def stocks_corr_analyzation(days, stock, *compare_stocks):
''' analyze the pct_change corr between stocks '''
compare_stock_data = {}
for s in compare_stocks:
try:
compare_stock_data[s.name] = get_recent_data(s.code,
s.market_code,
days,
update=False)
except Exception as e:
print_err(e)
df_compare_stocks_pct = DataFrame(
{stock: df['Adj Close']
for stock, df in compare_stock_data.items()}).pct_change()
if stock is not None:
if stock in compare_stocks:
ser_stock_pct = df_compare_stocks_pct[stock.name]
df_compare_stocks_pct.drop(columns=stock.name, inplace=True)
else:
df = get_recent_data(stock.code,
stock.market_code,
days,
update=False)
ser_stock_pct = df['Adj Close'].pct_change()
ser = df_compare_stocks_pct.corrwith(ser_stock_pct)
# 筛选出0.5以上的，并格式化
ser = ser[ser >= 0.5].map(lambda x: '{:.2f}'.format(x))
ser.name = '涨跌相关性'
return ser.to_frame()
else:
df = df_compare_stocks_pct.corr()
return df.applymap(lambda x: '{:.2f}'.format(x))
def start_scrapy():
count = 0
stocks = Stock.objects.filter()[count:]
print('[+] Total {} stocks '.format(stocks.count()))
for s in stocks:
try:
count += 1
print('[+] Scraping the {} item'.format(count))
print('[+] stock_code: {}, market_code: {}'.format(
s.code, s.market_code))
get_recent_data(s.code, s.market_code, 400)
print('[+] scrapy success.')
print('[+] sleep a random time...' + '\n')
time.sleep(random.random())
except Exception as e:
print('[-] Error happened.')
print_err(e)
def beta(stock_code, index_code, market_code):
''' 贝塔系数 '''
stock365 = get_recent_data(stock_code, market_code, 365, update=False)
if stock365.shape[0] < 200:
raise DataMissingError
index365 = get_recent_data(index_code, market_code, 365, update=False)
if index365.shape[0] < 200:
raise DataMissingError
s200 = stock365[:200]
i200 = index365[:200]
ser_s_pct = s200['Adj Close'].pct_change()
ser_i_pct = i200['Adj Close'].pct_change()
# 标准差
s_std = ser_s_pct.std()
i_std = ser_i_pct.std()
# 相关系统
corr = ser_s_pct.corr(ser_i_pct)
# 贝塔
b = corr * (s_std / i_std)
return '{:.2f}'.format(b)
def volume_mean(stock_code, market_code):
'''计算最近90,30,7交易日的平均成交量'''
_df365 = get_recent_data(stock_code, market_code, 365, update=False)
if _df365.shape[0] < 90:
raise DataMissingError
df90 = _df365[:90]
df30 = _df365[:30]
df7 = _df365[:7]
# 平均成交量
v_mean_30 = df30['Volume'].mean()
v_mean_90 = df90['Volume'].mean()
v_mean_7 = df7['Volume'].mean()
row_v_mean = Series([v_mean_90, v_mean_30,
v_mean_7]).map(lambda x: '{:.2f}'.format(x / 1000000))
return DataFrame(columns=['90日', '30日', '7日'],
index=['平均成交量/万手'],
data=[row_v_mean.values])
def recent_data(self, days):
return sdm.get_recent_data(self.code, self.market_code, days)
return self.col.delete_many(kwargs or {})
def create_index(self, col_name, unique):
return self.col.create_index([(col_name, pymongo.DESCENDING)],
unique=unique)
def is_index_exist(self, col_name):
return '{}_1'.format(col_name) in self.col.index_information()
def drop_index(self, col_name):
return self.col.drop_index('{}_1'.format(col_name))
if __name__ == '__main__':
# set up django env
import os
import sys
import django
pathname = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, pathname)
sys.path.insert(0, os.path.abspath(os.path.join(pathname, '../..')))
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "a_stock.settings")
django.setup()
import stock_analyze.helper.stock_data_manager as sd
df = sd.get_recent_data('000001', 1, 90)
sc = get_stock_collection(sd.get_stock_request_code('000001', 1))
sc.insert_dataframe(df)