def generate_feature_vector():
logger.info("In Generate Feature Vector...")
prepare_feature()
# 设置标题
title_list = list(featureDict.keys())
title_list.append('TARGET')
featureVectorList.append(title_list)
feature_size = len(featureDict.keys())
global newsFeatureList
newsFeatureList = CommonUtil.read_csv(NEWS_FEATURE_PATH)
global processedPriceList
file_path = PROCESSED_PRICE_PATH + '_' + str(
PRICE_SAMPLE_MINUTE) + CSV_FILE_SUFFIX
processedPriceList = CommonUtil.read_csv(file_path)
# 新闻从20160630开始到20171229，价格从20160701开始到20171229
last_news_begin = 0
news_feature_begin_index = last_news_begin
pre_price_item = list()
pre_price_item.append(PRICE_START_TIME)
pre_price_item.append(0)
price_start_time = CommonUtil.get_datetime_from_string(PRICE_START_TIME)
price_end_time = CommonUtil.get_datetime_from_string(PRICE_END_TIME)
# 将闭市时间内的新闻统一设置为开市前NEWS_INFLUENCE_MOST分钟时发生的
for news_index in range(0, len(newsFeatureList)):
news_feature = newsFeatureList[news_index]
news_time = news_feature[0]
# 重设新闻时间
news_feature[0] = CommonUtil.\
reset_news_time(news_time, NEWS_INFLUENCE_MOST, MARKET_OPEN_TIME, MARKET_CLOSE_TIME)
newsFeatureList[news_index] = news_feature
for current_price_item in processedPriceList:
current_price_time = CommonUtil.get_datetime_from_string(
current_price_item[0])
if price_start_time <= current_price_time < price_end_time:
# 计算价格的变化
price_delta = round(
(float(current_price_item[1]) - float(pre_price_item[1])) *
FEATURE_VECTOR_SCALE, CURRENCY_PAIR_PRECISION)
pre_price_time = CommonUtil.get_datetime_from_string(
pre_price_item[0])
logger.debug(current_price_time)
# 计算pre_price_time到current_price_time新闻的作用总和
# last_interval_minutes >= 1
last_interval_minutes = int(
CommonUtil.get_interval_seconds(current_price_time,
pre_price_time) / 60)
influence_feature_vector = [0.0] * feature_size
# 对两个价格之间的每个采样点计算新闻的影响
is_influenced_price = False
for minute_i in range(0, last_interval_minutes):
# 计算的时刻点，pre_price_time之后的时刻点，包括current_price_time
time_i = CommonUtil.get_minute_changed(pre_price_time,
minute_i + 1)
# 该时刻点受到影响对应的新闻
for news_feature_begin_index in range(last_news_begin,
len(newsFeatureList)):
interval_seconds = CommonUtil.get_interval_seconds(
time_i,
CommonUtil.get_datetime_from_string(
newsFeatureList[news_feature_begin_index][0]))
# 如果有新闻在影响范围内
if 0 <= interval_seconds <= NEWS_INFLUENCE_DACAY_THRESHOLD * 60:
for news_feature_end_index in range(
news_feature_begin_index,
len(newsFeatureList)):
if CommonUtil.get_datetime_from_string(newsFeatureList[news_feature_end_index][0]) \
> time_i:
break
str_begin_end = str(minute_i + 1) + ': news->' + str(
news_feature_begin_index) + ' : ' + str(
news_feature_end_index - 1)
logger.debug(str_begin_end)
for news_feature_index in range(
news_feature_begin_index,
news_feature_end_index):
current_news_feature = newsFeatureList[
news_feature_index]
influence_score = decay_influence(
CommonUtil.get_datetime_from_string(
current_news_feature[0]), time_i)
for value_i in range(0, feature_size):
influence_feature_vector[value_i] += float(current_news_feature[value_i + 1]) \
* influence_score
is_influenced_price = True
break
elif interval_seconds < 0:
break
last_news_begin = news_feature_begin_index
if is_influenced_price:
influence_feature_vector.append(price_delta)
featureVectorList.append(influence_feature_vector)
pre_price_item = current_price_item
file_path = FEATURE_VECTOR_PATH + '_' + str(
PRICE_SAMPLE_MINUTE) + CSV_FILE_SUFFIX
CommonUtil.write_csv(file_path, featureVectorList)
logger.info("Generate Feature Vector Done!")
