def __classifict(self, feature, sentences, incr=False):
if isinstance(sentences, basestring):
sentences = [sentences]
# 获得主客观分类器
feature.subjective = False
objective_clf = get_objective_classification(feature)
# 主客观部分
test_datas_objective, c_true_objective, danger_index_objective = feature.get_key_words(
sentences)
test_objective = test_datas_objective
if not sp.issparse(test_datas_objective):
test_objective = feature.cal_weight_improve(
test_datas_objective, c_true_objective)
c_pred_objective = objective_clf.predict(test_objective)
# 获得情绪分类器
feature.subjective = True
emotion_clf = get_emotion_classification(feature, incr=incr)
# 情绪部分
test_datas, c_true, danger_index = feature.get_key_words(sentences)
test = test_datas
if not sp.issparse(test_datas):
test = feature.cal_weight_improve(test_datas, c_true)
c_pred = []
for i in range(len(sentences)):
if i not in danger_index_objective and i not in danger_index:
before_i_in_danger_obj = np.sum(
np.asarray(danger_index_objective) < i)
before_i_in_danger_ = np.sum(np.asarray(danger_index) < i)
c = emotion_clf.predict(test[i - before_i_in_danger_])[0] if c_pred_objective[i - before_i_in_danger_obj] == "Y" \
else c_pred_objective[i - before_i_in_danger_obj]
c_pred.append(c)
else:
c_pred.append("none(insufficient key_words)")
return c_pred
def __classifict(self, feature, sentences, incr=False):
if isinstance(sentences, basestring):
sentences = [sentences]
# 获得主客观分类器
feature.subjective = False
objective_clf = get_objective_classification(feature)
# 主客观部分
test_datas_objective, c_true_objective, danger_index_objective = feature.get_key_words(sentences)
test_objective = test_datas_objective
if not sp.issparse(test_datas_objective):
test_objective = feature.cal_weight_improve(test_datas_objective, c_true_objective)
c_pred_objective = objective_clf.predict(test_objective)
# 获得情绪分类器
feature.subjective = True
emotion_clf = get_emotion_classification(feature, incr=incr)
# 情绪部分
test_datas, c_true, danger_index = feature.get_key_words(sentences)
test = test_datas
if not sp.issparse(test_datas):
test = feature.cal_weight_improve(test_datas, c_true)
c_pred = []
for i in range(len(sentences)):
if i not in danger_index_objective and i not in danger_index:
before_i_in_danger_obj = np.sum(np.asarray(danger_index_objective) < i)
before_i_in_danger_ = np.sum(np.asarray(danger_index) < i)
c = emotion_clf.predict(test[i - before_i_in_danger_])[0] if c_pred_objective[i - before_i_in_danger_obj] == "Y" \
else c_pred_objective[i - before_i_in_danger_obj]
c_pred.append(c)
else:
c_pred.append("none(insufficient key_words)")
return c_pred
def classifict(feature, sentences, incr=False, out=False):
if isinstance(sentences, basestring):
sentences = [sentences]
# 获得主客观分类器
feature.subjective = False
objective_clf = get_objective_classification(feature)
# 测试集
# 主客观部分
test_datas_objective, c_true_objective, danger_index_objective = feature.get_key_words(sentences)
test_objective = test_datas_objective
if not sp.issparse(test_datas_objective):
test_objective = feature.cal_weight_improve(test_datas_objective, c_true_objective)
c_pred_objective = objective_clf.predict(test_objective)
# 获得情绪分类器
feature.subjective = True
emotion_clf = get_emotion_classification(feature, incr=incr)
# 测试集
# 情绪部分
test_datas, c_true, danger_index = feature.get_key_words(sentences)
test = test_datas
if not sp.issparse(test_datas):
test = feature.cal_weight_improve(test_datas, c_true)
c_pred = []
for i in range(len(sentences)):
if i not in danger_index_objective and i not in danger_index:
before_i_in_danger_obj = np.sum(np.asarray(danger_index_objective) < i)
before_i_in_danger_ = np.sum(np.asarray(danger_index) < i)
c = emotion_clf.predict(test[i - before_i_in_danger_])[0] if c_pred_objective[i - before_i_in_danger_obj] == "Y"\
else c_pred_objective[i - before_i_in_danger_obj]
c_pred.append(c)
if out:
dir_ = os.path.join(OUT_BASE_URL, "out0")
FileUtil.mkdirs(dir_)
current = time.strftime('%Y-%m-%d %H:%M:%S')
o = os.path.join(dir_, current + ".xml")
with open(o, "w") as fp:
for i, s in enumerate(sentences):
if i not in danger_index_objective and i not in danger_index:
before_i_in_danger_obj = np.sum(np.asarray(danger_index_objective) < i)
before_i_in_danger_ = np.sum(np.asarray(danger_index) < i)
fp.write(
"""<weibo emotion-type="%s">
<sentence emotion-1-type="%s" emotion-2-type="none" emotion-tag="%s">
%s
</sentence>
</weibo>
""" % (c_pred[i - before_i_in_danger_], c_pred[i - before_i_in_danger_], "N" if c_pred_objective[i - before_i_in_danger_obj] == "N" else "Y", s))
else:
fp.write(
"""<weibo emotion-type="%s">
<sentence emotion-1-type="%s" emotion-2-type="none" emotion-tag="%s">
%s
</sentence>
</weibo>
""" % ("None", "None", "N", s + "\n Can't recognize because it has insufficient key_words"))
else:
print c_pred