def top10_holders():
n = 0
stock_count = len(stock_list(coll_stock_cache))
for code in stock_list(coll_stock_cache):
try:
print('开始读取code:', code)
df, data = ts.top10_holders(code=code, gdtype='1')
data['code'] = code
coll.insert(json.loads(data.to_json(orient='records')))
print('保存code:', code)
coll_stock_cache.delete_one({'code': code})
print('从缓存中删除code:', code)
n += 1
sleep_time = n / 100
print('当前进度{}:{}/{}'.format(code, n, stock_count))
print('▂▃▄▅▆▇█▉▉█▇▆▅▄▃▂暂停区')
if sleep_time.is_integer():
print('休息三分钟')
time.sleep(180)
except:
try:
# coll.deleteMany({'code': code})
update_new_cache(coll_stock_cache, coll_new_cache, code)
except:
coll_stock_cache.delete_one({'code': code})
finally:
print('重新开始top10_holders')
restar(top10_holders())
print('开始转换时间')
holders_time_convert(coll)
print('任务完成')
def update_top10_holders():
n = 0
stock_count = len(stock_list(coll_stock_cache))
for code in stock_list(coll_stock_cache):
try:
print('开始读取code:', code)
# 新股等,列表不存在,返回233
if date_holders(code) == 233:
query = {
'code': code,
}
field = {
'code': 1,
'_id': 1, # mogodb中连_id字段在内都相同的完全一样的字段不能插入
}
coll_new_cache.insert(coll_stock_cache.find(query, field))
print('可能为新股,不存在该代码,读取下一个')
# 不用更新的情况,返回[]
elif not date_holders(code):
print('未到更新时间,请等待')
# 报错为数据还未出来的股票
else:
for i in date_holders(code):
for k, v in i.items():
year = k
quarter = int(v)
df, data = ts.top10_holders(code=code,
year=year,
quarter=quarter,
gdtype='1')
data['code'] = code
coll.insert(json.loads(data.to_json(orient='records')))
print('保存{}:{}年第{}季度:'.format(code, year, quarter))
coll_stock_cache.delete_one({'code': code})
print('从缓存中删除code:', code)
n += 1
sleep_time = n / 100
print('当前进度{}:{}/{}'.format(code, n, stock_count))
print('▂▃▄▅▆▇█▉▉█▇▆▅▄▃▂暂停区')
if sleep_time.is_integer():
print('休息三分钟')
time.sleep(180)
except:
try:
update_new_cache(coll_stock_cache, coll_new_cache, code)
except:
# 出现new_cache中有重复code
coll_stock_cache.delete_one({'code': code})
finally:
print('重新开始update_top10_holders')
restar(update_top10_holders())
print('开始转换时间')
holders_time_convert(coll)
print('任务完成')
def top10_holders_worker(engine, codes, year, quarter):
pid = os.getpid()
tsl.log("pid %i start with %i codes..." % (pid, len(codes)))
df = pd.DataFrame()
temp = []
for code in codes:
try:
newdf = ts.top10_holders(code, year, quarter)[1]
if newdf is not None:
newdf['code'] = code
df = df.append(newdf, ignore_index=True)
except BaseException, e:
if 'timed out' in str(e) or 'urlopen error' in str(e):
temp.append(code)
else:
print e
tsl.log("pid %i error for %s" % (pid, code))
def refreshTop10Holders():
logger.info("refreshTop10Holders...")
mongoService.drop_collection('top10Holders')
mongoService.drop_collection('stockHoldersChanges')
res = mongoService.find('stocksBasics', {})
count = 1
for row in res:
try:
logger.info('count %d' % count)
logger.info('code is %s' % row['code'])
df = ts.top10_holders(row['code'], 2018, 3)
df[0]['code'] = row['code']
df[1]['code'] = row['code']
logger.info('Top10 Holders of %s' % (row['code']))
insertAndPrintResult('stockHoldersChanges', df[0])
insertAndPrintResult('top10Holders', df[1])
count += 1
except Exception:
logger.error(traceback.format_exc())
def Get_Top10_holders(self):
df = ts.top10_holders('600848')
# print df
# print type(df)
obj_series_tuple = pd.Series(df, index=list('abcdefgsll'))
print obj_series_tuple
def generate_stock_line(stock_id, Type, start_date, end_date, interval):
start_data = start_date.replace("/", "-").replace(
"\n", "") #convert to tushare readable date
end_data = end_date.replace("/", "-").replace("\n", "")
current_time = time.strftime("%Y/%m/%d")
if Type == "分笔":
if start_date != current_time:
array = ts.get_tick_data(stock_id, date=start_data) #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(stock_id) #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":
amount[idx] = -amount[idx]
if val == "中性盘":
amount[idx] = 0
returnarray = zip(date, amount, flag)
return returnarray
if Type == "季度饼图":
datestr = start_date.split("/")
thisyear = datestr[0]
df2 = ts.top10_holders(code=stock_id, 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(stock_id, date=start_data)
df.sort_values("time")
a = start_data + " " + 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)
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 != "Kline":
array = ts.get_k_data(stock_id,
start=start_data,
end=end_data,
ktype=interval)
if array is None:
return
Type1 = firstletter(Type)
target = array[Type1].tolist()
date = array["date"].tolist()
returnarray = zip(date, target)
return returnarray
else:
array = ts.get_k_data(stock_id,
start=start_data,
end=end_data,
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(stock_id,
start=start_data,
end=end_data,
autype=interval)
if array is None:
return
Type1 = firstletter(Type)
array = array.sort_index()
target = array[Type1].tolist()
date = array.index.format()
returnarray = zip(date, target)
return returnarray
else:
array = ts.get_h_data(stock_id,
start=start_data,
end=end_data,
autype=15)
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()
# list_array = [Date, Open, Close, Low, High]
Candlestick = zip(*[Date, Open, Close, Low, High])
return Candlestick
def Top10Holder(codenumber, startdate='2014-10-10'):
"""
Top10 holde 是将top10 股东用Pie 图进行可视化，其中包含一年股东变化的河流图.
Parameters
----------
codenumber: stock 代码
startdate='2014-10-10': 起始时间
Returns
-------
输出为 当前文件夹下 html ：top10.html
"""
if len(codenumber) != 6: #检查 code 长度 不符合6位全部错误
return False
elif len(codenumber) == 6:
datestr = startdate.split("-")
thisyear = datestr[0]
df2 = ts.top10_holders(code=codenumber, gdtype="1") # 下载数据
test = df2[1]["quarter"].tolist() #获取季度列表
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)
elif a[0] > thisyear:
idxlist.append(idx)
thing = df_ready.loc[idxlist]
thing = pd.DataFrame(thing)
thing = thing.sort_values(["quarter", "name"]) #排序所有流通股股东
quarterlist = thing.quarter.value_counts()
quarterlist = quarterlist.index.sort_values()
timeline = Timeline(
height=600,
width=800,
timeline_left=20,
timeline_right=100,
is_auto_play=False,
timeline_bottom=0,
timeline_symbol='diamond',
)
year_index = thing.quarter.apply(
lambda x: x[0:4]) # year list ('20xx')
yearlist = year_index.value_counts()
yearlist = yearlist.index.sort_values()
#print(quarterlist,year)
for quarters in list(quarterlist): # 将每个季度画成PIE 加入TIMELINE
df = thing[thing["quarter"] == quarters]
df.h_pro = df.h_pro.apply(lambda x: float(x))
df.hold = df.hold.apply(lambda x: float(x))
sum_pro = round(df.h_pro.sum(), 2)
sum_hold = round(np.mean(df.hold / df.h_pro) * sum_pro, 0)
s = pd.Series({
'name': '其他',
'h_pro': 100 - sum_pro,
'hold': sum_hold
})
df = df.append(s, ignore_index=True)
#df=df.sort_values(["name"])
pie = Pie('%s' % quarters + "-" + "top10holder",
title_pos='outside')
TopPie = pie.add(
'',
df.name,
df.hold,
radius=[20, 45],
center=[45, 50],
is_legend_show=True,
is_label_show=True,
# is_visualmap=True,
is_more_utils=True,
is_toolbox_show=True,
legend_pos='left',
legend_orient='vertical',
legend_top=25,
legend_text_size=12,
label_text_size=10,
label_text_color="#100",
tooltip_text_color="#F0F",
#is_label_emphasis=False,#是否显示高亮
label_formatter="{b}:\n {c}万股\n{d}%")
#gird= Grid()
#gird.add(pie,grid_bottom="20%")
#gird.add(tab,grid_bottom="60%")
#pietimeline.add(pie, quarters,)
timeline.add(
pie,
quarters,
)
#page = pyecharts.Page()
#page.add(pie)
#page.add(_treemap)
#timeline.add(pie,quarters,)
#timeline.add(_treemap,quarters,)
#pietimeline.top('40%')
trmtimeline = Timeline(
height=1200,
width=800,
timeline_left=20,
timeline_right=100,
is_auto_play=False,
timeline_bottom=0,
timeline_symbol='diamond',
)
#for y in list(yearlist):
datas_index = []
for i, _year in enumerate(year_index): #获取datas_index
if _year in list(yearlist)[-1:]:
datas_index.append(i)
else:
pass
print(thing.loc[datas_index, :])
collect_datas = thing.iloc[datas_index, :3]
collect_datas.hold = collect_datas.hold.apply(lambda x: float(x))
print(collect_datas)
name = collect_datas['name']
collect_datas.drop(labels=['name'], axis=1, inplace=True)
collect_datas.insert(2, 'name', name)
print(collect_datas.get_values())
tr = pyecharts.ThemeRiver(
"TOP 10 hold 河流图 ",
height=800,
width=800,
)
tr.add(name.get_values(),
collect_datas.get_values(),
is_label_show=False)
#trmtimeline.add(tr,"%s"%y,)
page = pyecharts.Page()
# page.add(trmtimeline)
page.add(timeline)
page.add(tr)
'''
them_dates=[]
for i in thing.index:
print (i)
collect_datas=thing[thing.index==i].iloc[:, 0:3]
name=collect_datas['name']
collect_datas.drop(labels=['name'], axis=1,inplace = True)
collect_datas.insert(2, 'name', name)
print (collect_datas.get_values())
'''
print('time line done')
return page
def graphpage(labels,mode_combo,startdate,enddate,optInterval,width1, height1):
#optInterval='D/W/M' labels
startdate = startdate.replace("/","-")#convert to tushare readable date
enddate = enddate.replace("/","-")
page = Page()
for label in labels: # generate numbers of graphs according to numbers of queries in treewidget
label1 = re.split("-", label)
overlap = Overlap()
if label1[2]!="分笔" and label1[2]!="季度饼图": #"K线" "复权" "历史分钟"
if mode_combo == "复权":
#if optInterval == "qfq" or optInterval == "hfq":#复权
array = ts.get_h_data(label1[1], start=startdate, end=enddate, autype="qfq")
array = array.sort_index()
time = array.index.format() # 日期正是index
elif mode_combo == "K线":
#elif optInterval.isalnum() :#历史K线
array = ts.get_k_data(label1[1], start=startdate, end=enddate, ktype=optInterval)
time = array['date'].tolist() # array.date
elif mode_combo == "历史分钟":
array_bfr = ts.get_tick_data(label1[1], date=startdate)
array_bfr.sort_values("time")
a = startdate + " " + array_bfr["time"]
array_bfr["time"] = a
array_bfr["time"] = pd.to_datetime(a)
array_bfr = array_bfr.set_index("time")
if label1[2] != "Volume" and label1[2] != "Amount":
price_df = array_bfr["price"].resample(optInterval).ohlc() # resample重新取样,选出ohlc=open/high/low，提取除价格之外另外4列.close,tushare是ohcl
price_df = price_df.dropna()
array = price_df
time = price_df.index.format()
elif label1[2] == "Volume":
vols = array_bfr["volume"].resample(optInterval).sum() #resample重新取样，累加间隔内数值 relevant data processing algorithm taken from Jimmy, Creator of Tushare
vols = vols.dropna()
vol_df = pd.DataFrame(vols, columns=["volume"])
array = vol_df
time = vol_df.index.format()
else:
amounts = array_bfr["amount"].resample(optInterval).sum()
amounts = amounts.dropna()
amount_df = pd.DataFrame(amounts, columns=["amount"])
array = amount_df
time = amount_df.index.format()
#绘图方法
if label1[2] == 'Kline':
re_array = array[['open', 'close', 'high', 'low']]
data_li = list(row.tolist() for index, row in re_array.iterrows()) # data_list = list(re_array.as_matrix())
close = array['close'].tolist()
kline = Kline(label1[0] + "-" + optInterval, width=width1*10/11, height = (height1*10/11) / len(labels))
kline.add(label1[0], time, data_li, is_datazoom_show=True, datazoom_type="slider", yaxis_interval=1)
overlap.add(kline)
if len(close) > 10:
ma10 = calculateMa(close, 10)
line1 = Line(title_color="#C0C0C0")
line1.add(label1[0] + "-" + "MA10", time, ma10)
overlap.add(line1)
if len(close) > 20:
ma20 = calculateMa(close, 20)
line2 = Line(title_color="#C0C0C0")
line2.add(label1[0] + "-" + "MA20", time, ma20)
overlap.add(line2)
if len(close) > 30:
ma30 = calculateMa(close, 30)
line3 = Line(title_color="#C0C0C0")
line3.add(label1[0] + "-" + "MA30", time, ma30)
overlap.add(line3)
page.add(overlap)
else:#When label1[2]==open/close/volume
if label1[2] == 'Open':
list_aft = array['open'].tolist()
elif label1[2] == 'Close':
list_aft = close
elif label1[2] == 'High':
list_aft = array['high'].tolist()
elif label1[2] == 'Low':
list_aft = array['low'].tolist()
elif label1[2] == 'Volume':#volume
list_aft = array['volume'].tolist()
else:#amount
list_aft = array['amount'].tolist()
line = Line(label1[0] + "-" + label1[2], width=width1 * 10 / 11, height=(height1 * 10 / 11) / len(labels))
line.add(label1[0] + "-" + label1[2], time, list_aft, is_datazoom_show=True, yaxis_max="dataMax",
yaxis_min="dataMin", datazoom_type="slider")
overlap.add(line)
page.add(overlap)
elif label1[2]=="分笔":
array = ts.get_tick_data(label1[1], date=startdate)
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 val == "卖盘":
amount[idx] = -amount[idx]
if val == "中性盘":
amount[idx] = 0
returnarray = list(zip(date, amount, flag, price))
form = [e[1] for e in returnarray]
time = [d[0] for d in returnarray]
bar = Bar(label1[0] + "-" + label1[2], width=width1 * 10 / 11, height=(height1 * 10 / 11) / len(labels))
bar.add(label1[0] + "-" + label1[2], time, form, is_datazoom_show=True, datazoom_type="slider", yaxis_min="dataMin", yaxis_max="dataMax")
overlap.add(bar)
line = Line(label1[0] + "price", width=width1 * 10 / 11, height=(height1 * 10 / 11) / len(labels))
price = [e[3] for e in returnarray]
line.add(label1[0] + "price", time, price, yaxis_min="dataMin", yaxis_max="dataMax", is_datazoom_show=True,
datazoom_type="slider",
yaxis_type="value")
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
page.add(overlap)
elif label1[2]=="季度饼图":
datestr = startdate.split("-")
thisyear = datestr[0]
df2 = ts.top10_holders(code=label1[1], 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 range(0, len(name), 10)]
valuearray = [value[j:j + 10] for j in range(0, len(value), 10)]
quarterarray = [quarter[k:k + 10] for k in range(0, len(quarter), 10)]
flag = ["pie" for i in namearray]
num = [len(value) for k in namearray]
returnarray = list(zip(namearray, valuearray, quarterarray, flag, num))
timeline = Timeline(is_auto_play=False, timeline_bottom=0) # zip(namearray,valuearray,quarter,flag,num)
namearray = [c[0] for c in returnarray]
valuearray = [d[1] for d in returnarray]
quarter = [e[2] for e in returnarray]
num = returnarray[0][4]
for x in range(0, int(num / 10)):
list1 = valuearray[x]
names = namearray[x]
quarters = quarter[x][0]
for idx, val in enumerate(list1):
list1[idx] = float(val)
pie = Pie(label1[0] + "-" + "前十股东", width=width1 * 10 / 11, height=(height1 * 10 / 11))
pie.add(label1[0] + "-" + "前十股东", names, list1, radius=[30, 55], is_legend_show=False,
is_label_show=True, label_formatter="{b}: {c}\n{d}%")
timeline.add(pie, quarters)
# namearray = [y for y in namearray[x]]
timeline.render()
page.render()
def FindLowStock():
shangHaiStockIds = utility.GetShangHaiStockIdStrArray()
np.random.shuffle(shangHaiStockIds)
mongoClient = MongoClient('127.0.0.1:27017')
ShangHaiStockDB = mongoClient["ShangHaiStock"]
dailyDataCollection = ShangHaiStockDB["DailyData"]
# pdTopList = ts.top_list('2016-06-12')
# print(pdTopList[ pdTopList["code"] == shangHaiStockIds[100] ].cout)
for id in shangHaiStockIds:
dupDate = []
dateArrOrg = []
valueCloseArrOrg = []
valueLowArrOrg = []
valueOpenArrOrg = []
valueHighArrOrg = []
valueExceptionDate = []
valueMeanLowArrOrg= []
volumeArrOrg = []
preClosePrice = None
preOpenPrice = None
cursor = dailyDataCollection.find({"StockId":id, "Date_":{"$gte":checkStartDate, "$lte":checkEndDate}}).sort([("Date_", pymongo.ASCENDING)])
for curItem in cursor:
try:
date = curItem["Date_"]
if date in dupDate:
continue
dupDate.append(date)
adjClose = float(curItem["Adj Close"])
openPrice = float(curItem["Open"])
low = float(curItem["Low"])
high = float(curItem["High"])
volumenVal = float(curItem["Volume"])
except:
continue
dateArrOrg.append(date)
valueCloseArrOrg.append(adjClose)
valueOpenArrOrg.append(openPrice)
valueHighArrOrg.append(high)
volumeArrOrg.append(volumenVal)
valueLowArrOrg.append(low)
if len(valueCloseArrOrg) < 200:
continue
dateArrOrg = np.array(dateArrOrg)
valueCloseArrOrg = np.array(valueCloseArrOrg)
volumeArrOrg = np.array(volumeArrOrg)
checkIndexes = np.where(dateArrOrg < checkRealEndDate)[0]
meanVal = np.mean(valueCloseArrOrg[checkIndexes])
stdVal = np.std(valueCloseArrOrg[checkIndexes])
meanVolumeVal = np.mean(volumeArrOrg[checkIndexes])
stdVolumeVal = np.std(valueCloseArrOrg[checkIndexes])
recentVolumeMean = np.mean(volumeArrOrg[checkIndexes][-20:])
recentMeanVal1 = np.mean(valueCloseArrOrg[checkIndexes][-20:])
recentMeanVal2 = np.mean(valueCloseArrOrg[checkIndexes][-40:-20])
print(meanVal - 0.5*stdVal)
if valueCloseArrOrg[checkIndexes][-1] < meanVal - stdVal and recentMeanVal1 < recentMeanVal2 and recentVolumeMean > meanVolumeVal + 1*stdVolumeVal:
_, data2 = ts.top10_holders(code=id, year=2017, quarter=1, gdtype='1')
# topBrokers = ts.broker_tops()
# print(topBrokers)
searchArr = ["中央汇金", "香港", "社保", "全国", "养老保险"] # ,"BERKSHIRE"
strHolders = str(data2)
print(strHolders)
bHave = False
for item in searchArr:
if strHolders.find(item)>0:
print(strHolders)
bHave = True
break
if not bHave:
print("no no no no no")
print(id)
fig, ax = plt.subplots()
ax.plot(dateArrOrg, valueCloseArrOrg)
ax.vlines([checkRealEndDate], np.min(valueCloseArrOrg), np.max(valueCloseArrOrg), color="red")
plt.show()
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("sh",
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)
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("sh",
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)
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 graphpage(labels, mode_combo, startdate, enddate, optInterval, width1,
height1):
#optInterval='D/W/M' labels
startdate = startdate.replace("/", "-") #convert to tushare readable date
enddate = enddate.replace("/", "-")
page = Page()
for label in labels: # generate numbers of graphs according to numbers of queries in treewidget
label1 = re.split("-", label)
overlap = Overlap()
if label1[2] != "分笔" and label1[2] != "季度饼图": #"K线" "复权" "历史分钟"
if mode_combo == "复权":
#if optInterval == "qfq" or optInterval == "hfq":#复权
array = ts.get_h_data(label1[1],
start=startdate,
end=enddate,
autype="qfq")
array = array.sort_index()
time = array.index.format() # 日期正是index
elif mode_combo == "K线":
#elif optInterval.isalnum() :#历史K线
array = ts.get_k_data(label1[1],
start=startdate,
end=enddate,
ktype=optInterval)
time = array['date'].tolist() # array.date
elif mode_combo == "历史分钟":
array_bfr = ts.get_tick_data(label1[1], date=startdate)
array_bfr.sort_values("time")
a = startdate + " " + array_bfr["time"]
array_bfr["time"] = a
array_bfr["time"] = pd.to_datetime(a)
array_bfr = array_bfr.set_index("time")
if label1[2] != "Volume" and label1[2] != "Amount":
price_df = array_bfr["price"].resample(optInterval).ohlc(
) # resample重新取样,选出ohlc=open/high/low，提取除价格之外另外4列.close,tushare是ohcl
price_df = price_df.dropna()
array = price_df
time = price_df.index.format()
elif label1[2] == "Volume":
vols = array_bfr["volume"].resample(optInterval).sum(
) #resample重新取样，累加间隔内数值 relevant data processing algorithm taken from Jimmy, Creator of Tushare
vols = vols.dropna()
vol_df = pd.DataFrame(vols, columns=["volume"])
array = vol_df
time = vol_df.index.format()
else:
amounts = array_bfr["amount"].resample(optInterval).sum()
amounts = amounts.dropna()
amount_df = pd.DataFrame(amounts, columns=["amount"])
array = amount_df
time = amount_df.index.format()
#绘图方法
if label1[2] == 'Kline':
re_array = array[['open', 'close', 'high', 'low']]
data_li = list(row.tolist()
for index, row in re_array.iterrows()
) # data_list = list(re_array.as_matrix())
close = array['close'].tolist()
kline = Kline(label1[0] + "-" + optInterval,
width=width1 * 10 / 11,
height=(height1 * 10 / 11) / len(labels))
kline.add(label1[0],
time,
data_li,
is_datazoom_show=True,
datazoom_type="slider",
yaxis_interval=1)
overlap.add(kline)
if len(close) > 10:
ma10 = calculateMa(close, 10)
line1 = Line(title_color="#C0C0C0")
line1.add(label1[0] + "-" + "MA10", time, ma10)
overlap.add(line1)
if len(close) > 20:
ma20 = calculateMa(close, 20)
line2 = Line(title_color="#C0C0C0")
line2.add(label1[0] + "-" + "MA20", time, ma20)
overlap.add(line2)
if len(close) > 30:
ma30 = calculateMa(close, 30)
line3 = Line(title_color="#C0C0C0")
line3.add(label1[0] + "-" + "MA30", time, ma30)
overlap.add(line3)
page.add(overlap)
else: #When label1[2]==open/close/volume
if label1[2] == 'Open':
list_aft = array['open'].tolist()
elif label1[2] == 'Close':
list_aft = array['close'].tolist()
elif label1[2] == 'High':
list_aft = array['high'].tolist()
elif label1[2] == 'Low':
list_aft = array['low'].tolist()
elif label1[2] == 'Volume': #volume
list_aft = array['volume'].tolist()
else: #amount
list_aft = array['amount'].tolist()
line = Line(label1[0] + "-" + label1[2],
width=width1 * 10 / 11,
height=(height1 * 10 / 11) / len(labels))
line.add(label1[0] + "-" + label1[2],
time,
list_aft,
is_datazoom_show=True,
yaxis_max="dataMax",
yaxis_min="dataMin",
datazoom_type="slider")
overlap.add(line)
page.add(overlap)
elif label1[2] == "分笔":
array = ts.get_tick_data(label1[1], date=startdate)
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 val == "卖盘":
amount[idx] = -amount[idx]
if val == "中性盘":
amount[idx] = 0
returnarray = list(zip(date, amount, flag, price))
form = [e[1] for e in returnarray]
time = [d[0] for d in returnarray]
bar = Bar(label1[0] + "-" + label1[2],
width=width1 * 10 / 11,
height=(height1 * 10 / 11) / len(labels))
bar.add(label1[0] + "-" + label1[2],
time,
form,
is_datazoom_show=True,
datazoom_type="slider",
yaxis_min="dataMin",
yaxis_max="dataMax")
overlap.add(bar)
line = Line(label1[0] + "price",
width=width1 * 10 / 11,
height=(height1 * 10 / 11) / len(labels))
price = [e[3] for e in returnarray]
line.add(label1[0] + "price",
time,
price,
yaxis_min="dataMin",
yaxis_max="dataMax",
is_datazoom_show=True,
datazoom_type="slider",
yaxis_type="value")
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
page.add(overlap)
elif label1[2] == "季度饼图":
datestr = startdate.split("-")
thisyear = datestr[0]
df2 = ts.top10_holders(code=label1[1], 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 range(0, len(name), 10)]
valuearray = [value[j:j + 10] for j in range(0, len(value), 10)]
quarterarray = [
quarter[k:k + 10] for k in range(0, len(quarter), 10)
]
flag = ["pie" for i in namearray]
num = [len(value) for k in namearray]
returnarray = list(
zip(namearray, valuearray, quarterarray, flag, num))
timeline = Timeline(is_auto_play=False, timeline_bottom=0
) # zip(namearray,valuearray,quarter,flag,num)
namearray = [c[0] for c in returnarray]
valuearray = [d[1] for d in returnarray]
quarter = [e[2] for e in returnarray]
num = returnarray[0][4]
for x in range(0, int(num / 10)):
list1 = valuearray[x]
names = namearray[x]
quarters = quarter[x][0]
for idx, val in enumerate(list1):
list1[idx] = float(val)
pie = Pie(label1[0] + "-" + "前十股东",
width=width1 * 10 / 11,
height=(height1 * 10 / 11))
pie.add(label1[0] + "-" + "前十股东",
names,
list1,
radius=[30, 55],
is_legend_show=False,
is_label_show=True,
label_formatter="{b}: {c}\n{d}%")
timeline.add(pie, quarters)
# namearray = [y for y in namearray[x]]
timeline.render()
page.render()
import tushare as ts
import pandas as pd
from IPython.display import HTML
StockCode = '300036'
#历年前十大股东持股情况
#df1为季度统计摘要，data1为前十大持股明细统计
df1, data1 = ts.top10_holders(code=StockCode,
gdtype='1') #gdtype等于1时表示流通股，默认为0
df1 = df1.sort_values('quarter', ascending=True)
qts = list(df1['quarter'])
data = list(df1['props'])
lgdstr = """
var axisData = """ + str(qts) + """;
var data = """ + str(data) + """;
var links = data.map(function (item, i) {
return {
source: i,
target: i + 1
};
});
links.pop();
option = {
title: {
text: '【超图软件】前十大流通股东持股占比'
},
tooltip: {
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!="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
