def test_classification(feature, incr=False):
clf = get_classification(feature, incr)
# 加载测试数据集
if feature.subjective:
test = Load.load_test_balance()
else:
test = Load.load_test_objective_balance()
test_datas, c_true, _ = feature.get_key_words(test)
test = test_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(test_datas):
test = feature.cal_weight_improve(test_datas, c_true)
c_pred_unknow = clf.predict_unknow(test)
print c_pred_unknow
print "precision:", clf.metrics_precision(c_true, c_pred_unknow)
print "recall:", clf.metrics_recall(c_true, c_pred_unknow)
print "f1:", clf.metrics_f1(c_true, c_pred_unknow)
print "origin accuracy:", clf.metrics_accuracy(c_true, c_pred_unknow)
print "zero_one_loss:", clf.metrics_zero_one_loss(c_true, c_pred_unknow)
test_proba = clf.predict_max_proba(test)
print "my_zero_one_loss:", clf.metrics_my_zero_one_loss(test_proba)
print
clf.metrics_correct(c_true, c_pred_unknow)
def get_classification(feature, incr=False):
"""
获得分类器
:param feature:
:param incr
:return:
"""
train_datas, class_label, _ = feature.get_key_words()
train = train_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(train_datas):
train = feature.cal_weight_improve(train_datas, class_label)
if incr:
bayes = IncrBayes()
else:
bayes = Bayes()
clf = Classification(bayes=bayes, subjective=feature.subjective)
clf.get_classificator(train, class_label)
if incr:
incr_train_datas = Load.load_incr_datas()
incr_train, incr_class_label, _ = feature.get_key_words(incr_train_datas)
# 构建适合 bayes 分类的增量集
if not sp.issparse(incr_train):
incr_train = feature.cal_weight_improve(incr_train, incr_class_label)
clf.get_incr_classificator(incr_train, incr_class_label, train, class_label, method="five")
return clf
def get_classification(feature, incr=False):
"""
获得分类器
:param feature:
:param incr
:return:
"""
train_datas, class_label, _ = feature.get_key_words()
train = train_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(train_datas):
train = feature.cal_weight_improve(train_datas, class_label)
if incr:
bayes = IncrBayes()
else:
bayes = Bayes()
clf = Classification(bayes=bayes, subjective=feature.subjective)
clf.get_classificator(train, class_label)
if incr:
incr_train_datas = Load.load_incr_datas()
incr_train, incr_class_label, _ = feature.get_key_words(
incr_train_datas)
# 构建适合 bayes 分类的增量集
if not sp.issparse(incr_train):
incr_train = feature.cal_weight_improve(incr_train,
incr_class_label)
clf.get_incr_classificator(incr_train,
incr_class_label,
train,
class_label,
method="five")
return clf
def _get_splited_train(self):
"""
优先从文件中读取训练集分词后的结果
:return:
"""
dir_ = os.path.join(TEXT_OUT, "split")
if self.subjective:
split_txt = os.path.join(dir_, self.__class__.__name__ + ".txt")
training_datas = Load.load_training_balance()
else:
split_txt = os.path.join(dir_, self.__class__.__name__ + "_objective.txt")
training_datas = Load.load_training_objective_balance()
if self.f or not FileUtil.isexist(split_txt) or FileUtil.isempty(split_txt):
# 加载训练集
# 每个句子还包含类别信息
splited_words_list = Feature.__split(flatten(training_datas))
# splited_words_list = Feature.__del_low_frequency_word(splited_words_list)
FileUtil.write(split_txt, splited_words_list)
else:
splited_words_list = FileUtil.read(split_txt)
return splited_words_list
# l = [sentence]
# fit_sentence = Feature_Hasher.transform(l).toarray()
b_matrix = sentence.toarray()
np.power(correct_row + b_matrix, 1, correct_row)
np.power(copy_feature_count, 1, out)
return copy_feature_count
if __name__ == "__main__":
# 加载情绪分类数据集
feature = CHIFeature()
train_datas, class_label, _ = feature.get_key_words()
train = train_datas
if not sp.issparse(train_datas):
train = feature.cal_weight_improve(train_datas, class_label)
test = Load.load_test_balance()
test_datas, test_label, _ = feature.get_key_words(test)
test = test_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(test_datas):
test = feature.cal_weight_improve(test_datas, test_label)
crossvalidate = False
# 若不交叉验证 记得修改 load_sample.py 中加载 train 的比例
if crossvalidate:
out = os.path.join(TEXT_OUT, "best_train_test_index/test_index.txt")
if not FileUtil.isexist(out) or FileUtil.isempty(out):
clf0 = Classification()
clf0.cross_validation(train, class_label, score="recall")
test_index = np.loadtxt(out, dtype=int)
test = train[test_index]
raise ValueError("the two lists have different size!")
l = filter(lambda x: x[1] != "unknow", zip(c_true, c_pred))
temp = zip(*l)
return temp[0], temp[1]
if __name__ == "__main__":
print
# 加载情绪分类数据集
feature = CHIFeature()
train_datas, class_label, _ = feature.get_key_words()
train = train_datas
if not sp.issparse(train_datas):
train = feature.cal_weight_improve(train_datas, class_label)
test = Load.load_test_balance()
test_datas, test_label, _ = feature.get_key_words(test)
test = test_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(train_datas):
test = feature.cal_weight_improve(test_datas, test_label)
clf = Classification()
crossvalidate = False
# 若不交叉验证 记得修改 load_sample.py 中加载 train 的比例
if crossvalidate:
out = os.path.join(TEXT_OUT, "best_train_test_index/test_index.txt")
if not FileUtil.isexist(out) or FileUtil.isempty(out):
clf.cross_validation(train, class_label, score="recall")
test_index = np.loadtxt(out, dtype=int)
test = train[test_index]
raise ValueError("the two lists have different size!")
l = filter(lambda x: x[1] != "unknow", zip(c_true, c_pred))
temp = zip(*l)
return temp[0], temp[1]
if __name__ == "__main__":
print
# 加载情绪分类数据集
feature = CHIFeature()
train_datas, class_label, _ = feature.get_key_words()
train = train_datas
if not sp.issparse(train_datas):
train = feature.cal_weight_improve(train_datas, class_label)
test = Load.load_test_balance()
test_datas, test_label, _ = feature.get_key_words(test)
test = test_datas
# 构建适合 bayes 分类的数据集
if not sp.issparse(train_datas):
test = feature.cal_weight_improve(test_datas, test_label)
clf = Classification()
crossvalidate = False
# 若不交叉验证 记得修改 load_sample.py 中加载 train 的比例
if crossvalidate:
out = os.path.join(TEXT_OUT, "best_train_test_index/test_index.txt")
if not FileUtil.isexist(out) or FileUtil.isempty(out):
clf.cross_validation(train, class_label, score="recall")
test_index = np.loadtxt(out, dtype=int)
test = train[test_index]
