def get_tick_feng(_stock_id, _trade_date):
df = None
try:
df = ts.get_tick_data(_stock_id, date=_trade_date, retry_count=5, pause=1)
except Exception:
log_error("warn: %s get ticks exception!", _stock_id)
time.sleep(5)
return None
if df is None :
log_error("warn: stock %s, %s is None, next", _stock_id, _trade_date)
return None
if df.empty:
log_error("warn: stock %s, %s is empty, next", _stock_id, _trade_date)
return None
if len(df) <= 5:
log_error("warn: stock %s, %s is short %d, next", _stock_id, _trade_date, len(df))
return None
df = df.set_index('time').sort_index()
return df
def xtick_down100(qx, ftg):
'''
根据指定的日期，股票代码，数据文件名：ftg
下载指定股票指定日期的ticks数据，并保存到ftg
[输入]
qx.code，股票代码
qx.xtimSgn，当前日期的字符串
ftg，保存tick数据的文件名
'''
df, dn = [], 0
try:
df = ts.get_tick_data(qx.code, date=qx.xtimSgn) # print(df.head())
except IOError:
pass # skip,error
datFlag, dn = False, len(df)
print(' n', dn, ftg) # 跳过无数据 日期
# if zwt.xin(dn,0,9):print('n2',dn,ftg)
if dn > 10:
df['type'] = df['type'].str.replace(u'中性盘', 'norm')
df['type'] = df['type'].str.replace(u'买盘', 'buy')
df['type'] = df['type'].str.replace(u'卖盘', 'sell')
df.to_csv(ftg, index=False, encoding='utf')
datFlag = True
#
return datFlag, dn
def get_tick_history(exsymbol, days=10):
store = get_store(store_type)
dates = store.get('id000001').index
symbol = exsymbol_to_symbol(exsymbol)
df_res = pd.DataFrame(columns=["kaipan_vol", "kaipan_money", "shoupan_vol", "shoupan_money"])
for i in range(days, 0, -1):
date = dates[len(dates)-i].strftime("%Y-%m-%d")
df = ts.get_tick_data(symbol, date=date, src="tt")
if df is None or len(df) == 0:
continue
df["time"] = pd.to_datetime(df["time"], format='%H:%M:%S')
kaipan_time = df.iloc[0].time
kaipan_vol = 0
kaipan_money = 0
if kaipan_time.hour == 9 and kaipan_time.minute < 30:
kaipan_vol = df.iloc[0].volume
kaipan_money = df.iloc[0].amount
shoupan_time = df.iloc[len(df)-1].time
shoupan_vol = 0
shoupan_money = 0
if shoupan_time.hour >= 15 and shoupan_time.minute >= 0:
shoupan_vol = df.iloc[len(df)-1].volume
shoupan_money = df.iloc[len(df)-1].amount
df_res.loc[date] = [kaipan_vol, kaipan_money, shoupan_vol, shoupan_money]
return df_res
def __init__(self, tableName):
'''
Constructor
'''
bdl.BaseDataLoader.__init__(self, tableName)
#self.db = msql.MySQLConnection.GetConnection()
#self.ml = mlg.MyLogger.getLogger()
#tradingday = datetime.strftime(datetime.today(), "%Y-%m-%d")
code = '600848'
tradingday = '2015-11-30'
self.ml.info("Loading Data")
data = ts.get_tick_data(code=code, date=tradingday)
data['tradingday'] = tradingday
data['code'] = code
indexdata = data.set_index(['tradingday', 'code'])
self.ml.info("Saving Data")
indexdata.to_sql(self.tableName, self.db, flavor="mysql", if_exists="append")
#关闭连接
#db.close()
self.ml.info("Saving Success")
def get_in_out(symbol, date):
df = ts.get_tick_data(symbol, date=date, src='tt')
thre = df.amount.quantile(0.99)
thre = np.max([thre, 1e6])
in_amount = df[(df.amount>thre)&(df.type=="买盘")].amount.sum()/1e8
out_amount = df[(df.amount>thre)&(df.type=="卖盘")].amount.sum()/1e8
return [in_amount, out_amount]
def db():
df = ts.get_tick_data('600848', date='2014-12-22')
engine = create_engine('mysql://*****:*****@127.0.0.1/mystock?charset=utf8')
# db = MySQLdb.connect(host='127.0.0.1',user='******',passwd='jimmy1',db="mystock",charset="utf8")
# df.to_sql('TICK_DATA',con=db,flavor='mysql')
# db.close()
df.to_sql('tick_data', engine, if_exists='append')
def get_sd(id, label_start_date, fea_delta = 240):
# delta 指的是 确定label；的时候 是一个星期的涨幅还是什么
# fea delta 指的是， 我要准备多久的数据
## 获取分笔数据
# get all time ticks
# 创建一个日期列表
ticks = None
date_list = dt_tool.dt_range(label_start_date, -fea_delta)
for date in date_list:
try:
tick = ts.get_tick_data(id, date)
except Exception, e:
print e
continue
if tick is None:
continue
tick.type = tick.type.apply(lambda x : type2id(x))
ft = tick.sort('amount', ascending=False).head(10).reset_index().drop(['index', 'time', 'change'], 1).stack().reset_index()
ft.index = ft.level_0.map(str) + '_' + ft.level_1
fT = ft.drop(['level_0', 'level_1'], 1).T
fT['date'] = dt_tool.format(date)
if ticks is None:
ticks = fT
else:
ticks = ticks.append(fT)
ticks.to_csv('data/ticks.csv', index=None)
def get_tick(code, start, end=None, file=None):
date = get_dates(start, end)
if not file:
file = '-'.join([code, start.replace('-', ''), str(len(date))]) + r'.csv'
for d in date:
df = ts.get_tick_data(code, date=d)
df.to_csv(file, mode='a')
def deal_list_download(self, stock, engine, start='2014-10-16'):
'''
分时数据下载
'''
deals = ts.get_tick_data(stock, date='2015-10-16')
table_name = stock + '_deal'
deals.to_sql(table_name, engine)
def multi_write((start_date,end_date)):
startdate=datetime.datetime.strptime(start_date,'%Y-%m-%d').date()
enddate = datetime.datetime.strptime(end_date, '%Y-%m-%d').date()
#string-to-dateobject conversion
date_list=date_loop.date_loop(start_date= startdate,end_date= enddate)
#return a list of date
#engine=create_engine('mysql+mysqldb://root:15921998273@localhost:3306/tusharedb?charset=utf8')
DTS=[]
for dates in date_list:
preDTS = ts.get_tick_data('600640', date=dates)
#DTS=Data To be Saved
try:
preDTS['type'][0].split()
#throw an AttributeError when no data is available
preDTS.sort_index(axis=0, ascending=True)
#reverse the dataframe with latest data placed at the bottom
preDTS['date'] = dates
#insert date column
#sql table will be named like 'hist_Part0,1,2,3,4...'
DTS.append(preDTS)
except AttributeError:
print 'No available data for ', dates
try:
DTS = pd.concat(DTS)
except ValueError :
DTS=None
return DTS
def get_tick_data(self, code, t_date = None):
if t_date is None:
t_date = dataTime.datetimeRelative(delta = 0)
t_date = t_date.replace(' 00:00:00', '')
df = ts.get_tick_data(code, date = t_date)
df = self.format_date_to_datetime(df, t_date = t_date)
return df
def pankou(name):
# rang =pd.date_range('20150101', periods=5)
# a = ts.get_tick_data(code, rang)
a = ts.get_tick_data(name, date='2017-03-09')
buy_sum = 0
sell_sum = 0
other_sum = 0
for item in range(0, len(a)):
row = a[item:item + 1]
type = row['type']
if type[item] == '卖盘':
sell_sum += row['amount'][item]
elif type[item] == '买盘':
buy_sum += row['amount'][item]
else:
other_sum += row['amount'][item]
pan_sum = sum([sell_sum, buy_sum, other_sum])
mp = buy_sum / pan_sum
sp = sell_sum / pan_sum
zx = other_sum / pan_sum
# print('股票',code,(sell_sum, buy_sum, other_sum)/pan_sum)
print('股票', name, mp, sp, zx)
if isnan(mp):
return
with UseDatabase(config) as cursor:
_SQL = """insert into pankou
(name, mp, sp, zx)
values
(%s, %s, %s, %s)"""
cursor.execute(_SQL, (name, mp, sp, zx))
def request_test_tick(code, engine, start_date, end_date):
create_test_talbe(code)
cur_day = start_date
logging.info('requesting tick, code: ' + code + str(threading.currentThread()))
while cur_day != end_date:
try:
#logging.info('cur_day: ' + str(cur_day) + str(threading.currentThread()))
tick = ts.get_tick_data(code, date=cur_day.date(), retry_count=500, src='tt')
if not tick.empty:
if tick.time[0] != 'alert("当天没有数据");':
tick['type'] = tick['type'].apply(lambda x: trade_type_dic[x])
tick['change'] = tick['change'].apply(change_dic)
tick['time'] = str(cur_day.date()) + ' '+ tick['time']
tick.to_sql('test_' + code, engine, if_exists='append', dtype={'time': DateTime})
logging.info('save to test_' + code + ' on '+ str(cur_day) + ' thread ' + str(threading.currentThread()))
except Exception:
logging.error(str(code) + ' request tick failed on ' + str(cur_day) + str(threading.currentThread()))
delta = datetime.timedelta(days=1)
cur_day = cur_day + delta
def tick(tstamp):
date = tstamp.split(" ")[0]
tick_data = ts.get_tick_data(code,date=date,retry_count=10,pause=5)
nrows = tick_data.shape[0]
tick_data['date'] = pd.Series([date]*nrows)
return tick_data
def check_if_reach_limit(code, date=datetime.now().strftime("%Y-%m-%d")):
"""
"""
kdata = ts.get_hist_data(code,date,date,ktype='D')
if kdata.ix[0]['p_change'] < 9.9:
return False
stock = ts.get_tick_data(code,date)[['time','price']]
indx, = np.where(np.diff(list(reversed(stock['price'])))==0)
# print "length: ", len(indx)
arr = []
beg = 0
cur = indx[0]-1
for i,val in enumerate(indx):
if cur+1 == val:
cur += 1
else:
if i > (beg+1):
arr.append((indx[beg], indx[i-1]))
beg = i
cur = val
arr.append((indx[beg],cur))
mindx = np.argmax([x[1]-x[0] for x in arr])
print "length of arr: ", len(arr)
p = arr[mindx][0]
print 'starting index: ', p
print 'starting time: ', stock.ix[stock.shape[0]-p-1]['time']
return stock.ix[stock.shape[0]-p-1]['time']
def multi_write((code,start_date,end_date)):
startdate=datetime.datetime.strptime(start_date,'%Y-%m-%d').date()
enddate = datetime.datetime.strptime(end_date, '%Y-%m-%d').date()
#string-to-dateobject conversion
date_list=date_loop.date_loop(start_date= startdate,end_date= enddate)
#return a list of dates
DTS=[]
for dates in date_list:
preDTS = ts.get_tick_data(code, date=dates)
#DTS=Data To be Saved
try:
preDTS['type'][0].split()
#throw an AttributeError when no data is available
preDTS['date'] = dates
#insert date column
preDTS=preDTS.sort_values(by='time',ascending= True)
#sql table will be named like 'hist_Part0,1,2,3,4...'
DTS.append(preDTS)
except AttributeError:
print 'No available data for ', dates
try:
DTS = pd.concat(DTS)
except ValueError :
DTS=None
return DTS
def get_multiday_ave_compare_silent(code, dayl='10'):
dtick = ts.get_today_ticks(code)
d_hist = ema.getdata_ema_trend_silent(code, dayl, 'd')
# print d_hist
day_t = ema.get_today()
if day_t in d_hist.index:
dl = d_hist.drop(day_t).index
else:
dl = d_hist.index
# print dl
# print dl
ep_list = []
for da in dl.values:
# print code,da
td = ts.get_tick_data(code, da)
# print td
if not type(td) == types.NoneType:
ep = td['amount'].sum() / td['volume'].sum()
ep_list.append(ep)
# print ("D: %s P: %s" % (da[-5:], ep))
ave = ema.less_average(ep_list)
if len(dtick.index) > 0:
ep = dtick['amount'].sum() / dtick['volume'].sum()
p_now = dtick['price'].values[0] * 100
if p_now > ave or ep > ave:
print ("GOLD:%s ep:%s UP:%s!!! A:%s %s !!!" % (code, ep, p_now, ave, get_now_time()))
# elif p_now > ave and ep < ave:
# print ("gold:%s ep:%s UP:%s! A:%s %s !" % (code, ep, p_now, ave, get_now_time()))
# elif p_now < ave and ep > ave:
# print ("down:%s ep:%s Dow:%s? A:%s %s ?" % (code, ep, p_now, ave, get_now_time()))
return True
else:
if p_now < ave and ep < ave:
print ("DOWN:%s ep:%s now:%s??? A:%s %s ???" % (code, ep, p_now, ave, get_now_time()))
return False
def nosql():
import pymongo
import json
conn = pymongo.Connection('127.0.0.1', port=27017)
df = ts.get_tick_data('600848', date='2014-12-22')
print(df.to_json(orient='records'))
conn.db.tickdata.insert(json.loads(df.to_json(orient='records')))
def virance_a_day(day):
try:
datas = tushare.get_tick_data(code, date=day, retry_count = 5)
prices = [value[1] for value in datas.values]
ave_price = sum(prices) / len(prices)
virance = sum([(price - ave_price) ** 2 for price in prices])
return virance
except:
return None
def get_zhangting_sell(symbol, date):
df = ts.get_tick_data(symbol, date=date, src='tt')
high = df.price.max()
df_zt = df[(df.price==high) & (df.type=="卖盘")]
thre = df_zt.amount.quantile(0.99)
thre = np.max([thre, 1e6])
inst_amount = df_zt[df_zt.amount >= thre].amount.sum() / 1e8
total_amount = df_zt.amount.sum() / 1e8
return [inst_amount, total_amount]
def tick(code,date):
dftick = ts.get_tick_data(code,date=date)
dftick.insert(0,'uploadtime',nowtime)
dftick.insert(0,'code',code)
dftick.to_sql('mkt_tick',engine,if_exists='append')
counttick = cursor.execute('show columns from mkt_tick like \'tick_id\'')
if counttick == 0:
insertidtick()
def get_acf(code):
day = get_last_day()
print str(day)
today_prices = tushare.get_tick_data(code=code,
date=str(day-datetime.timedelta(days=3)),
retry_count=50)
today_prices = [(value[0], value[1]) for value in today_prices.values]
train_prices = [price for time, price in today_prices if time > "13:00:00"]
return ar_model.AR.fit(train_prices)
def _fill_history_bars(self, replay_days):
now = datetime.datetime.now()
for day in get_trading_days(now, replay_days):
bars_dict = {}
for identifier in self.__identifiers:
df = ts.get_tick_data(identifier, date=day.date().isoformat())
bars_dict[identifier] = get_bar_list(df, self.__frequency, day)
self.__fill_bars(bars_dict)
def get_acf(code):
print code
today = datetime.date.today()
print str(today)
today_prices = tushare.get_tick_data(code=code, date=str(today),
retry_count=50)
print today_prices
today_prices = [(value[0], value[1]) for value in today_prices.values]
train_prices = [price for time, price in today_prices if time > "13:00:00"]
print train_prices
def get_stock_intraday_data(code, date):
"""
获取一只股票的历史某天的日内交易数据，让后保存到csv文件中
"""
data_frame = ts.get_tick_data(code, date=date)
current_dir = os.path.dirname(__file__)
ab_path = os.path.join( current_dir, "..\\", "..\\" )
data_root_path = os.path.abspath( ab_path ) + "\\intradate_data\\"
code_path = data_root_path + code
if not os.path.exists(code_path):
os.makedirs(code_path)
save_path = code_path + "\\" + date + ".csv"
data_frame.to_csv(save_path, encoding='utf-8', index=False)
def Get_stock_ticks(code, time_to_market):
import tushare as ts
import pandas as pd
import logging
import datetime as dt
import os
import socket
import pydoop.hdfs as hdfs
import shutil
if time_to_market !=0:
logger = logging.getLogger("D_stock")
logger_handler=logging.FileHandler("/tmp/D_stock.log")
logger_handler.setFormatter(logging.Formatter("%(asctime)s -- %(message)s"))
logger_handler.setLevel(logging.DEBUG)
logger.setLevel(logging.DEBUG)
logger.addHandler(logger_handler)
logger.info(">"*15+code+">"*15)
all_days=pd.date_range(start=str(time_to_market),end=dt.date.today(),freq="B")
all_days=[x.date() for x in all_days]
for day in all_days[::-1]:
logger.info("Saving "+code+"@"+str(day)+"...")
while True:
try:
df=ts.get_tick_data(code,date=day)
except Exception as e:
print e
continue
break
if df.index.size >3:
dir_name="/tmp/ticks/"+str(code)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
file_name=dir_name+"/"+str(day)+".csv"
df.to_csv(file_name)
"""
Write to HDFS
"""
if os.path.exists(dir_name):
s=hdfs.hdfs(host="spark-1",port=9000)
if not s.exists("ticks"):
s.create_directory("ticks")
hdfs.put(dir_name,"./ticks/")
shutil.rmtree(dir_name)
logger.info("<"*15+code+"<"*15)
return (socket.gethostname(),code)
def get_tick(stockCode=None, date=None):
"""
根据股票列表的股票代码获取当日/指定日期历史分笔
Return
--------
DataFrame
"""
tick_data = ''
if date != None and date != '':
tick_data = ts.get_tick_data(stockCode, date)
else:
tick_data = ts.get_today_ticks(stockCode)
if not tick_data.dropna(axis=0, how='any', thresh=None).empty:
tick_data.insert(0, 'code', stockCode) #插入股票代码字段
return tick_data
def get_data(stock_id,date):
if os.path.exists(stock_id+'_'+date+'.xlsx'):
df = pd.read_excel(stock_id+'_'+date+'.xlsx')
else:
df = ts.get_tick_data(stock_id,date=date)
df['type'] = df['type'].apply(lambda x:x.decode('utf8','ignore'))
df.to_excel(stock_id+'_'+date+'.xlsx')
tmp = df[['time','price']]
tmp = df.sort_index(by=['time'],ascending=True)
X = tmp['price'].values
#plt.figure()
plt.plot(X)
plt.plot(quad_smooth(X,50))
def get_stock_data():
while True:
code = random.choice(codes)
prices = []
days = ["2015-12-05", "2015-12-06", "2015-12-07", "2015-12-08", "2015-12-09"]
prices = []
for day in days:
df = tushare.get_tick_data(code, day)
for p in df['price']:
if not math.isnan(p):
prices.append(p)
if len(prices) >= 2000:
max_p = max(prices)
min_p = min(prices)
return map(lambda x: -1.0+(x-min_p)/(max_p-min_p),
prices)
def download_stock_quotes(code, date_start='', date_end=str(datetime.date.today())):
code = util.getSixDigitalStockCode(code)
try:
if date_start == '':
date = datetime.datetime.today().date() + datetime.timedelta(-365*3)
date_start = str(date)
dateStart = datetime.datetime.strptime(str(date_start), "%Y-%m-%d")
for i in range(du.diff_day(date_start, date_end)):
date = dateStart + datetime.timedelta(i)
strDate = date.strftime("%Y-%m-%d")
df = ts.get_tick_data(code, strDate)
print df
except Exception as e:
print str(e)
# -*- coding: utf-8 -*-
"""
Created on Tue Feb 9 18:02:42 2016
@author: Administrator
"""
#==============================================================================
# 主力资金流数据
#==============================================================================
import tushare as ts
stock_data = ts.get_tick_data('600428', date='2016-02-05')
# 计算平均每笔成交量
print('平均每笔成交量:%d手' % stock_data['volume'].mean())
# 计算资金流入流出
data = stock_data.groupby('type')['amount'].sum()
if '买盘' in data.index:
print('资金流入:%d元' % data['买盘'])
if '卖盘' in data.index:
print('资金流出:%d元' % data['卖盘'])
# 计算主力资金流入流出
data = stock_data[stock_data['volume'] > 500].groupby('type')['amount'].sum()
if '买盘' in data.index:
print('主力资金流入:%d元' % data['买盘'])
if '卖盘' in data.index:
print('主力资金流出:%d元' % data['卖盘'])
mp = 446.74 * 100000000
b_r = 0.0002
m_r = b_r / 2
code, time_to_market = data
time_to_market = '20170104'
lastdate = date_add(str(time_to_market), 0, '%Y%m%d')
while lastdate <= today_date:
print lastdate
try:
open_price, close_price = session.execute(
'select open,close from day_k_data where code in ("002230") and date="'
+ lastdate + ' 00:00:00.000000";').fetchall()[0]
except:
lastdate = date_add(lastdate, 1, '%Y-%m-%d')
continue
df = ts.get_tick_data(code, date=lastdate, pause=2)
df.insert(0, 'date', lastdate)
df.insert(0, 'code', code)
df = df.set_index('date')
fq = round(df.iloc[0]['price'] / close_price, 3)
df['change'][df['change'] == '--'] = 0.0
df['change'] = df['change'].apply(float)
df['type'][df['change'] == 0.0] = 'equal'
df['type'][df['change'] > 0] = 'buy'
df['type'][df['change'] < 0] = 'sell'
df['price'] = (df['price'] / fq).apply(round, args=(3, ))
df['change'] = df['change'] / fq
df['change'] = df['change'].apply(round, args=(3, ))
df_count = {}
print b_r * mp
df_count['big_buy'] = df['amount'][(df['type'] == 'buy')
def to_mongodb():
import pymongo
import json
conn=pymongo.Connection ('127.0.0.1',port =27017)
df=ts.get_tick_data('600848',date='2014-12-22')
conn.db.tickdata.insert(json.loads(df.to_json(orient ='records')))
股票数据：名称、上市交易所 上市时间， 历史日数据
历史某天的分笔数据
'''
#DataAPI.TickRTIntraDayMoneyFlowOrderGet(securityID=u"000001.XSHE",startTime=u"09:30",endTime=u"11:00",field=u"",pandas="1")
eq_mt = ts.Master()
SecID = eq_mt.SecID(cnSpell='gxgk')
eq_tl = ts.Equity()
candi_stock_ipo = eq_tl.EquIPO(secID='002074.XSHE')
candi_stock_d = ts.get_h_data('002074', start='2006-10-18', end='2016-04-12')
## 获取历史分笔数据
candi_stock_fb = ts.get_tick_data('002074', date='2016-04-12')
candi_stock_fb.head(10)
dates = pd.to_datetime(shz.index)
## 第一种作图方法
def simple_plot(dates, data):
fig = plt.figure(figsize=(10, 4))
plt_sh = fig.add_subplot(1, 1, 1)
daysFmt = mdates.DateFormatter('%m-%d-%Y')
plt_sh.plot(dates, data, color='b', linewidth=1.5)
plt_sh.xaxis.set_major_formatter(daysFmt)
plt_sh.autoscale_view()
plt_sh.fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
fig.autofmt_xdate()
df.to_csv('603299_60_Mins.csv')
open('603299_30_Mins.csv','w')
df=ts.get_hist_data('603299',ktype='30') #获取上证指数k线数据
df.to_csv('603299_30_Mins.csv')
open('603299_15_Mins.csv','w')
df=ts.get_hist_data('603299',ktype='15') #获取上证指数k线数据
df.to_csv('603299_15_Mins.csv')
open('603299_5_Mins.csv','w')
df=ts.get_hist_data('603299',ktype='5') #获取上证指数k线数据
df.to_csv('603299_5_Mins.csv')
# 历史分笔数据 获取2016-01-11以及2016-01-12的分笔数据
open('603299_fb060111.csv','w')
df = ts.get_tick_data('603299',date='2016-01-11')
df.to_csv('603299_fb060111.csv')
open('603299_fb060112.csv','w')
df = ts.get_tick_data('603299',date='2016-01-12')
df.to_csv('603299_fb060112.csv')
# # 大单交易数据 获取2016-01-11以及2016-01-12的大于600手的数据，目前这个数据可能出现了bug
# open('603299_ddsj060111.csv','w')
# df = ts.get_sina_dd('603299', date='2016-01-11', vol=500) #指定大于等于500手的数据
# df.to_csv('603299_ddsj060111.csv')
#
# open('603299_ddsj060112.csv','w')
# df = ts.get_sina_dd('603299', date='2016-01-12', vol=500) #指定大于等于500手的数据
# df.to_csv('603299_ddsj060112.csv')
def ts_handle_data(addcsv, prepath, bhist, url, code, qdate, sarr):
todayUrl = "http://hq.sinajs.cn/list=" + code
#if Handle_Mid==0:
# print "Message: Ignore 中性盘"
if not os.path.isdir(prepath):
os.makedirs(prepath)
dataObj = []
if cmp(sarr, '')==0:
sarr = dftsarr
volObj = sarr.split(',')
arrlen = len(volObj)
for i in range(0,arrlen):
obj = fitItem(int(volObj[i]))
dataObj.append(obj)
wb = Workbook()
# grab the active worksheet
ws = wb.active
totalline = 0
filename = code+ '_' + qdate
fctime = ''
todayData = []
todayDataLen = 0
bGetToday = 0
last_close = 0
cur=datetime.datetime.now()
if bhist==0:
fctime = '%02d:%02d' %(cur.hour, cur.minute)
filename = '%s_%02d-%02d' %(filename, cur.hour, cur.minute)
bGetToday = 1
if (bhist==2 and cur.hour>=15 and cur.minute>0):
bGetToday = 1
if (bGetToday==1):
try:
req = urllib2.Request(todayUrl)
stockData = urllib2.urlopen(req, timeout=5).read()
except:
loginfo(1)
print "URL timeout"
else:
stockObj = stockData.split(',')
if len(stockObj)<10:
print code, ": No trade data"
return -1
closePrice = float(stockObj[3])
lastClsPrice = float(stockObj[2])
last_close = lastClsPrice
openPrice = float(stockObj[1])
highPrice = float(stockObj[4])
lowPrice = float(stockObj[5])
exVolume = int(stockObj[8])/100
exAmount = float(stockObj[9])
f1 = '%02.02f'%( ((closePrice-lastClsPrice)/lastClsPrice)*100 )
exFluc = float(f1)
todayData.append(closePrice)
todayData.append(exFluc)
todayData.append(lastClsPrice)
todayData.append(openPrice)
todayData.append(highPrice)
todayData.append(lowPrice)
todayData.append(exVolume)
todayData.append(exAmount)
todayDataLen = len(todayData)
if addcsv==1:
filecsv = prepath + filename + '.csv'
fcsv = open(filecsv, 'w')
strline = '成交时间,成交价,涨跌幅,价格变动,成交量,成交额,性质'
fcsv.write(strline)
fcsv.write("\n")
strline = u'成交时间,成交价,涨跌幅,价格变动,成交量,成交额,性质,收盘价,涨跌幅,前收价,开盘价,最高价,最低价,成交量,成交额'
strObj = strline.split(u',')
ws.append(strObj)
stockInfo = []
#每一页的数据，如果找到匹配数据则设置为1；解决有时候页面有数据但是收不到，
#count为0，重新加载尝试再次获取；如果解析到数据的页面，如果count为0就不再继续解析数据
matchDataFlag = 0
excecount = 0
savedTrasData = []
savedTrasData2 = []
largeTrasData = []
i = 1
curcode = code
if len(code)==8:
curcode = code[2:8]
#历史当天行情数据通过此方法获得
if bhist==1:
df = ts.get_hist_data(curcode, start=qdate, end=qdate)
if df is None or df.empty or len(df)!=1:
print qdate, ": No data"
return -1
#print qdate, df
for index,row in df.iterrows():
last_close = float(row['close'])-float(row['price_change'])
stockInfo.append(row['close'])
stockInfo.append(row['p_change'])
stockInfo.append(last_close)
stockInfo.append(row['open'])
stockInfo.append(row['high'])
stockInfo.append(row['low'])
stockInfo.append(row['volume'])
stockInfo.append(row['turnover'])
while excecount<=3:
if bhist==0:
df = ts.get_today_ticks(curcode)
else:
df = ts.get_tick_data(curcode, qdate)
#print df
if df is None:
excecount += 1
continue;
if df.size==18:
excecount += 1
continue;
else:
break;
#尝试3次，检查结果
if df is None:
print qdate, ": None Object"
return -1
if df.size==18:
print qdate, ": Fail to get data"
return -1
for index,row in df.iterrows():
curtime = row['time']
curprice = row['price']
range_per = ''
if last_close!=0:
range_val = ((float(curprice)-last_close) * 100) / last_close
range_per = round(range_val, 2)
fluctuate = row['change']
curvol = int(row['volume'])
volume = curvol
amount = row['amount']
if bhist==0:
state = row['type']
else:
state = row['type'].decode('utf-8')
#print state.decode('utf8')
ret,hour,minute,second = parseTime(curtime)
if (ret==-1):
continue
if (int(amount)==0 and not (hour==15 and minute==0)):
continue
bAddVolumn = 1
if (hour==9 and minute==25) or (hour==15 and minute==0):
bAddVolumn = 0
stateStr = state
st_buy = '买盘'.decode('gbk')
st_sell = '卖盘'.decode('gbk')
st_mid = '中性盘'.decode('gbk')
if cmp(state, st_sell)==0:
if bAddVolumn==1:
handle_volumn(volume, dataObj, 2)
stateStr = 'SELL卖盘'.decode('gbk')
elif cmp(state, st_buy)==0:
if bAddVolumn==1:
handle_volumn(volume, dataObj, 1)
#目前中性盘没有处理
elif cmp(state, st_mid)==0:
if bAddVolumn==1:
ret = handle_middle_volumn(volume, dataObj, curtime, fluctuate, 0)
else:
ret = 0
if ret==1:
stateStr = st_buy
elif ret==2:
stateStr = st_sell
if addcsv==1:
strline = curtime +","+ curprice +","+ range_per +","+ fluctuate +","+ curvol +","+ amount +","+ stateStr + "\n"
fcsv.write(strline)
totalline += 1
row = totalline+1
price = float(curprice)
cell = 'A' + str(row)
ws[cell] = curtime
cell = 'B' + str(row)
ws[cell] = price
cell = 'C' + str(row)
ws[cell] = range_per
cell = 'D' + str(row)
ftfluct = fluctuate
if (fluctuate=='--'):
ws[cell] = fluctuate
else:
ftfluct = float(fluctuate)
ws[cell] = ftfluct
cell = 'E' + str(row)
ws[cell] = curvol
cell = 'F' + str(row)
ws[cell] = int(amount)
cell = 'G' + str(row)
s1 = stateStr
ws[cell] = s1
#将当天的数据在Sheet页面更新
if (row==2 and (bhist==0 or bhist==1 or (bhist==2 and cur.hour>=15)) and todayDataLen>0):
ascid = 72
for k in range(0, todayDataLen):
cell = chr(ascid+k) + str(row)
ws[cell] = todayData[k]
#将开始和最后成交数据保存
bSaveFlag = 0
if (totalline==1 or (totalline<4 and curvol>100)):
bSaveFlag = 1
elif (hour==9 and minute==30 and curvol>300) or (hour==9 and minute<30):
bSaveFlag = 2
if bSaveFlag==1 or bSaveFlag==2:
rowData = []
rowData.append(curtime)
rowData.append(price)
rowData.append(range_per)
rowData.append(ftfluct)
rowData.append(curvol)
rowData.append(int(amount))
rowData.append(s1)
if bSaveFlag==1:
savedTrasData.append(rowData)
elif bSaveFlag==2:
savedTrasData2.append(rowData)
#增加大单成交记录
if (curvol>=Large_Volume):
rowData = []
rowData.append(curtime)
rowData.append(price)
rowData.append(range_per)
rowData.append(ftfluct)
rowData.append(curvol)
rowData.append(int(amount))
rowData.append(s1)
largeTrasData.append(rowData)
if (row==2 and bhist==1):
ascid = 72
number = len(stockInfo)
for k in range(0,number):
cell = chr(ascid+k) + str(row)
ws[cell] = stockInfo[k]
ws.auto_filter.ref = "A1:G1"
if addcsv==1:
fcsv.close()
if (totalline==0):
os.remove(filecsv)
if totalline>0:
startIdx = 0
savedTrasLen = len(savedTrasData2)
if savedTrasLen>0:
if savedTrasLen>Tras_Count:
startIdx = savedTrasLen-Tras_Count
for j in range(startIdx, savedTrasLen):
savedTrasData.append(savedTrasData2[j])
ws = wb.create_sheet()
write_statics(ws, fctime, dataObj, qdate, savedTrasData, largeTrasData)
filexlsx = prepath +filename+ '.xlsx'
if (os.path.exists(filexlsx) and bhist==0):
j = 1
while True:
filexlsx = prepath + filename + '_' + str(j) + '.xlsx'
j += 1
if not os.path.exists(filexlsx):
break;
wb.save(filexlsx)
return 0
def add_money_flow():
"""
沪深300生成小单统计数据
tips:成交明细列表中的买盘/卖盘：“买盘”表示以比市价高的价格进行委托买入，并已经“主动成交”，代表外盘；
“卖盘”表示以比市价低的价格进行委托卖出，并已经“主动成交”，代表内盘
:return:
"""
print('插入历史现金流信息开始......')
try:
hs300_index = tushare.get_hs300s()
ts_codes = hs300_index['code'].apply(util.stock_code_change)
for ts_code in ts_codes:
daily_info = tushare.pro_bar(ts_code,
api=tushare_data.get_tushare_pro())
if daily_info is None:
continue
for index, row in daily_info.iterrows():
date = row['trade_date']
date = date[:4] + '-' + date[4:6] + '-' + date[6:]
code = row['ts_code'][:6]
if date > '2018-06-30':
df = tushare.get_tick_data(code, date=date, src='tt')
if df is None:
continue
total_amt = df['amount'].sum()
total_vol = df['volume'].sum()
sell_trade = df.loc[(df['type'] == '卖盘')]
total_sell_vol = sell_trade['volume'].sum()
total_sell_amt = sell_trade['amount'].sum()
small_trade_amount = util.trade_scale(row['close'])
sell_sm_trade = df.loc[(df['type'] == '卖盘') &
(df['amount'] < small_trade_amount)]
sell_sm_vol = sell_sm_trade['volume'].sum()
sell_sm_amt = sell_sm_trade['amount'].sum()
buy_trade = df.loc[(df['type'] == '买盘')]
total_buy_vol = buy_trade['volume'].sum()
total_buy_amt = buy_trade['amount'].sum()
buy_sm_trade = df.loc[(df['type'] == '买盘') &
(df['amount'] < small_trade_amount)]
buy_sm_vol = buy_sm_trade['volume'].sum()
buy_sm_amt = buy_sm_trade['amount'].sum()
total_sm_trade = df.loc[df['amount'] < small_trade_amount]
total_sm_amt = total_sm_trade['amount'].sum()
total_sm_vol = total_sm_trade['volume'].sum()
id = code + row['trade_date']
tables.add_money_flow(id=id,
code=code,
date=row['trade_date'],
sell_sm_vol=sell_sm_vol,
sell_sm_amt=sell_sm_amt,
buy_sm_vol=buy_sm_vol,
buy_sm_amt=buy_sm_amt,
total_sell_vol=total_sell_vol,
total_sell_amt=total_sell_amt,
total_buy_vol=total_buy_vol,
total_buy_amt=total_buy_amt,
total_amt=total_amt,
total_vol=total_vol,
total_sm_amt=total_sm_amt,
total_sm_vol=total_sm_vol)
print('插入历史现金流信息完成......')
except Exception as err:
print('插入历史现金流信息失败......')
raise err
def generateline(stocknumber,Type,startdate,enddate,interval):
startdata = startdate.encode("ascii").replace("/","-").replace("\n","") #convert to tushare readable date
enddata = enddate.encode("ascii").replace("/","-").replace("\n","")
#print startdata
#print enddata
current_time = time.strftime("%Y/%m/%d")
if Type == "分笔".decode("utf-8"):
if startdate!=current_time:
array = ts.get_tick_data(stocknumber, date = startdata)#分笔
if array is None:
return
array = array.sort_values("time")
date = array["time"].tolist()
amount = array["amount"].tolist()
atype = array["type"].tolist()
price = array["price"].tolist()
flag = ["bar" for i in date]
for idx,val in enumerate(atype):#if卖盘，交易变成负数
if val == "卖盘":
amount[idx] = -amount[idx]
if val == "中性盘":#if中性盘，则忽略. Might have a problem with this part??
amount[idx] = 0
returnarray = zip(date,amount,flag,price)
return returnarray
else:
array = ts.get_today_ticks(stocknumber)#Tushare里今日分笔和历史分笔需要分别对待
if array is None:
return
array = array.sort_values("time")
date = array["time"].tolist()
amount = array["amount"].tolist()
atype = array["type"].tolist()
flag = ["bar" for i in date]
for idx, val in enumerate(atype):
if val == "卖盘".decode("utf-8"):
amount[idx] = -amount[idx]
if val == "中性盘".decode("utf-8"):
amount[idx] = 0
returnarray = zip(date, amount, flag)
return returnarray
if Type=="季度饼图".decode("utf-8"):
datestr = startdate.split("/")
thisyear = datestr[0]
df2 = ts.top10_holders(code=stocknumber, gdtype="1")
test = df2[1]["quarter"].tolist()
df_ready = df2[1]
idxlist = []
for idx, val in enumerate(test):
a = val.split("-")
if a[0] == thisyear:
# print a[0],idx
idxlist.append(idx)
thing = df_ready.loc[idxlist]
thing = thing.sort_values(["quarter", "name"])
# print a[0],id
name = thing["name"].tolist()
value = thing["hold"].tolist()
quarter = thing["quarter"].tolist()
namearray = [name[i:i + 10] for i in xrange(0, len(name), 10)]
valuearray = [value[j:j + 10] for j in xrange(0, len(value), 10)]
quarterarray = [quarter[k:k + 10] for k in xrange(0, len(quarter), 10)]
flag = ["pie" for i in namearray]
num = [len(value) for k in namearray]
returnarray = zip(namearray,valuearray,quarterarray,flag,num)
return returnarray
if interval!="qfq" and interval!="hfq":
if interval=="1min" or interval=="5min" or interval=="15min" or interval=="30min" or interval=="60min":
df = ts.get_tick_data(stocknumber, date=startdata)
df.sort_values("time")
a = startdata + " " + df["time"]
df["time"] = a
df["time"] = pd.to_datetime(a)
df = df.set_index("time")
price_df = df["price"].resample(interval).ohlc()
price_df = price_df.dropna()
vols = df["volume"].resample(interval).sum() #relevant data processing algorithm taken from Jimmy, Creator of Tushare
vols = vols.dropna()
vol_df = pd.DataFrame(vols, columns=["volume"])
amounts = df["amount"].resample(interval).sum()
amounts = amounts.dropna()
amount_df = pd.DataFrame(amounts, columns=["amount"])
newdf = price_df.merge(vol_df, left_index=True, right_index=True).merge(amount_df, left_index=True,
right_index=True)
if Type != "Kline":
Type1 = firstletter(Type).encode("ascii")
target = newdf[Type1].tolist()
date = newdf.index.format()
returnarray = zip(date, target)
return returnarray
else:
Date = newdf.index.format()
Open = newdf["open"].tolist()
Close = newdf["close"].tolist()
High = newdf["high"].tolist()
Low = newdf["low"].tolist()
Candlestick = zip(*[Date, Open, Close, Low, High])
return Candlestick
#正常历史k线
if Type == "差价图".decode("utf-8"):
global array300
if array300 is None:
array300 = ts.get_k_data("399300", start=startdata, end=enddata, ktype=interval)
array = ts.get_k_data(stocknumber, start=startdata, end=enddata, ktype=interval, autype='qfq')
if array is None or array300 is None:
return None
target = []
benchmark_list = []
try:
close_list = array["close"].tolist()
date = array["date"].tolist()
date300 = array300["date"].tolist()
close300 = array300["close"].tolist()
if len(close_list) is 0:
return None
data_price_300_map = dict()
benchmark300 = 100 / (close300[0])
benchmark = 100 / (close_list[0])
for index, day in zip(range(0, len(date300)), date300):
data_price_300_map[day] = close300[index]
for index, close in zip(range(1, len(close_list)), close_list):
price300 = data_price_300_map[date[index]] * benchmark300
target.append(round(close * benchmark - price300, 3))
benchmark_list.append(0)
returnarray = zip(date, target, benchmark_list)
if checkValid(returnarray) is False:
return None
return returnarray
except Exception as e:
print e
return None
elif Type == "价格指数".decode("utf-8"):
global array300
if array300 is None:
array300 = ts.get_k_data("399300", start=startdata, end=enddata, ktype=interval)
array = ts.get_k_data(stocknumber, start=startdata, end=enddata, ktype=interval, autype='qfq')
if array is None or array300 is None:
return None
price_list = []
price300_list = []
try :
close_list = array["close"].tolist()
date = array["date"].tolist()
close300_list = array300["close"].tolist()
if len(close_list) is 0:
return None
benchmark300 = 100 / (close300_list[0])
benchmark = 100 / (close_list[0])
for close in close_list:
price_list.append(close * benchmark)
for close300 in close300_list:
price300_list.append(close300 * benchmark300)
returnarray = zip(date, price_list, price300_list)
if checkValid(returnarray) is False:
return None
return returnarray
except Exception as e:
print e
return None
elif Type!="Kline":
array = ts.get_k_data(stocknumber, start=startdata, end=enddata, ktype=interval)
if array is None:
return
Type1 = firstletter(Type).encode("ascii")
target = array[Type1].tolist()
date = array["date"].tolist()
returnarray = zip(date,target)
return returnarray
else:
array = ts.get_k_data(stocknumber, start=startdata, end=enddata, ktype=interval)
if array is None:
return
Date = array["date"].tolist()
Open = array["open"].tolist()
Close = array["close"].tolist()
High = array["high"].tolist()
Low = array["low"].tolist()
Candlestick = zip(*[Date,Open,Close,Low,High])
return Candlestick
else:
if Type!="Kline": # 复权
array = ts.get_h_data(stocknumber, start = startdata, end = enddata, autype= interval)
if array is None:
return
Type1 = firstletter(Type).encode("ascii")
array = array.sort_index()
target = array[Type1].tolist()
date = array.index.format()
returnarray = zip(date, target)
return returnarray
else :
array = ts.get_h_data(stocknumber, start=startdata, end=enddata, autype=interval)
if array is None:
return
array = array.sort_index()
Date = array.index.format()
Open = array["open"].tolist()
Close = array["close"].tolist()
High = array["high"].tolist()
Low = array["low"].tolist()
Candlestick = zip(*[Date, Open, Close, Low, High])
return Candlestick
def QA_fetch_get_stock_tick(name, date):
if (len(name) != 6):
name = str(name)[0:6]
return QATs.get_tick_data(name, date)
spam_writer = csv.writer(file_csv, dialect='excel')
spam_writer.writerow([
'code', 'name', 'average', "close", 'open', 'high', 'low', "growth",
'average_growth'
])
today_all = ts.get_today_all()
for index, row in today_all.iterrows():
_code = row['code']
_amount = row['amount']
if _amount < 1:
spam_writer.writerow(
[_code, row['name'].encode('gbk'), 0, 0, 0, 0, 0, 0, 0])
continue
print '\nget' + str(_code) + '\'s tick data'
_tick_data = ts.get_tick_data(_code, date=format_time, pause=3)
_total_volume = 0
_total_amount = 0
for _tick_index, _tick_row in _tick_data.iterrows():
_total_volume += _tick_row['volume']
_total_amount += _tick_row['price'] * _tick_row['volume']
if _total_volume == 0:
print '\ntotal volume is zero'
continue
_average_price = _total_amount / _total_volume
_close = row['trade']
_open = row['open']
_high = row['high']
_low = row['low']
if _close == 0:
_average_growth = 0
def get_ticks(self, code, date):
df = ts.get_tick_data(code, date=date, src='tt')
# today = datetime.date.today().strftime('%Y-%m-%d')
df['time'] = df['time'].map(lambda x: date + ' ' + x)
return df
import tushare as ts
df = ts.get_tick_data('000965', date='2017-08-03')
p = df.amount
p[1]
s = 0
x = len(p)
for i in range(0, x):
s = p[i] + s
print(s)
b = p.index
print(b)
def tick_insert1(code, date):
stock_tick_date = tushare.get_tick_data(code=code, date=date, src='tt')
stock_tick_date['code'] = code
stock_tick_date['date'] = date
return pandas.DataFrame(stock_tick_date)
def fetchAllStocksHistoryTickData():
"""
获取所有的股票的成交明细历史数据，
同时把数据存到数据库。
这个函数应该只运行一次
"""
str_price_json={
'metric':'security.price',
'time':'time',
'value':'price',
'code':'code',
'tags':{
'period': 'tick'
}
}
str_volume_json={
'metric':'security.volume',
'time':'time',
'value':'volume',
'code':'code',
'tags':{
'period':'tick',
'type': True
}
}
today=dt.now()
label=False
today=dt(today.year, today.month, today.day)
delta=td(1,0,0) #间隔一天
for i in stolist:
date=dt(2004,10,5)
label=False
while date<today:
if label:
pool=Pool(14)
for d in range(14):
timestr=dt.strftime(date,'%Y-%m-%d')
print(timestr+' fast mood')
pool.apply_async(fetchDt, args=(i,timestr,), error_callback=printError)
date=date+delta
pool.close()
pool.join()
continue
timestr=dt.strftime(date,'%Y-%m-%d')
print(timestr+' not fast mood')
df=ts.get_tick_data(i,date=timestr)
if df.empty or df.iloc[0,0].startswith('alert'):
print('no data or failed')
date=date+delta
continue
# print(timestr)
timestr=timestr+' '
if not label: #提取tickStart
if not df.iloc[0,0].startswith('alert'):
label=True
try:
sec=Securities.objects.get({'code':i})
except Securities.DoesNotExist:
sec=Securities(config.StocksList[i], i, exchange).save()
TimeSeries(sec, 'security.price','tick', timestr+df.iloc[-1,0])
# MongodbJson[i]['tickStart']=timestr+df.iloc[-1,0]
result=_dataFrame2MetricsList(df,str_volume_json,date=timestr,code=i)
database.insertList(result)
result=_dataFrame2MetricsList(df,str_price_json,date=timestr,code=i)
database.insertList(result)
date=date+delta
pass
with open('progress.ini','w') as f:
f.write(str(i))
pass
# ts.get_hist_data('600848', ktype='15') #获取15分钟k线数据
# ts.get_hist_data('600848', ktype='30') #获取30分钟k线数据
# ts.get_hist_data('600848', ktype='60') #获取60分钟k线数据
# ts.get_hist_data('sh'）#获取上证指数k线数据，其它参数与个股一致，下同
# ts.get_hist_data('sz'）#获取深圳成指k线数据
# ts.get_hist_data('hs300'）#获取沪深300指数k线数据
# ts.get_hist_data('sz50'）#获取上证50指数k线数据
# ts.get_hist_data('zxb'）#获取中小板指数k线数据
# ts.get_hist_data('cyb'）#获取创业板指数k线数据
History_bar_df1 = ts.get_h_data(target_stock_code, start='2015-01-01', end='2015-03-16') #两个日期之间的前复权数据
'''获取全部历史数据'''
# ts.get_h_data('002337') #前复权
# ts.get_h_data('002337', autype='hfq') #后复权
# ts.get_h_data('002337', autype=None) #不复权
# ts.get_h_data('399106', index=True) #深圳综合指数
History_tick_df = ts.get_tick_data(target_stock_code,date='2014-01-09')
'''历史分笔数据明细(无bidask)'''
#==============================================================================即时数据==============================================================================
realTimeAll = ts.get_today_all()
'''当前交易所有股票的行情数据'''
realTimeIndex = ts.get_index()
'''当前大盘的行情数据'''
realtime_tran_data = ts.get_realtime_quotes(target_stock_code)
'''实时分笔数据'''
#ts.get_realtime_quotes(['600848','000980','000981']) #symbols from a list
#ts.get_realtime_quotes('sh')#上证指数
#ts.get_realtime_quotes(['sh','sz','hs300','sz50','zxb','cyb'])#上证指数 深圳成指 沪深300指数 上证50 中小板 创业板
#ts.get_realtime_quotes(['sh','600848'])#或者混搭
realday_deal_data = ts.get_today_ticks(target_stock_code)
'''当日历史分笔'''
big_deal_data = ts.get_sina_dd(target_stock_code, date=transaction_day)
# -*- coding: utf-8 -*-
import tushare as ts
df = ts.get_hist_data('600848')
ts.get_hist_data('600848', ktype='W') #获取周k线数据
ts.get_hist_data('600848', ktype='M') #获取月k线数据
ts.get_hist_data('600848', ktype='5') #获取5分钟k线数据
ts.get_hist_data('600848', ktype='15') #获取15分钟k线数据
ts.get_hist_data('600848', ktype='30') #获取30分钟k线数据
ts.get_hist_data('600848', ktype='60') #获取60分钟k线数据
ts.get_hist_data('sh') #获取上证指数k线数据，其它参数与个股一致，下同
ts.get_hist_data('sz') #获取深圳成指k线数据 ts.get_hist_data('hs300'）#获取沪深300指数k线数据
ts.get_hist_data('sz50') #获取上证50指数k线数据
ts.get_hist_data('zxb') #获取中小板指数k线数据
ts.get_hist_data('cyb') #获取创业板指数k线数据
#Python财经数据接口包TuShare的使用
#获取历史分笔数据
df = ts.get_tick_data('000756', '2015-03-27')
#print(df.head(10))
if r != 0:
return df_yestoday
cur_datetime = yestoday_datetime
#python main.py -s 603611 -d 2018-04-09
if __name__ == "__main__":
opts, args = getopt.getopt(sys.argv[1:], "s:d:", ["sid=", "date="])
sid = getOptvalue(opts, '-s')
date = getOptvalue(opts, '-d')
cur_datetime = datetime.strptime(date, '%Y-%m-%d')
df_yestoday = getBeforeData(sid, cur_datetime)
print(df_yestoday)
close_yestoday = float(df_yestoday.close)
df = ts.get_tick_data(sid, date=date)
filename = sid + ".csv"
df.to_csv(filename)
all_datas = []
with codecs.open(filename, 'r', 'utf-8') as f:
f_csv = csv.reader(f)
headers = next(f_csv)
print(headers)
for row in f_csv:
all_datas.insert(0, row)
predatetime = None
prePrice = 0
dis = 0
suList = []
for data in all_datas:
dtstr = date + ' ' + data[1]
import tushare as ts
import pandas as pd
all_pd = []
calData = ts.get_k_data('600036',
start='2016-01-01',
end='2016-12-31',
autype='qfq')
#calData = ts.get_h_data('600036', start='2016-01-01', end='2016-12-31')
for i in range(len(calData)): #list(calData.index):
time_list = []
one_date = calData.at[i, 'date']
print one_date
df = ts.get_tick_data('600036', date=one_date)
try:
df['time'] = one_date + ' ' + df['time']
df['time'] = pd.to_datetime(df['time'])
except:
print df
continue
df = df.set_index('time')
#进行采样得到开始的价格，最高价，最低价，结束的价格
price_df = df['price'].resample('1min').ohlc()
price_df = price_df.dropna() #删除空值
all_pd.append(price_df)
result = pd.concat(all_pd)
def add_money_flow_today():
"""
沪深300当日生成小单统计数据
tips:成交明细列表中的买盘/卖盘：“买盘”表示以比市价高的价格进行委托买入，并已经“主动成交”，代表外盘；
“卖盘”表示以比市价低的价格进行委托卖出，并已经“主动成交”，代表内盘
:return:
"""
print('插入当日现金流信息开始......')
hs300_index = tushare.get_hs300s()
ts_codes = hs300_index['code'].apply(util.stock_code_change)
for ts_code in set(ts_codes):
try:
date = datetime.datetime.now().strftime('%Y%m%d')
daily_info = tushare_data.get_tushare_pro().daily(ts_code=ts_code,
trade_date=date)
close = daily_info['close']
df = tushare.get_tick_data(str(ts_code[:6]), date=date, src='tt')
if df is None:
continue
total_amt = df['amount'].sum()
total_vol = df['volume'].sum()
sell_trade = df.loc[(df['type'] == '卖盘')]
total_sell_vol = sell_trade['volume'].sum()
total_sell_amt = sell_trade['amount'].sum()
small_trade_amount = util.trade_scale(close)
sell_sm_trade = df.loc[(df['type'] == '卖盘')
& (df['amount'] < small_trade_amount)]
sell_sm_vol = sell_sm_trade['volume'].sum()
sell_sm_amt = sell_sm_trade['amount'].sum()
buy_trade = df.loc[(df['type'] == '买盘')]
total_buy_vol = buy_trade['volume'].sum()
total_buy_amt = buy_trade['amount'].sum()
buy_sm_trade = df.loc[(df['type'] == '买盘')
& (df['amount'] < small_trade_amount)]
buy_sm_vol = buy_sm_trade['volume'].sum()
buy_sm_amt = buy_sm_trade['amount'].sum()
total_sm_trade = df.loc[df['amount'] < small_trade_amount]
total_sm_amt = total_sm_trade['amount'].sum()
total_sm_vol = total_sm_trade['volume'].sum()
id = ts_code[:6] + date
tables.add_money_flow(id=id,
code=str(ts_code[:6]),
date=date,
sell_sm_vol=sell_sm_vol,
sell_sm_amt=sell_sm_amt,
buy_sm_vol=buy_sm_vol,
buy_sm_amt=buy_sm_amt,
total_sell_vol=total_sell_vol,
total_sell_amt=total_sell_amt,
total_buy_vol=total_buy_vol,
total_buy_amt=total_buy_amt,
total_amt=total_amt,
total_vol=total_vol,
total_sm_amt=total_sm_amt,
total_sm_vol=total_sm_vol)
print('插入当日现金流信息完成......')
except Exception as err:
print('插入当日现金流信息失败......')
raise err
end_date = '2020-10-28'
stock_k = ts.get_hist_data(stock_code, start=start_date, end=end_date)
print(stock_k)
# print(stock_k.index)
# Index(['2020-10-28', '2020-10-27'], dtype='object', name='date')
# 建立一个空的DataFrame，用于存储当前股票的信息
stock_table = pd.DataFrame()
for current_date in stock_k.index:
# # 通过loc定位K线图中对应current_date这天的行数据
current_k_line = stock_k.loc[current_date]
df = ts.get_tick_data(stock_code, date=current_date, src='tt')
df['time'] = pd.to_datetime(current_date + ' ' + df['time'])
t = pd.to_datetime(current_date).replace(hour=9, minute=40)
df_10 = df[df['time'] < t]
#vol=df_10.volume.sum()
vol = df_10['volume'].sum()
# 存入字典
current_stock_info = {
'名称': stock_name,
'日期': pd.to_datetime(current_date),
'开盘价': current_k_line.open,
def generateline(stocknumber, Type, startdate, enddate, interval):
startdata = startdate.encode("ascii").replace("/", "-").replace(
"\n", "") #convert to tushare readable date
enddata = enddate.encode("ascii").replace("/", "-").replace("\n", "")
array = df()
#print startdata
#print enddata
current_time = time.strftime("%Y/%m/%d")
if Type == "分笔".decode("utf-8"):
if startdate != current_time:
array = ts.get_tick_data(stocknumber, date=startdata) #分笔
if array is None:
return
array = array.sort_values("time")
date = array["time"].tolist()
amount = array["amount"].tolist()
atype = array["type"].tolist()
price = array["price"].tolist()
flag = ["bar" for i in date]
for idx, val in enumerate(atype): #if卖盘，交易变成负数
if val == "卖盘":
amount[idx] = -amount[idx]
if val == "中性盘": #if中性盘，则忽略. Might have a problem with this part??
amount[idx] = 0
returnarray = zip(date, amount, flag, price)
return returnarray
else:
array = ts.get_today_ticks(stocknumber) #Tushare里今日分笔和历史分笔需要分别对待
if array is None:
return
array = array.sort_values("time")
date = array["time"].tolist()
amount = array["amount"].tolist()
atype = array["type"].tolist()
flag = ["bar" for i in date]
for idx, val in enumerate(atype):
if val == "卖盘".decode("utf-8"):
amount[idx] = -amount[idx]
if val == "中性盘".decode("utf-8"):
amount[idx] = 0
returnarray = zip(date, amount, flag)
return returnarray
if interval != "qfq" and interval != "hfq": #正常历史k线
if Type != "Kline":
array = ts.get_k_data(stocknumber,
start=startdata,
end=enddata,
ktype=interval)
if array is None:
return
Type1 = firstletter(Type).encode("ascii")
target = array[Type1].tolist()
date = array["date"].tolist()
returnarray = zip(date, target)
return returnarray
else:
array = ts.get_k_data(stocknumber,
start=startdata,
end=enddata,
ktype=interval)
if array is None:
return
Date = array["date"].tolist()
Open = array["open"].tolist()
Close = array["close"].tolist()
High = array["high"].tolist()
Low = array["low"].tolist()
Candlestick = zip(*[Date, Open, Close, Low, High])
return Candlestick
else:
if Type != "Kline": # 复权
array = ts.get_h_data(stocknumber,
start=startdata,
end=enddata,
autype=interval)
if array is None:
return
Type1 = firstletter(Type).encode("ascii")
array = array.sort_index()
target = array[Type1].tolist()
date = array.index.format()
returnarray = zip(date, target)
return returnarray
else:
array = ts.get_h_data(stocknumber,
start=startdata,
end=enddata,
autype=interval)
if array is None:
return
array = array.sort_index()
Date = array.index.format()
Open = array["open"].tolist()
Close = array["close"].tolist()
High = array["high"].tolist()
Low = array["low"].tolist()
Candlestick = zip(*[Date, Open, Close, Low, High])
return Candlestick
import tushare as ts
ts.set_token('7483f126babf5e250781d90a96d28f057961392f482e10b98ef2914c')
pro = ts.pro_api()
# 历史名称变更记录
df = pro.namechange(ts_code='600848.SH',
fields='ts_code,name,start_date,end_date,change_reason')
print(df)
df = ts.get_tick_data('600848', date='2018-12-12', src='tt')
print(df.head(10))
import tushare as ts
myStockData = ts.get_realtime_quotes("300445")
ts.get_tick_data("600096",date= "2017-06-26")
#
# some thing that is really useful
#
data = ts.get_hist_data("600096",start = '2017-06-23',end="2017-06-26")
# return type
# date：日期
# open：开盘价
# high：最高价
# close：收盘价
# low：最低价
# volume：成交量
# price_change：价格变动
# p_change：涨跌幅
# ma5：5日均价
# ma10：10日均价
# ma20:20日均价
# v_ma5:5日均量
# v_ma10:10日均量
# v_ma20:20日均量
# turnover:换手率[注：指数无此项]
#print myStockData.value
for key in myStockData:
print(myStockData[key])
def test2():
import tushare as ts
df = ts.get_tick_data('603106', date='2019-05-13', src='tt')
print(df)
# -*- coding: utf-8 -*-
"""
@author:
@file: .py
@date:
"""
import tushare as ts
data = ts.get_hist_data('600848', start='2015-01-05', end='2015-01-09')
df = ts.get_tick_data('600848', date='2015-12-24')
ns = ts.new_stocks()
print data
print df
def get_deal_detail(code, date):
df = ts.get_tick_data(code, date=date)
df = df.head(100)
df.columns = ["交易时间", "成交价格", "价格变动", "成交手", "成交金额", "买卖类型"]
return df
def tick2period(code, period, start, end):
""" get tick data from tushare and resample to certain period data
selected by input: period
"""
import tushare as ts
import numpy as np
import pandas as pd
dfout = None
#get valid trade date
valid_dates = ts.get_hist_data(code, start=start, end=end).index
for date in valid_dates:
#date=date.strftime('%Y-%m-%d')
rng = pd.date_range(
date + ' 9:30:00', date + ' 15:00', closed='right',
freq=period) #setup trade time grid by period selected
sr = pd.Series(np.nan, index=rng)
df = ts.get_tick_data(code, date=date)
df.loc[df.time < '09:30:00',
'time'] = '09:30:01' #process open call auction
df.loc[df.time > '15:00:00',
'time'] = '14:59:59' #process close call auction
df['time'] = date + ' ' + df['time']
df = df.rename(columns={'time': 'datetime'})
df['datetime'] = pd.to_datetime(df['datetime'])
df = df.set_index('datetime').sort()
df2 = df['volume'].resample(period,
how='sum',
closed='right',
label='right')
df2, dummy = df2.align(sr, axis=0) #align to standard time
df3 = df2.truncate(before=date + ' 13:00:01', after=date + ' 15:00')
df2 = df2.truncate(before=date + ' 9:30:01',
after=date + ' 11:30') #remove non-trade time
df2 = df2.append(df3).fillna(
0) #fill with 0 for period without valid deal
df1 = df['price'].resample(period,
how='ohlc',
closed='right',
label='right')
df1, dummy = df1.align(sr, axis=0) #align to standard time
df3 = df1.truncate(before=date + ' 13:00:01', after=date + ' 15:00')
df1 = df1.truncate(before=date + ' 9:30:01',
after=date + ' 11:30') #remove non-trade time
df1 = df1.append(df3)
if np.isnan(
df1.ix[0, 'close']
): #use last day's close as initial price if there is no deal after open
from datetime import timedelta
aDay = timedelta(
days=-10
) #get enough days to ensure at least one trading day is involved
pre = (pd.to_datetime(date) + aDay).strftime('%Y-%m-%d')
df1.ix[0, 'close'] = ts.get_hist_data(code, start=pre,
end=date).ix[-2, 'close']
df1['close'].fillna(
method='pad', inplace=True
) #use price before if there is no deal during current period
df1.fillna(
method='bfill', inplace=True, axis=1
) #use close as open,high,low if there is no deal during current period
df1['volume'] = df2.values
dfout = pd.concat([dfout, df1])
#print dfout
#assert(False)
return dfout
def _get_tick_history(self, day):
return ts.get_tick_data(self.code, date=day)
def tushare_to_mongo():
conn = pymongo.Connection('127.0.0.1', port=27017)
df_index = ts.get_tick_data('600848', date='2014-12-22')
df = df_index.reset_index()
conn.db.tickdata.insert(json.loads(df.to_json(orient='records')))
import tushare as ts
import cn.apking.config as config
ts.set_token(config.token)
pro = ts.pro_api()
# wanke = ts.get_k_data('000002', start='2016-01-01', end='2019-01-31')
# print(wanke)
# df = pro.new_share(start_date='20210210', end_date='20210220')
# print(df)
from sqlalchemy import create_engine
import tushare as ts
df = ts.get_tick_data('600848', date='2014-12-22')
engine = create_engine('mysql://*****:*****@127.0.0.1/db_name?charset=utf8')
#存入数据库
df.to_sql(df, engine)
#追加数据到现有表
#df.to_sql('tick_data',engine,if_exists='append')
