def handle_five(clf):
"""
类支持度和无显著性差异的结合
:param clf:
:return:
"""
predict_true = handle(clf, "zero")
if predict_true:
return predict_true
fit_for_class_support = handle(clf, "third")
print "The result of class-support: %d samples" % len(
fit_for_class_support)
# fit_for_class_support = filter(lambda x: x[4] > clf.bayes.class_log_prior_[np.where(clf.bayes.classes_ == x[2])[0][0]], fit_for_class_support)
# print "The result of class-support: %d samples" % len(fit_for_class_support)
# My Own Idea
# 存放 Test 的结果
f_res = []
origin_class_log_prob_ = clf.bayes.class_log_prior_
origin_feature_log_prob_ = clf.bayes.feature_log_prob_
origin_proba = clf.predict_max_proba(test_datas)
origin_label = clf.predict(test_datas)
for i0 in range(len(fit_for_class_support)):
text0 = fit_for_class_support[i0][1]
c_pred0 = fit_for_class_support[i0][2]
clf.bayes.class_log_prior_, clf.bayes.feature_log_prob_ = clf.bayes.update(
c_pred0, text0, copy=True)
test_proba = clf.predict_max_proba(test_datas)
label = clf.predict(test_datas)
# 考虑到类别的影响
# 会出现以下的情况：某个样本属于某个类的概率很高，update后属于某个类别的概率也很高，但是
# 前后两个类别可能不一致
smooth = np.asarray([
1 if origin_label[j] == label[j] else -1
for j in range(len(origin_label))
])
np.multiply(test_proba, smooth, test_proba)
f_test0 = pair_test(origin_proba, test_proba)
if f_test0:
loss0 = clf.metrics_another_zero_one_loss(
origin_proba, test_proba)
else:
loss0 = -1
f_res.append((loss0, text0, c_pred0, i0, f_test0))
clf.bayes.class_log_prior_ = origin_class_log_prob_
clf.bayes.feature_log_prob_ = origin_feature_log_prob_
res = filter(lambda x: x[4], f_res)
return [(r[0], r[1], r[2], r[3]) for r in res]
def handle_five(clf):
"""
类支持度和无显著性差异的结合
:param clf:
:return:
"""
predict_true = handle(clf, "zero")
if predict_true:
return predict_true
fit_for_class_support = handle(clf, "third")
print "The result of class-support: %d samples" % len(fit_for_class_support)
# fit_for_class_support = filter(lambda x: x[4] > clf.bayes.class_log_prior_[np.where(clf.bayes.classes_ == x[2])[0][0]], fit_for_class_support)
# print "The result of class-support: %d samples" % len(fit_for_class_support)
# My Own Idea
# 存放 Test 的结果
f_res = []
origin_class_log_prob_ = clf.bayes.class_log_prior_
origin_feature_log_prob_ = clf.bayes.feature_log_prob_
origin_proba = clf.predict_max_proba(test_datas)
origin_label = clf.predict(test_datas)
for i0 in range(len(fit_for_class_support)):
text0 = fit_for_class_support[i0][1]
c_pred0 = fit_for_class_support[i0][2]
clf.bayes.class_log_prior_, clf.bayes.feature_log_prob_ = clf.bayes.update(c_pred0, text0, copy=True)
test_proba = clf.predict_max_proba(test_datas)
label = clf.predict(test_datas)
# 考虑到类别的影响
# 会出现以下的情况：某个样本属于某个类的概率很高，update后属于某个类别的概率也很高，但是
# 前后两个类别可能不一致
smooth = np.asarray([1 if origin_label[j] == label[j] else -1 for j in range(len(origin_label))])
np.multiply(test_proba, smooth, test_proba)
f_test0 = pair_test(origin_proba, test_proba)
if f_test0:
loss0 = clf.metrics_another_zero_one_loss(origin_proba, test_proba)
else:
loss0 = -1
f_res.append((loss0, text0, c_pred0, i0, f_test0))
clf.bayes.class_log_prior_ = origin_class_log_prob_
clf.bayes.feature_log_prob_ = origin_feature_log_prob_
res = filter(lambda x: x[4], f_res)
return [(r[0], r[1], r[2], r[3]) for r in res]
def handle_four(clf):
# My Own Idea
# 存放 Test 的结果
predict_true = handle(clf, "zero")
if predict_true:
return predict_true
f_res = []
origin_class_log_prob_ = clf.bayes.class_log_prior_
origin_feature_log_prob_ = clf.bayes.feature_log_prob_
origin_proba = clf.predict_max_proba(test_datas)
origin_label = clf.predict(test_datas)
for i0 in range(fit_incr_datas.shape[0]):
text0 = fit_incr_datas.getrow(i0)
c_pred0 = clf.predict(text0)[0]
clf.bayes.class_log_prior_, clf.bayes.feature_log_prob_ = clf.bayes.update(
c_pred0, text0, copy=True)
test_proba = clf.predict_max_proba(test_datas)
label = clf.predict(test_datas)
# 考虑到类别的影响
# 会出现以下的情况：某个样本属于某个类的概率很高，update后属于某个类别的概率也很高，但是
# 前后两个类别可能不一致
smooth = np.asarray([
1 if origin_label[j] == label[j] else -1
for j in range(len(origin_label))
])
np.multiply(test_proba, smooth, test_proba)
f_test0 = pair_test(origin_proba, test_proba)
if f_test0:
loss0 = clf.metrics_another_zero_one_loss(
origin_proba, test_proba)
else:
loss0 = -1
f_res.append((loss0, text0, c_pred0, i0, f_test0))
clf.bayes.class_log_prior_ = origin_class_log_prob_
clf.bayes.feature_log_prob_ = origin_feature_log_prob_
res = filter(lambda x: x[4], f_res)
return [(r[0], r[1], r[2], r[3]) for r in res]
def handle_four(clf):
# My Own Idea
# 存放 Test 的结果
predict_true = handle(clf, "zero")
if predict_true:
return predict_true
f_res = []
origin_class_log_prob_ = clf.bayes.class_log_prior_
origin_feature_log_prob_ = clf.bayes.feature_log_prob_
origin_proba = clf.predict_max_proba(test_datas)
origin_label = clf.predict(test_datas)
for i0 in range(fit_incr_datas.shape[0]):
text0 = fit_incr_datas.getrow(i0)
c_pred0 = clf.predict(text0)[0]
clf.bayes.class_log_prior_, clf.bayes.feature_log_prob_ = clf.bayes.update(c_pred0, text0, copy=True)
test_proba = clf.predict_max_proba(test_datas)
label = clf.predict(test_datas)
# 考虑到类别的影响
# 会出现以下的情况：某个样本属于某个类的概率很高，update后属于某个类别的概率也很高，但是
# 前后两个类别可能不一致
smooth = np.asarray([1 if origin_label[j] == label[j] else -1 for j in range(len(origin_label))])
np.multiply(test_proba, smooth, test_proba)
f_test0 = pair_test(origin_proba, test_proba)
if f_test0:
loss0 = clf.metrics_another_zero_one_loss(origin_proba, test_proba)
else:
loss0 = -1
f_res.append((loss0, text0, c_pred0, i0, f_test0))
clf.bayes.class_log_prior_ = origin_class_log_prob_
clf.bayes.feature_log_prob_ = origin_feature_log_prob_
res = filter(lambda x: x[4], f_res)
return [(r[0], r[1], r[2], r[3]) for r in res]
