siat 3.4.37__py3-none-any.whl → 3.5.2__py3-none-any.whl

siat/sector_china.py

@@ -731,7 +731,7 @@ def sector_position_china(ticker,sector="new_dlhy"):
 
 #==============================================================================
 
-def invest_concept_china(num=10):
+def invest_concept_china(num=10,max_sleep=30):
     """
     废弃！
     功能：汇总投资概念股票名单，排行
@@ -755,7 +755,7 @@ def invest_concept_china(num=10):
     
     import pandas as pd
     totaldf=pd.DataFrame()
-    import time
+    import time; import random
     i=0
     #新浪财经有反爬虫，这个循环做不下去
     for c in clist:
@@ -769,7 +769,10 @@ def invest_concept_china(num=10):
             print(', failed:-(')
             #continue
                     #等待一会儿，避免被禁访问
-        time.sleep(10)
+        #time.sleep(max_sleep)
+        random_int=random.randint(1,max_sleep)
+        time.sleep(random_int)
+
         i=i+1
         if i % 20 == 0:
             print(int(i/cnum*100),'\b%',end=' ')
@@ -804,7 +807,7 @@ def invest_concept_china(num=10):
 #==============================================================================
 def industry_sw_list_all():
     """
-    功能：输出申万指数所有代码df。动态，每次重新获取
+    功能：输出申万指数所有代码df。动态，每次重新获取，自动更新！
     输入：
     输出：df，包括市场表征指数F，一级行业指数I，二级行业T，风格指数S，三级行业3
     """
@@ -816,6 +819,7 @@ def industry_sw_list_all():
     industry=pd.DataFrame()
     for s in symboltypes:
         try:
+            #目前有问题！
             dft = ak.index_realtime_sw(symbol=s)
         except: continue
         
@@ -944,38 +948,62 @@ if __name__=='__main__':
     iname='食品饮料'
     iname='银行'
     iname='汽车'
+    iname='高价股指数'
+    iname='申万Ａ指'
+    iname='大类风格-医药医疗'
+    
     numberPerLine=5
     colalign='right'
     
     print_industry_component_sw(iname,numberPerLine=5,colalign='right')
 
-def print_industry_component_sw(iname,numberPerLine=5,colalign='left',return_result=False):
+def print_industry_component_sw(iname,numberPerLine=5,colalign='left', \
+                                printout=True,return_result=False):
     """
     打印申万行业的成分股，名称(代码)
     """
     try:
         icode=industry_sw_code(iname)
     except:
-        print("  #Warning(print_industry_component_sw): sector or industry name not found for",iname)
-        return
+        print("  #Warning(print_industry_component_sw): failed to find index name for",iname)
+        if return_result:
+            return []
+        else:
+            return
+    
+    if icode=='':
+        print("  #Warning(print_industry_component_sw): relevent index code not found for",iname)
+        if return_result:
+            return []
+        else:
+            return
+    
+    clist,cdf=industry_stock_sw(icode,top=1000)  
+    if clist is None:
+        if return_result:
+            print("  #Warning(print_industry_component_sw): no component stock found for",iname)
+            return []
+        else:
+            return
     
-    clist,cdf=industry_stock_sw(icode,top=1000)    
-
     #cdf['icode']=cdf['证券代码'].apply(lambda x: x+'.SS' if x[:1] in ['6'] else (x+'.SZ' if x[:1] in ['0','3'] else x+'.BJ' ))
     cdf['icode']=cdf['证券代码']
     
     # 删除'证券名称'为None的行
     cdf=cdf.mask(cdf.eq('None')).dropna()
-    cdf['name_code']=cdf.apply(lambda x: x['证券名称']+'('+x['icode']+')',axis=1)
     
-    #标题
-    import datetime as dt; stoday=dt.date.today()    
+    # 合成证券名称与代码
+    cdf['name_code']=cdf.apply(lambda x: x['证券名称']+'('+x['icode']+')',axis=1)
     ilist=list(cdf['name_code'])
 
-    titletxt=iname+"("+icode+")行业/板块成分股：计"+str(len(ilist))+'只，按行业指数权重降序排列，'+str(stoday)
-    print("\n"+titletxt,end='')
-    #表格
-    printInLine_md(ilist,numberPerLine=numberPerLine,colalign=colalign)
+    if printout:    
+        #标题
+        import datetime as dt; stoday=dt.date.today()    
+    
+        titletxt=iname+"("+icode+")行业/板块成分股：计"+str(len(ilist))+'只，按行业指数权重降序排列，'+str(stoday)
+        print("\n"+titletxt,end='')
+        #表格
+        printInLine_md(ilist,numberPerLine=numberPerLine,colalign=colalign)
     
     if return_result:
         return ilist
@@ -1025,6 +1053,8 @@ def print_industry_component_sw2(icode,numberPerLine=5,colalign='left'):
 
 #==============================================================================
 if __name__=='__main__':
+    iname='大类风格--医药医疗'
+    
     industry_sw_code('光伏设备')
 
 def industry_sw_code(iname):
@@ -1108,7 +1138,10 @@ def industry_ranking_sw(start,end,measure='Exp Ret%', \
     """
     完整版，全流程
     功能：模板，遍历某类申万指数，计算某项业绩指标，汇集排序
-    itype: F表征指数，n=1/2/3行业指数，S风格指数，B大类风格指数，C金创指数
+    itype: 
+    股票类指数：F表征指数，n=1/2/3行业指数，S风格指数，B大类风格指数，C金创指数？
+    基金类指数：J1/2/3基础一二三级，JF特色指数
+
     period="day"; choice of {"day", "week", "month"}
     绘图：柱状图，可选
     """
@@ -1133,13 +1166,22 @@ def industry_ranking_sw(start,end,measure='Exp Ret%', \
     fail_list=[]
     for i in ilist:
         
-        print("  Processing industry",i,"\b, please wait ...")
+        print("  Processing index",i,"\b, please wait ...")
         #抓取指数价格，选取期间范围
         try:
             dft = ak.index_hist_sw(symbol=i,period="day")
         except:
-            fail_list=fail_list+[i]
-            continue
+            try:
+                dft = ak.index_hist_fund_sw(symbol=i,period="day")
+                dft['代码']=i
+                dft['收盘']=dft['收盘指数']
+                dft['开盘']=dft['收盘指数']
+                dft['最高']=dft['收盘指数']
+                dft['最低']=dft['收盘指数']
+                dft['成交量']=0; dft['成交额']=0
+            except:
+                fail_list=fail_list+[i]
+                continue
         
         dft['ticker']=dft['代码']
         dft['date']=dft['日期'].apply(lambda x: pd.to_datetime(x))
@@ -1179,10 +1221,10 @@ def industry_ranking_sw(start,end,measure='Exp Ret%', \
     df['name']=df['ticker'].apply(lambda x: industry_sw_name(x))
     df.set_index('name',inplace=True)
     colname='value'
-    titletxt="行业分析：业绩排名"
+    titletxt="行业/指数分析：业绩排名"
     import datetime; today=datetime.date.today()
     footnote0=ectranslate(measure)+' ==>\n'
-    footnote1='申万行业分类，观察期：'+start+'至'+iend+'\n'
+    footnote1='申万行业/指数分类，观察期：'+start+'至'+iend+'\n'
     footnote2="数据来源: 申万宏源, "+str(today)
     footnote=footnote0+footnote1+footnote2
     
@@ -1190,11 +1232,12 @@ def industry_ranking_sw(start,end,measure='Exp Ret%', \
     #plot_barh2(df,colname,titletxt,footnote)
     
     if len(fail_list) > 0:
-        print("  Unable to retrieve",len(fail_list),"industry(ies) as follows:")
+        print("  Unable to retrieve",len(fail_list),"industry(ies) as follows:",end='')
         if len(fail_list) >= 10:
             printInLine_md(fail_list,numberPerLine=10,colalign='left',font_size='16px')
         else:
             printInLine_md(fail_list,numberPerLine=len(fail_list),colalign='left',font_size='16px')
+        print('') #空一行
 
     return df
     
@@ -1247,8 +1290,17 @@ def industry_ranking_sw2(industrylist,start,end,measure='Exp Ret%', \
         try:
             dft = ak.index_hist_sw(symbol=i,period="day")
         except:
-            print("  #Warning(industry_ranking_sw2): industry not found for",i)
-            continue
+            try:
+                dft = ak.index_hist_fund_sw(symbol=i,period="day")
+                dft['代码']=i
+                dft['收盘']=dft['收盘指数']
+                dft['开盘']=dft['收盘指数']
+                dft['最高']=dft['收盘指数']
+                dft['最低']=dft['收盘指数']
+                dft['成交量']=0; dft['成交额']=0
+            except:                
+                print("  #Warning(industry_ranking_sw2): index not found for",i)
+                continue
         
         dft['ticker']=dft['代码']
         dft['date']=dft['日期'].apply(lambda x: pd.to_datetime(x))
@@ -1291,10 +1343,10 @@ def industry_ranking_sw2(industrylist,start,end,measure='Exp Ret%', \
     df.dropna(inplace=True)
     
     colname='value'
-    titletxt="行业分析：业绩排名"
+    titletxt="行业/指数分析：业绩排名"
     import datetime; today=datetime.date.today()
     footnote0=ectranslate(measure)+' ==>\n'
-    footnote1='申万行业分类，观察期：'+start+'至'+iend+'\n'
+    footnote1='申万行业/指数分类，观察期：'+start+'至'+iend+'\n'
     footnote2="数据来源: 申万宏源, "+str(today)
     footnote=footnote0+footnote1+footnote2
     
@@ -1311,10 +1363,13 @@ if __name__=='__main__':
     period="day"
     industry_list='all'    
     
-def get_industry_sw(itype='1',period="day",industry_list='all',max_sleep=15):
+def get_industry_sw(itype='1',period="day",industry_list='all',max_sleep=30):
     """
     功能：遍历某类申万指数，下载数据
-    itype: F表征指数，n=1/2/3行业指数，S风格指数，B大类风格，C金创类
+    itype: 
+    股票类指数：F表征指数，n=1/2/3行业指数，S风格指数，B大类风格指数，C金创指数？
+    基金类指数：J1/2/3基础一二三级，JF特色指数
+
     period="day"; choice of {"day", "week", "month"}
     industry_list: 允许选择部分行业
     """
@@ -1345,7 +1400,7 @@ def get_industry_sw(itype='1',period="day",industry_list='all',max_sleep=15):
     import datetime; import random; import time
     df=pd.DataFrame()
 
-    print("  Start searching industry data, it takes time, please wait ...")
+    print("  Searching industry data, it takes time, please wait ...")
     num=len(ilist)
     if num <= 10:
         steps=5
@@ -1362,9 +1417,18 @@ def get_industry_sw(itype='1',period="day",industry_list='all',max_sleep=15):
         try:
             dft = ak.index_hist_sw(symbol=i,period="day")
         except:
-            #print("  #Warning(get_industry_sw): unsupported industry",i)
-            fail_list=fail_list+[i]
-            continue
+            try:
+                dft = ak.index_hist_fund_sw(symbol=i,period="day")
+                dft['代码']=i
+                dft['收盘']=dft['收盘指数']
+                dft['开盘']=dft['收盘指数']
+                dft['最高']=dft['收盘指数']
+                dft['最低']=dft['收盘指数']
+                dft['成交量']=0; dft['成交额']=0
+            except:            
+                #print("  #Warning(get_industry_sw): unsupported industry",i)
+                fail_list=fail_list+[i]
+                continue
         
         dft['ticker']=dft['代码']
         dft['date']=dft['日期'].apply(lambda x: pd.to_datetime(x))
@@ -1393,11 +1457,8 @@ def get_industry_sw(itype='1',period="day",industry_list='all',max_sleep=15):
         time.sleep(random_int)        
     
     #num=list(set(list(df['ticker'])))
-    if len(fail_list)==0: 
-        print("  Successfully retrieved",len(df),"records in",len(ilist),"industries")
-    else:
-        print("\n  Successfully retrieved",len(df),"records in",len(ilist),"industries")
-    #print("  Successfully retrieved",len(df),"records in",num,"industries")
+    if len(df)>0: 
+        print("  Successfully retrieved",len(df),"records in",len(ilist)-len(fail_list),"industries")
     
     if len(fail_list) > 0:
         print("  Failed to retrieve",len(fail_list),"industry(ies) as follows:")
@@ -1421,7 +1482,7 @@ if __name__=='__main__':
     industry_list=['850831.SW','801785.SW','801737.SW','801194.SW',
                    '801784.SW','801783.SW','801782.SW']    
     
-def get_industry_sw2(industry_list,period="day",max_sleep=15):
+def get_industry_sw2(industry_list,period="day",max_sleep=30):
     """
     功能：遍历指定的申万指数列表，下载数据
     period="day"; choice of {"day", "week", "month"}
@@ -1454,9 +1515,18 @@ def get_industry_sw2(industry_list,period="day",max_sleep=15):
         try:
             dft = ak.index_hist_sw(symbol=i,period="day")
         except:
-            #print("  #Warning(get_industry_sw): unsupported industry",i)
-            fail_list=fail_list+[i]
-            continue
+            try:
+                dft = ak.index_hist_fund_sw(symbol=i,period="day")
+                dft['代码']=i
+                dft['收盘']=dft['收盘指数']
+                dft['开盘']=dft['收盘指数']
+                dft['最高']=dft['收盘指数']
+                dft['最低']=dft['收盘指数']
+                dft['成交量']=0; dft['成交额']=0
+            except:            
+                #print("  #Warning(get_industry_sw): unsupported industry",i)
+                fail_list=fail_list+[i]
+                continue
         
         dft['ticker']=dft['代码']
         dft['date']=dft['日期'].apply(lambda x: pd.to_datetime(x))
@@ -1484,11 +1554,9 @@ def get_industry_sw2(industry_list,period="day",max_sleep=15):
         time.sleep(random_int)        
     
     #num=list(set(list(df['ticker'])))
-    if len(fail_list) > 0:
-        print("\n  Successfully retrieved",len(df),"records in",len(ilist),"industries")
-    else:
-        print("  Successfully retrieved",len(df),"records in",len(ilist),"industries")
-    #print("  Successfully retrieved",len(df),"records in",num,"industries")
+    if len(df) > 0:
+        print("\n  Successfully retrieved",len(df),"records in",len(ilist)-len(fail_list),"industries")
+
     if len(fail_list) > 0:
         print("  Failed to retrieve",len(fail_list),"industry(ies) as follows:")
         if len(fail_list) >= 10:
@@ -1501,8 +1569,8 @@ def get_industry_sw2(industry_list,period="day",max_sleep=15):
 
 #==============================================================================
 if __name__=='__main__':
-    start='2018-1-1'
-    end='2022-10-31'
+    start='2023-8-31'
+    end='2024-9-30'
     df=get_industry_sw('F')
     
 def calc_industry_sw(df,start,end):
@@ -1514,7 +1582,7 @@ def calc_industry_sw(df,start,end):
     #检查日期的合理性
     result,start1,end1=check_period(start,end)
     if not result:
-        print("  #Error(calc_industry_sw): invalid date period",start,end)
+        print("  #Warning(calc_industry_sw): invalid date period",start,end)
         return None
 
     #屏蔽函数内print信息输出的类
@@ -1672,10 +1740,10 @@ def rank_industry_sw(idf,measure='Exp Ret%',industries=[], \
         gdf1=gdf
     
     if printout or graph:
-        titletxt="行业板块分析：最新业绩排名"
+        titletxt="行业板块/指数分析：最新业绩排名"
         import datetime; today=datetime.date.today()
         footnote0=ectranslate(measure)+' -->\n\n'
-        footnote1='申万行业分类，'+iend+'快照'
+        footnote1='申万行业/指数分类，'+iend+'快照'
         footnote2='观察期：'+istart+'至'+iend+'，'
         footnote3="数据来源: 申万宏源, "+str(today)+'统计'
         footnote=footnote0+footnote1+'\n'+footnote2+footnote3
@@ -1684,7 +1752,7 @@ def rank_industry_sw(idf,measure='Exp Ret%',industries=[], \
         gdf2=gdf1.sort_values(by=measure,ascending=False)
         gdf2.reset_index(inplace=True)
         gdf2.index=gdf2.index+1
-        gdf2.columns=['行业名称','行业代码',ectranslate(measure),'开始日期','结束日期']
+        gdf2.columns=['行业/指数名称','行业/指数代码',ectranslate(measure),'开始日期','结束日期']
         """
         print("***",titletxt,'\n')
         alignlist=['center']+['left']*(len(list(gdf2))-1)
@@ -1705,7 +1773,7 @@ def rank_industry_sw(idf,measure='Exp Ret%',industries=[], \
                 footnote=footnote0+footnote1+'\n'+footnote2+footnote3
                 plot_barh(gdf1,colname,titletxt,footnote,axisamp=axisamp)
             else: #使用plotly_express
-                titletxt="行业板块业绩排名："+ectranslate(measure)
+                titletxt="行业板块/指数业绩排名："+ectranslate(measure)
                 footnote=footnote1+'。'+footnote2+footnote3
                 plot_barh2(gdf1,colname,titletxt,footnote)
         else:
@@ -1772,6 +1840,11 @@ def compare_mindustry_sw(industry_list,measure,start,end, \
     
     #获取数据
     ddf=get_industry_sw(itype=itype,period=period,industry_list=industry_list)
+    found=df_have_data(ddf)
+    if not found=='Found':
+        print("  #Warning(compare_mindustry_sw): data tentatively unavailable for group",itype)
+        print("  Data is sometimes unavialble at certain tie points, eg public holidays")
+        return None
     
     #计算指标
     _,idf=calc_industry_sw(ddf,start,end)
@@ -1815,13 +1888,13 @@ def compare_mindustry_sw(industry_list,measure,start,end, \
     dfs1=dfs[(dfs.index >= istartpd) & (dfs.index <= iendpd)]
     
     y_label=measure
-    title_txt="行业板块分析：市场业绩趋势与评价"
+    title_txt="行业板块/指数分析：市场业绩趋势与评价"
     import datetime; today = datetime.date.today()
     if graph:
         colname=measure
         
         import datetime; today=datetime.date.today()
-        footnote1='\n申万行业分类，观察期：'+istart+'至'+iend+'\n'
+        footnote1='\n申万行业/指数分类，观察期：'+istart+'至'+iend+'\n'
         footnote2="数据来源: 申万宏源, "+str(today)+'统计'
         footnote=footnote1+footnote2
 
@@ -1905,6 +1978,11 @@ def compare_mindustry_sw2(industry_list,measure,start,end, \
     
     #获取数据
     ddf=get_industry_sw2(industry_list=industry_list,period=period)
+    found=df_have_data(ddf)
+    if not found=='Found':
+        print("  #Warning(compare_mindustry_sw): data tentatively unavailable for",industry_list)
+        print("  Data is sometimes unavialble at certain tie points, eg public holidays")
+        return None
     
     #计算指标
     _,idf=calc_industry_sw(ddf,start,end)
@@ -1948,13 +2026,13 @@ def compare_mindustry_sw2(industry_list,measure,start,end, \
     dfs1=dfs[(dfs.index >= istartpd) & (dfs.index <= iendpd)]
     
     y_label=measure
-    title_txt="行业(板块)分析：市场业绩趋势与评价"
+    title_txt="行业(板块)/指数分析：市场业绩趋势与评价"
     import datetime; today = datetime.date.today()
     if graph:
         colname=measure
-        title_txt="行业(板块)分析：市场业绩趋势"
+        title_txt="行业(板块)/指数分析：市场业绩趋势"
         import datetime; today=datetime.date.today()
-        footnote1='\n申万行业分类，观察期：'+istart+'至'+iend+'\n'
+        footnote1='\n申万行业/指数分类，观察期：'+istart+'至'+iend+'\n'
         footnote2="数据来源: 申万宏源, "+str(today)+'统计'
         footnote=footnote1+footnote2
 
@@ -2088,10 +2166,10 @@ def compare_industry_sw(idfall,industry_list,measure,graph=True):
     if graph:
         y_label=measure
         colname=measure
-        title_txt="行业板块分析：市场业绩趋势"
+        title_txt="行业板块/指数分析：市场业绩趋势"
         
         import datetime; today=datetime.date.today()
-        footnote1='\n申万行业分类，观察期：'+istart+'至'+iend+'\n'
+        footnote1='\n申万行业/指数分类，观察期：'+istart+'至'+iend+'\n'
         footnote2="数据来源: 申万宏源, "+str(today)+'统计'
         footnote=footnote1+footnote2
 
@@ -2147,11 +2225,11 @@ def compare_industry_sw_sharpe(idfall,industries,base_return='Annual Ret%',graph
     sdf=atmp[industrylist]
     if graph:
         y_label='夏普比率（基于'+ectranslate(base_return)+'）'
-        title_txt="行业板块分析：市场发展趋势"
+        title_txt="行业板块/指数分析：市场发展趋势"
         
         istart=sdf.index[0].strftime('%Y-%m-%d')
         iend=sdf.index[-1].strftime('%Y-%m-%d')
-        footnote1='\n申万行业分类，观察期：'+istart+'至'+iend+'\n'
+        footnote1='\n申万行业/指数分类，观察期：'+istart+'至'+iend+'\n'
         import datetime; today=datetime.date.today()
         #footnote2="数据来源: 申万宏源, "+str(today)+'统计（未计入无风险利率）'
         footnote2="数据来源: 申万宏源, "+str(today)+'统计'
@@ -2211,10 +2289,10 @@ def rank_industry_sw_sharpe(idfall,base_return='Exp Ret%',graph=True,axisamp=0.8
 
     if graph:
         colname=col
-        titletxt="行业板块分析：最新业绩排名"
+        titletxt="行业板块/指数分析：最新业绩排名"
         import datetime; today=datetime.date.today()
         footnote0='夏普比率(基于'+ectranslate(base_return)+') -->\n\n'
-        footnote1='申万行业分类，'+iend+'快照'
+        footnote1='申万行业/指数分类，'+iend+'快照'
         footnote2='观察期：'+istart+'至'+iend+'，'
         footnote3="数据来源: 申万宏源, "+str(today)+'统计'
         footnote=footnote0+footnote1+'\n'+footnote2+footnote3
@@ -2222,7 +2300,7 @@ def rank_industry_sw_sharpe(idfall,base_return='Exp Ret%',graph=True,axisamp=0.8
             footnote=footnote0+footnote1+'\n'+footnote2+footnote3
             plot_barh(dftail3,colname,titletxt,footnote,axisamp=axisamp)
         else: #使用plotly_express
-            titletxt="行业板块业绩排名：夏普比率(基于"+ectranslate(base_return)+')'
+            titletxt="行业板块/指数业绩排名：夏普比率(基于"+ectranslate(base_return)+')'
             footnote=footnote1+'。'+footnote2+footnote3
             plot_barh2(dftail3,colname,titletxt,footnote)
 
@@ -2235,6 +2313,8 @@ if __name__=='__main__':
     industry='801193.SW'
     industry='851811.SW'
     industry='801181.SW'
+    industry='801841.SW'
+    
     top=5
     df=industry_stock_sw(industry)
 
@@ -2257,10 +2337,14 @@ def industry_stock_sw(industry='801270.SW',top=5,printout=False):
     try:
         cdf = ak.index_component_sw(industry)
     except:
-        print("  #Warning(industry_stock_sw): failed to retrieve component info for",industry)
-        print("  Solution: upgrade akshare, restart jupyter and try again")
+        print("  #Warning(industry_stock_sw): failed to retrieve component for index",industry)
+        print("  Try solution: upgrade akshare, restart jupyter and try again")
         return None,None
 
+    #去重，保留最新日期的记录
+    cdf.sort_values(by=['证券代码','计入日期'],ascending=[True,False],inplace=True)
+    cdf.drop_duplicates(subset=['证券代码'],keep='first',inplace=True)
+    
     # 删除'证券名称'为None的行
     cdf=cdf.mask(cdf.eq('None')).dropna()
     cdf_total=len(cdf)
@@ -2290,9 +2374,9 @@ def industry_stock_sw(industry='801270.SW',top=5,printout=False):
     if printout:
         if '.SW' not in industry:
             industry=industry+'.SW'
-        titletxt="申万行业指数成分股："+industry_sw_name(industry)+'('+industry+')'
+        titletxt="申万指数成分证券："+industry_sw_name(industry)+'('+industry+')'
         import datetime as dt; todaydt=str(dt.date.today())
-        footnote="成分股总数："+str(cdf_total)+"，数据来源：申万宏源，"+str(todaydt)
+        footnote="成分证券数量："+str(cdf_total)+"，申万宏源，"+str(todaydt)
         
         #df_directprint(cdf1,title_txt,footnote)
         df_display_CSS(cdf1,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=3, \
@@ -2355,6 +2439,11 @@ def get_industry_info_sw(start,end,itype='1'):
     print("\n*** Step 1:")
     # 获取行业历史数据，本步骤所需时间较长
     df=get_industry_sw(itype=itype)
+    found=df_have_data(df)
+    if not found=='Found':
+        print("  #Warning(compare_mindustry_sw): data tentatively unavailable for group",itype)
+        print("  Data is sometimes unavialble at certain time points, try again later")
+        return None 
     
     print("\n*** Step 2:")
     # 计算基础数据，本步骤所需时间较长
@@ -2389,6 +2478,11 @@ def get_industry_info_sw2(industry_list,start,end):
     print("\n*** Step 1:")
     # 获取行业历史数据，本步骤所需时间较长
     df=get_industry_sw2(industry_list)
+    found=df_have_data(df)
+    if not found=='Found':
+        print("  #Warning(compare_mindustry_sw): data tentatively unavailable for",industry_list)
+        print("  Data is sometimes unavialble at certain time points, try again later")
+        return None 
     
     print("\n*** Step 2:")
     # 计算基础数据，本步骤所需时间较长
@@ -2653,7 +2747,7 @@ def industry_correlation_sw(df,tickers,start,end, \
                     elif  pv< 0.001:
                         ax1.text(n+widthx,m+widthy,'***',ha = 'center',color = 'k',fontdict=font_dict)
     
-    plt.title("行业板块"+info_type_cn+"之间的相关性")
+    plt.title("行业板块/指数"+info_type_cn+"之间的相关性")
     plt.tick_params(labelsize=corr_size)
     
     footnote1="\n显著性数值：***非常显著(<0.001)，**很显著(<0.01)，*显著(<0.05)，其余为不显著"
@@ -2661,7 +2755,7 @@ def industry_correlation_sw(df,tickers,start,end, \
 
     footnote3="\n观察期间: "+start+'至'+end
     import datetime as dt; stoday=dt.date.today()    
-    footnote4="；来源：Sina/EM，"+str(stoday)+"；基于申万行业分类"
+    footnote4="；来源：Sina/EM，"+str(stoday)+"；基于申万行业/指数分类"
     
     fontxlabel={'size':corr_size}
     plt.xlabel(footnote1+footnote2+footnote3+footnote4,fontxlabel)
@@ -2865,8 +2959,17 @@ def get_sw_index(ticker,start,end):
     try:
         dft = ak.index_hist_sw(symbol=symbol,period="day")
     except:
-        print("  #Error(get_sw_index): failed to retrieve info for Shenwan industry index",symbol)
-        return None
+        try:
+            dft = ak.index_hist_fund_sw(symbol=symbol,period="day")
+            dft['代码']=symbol
+            dft['收盘']=dft['收盘指数']
+            dft['开盘']=dft['收盘指数']
+            dft['最高']=dft['收盘指数']
+            dft['最低']=dft['收盘指数']
+            dft['成交量']=0; dft['成交额']=0
+        except:        
+            print("  #Error(get_sw_index): failed to retrieve index",symbol)
+            return None
         
     dft['ticker']=dft['代码'].apply(lambda x: x+'.SW')
     
@@ -2979,7 +3082,8 @@ if __name__ =="__main__":
 
 
 def industry_scan_china(sw_level='F', \
-                        indicator='Exp Ret%', \
+                        indicator='Exp Adj Ret%', \
+                        base_return='Exp Adj Ret%', \
                         start='MRY',end='default', \
                         RF=0, \
                         printout='smart', \
@@ -2989,16 +3093,25 @@ def industry_scan_china(sw_level='F', \
     申万行业分类sw_level：F--市场表征（默认），S--投资风格（策略），B--大类风格，C--金创，
     1--一级行业，2--二级行业，3--三级行业
     评估期间start与end：允许MRM/MRQ/MRY（默认）/YTD/L3Y(近三年)/L5Y(近五年)
+    base_return：计算sharpe和sortino比率使用的收益率类型。
+    当indicator不是sharpe或sortino比率时，base_return需要与indicator保持一致。
     RF：年化无风险收益率，默认0，可参照一年期国债收益率
     筛选方式printout：smart--收益前10名与后10名（默认），winner--仅限收益为正的行业，
     loser--仅限收益为负的行业，50--收益前50名，-10--收益后10名，all--所有行业
     """
     #indicator='Exp Ret%'
     
-    print("  Collecting industry info, it may take very long time ... ...")
+    #print("  Evaluating industry performance, it may take up to hours ... ...")
+
+    #节省获取数据的量和时间
+    if start=='MRY' and end=='default': #默认参数
+        if 'Weekly' in indicator or 'Weekly' in base_return:
+            start='MRM'
+        if 'Monthly' in indicator or 'Monthly' in base_return:
+            start='MRQ'
     
     # 检查申万行业
-    sw_level_list=['1','2','3','F','S','B','C']
+    sw_level_list=['1','2','3','F','S','B','C','J1','J2','J3','JF']
     if sw_level not in sw_level_list:
         print("  #Warning(industry_scan_china): invalid Shenwan industry types for",sw_level)
         print("  Valid Shenwan industry types:",end='')
@@ -3006,14 +3119,38 @@ def industry_scan_china(sw_level='F', \
         return None
 
     # 检查支持的指标
-    indicator_list=['Exp Ret%','Exp Ret Volatility%','Exp Ret LPSD%', \
-                    'sharpe','sortino']
+    base_return_list=['Exp Ret%','Exp Ret Volatility%','Exp Ret LPSD%', \
+                    'Exp Adj Ret%','Exp Adj Ret Volatility%','Exp Adj Ret LPSD%', \
+                        
+                    'Annual Ret%','Annual Ret Volatility%','Annual Ret LPSD%', \
+                    'Annual Adj Ret%','Annual Adj Ret Volatility%','Annual Adj Ret LPSD%', \
+                        
+                    'Quarterly Ret%','Quarterly Ret Volatility%','Quarterly Ret LPSD%', \
+                    'Quarterly Adj Ret%','Quarterly Adj Ret Volatility%','Quarterly Adj Ret LPSD%', \
+                        
+                    'Monthly Ret%','Monthly Ret Volatility%','Monthly Ret LPSD%', \
+                    'Monthly Adj Ret%','Monthly Adj Ret Volatility%','Monthly Adj Ret LPSD%', \
+                        
+                    'Weekly Ret%','Weekly Ret Volatility%','Weekly Ret LPSD%', \
+                    'Weekly Adj Ret%','Weekly Adj Ret Volatility%','Weekly Adj Ret LPSD%', \
+                    ]
+    if base_return not in base_return_list:
+        print("  #Warning(industry_scan_china): unsupported base return type for",base_return)
+        print("  Supported base return:")
+        printlist(base_return_list,numperline=5,beforehand='  ',separator=', ')
+        return None
+    
+        
+    indicator_list=base_return_list + ['sharpe','sortino']
+    
+    if indicator.lower() in ['sharpe','sortino']:
+        indicator=indicator.lower()
+
     if indicator not in indicator_list:
         print("  #Warning(industry_scan_china): unsupported indicator for",indicator)
         print("  Supported indicators:")
         printlist(indicator_list,numperline=5,beforehand='  ',separator=', ')
         return None
-
     
     # 检查日期：
     fromdate,todate=start_end_preprocess(start,end)
@@ -3050,7 +3187,8 @@ def industry_scan_china(sw_level='F', \
             fromdate=date_adjust(todate,adjust=-31)      
     """
     # 获取申万行业类别内部标识
-    itype_list=['1','2','3','F','S','B','C']
+    #itype_list=['1','2','3','F','S','B','C']
+    itype_list=sw_level_list
     pos=sw_level_list.index(sw_level)
     itype=itype_list[pos]
     
@@ -3060,21 +3198,68 @@ def industry_scan_china(sw_level='F', \
     
     # 循环获取行业指数，简单计算指数增长率，排序
     #print("  Retrieving industry info, which may need up to hours, take a break ...")
-    print("\n  *** Step 1: Retrieving information")
+    #print("\n  *** Step 1: Retrieving industry information")
+    print("  *** Step 1: ")
     # 获取行业历史数据，本步骤所需时间较长
     df=get_industry_sw(itype=itype)    
+    found=df_have_data(df)
+    if not found=='Found':
+        print("  #Warning(compare_mindustry_sw): data tentatively unavailable for group",itype)
+        print("  Data is sometimes unavialble at certain time points, try again later")
+        return None 
     
     # 计算指标
-    print("\n  *** Step 2: Computing indicators")
+    #print("\n  *** Step 2: Computing performance indicators")
+    print("\n  *** Step 2: ")
     # 计算基础数据，本步骤所需时间较长
     idf,idfall=calc_industry_sw(df,fromdate,todate)  
     
-    RF_daily=RF/365*100 #百分数
-    #RF_daily=RF/365
-    RF_days=RF_daily * calculate_days(fromdate, todate)
-    
-    idf['sharpe']=(idf['Exp Ret%']-RF_days) / idf['Exp Ret Volatility%']
-    idf['sortino']=(idf['Exp Ret%']-RF_days) / idf['Exp Ret LPSD%']
+    #设置base_return：非['sharpe','sortino']时
+    if not indicator in ['sharpe','sortino']:
+        #以下的判断顺序不可轻易改变
+        if 'Ret Volatility%' in indicator:
+            base_return=indicator.replace('Ret Volatility%','Ret%')
+        elif 'Ret Volatility' in indicator:
+            base_return=indicator.replace('Ret Volatility','Ret')
+        elif 'Ret LPSD%' in indicator:
+            base_return=indicator.replace('Ret LPSD%','Ret%')
+        elif 'Ret LPSD' in indicator:
+            base_return=indicator.replace('Ret LPSD','Ret')
+        else:
+            base_return=indicator
+            
+            
+    #计算期间内的无风险收益率：RF为小数，而idf中的收益率为百分数
+    if '%' in base_return:
+        RFS=RF*100 #百分数
+        
+        base_return_volatility=base_return.replace('Ret%','Ret Volatility%')
+        base_return_lpsd=base_return.replace('Ret%','Ret LPSD%')
+    else:
+        RFS=RF
+        
+        base_return_volatility=base_return.replace('Ret','Ret Volatility')
+        base_return_lpsd=base_return.replace('Ret','Ret LPSD')
+        
+    if 'Exp' in base_return:
+        RF_daily=RFS/365
+        RF_days=RF_daily * calculate_days(fromdate, todate)
+
+    elif 'Annual' in base_return:
+        RF_days=RFS
+        
+    elif 'Quarterly' in base_return:
+        RF_days=RFS/4
+        
+    elif 'Monthly' in base_return:
+        RF_days=RFS/12 
+        
+    elif 'Weekly' in base_return:
+        RF_days=RFS/52        
+        
+    idf['sharpe']=(idf[base_return]-RF_days) / idf[base_return_volatility]
+    idf['sortino']=(idf[base_return]-RF_days) / idf[base_return_lpsd]
+        
     
     # 排序
     idf.sort_values(indicator,ascending=False,inplace=True)
@@ -3107,9 +3292,9 @@ def industry_scan_china(sw_level='F', \
     if printout=='all':
         df_prt=df2
     elif printout=='winner':
-        df_prt=df2[df2['Exp Ret%'] > 0]
+        df_prt=df2[df2[indicator] > 0]
     elif printout=='loser':
-        df_prt=df2[df2['Exp Ret%'] <= 0]    
+        df_prt=df2[df2[indicator] <= 0]    
     else:
         try:
             printoutd=int(printout)
@@ -3121,10 +3306,10 @@ def industry_scan_china(sw_level='F', \
             pass
     
     # 标题改中文
-    df_prt.rename(columns={'Industry Code':'行业代码','Industry Name':'行业名称', \
-                           'Exp Ret%':'投资收益率%', \
-                           'Exp Ret Volatility%':'投资收益波动率%', \
-                           'Exp Ret LPSD%':'投资收益损失风险%', \
+    df_prt.rename(columns={'Industry Code':'代码','Industry Name':'名称', \
+                           base_return:ectranslate(base_return), \
+                           base_return_volatility:ectranslate(base_return_volatility), \
+                           base_return_lpsd:ectranslate(base_return_lpsd), \
                            'sharpe':'夏普比率','sortino':'索替诺比率'}, \
                   inplace=True)
     
@@ -3143,6 +3328,14 @@ def industry_scan_china(sw_level='F', \
         sw_level_txt='申万二级行业'
     elif sw_level=='3':
         sw_level_txt='申万三级行业'
+    elif sw_level=='J1':
+        sw_level_txt='申万基金基础一级指数'  
+    elif sw_level=='J2':
+        sw_level_txt='申万基金基础二级指数'  
+    elif sw_level=='J3':
+        sw_level_txt='申万基金基础三级指数' 
+    elif sw_level=='JF':
+        sw_level_txt='申万基金特色指数'         
     else:
         sw_level_txt='未知类别'
 
@@ -3161,9 +3354,9 @@ def industry_scan_china(sw_level='F', \
             num=int(printout)
             if len(df2) > abs(num):
                 if num > 0:
-                    printout_txt='收益前'+printout+"名"
+                    printout_txt='收益排名前'+printout+"名"
                 else:
-                    printout_txt='收益后'+str(abs(num))+"名"
+                    printout_txt='收益排名后'+str(abs(num))+"名"
             else:
                 printout_txt='所有指数'
         except:
@@ -3171,7 +3364,7 @@ def industry_scan_china(sw_level='F', \
         
     #titletxt="申万行业业绩排行榜："+sw_level_txt+'，共'+str(len(df_prt))+"个指数符合条件"
     #titletxt="行业业绩排行榜："+sw_level_txt+'，'+ectranslate(indicator)+'，筛选方式：'+printout_txt
-    titletxt="中国股市板块表现排行榜："+sw_level_txt+'，'+printout_txt
+    titletxt="申万宏源行业/指数业绩龙虎榜："+sw_level_txt+'，'+printout_txt
     #print("\n***",titletxt,'\n')
     """
     alignlist=['center']+['left']*(len(list(df_prt))-1)
@@ -3179,28 +3372,34 @@ def industry_scan_china(sw_level='F', \
     """
     #print("\n *** 数据来源：综合申万宏源/东方财富/新浪财经,",todaydt,"\b；分析期间:",fromdate+'至'+todate)
     #footnote1="筛选方式：all-所有，smart-收益最高最低各10个，winner-收益为正，loser-收益为负"
-    footnote2="数据来源：申万宏源，统计期间："+str(fromdate)+'至'+str(todate)+"(截至昨日)。"+str(todaydt)+"制表"
-    #footnote=footnote1+'\n'+footnote2
-    footnote=footnote2
+    footnote1="注：夏普/索梯诺比率基于"+ectranslate(base_return)+"，年化无风险利率"+str(round(RF*100,4))+'%'
+    footnote2="评估期间："+str(fromdate)+'至'+str(todate)+"，数据来源：申万宏源，"+str(todaydt)+"制表"
+    footnote=footnote1+'\n'+footnote2
+    #footnote=footnote2
     
     #确定表格字体大小
     titile_font_size=font_size
     heading_font_size=data_font_size=str(int(font_size.replace('px',''))-1)+'px'
     
     df_prt['序号']=df_prt.index
-    if indicator=='Exp Ret%':
-        df_prt=df_prt[['序号','行业名称','行业代码','投资收益率%','投资收益波动率%','投资收益损失风险%','夏普比率','索替诺比率']]
-    elif indicator=='Exp Ret Volatility%':
-        df_prt=df_prt[['序号','行业名称','行业代码','投资收益波动率%','投资收益率%','投资收益损失风险%','夏普比率','索替诺比率']]  
-    elif indicator=='Exp Ret LPSD%':
-        df_prt=df_prt[['序号','行业名称','行业代码','投资收益损失风险%','投资收益波动率%','投资收益率%','夏普比率','索替诺比率']]  
-    elif indicator=='sharpe':
-        df_prt=df_prt[['序号','行业名称','行业代码','夏普比率','索替诺比率','投资收益率%','投资收益波动率%','投资收益损失风险%']]  
+    if indicator=='sharpe':
+        df_prt=df_prt[['序号','名称','代码','夏普比率','索替诺比率', \
+                       ectranslate(base_return),ectranslate(base_return_volatility),ectranslate(base_return_lpsd)]]  
     elif indicator=='sortino':
-        df_prt=df_prt[['序号','行业名称','行业代码','索替诺比率','夏普比率','投资收益率%','投资收益波动率%','投资收益损失风险%']]  
-        
-        
+        df_prt=df_prt[['序号','名称','代码','索替诺比率','夏普比率', \
+                       ectranslate(base_return),ectranslate(base_return_volatility),ectranslate(base_return_lpsd)]]  
+
+    elif 'Volatility' in indicator:
+        df_prt=df_prt[['序号','名称','代码',ectranslate(base_return_volatility),ectranslate(base_return_lpsd), \
+                       ectranslate(base_return),'夏普比率','索替诺比率']]
+    elif 'LPSD' in indicator:
+        df_prt=df_prt[['序号','名称','代码',ectranslate(base_return_lpsd),ectranslate(base_return_volatility), \
+                       ectranslate(base_return),'夏普比率','索替诺比率']]  
+    else:
+        df_prt=df_prt[['序号','名称','代码',ectranslate(base_return), \
+                       ectranslate(base_return_volatility),ectranslate(base_return_lpsd),'夏普比率','索替诺比率']]  
         
+    #显示表格        
     df_display_CSS(df_prt,titletxt=titletxt,footnote=footnote,facecolor=facecolor, \
                    first_col_align='center',second_col_align='left', \
                    last_col_align='center',other_col_align='center', \
@@ -3233,12 +3432,12 @@ if __name__=='__main__':
     
     find_industry_sw(ticker)
     
-def find_industry_sw(ticker,level='1',ticker_order=True,max_sleep=10):
+def find_industry_sw(ticker,level='1',ticker_order=True,max_sleep=30):
     """
     功能：寻找一只或一组股票所属的申万行业，支持股票代码和股票名称。
     level='1'：默认只查找申万1级行业,以便节省时间
     ticker_order=True：默认输出结果按照ticker中的顺序,而非按照所属行业排序
-    max_sleep=8：为防止反爬虫，默认每次爬虫后睡眠最多几秒钟
+    max_sleep：为防止反爬虫，默认每次爬虫后睡眠最多几秒钟
     """
     print("  Searching shenwan industries for securities ... ...")
     
@@ -3755,4 +3954,42 @@ def stock_peers_sw(ticker):
         print(footnote)
     return
         
+#==============================================================================
+if __name__ == '__main__':
+    sw_index=['绩优股指数','大盘指数','中市盈率指数','高市净率指数',]
+    sw_index=['大类风格-先进制造','大类风格--医药医疗']
+    
+    index_intersection_sw(sw_index)
+
+def index_intersection_sw(sw_index=[]):
+    #寻找多个申万指数中共同的成分股
+    if len(sw_index)==0:
+        print("  #Warning(stock_intersection_sw): no index found for intersection")
+        return
+    
+    if isinstance(sw_index,str):
+        sw_index=[sw_index]
+        
+    result_list=[]
+    for i in sw_index:
+        try:
+            ilist=print_industry_component_sw(i,printout=False,return_result=True)  
+        except:
+            print("  #Warning(stock_intersection_sw): failed to find component for index",i)
+            continue
+        
+        if len(result_list)==0:
+            result_list=[ilist]
+        else:
+            result_list=result_list+[ilist]
+            
+    list_intersection(result_list)
+    
+    return
+#==============================================================================
+#==============================================================================
+#==============================================================================
+#==============================================================================
+#==============================================================================
+#==============================================================================