errs
ranked = rank(margin_fractions)
print_ranks(ranked)
pred = adaboost.predict(X_test)
print 'Accuracy: {}'.format(accuracy_score(adaboost._check_y_not_zero(y_test), adaboost._check_y_not_zero(pred)))
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 q2(): # Done
"""
standard deviation for some columns is 0
"""
data = utils.load_and_normalize_polluted_spam_data()
#data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
#data, _ = utils.random_sample(data, None, 300) #TODO - remove
#GaussianNB(data)
GaussianNB(data, num_features=100)
