def text_kmeans_clustering():
# 聚类评价时选取TOPK_FREQ_WORD的高频词
TOPK_FREQ_WORD = 50
# 聚类评价时最小簇的大小
LEAST_SIZE = 8
eventcomment = EventComments(topicid)
newsIds = eventcomment.getNewsIds()
for news_id in newsIds:
results = eventcomment.getNewsComments(news_id)
inputs = []
for r in results:
r['title'] = ''
r['content'] = r['content168'].encode('utf-8')
r['text'] = r['content168']
item = ad_filter(r)
if item['ad_label'] == 0:
inputs.append(item)
# 情绪计算
for r in inputs:
sentiment = triple_classifier(r)
comment = Comment(r['_id'])
comment.update_comment_sentiment(sentiment)
# kmeans 聚类及评价
kmeans_results = kmeans(inputs, k=10)
reserve_num = 5
final_cluster_results, tfidf_dict = cluster_evaluation(kmeans_results, \
top_num=reserve_num, topk_freq=TOPK_FREQ_WORD, least_size=LEAST_SIZE, min_tfidf=None)
inputs = []
for label, items in final_cluster_results.iteritems():
if label != 'other':
inputs.extend(items)
for item in items:
news = News(item['news_id'])
if label == 'other':
label = news.otherClusterId
comment = Comment(item['_id'])
comment.update_comment_label(label)
eventcomment.save_cluster(label, news_id, int(time.time()))
#计算各簇特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
eventcomment.update_feature_words(label, fwords)
#计算文本权重
for input in inputs:
weight = text_weight_cal(input, cluster_feature[input['label']])
comment = Comment(input['_id'])
comment.update_comment_weight(weight)
def main():
# Sliding window size is 200*140(h*w)
train_list = []
response_list = []
print "in main..."
# Process sample images
for SIGN in SIGN_LIST:
for sample_image in load_sample_image(SIGN):
train_data = feature.extract_feature(sample_image)
train_list.append(train_data)
response_list.append(SIGN)
# SVM in OpenCV 3.1.0 for Python
SVM = cv2.ml.SVM_create()
SVM.setKernel(cv2.ml.SVM_LINEAR)
SVM.setP(0.2)
SVM.setType(cv2.ml.SVM_EPS_SVR)
SVM.setC(1.0)
print "building tl..."
tl = np.array(train_list, np.float32)
print "building rl..."
rl = np.array(response_list, np.int32)
# Train SVM model
# svm = cv2.SVM()
SVM.train(tl, cv2.ml.ROW_SAMPLE, rl)
SVM.save('svm_data2.dat')
return
def text_kmeans_clustering():
# 聚类评价时选取TOPK_FREQ_WORD的高频词
TOPK_FREQ_WORD = 50
# 聚类评价时最小簇的大小
LEAST_SIZE = 8
eventcomment = EventComments(topicid)
newsIds = eventcomment.getNewsIds()
for news_id in newsIds:
results = eventcomment.getNewsComments(news_id)
inputs = []
for r in results:
r['title'] = ''
r['content'] = r['content168'].encode('utf-8')
r['text'] = r['content168']
item = ad_filter(r)
if item['ad_label'] == 0:
inputs.append(item)
# 情绪计算
for r in inputs:
sentiment = triple_classifier(r)
comment = Comment(r['_id'])
comment.update_comment_sentiment(sentiment)
# kmeans 聚类及评价
kmeans_results = kmeans(inputs, k=10)
reserve_num = 5
final_cluster_results, tfidf_dict = cluster_evaluation(kmeans_results, \
top_num=reserve_num, topk_freq=TOPK_FREQ_WORD, least_size=LEAST_SIZE, min_tfidf=None)
inputs = []
for label, items in final_cluster_results.iteritems():
if label != 'other':
inputs.extend(items)
for item in items:
news = News(item['news_id'])
if label == 'other':
label = news.otherClusterId
comment = Comment(item['_id'])
comment.update_comment_label(label)
eventcomment.save_cluster(label, news_id, int(time.time()))
#计算各簇特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
eventcomment.update_feature_words(label, fwords)
#计算文本权重
for input in inputs:
weight = text_weight_cal(input, cluster_feature[input['label']])
comment = Comment(input['_id'])
comment.update_comment_weight(weight)
def step3_cal():
"""计算各簇的特征词、代表文本、去重, 更新簇的大小、增幅信息
"""
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s start step3' % ts2datetime(timestamp)
inputs = []
subevents = event.getSubEvents()
for subevent in subevents:
subeventid = subevent["_id"]
inputs.extend(event.getSubeventInfos(subeventid))
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
r["label"] = r["subeventid"]
# 计算各簇的存量特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
feature = Feature(label)
feature.upsert_newest(fwords)
# 计算文本权重
for r in inputs:
weight = text_weight_cal(r, cluster_feature[r['label']])
news = News(r["_id"], event.id)
news.update_news_weight(weight)
# 文本去重
items_dict = {}
for r in inputs:
try:
items_dict[r["label"]].append(r)
except KeyError:
items_dict[r["label"]] = [r]
for label, items in items_dict.iteritems():
results = duplicate(items)
for r in results:
news = News(r["_id"], event.id)
news.update_news_duplicate(r["duplicate"], r["same_from"])
# 更新簇的大小、增幅信息
before_size = event.get_subevent_size(label)
event.update_subevent_size(label, len(items))
event.update_subevent_addsize(label, len(items) - before_size)
if initializing:
# 更新事件状态由initializing变为active
event.activate()
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
def step3_cal():
"""计算各簇的特征词、代表文本、去重, 更新簇的大小、增幅信息
"""
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s start step3' % ts2datetime(timestamp)
inputs = []
subevents = event.getSubEvents()
for subevent in subevents:
subeventid = subevent["_id"]
inputs.extend(event.getSubeventInfos(subeventid))
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
r["label"] = r["subeventid"]
# 计算各簇的存量特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
feature = Feature(label)
feature.upsert_newest(fwords)
# 计算文本权重
for r in inputs:
weight = text_weight_cal(r, cluster_feature[r['label']])
news = News(r["_id"], event.id)
news.update_news_weight(weight)
# 文本去重
items_dict = {}
for r in inputs:
try:
items_dict[r["label"]].append(r)
except KeyError:
items_dict[r["label"]] = [r]
for label, items in items_dict.iteritems():
results = duplicate(items)
for r in results:
news = News(r["_id"], event.id)
news.update_news_duplicate(r["duplicate"], r["same_from"])
# 更新簇的大小、增幅信息
before_size = event.get_subevent_size(label)
event.update_subevent_size(label, len(items))
event.update_subevent_addsize(label, len(items) - before_size)
if initializing:
# 更新事件状态由initializing变为active
event.activate()
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
def get_cnn_feature(input, reuse, mode):
input_shape = input.get_shape().as_list()
if len(input_shape) > 4:
input = tf.reshape(input, [-1] + input_shape[2:])
is_train = True if mode == ModeKeys.TRAIN else False
with tf.variable_scope('feature_extraction', reuse=reuse):
cnn_feature = extract_feature(is_train, input)
if len(input_shape) > 4:
cnn_feature_shape = cnn_feature.get_shape().as_list()
cnn_feature = tf.reshape(cnn_feature,
input_shape[0:2] + cnn_feature_shape[1:])
return cnn_feature
# 返回pandas.DataFrame类型的特征矩阵
f_datafram = pd.DataFrame([feature[k] for k in feature.keys()],
index=list(feature.keys())).T
# 返回 FX，Fy
features = [
'mean', 'rms', 'std', 'skewness', 'kurtosis', 'maxf', 'signal_entropy',
'am_median_pdf'
]
FX, Fy = f_datafram[features], f_datafram['label']
return FX, Fy
if __name__ == "__main__":
from augment import preprocess
from feature import extract_feature
# -1- 载入数据
path = r"./data/0HP"
data_mark = "FE"
len_data = 1024
overlap_rate = 50 # 50%
random_seed = 1
fs = 12000
X, y = preprocess(path, data_mark, fs, len_data / fs, overlap_rate,
random_seed)
# -2- 提取特征
FX, Fy = extract_feature(X, y, fs)
# -*- encoding:utf8 -*- import sys from model import RandomForestModel from feature import extract_feature from model import LinearRegModel if __name__ == '__main__': try: if sys.argv[1] == 'feature': if len(sys.argv) < 3: print 'Usage: python main.py feature [train raw feature] [test raw feature]' else: features = extract_feature(sys.argv[2], sys.argv[3]) # load train features elif sys.argv[1] == 'model': if len(sys.argv) < 4: print 'usage: python main.py model [train_feature] [model_file] [test_file]' model = RandomForestModel(sys.argv[2], sys.argv[3], n_estimators = 200) """ model = LinearRegModel(sys.argv[2], sys.argv[3], alpha = 0.5) """ """ model = GBDTModle(sys.argv[2],
