def check_boosting():
np.random.seed(5)
test_classifiers = set()
s_set = {1, -1}
b_set = {1, 3, 5, 7, 9, 11}
for s in s_set:
for b in b_set:
test_classifiers.add(DecisionStump(s, b, 0))
test_features = [[2], [4], [6], [8], [10]]
test_labels = [1, 1, -1, -1, 1]
try:
import boosting
except:
return 0
try:
test_ada1 = boosting.AdaBoost(test_classifiers, 1)
test_ada2 = boosting.AdaBoost(test_classifiers, 3)
test_ada1.train(test_features, test_labels)
test_ada2.train(test_features, test_labels)
predictions_ada1 = test_ada1.predict(test_features)
predictions_ada2 = test_ada2.predict(test_features)
if predictions_ada1 == [1, 1, -1, -1, -1
] and predictions_ada2 == [1, 1, -1, -1, 1]:
score_ada = 0.5
else:
score_ada = 0
except:
score_ada = 0
try:
test_logit1 = boosting.LogitBoost(test_classifiers, 1)
test_logit2 = boosting.LogitBoost(test_classifiers, 3)
test_logit1.train(test_features, test_labels)
test_logit2.train(test_features, test_labels)
predictions_logit1 = test_logit1.predict(test_features)
predictions_logit2 = test_logit2.predict(test_features)
if predictions_logit1 == [1, 1, -1, -1, -1] and predictions_logit2 == [
1, 1, -1, -1, 1
]:
score_logit = 0.5
else:
score_logit = 0
except:
score_logit = 0
return round(score_ada + score_logit, 1)
'''
# data
features_1, labels_1 = data_loader.toy_data_1()
# clfs
h_set = set()
s_set = {1, -1}
b_set = {-2, -0.5, 0.5, 2}
d_set = {0, 1}
for s in s_set:
for b in b_set:
for d in d_set:
h_set.add(decision_stump.DecisionStump(s, b, d))
# boost
Ada_1 = boosting.AdaBoost(h_set, T=1)
Ada_1.train(features_1, labels_1)
Log_1 = boosting.LogitBoost(h_set, T=1)
Log_1.train(features_1, labels_1)
# check
print('━━━━━━━━━━ Toy example 1 ━━━━━━━━━━')
print('This toy example checks the format. Any of the stump is correct.')
print('(Can you explain why?)')
print('Ada_1: s = {:01d}, b = {:.1f}, d = {:01d}'.format(
Ada_1.clfs_picked[0].s, Ada_1.clfs_picked[0].b, Ada_1.clfs_picked[0].d))
print('Log_1: s = {:01d}, b = {:.1f}, d = {:01d}'.format(
Log_1.clfs_picked[0].s, Log_1.clfs_picked[0].b, Log_1.clfs_picked[0].d))
if Ada_1.betas[0] == 0 and Log_1.betas[0] == 0.5:
print('Betas are correct')
else:
print('▁▂▃▄▅▆▇█ Betas are not correct █▇▆▅▄▃▂▁')
s_set = {1, -1}
b_set = set(np.linspace(0, 10, 51))
d_set = {0, 1, 2, 3}
for s in s_set:
for b in b_set:
for d in d_set:
h_set.add(decision_stump.DecisionStump(s, b, d))
# training
Adas = []
Logs = []
for idx, T in enumerate([10, 20, 30]):
Adas.append(boosting.AdaBoost(h_set, T=T))
Adas[idx].train(X_train, y_train)
Logs.append(boosting.LogitBoost(h_set, T=T))
Logs[idx].train(X_train, y_train)
# testing
Ada_preds = []
Log_preds = []
Ada_accus = []
Log_accus = []
for Ada in Adas:
pred = Ada.predict(X_test)
Ada_preds.append(pred)
Ada_accus.append(accuracy_score(pred, y_test))
for Log in Logs:
pred = Log.predict(X_test)
Log_preds.append(pred)
Log_accus.append(accuracy_score(pred, y_test))