siat 3.0.44__py3-none-any.whl → 3.1.1__py3-none-any.whl

siat/fund_china.py

@@ -25,12 +25,12 @@ if __name__=='__main__':
     quarter1='2022Q4'
     quarter2='2023Q1'
     
-    df=fund_stock_holding_compare_china(fund,quarter1,quarter2,top=10)
+    df=fund_stock_holding_compare_china(fund,quarter1,quarter2,rank=10)
 
 #比较两个季度之间的基金持仓变化
-def fund_stock_holding_compare_china(fund,quarter1,quarter2,top=10):
+def fund_stock_holding_compare_china(fund,quarter1,quarter2,rank=10):
     """
-    功能：基金fund在两个季度quarter1和quarter2的持仓股票对比（股数和金额），前top名股票
+    功能：基金fund在两个季度quarter1和quarter2的持仓股票对比（股数和金额），前rank名股票
     参数：
     fund,str,基金代码;
     quarter1,str,靠前的季度, 格式为 'YYYYQ1',例如: '2021Q2';
@@ -130,10 +130,10 @@ def fund_stock_holding_compare_china(fund,quarter1,quarter2,top=10):
     df_merge = df_merge[['股票代码', '股票名称', s1_share,s1_value, s1_ratio,s2_share,s2_value,s2_ratio, '持股数变化']]
     
     df_merge.reset_index(drop=True,inplace=True)
-    if top>0:
-        df=df_merge.head(top)
+    if rank>0:
+        df=df_merge.head(rank)
     else:
-        df=df_merge.head(-top)
+        df=df_merge.head(-rank)
     """
     #持股数和持仓比例取整数
     df.fillna(0)
@@ -171,14 +171,14 @@ def fund_stock_holding_compare_china(fund,quarter1,quarter2,top=10):
     name=get_fund_name_china2(fund)
     
     order='前'
-    if top <0: 
+    if rank <0: 
         order='后'
-        top=-top
+        rank=-rank
         
     # 替换空值
     df.fillna('---')
     
-    print("===== 中国基金持仓股票分析："+name+'，'+s1+"对比"+s2,"(按后者持仓比例高低排列，"+order+str(top)+"名股票) =====\n")
+    print("===== 中国基金持仓股票分析："+name+'，'+s1+"对比"+s2,"(按后者持仓比例高低排列，"+order+str(rank)+"名股票) =====\n")
     print(df.to_string(index=False))
     import datetime; today = datetime.date.today()
     print("\n*** 注：持股数为万股，持仓市值为万元，持仓比例为占基金资产净值比例%，包括A股与非A股")
@@ -329,9 +329,9 @@ def fund_stock_holding_rank_china(fund,year_num=2):
 #==============================================================================
 if __name__=='__main__':
     fund='180801'
-    top=10
+    rank=10
 
-def reits_jsl_china(fund='',top=10):
+def reits_jsl_china(fund='',rank=10):
     """
     功能：REITs基金信息概述和列表
     目前不能正常工作，因为集思录数据源现在需要会员登陆才能显示和下载信息
@@ -358,10 +358,10 @@ def reits_jsl_china(fund='',top=10):
     dfa=df[df['代码']==fund]
     # 未找到
     if len(dfa)==0:
-        if top > 0:
-            dfa=df.head(top)
+        if rank > 0:
+            dfa=df.head(rank)
         else:
-            dfa=df.tail(-top)
+            dfa=df.tail(-rank)
         dfb=dfa[['代码','名称','昨收','规模(亿元)','到期日']]
         
         #设置打印对齐
@@ -372,10 +372,10 @@ def reits_jsl_china(fund='',top=10):
         pd.set_option('display.unicode.east_asian_width', True)
         
         order='前'
-        if top <0: 
+        if rank <0: 
             order='后'
-            top=-top
-        print("\n===== 中国REITs基金列表(按最新价高低排列，"+order+str(top)+"名) =====\n")
+            rank=-rank
+        print("\n===== 中国REITs基金列表(按最新价高低排列，"+order+str(rank)+"名) =====\n")
         print(dfb)
 
         print("*** 数据来源：东方财富/集思录, 总计"+str(num)+"只REITs基金,",today)         
@@ -399,14 +399,14 @@ def reits_jsl_china(fund='',top=10):
 
 #==============================================================================
 if __name__=='__main__':
-    top=10
+    rank=10
     
-    df=reits_list_china(top=10)
+    df=reits_list_china(rank=10)
 
-def reits_list_china(top=20):
+def reits_list_china(rank=10,sort='最新价'):
     """
     功能：REITs基金信息概述和列表
-    目前不能正常工作，因为数据源集思录现在需要会员登陆才能显示信息
+    目前能正常工作
     """
     import akshare as ak
     try:
@@ -414,11 +414,18 @@ def reits_list_china(top=20):
     except:
         print("  #Error(reits_profile_china): akshare does not work properly now")
         return None
+    df2.drop('序号', axis=1, inplace=True)
+    
+    sortlist=list(df2)
+    if sort not in sortlist:
+        print("  #Error(reits_list_china):",sort,"is not supported")
+        print("  Supported sort method:",sortlist)
+        return None
     
     #df2.sort_values(by=['昨收'],ascending=False,inplace=True)
-    df2.sort_values(by=['最新价'],ascending=False,inplace=True)
+    df2.sort_values(by=[sort],ascending=False,inplace=True)
     df2.reset_index(drop=True,inplace=True)
-    df2['序号']=df2.index + 1
+    #df2['序号']=df2.index + 1
     num=len(df2)
     
     #设置打印对齐
@@ -428,22 +435,24 @@ def reits_list_china(top=20):
     pd.set_option('display.unicode.ambiguous_as_wide', True)
     pd.set_option('display.unicode.east_asian_width', True)
         
-    if top > 0:
+    if rank > 0:
         order='前'
-        dfb=df2.head(top)
+        dfb=df2.head(rank)
     else: 
         order='后'
-        top=-top
-        dfb=df2.tail(top)
+        rank=-rank
+        dfb=df2.tail(rank)
     
     dfb.fillna("---",inplace=True)
     dfb['成交额']=dfb['成交额'].apply(lambda x: int(x))
     
-    print("\n===== 中国REITs基金列表(按最新价高低排列，"+order+str(top)+"名) =====\n")
+    #print("\n===== 中国REITs基金列表(按最新价高低排列，"+order+str(rank)+"名) =====\n")
+    titletxt="中国REITs基金列表（按"+sort+"降序排列，"+order+str(rank)+"名）"
     """
     print(dfb.to_string(index=False))
     """
     #print('')   #在标题与表格之间空一行
+    """
     alignlist=['right','center','left']+['right']*9
     try:   
         print(dfb.to_markdown(index=False,tablefmt='plain',colalign=alignlist))
@@ -452,10 +461,16 @@ def reits_list_china(top=20):
         print_df=dfb.to_markdown(index=False,tablefmt='plain',colalign=alignlist)
         print_df2=print_df.encode("utf-8",errors="strict")
         print(print_df2)       
-        
-    import datetime
-    today = datetime.date.today()
-    print("\n*** 数据来源：东方财富, 总计"+str(num)+"只REITs基金,",today)         
+    """    
+    import datetime; todaydt = datetime.date.today()
+    #print("\n*** 数据来源：东方财富, 总计"+str(num)+"只REITs基金,",today)  
+    footnote="数据来源：东方财富, 总计"+str(num)+"只REITs基金，"+str(todaydt)  
+
+    df_display_CSS(dfb,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=3, \
+                       first_col_align='left',second_col_align='left', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')     
     
     return df2
 
@@ -478,7 +493,9 @@ def pof_list_china(fund_type='全部类型',printout=True):
     df = ak.fund_name_em()
     
     df.sort_values(by=['拼音全称'],na_position='first',inplace=True)
-    df.drop_duplicates(subset=['基金代码','基金类型'], keep='first',inplace=True)    
+    df.drop_duplicates(subset=['基金代码','基金类型'], keep='first',inplace=True) 
+    df=df[df['基金类型'] != '']
+    df['基金类型']=df['基金类型'].apply(lambda x: x.upper())
     
     #获取基金类型列表，并去掉重复项
     typelist=list(set(list(df['基金类型'])))
@@ -509,11 +526,14 @@ def pof_list_china(fund_type='全部类型',printout=True):
         if fund_type != '全部类型':
             print(texttranslate("共找到")+str(num)+texttranslate("支基金, 类型为")+fund_type)
             return df3
-        
+        """
         print("\n",texttranslate("======= 中国公募基金种类概况 ======="))
         print(texttranslate("公募基金总数："),"{:,}".format(num))
         print(texttranslate("其中包括："))
-       
+        """
+        titletxt="中国公募基金的种类与分布概况"
+        footnote1="【注】公募基金总数："+str("{:,}".format(num))+'\n'
+        
         maxlen=0
         for t in typelist:
             tlen=hzlen(t)
@@ -529,18 +549,24 @@ def pof_list_china(fund_type='全部类型',printout=True):
         except:
             pass
         
-        for t in typelist2:
-            n=len(df[df['基金类型']==t])
-            """
-            tlen=strlen(t)
-            prefix=' '*4+t+' '*(maxlen-tlen)+':'
-            print(prefix,"{:,}".format(n),"\b,",round(n/num*100,2),'\b%')
-            """
-            print('{t:<{len}}\t'.format(t=t,len=maxlen-len(t.encode('GBK'))+len(t)+2),str(n).rjust(6,' '),"\t",(str(round(n/num*100,2))+'%').rjust(6,' '))
-
-        import datetime
-        today = datetime.date.today()
-        print(texttranslate("数据来源：东方财富/天天基金,"),today)
+        dfg.rename(columns={0:'基金数量'}, inplace=True)
+        dfg['数量占比']=dfg['基金数量'].apply(lambda x: str(round(x/num*100,3))+'%')
+        dfg.reset_index(inplace=True)
+        
+        collist=list(dfg)
+        dfg['序号']=dfg.index+1
+        dfg=dfg[['序号']+collist]
+        
+        import datetime; todaydt = datetime.date.today()
+        #print(texttranslate("数据来源：东方财富/天天基金,"),today)
+        footnote2="数据来源：东方财富/天天基金，"+str(todaydt)
+        footnote=footnote1+footnote2
+        
+        df_display_CSS(dfg,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=3, \
+                           first_col_align='center',second_col_align='left', \
+                           last_col_align='right',other_col_align='right', \
+                           titile_font_size='16px',heading_font_size='15px', \
+                           data_font_size='15px')
         
     return df3
 
@@ -569,13 +595,19 @@ def oef_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     df1 = ak.fund_open_fund_daily_em()
     collist=list(df1)
     nvname1=collist[2]
-    nvdate=nvname1[:10]
     nvname2=collist[3]
+    if df1[nvname1].isna().all() or df1[nvname1].eq(0).all() or df1[nvname1].eq('').all():
+        nvname1=collist[4]
+        nvname2=collist[5]
+    nvdate=nvname1[:10]
+    
+    df1x=df1[df1[nvname1] != '']
+    
     #修改列名
-    df1.rename(columns={nvname1:'单位净值',nvname2:'累计净值'}, inplace=True) 
+    df1x.rename(columns={nvname1:'单位净值',nvname2:'累计净值'}, inplace=True) 
     #df1a=df1.drop(df1[df1['单位净值']==''].index)
     #df1b=df1a.drop(df1a[df1a['累计净值']==''].index)
-    df1c=df1[['基金代码','基金简称','单位净值','累计净值','日增长率','申购状态','赎回状态','手续费']]
+    df1c=df1x[['基金代码','基金简称','单位净值','累计净值','日增长率','申购状态','赎回状态','手续费']]
     
     
     #获取所有公募基金类型信息
@@ -634,23 +666,27 @@ def oef_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
         df['单位净值']=df['单位净值'].apply(lambda x: round(x,2))
         df.sort_values(by=['单位净值'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','基金类型','单位净值','申购状态','赎回状态']]
-        print(texttranslate("\n===== 中国开放式基金排名：单位净值 ====="))
+        #print(texttranslate("\n===== 中国开放式基金排名：单位净值 ====="))
+        titletxt="中国开放式基金排名：单位净值"
     
     if info_type == '累计净值':
         df['累计净值']=df['累计净值'].apply(lambda x: round(x,2))
         df.sort_values(by=['累计净值'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','基金类型','累计净值','申购状态','赎回状态']]
-        print(texttranslate("\n===== 中国开放式基金排名：累计净值 ====="))      
+        #print(texttranslate("\n===== 中国开放式基金排名：累计净值 =====")) 
+        titletxt="中国开放式基金排名：累计净值"
     
     if info_type == '手续费':
         df.sort_values(by=['手续费'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','基金类型','手续费','申购状态','赎回状态']]
-        print(texttranslate("\n===== 中国开放式基金排名：手续费 ====="))          
+        #print(texttranslate("\n===== 中国开放式基金排名：手续费 =====")) 
+        titletxt="中国开放式基金排名：手续费"         
     
     if info_type == '增长率':
         df.sort_values(by=['日增长率'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','基金类型','日增长率','申购状态','赎回状态']]
-        print(texttranslate("\n===== 中国开放式基金排名：增长率% ====="))          
+        #print(texttranslate("\n===== 中国开放式基金排名：增长率% ====="))  
+        titletxt="中国开放式基金排名：增长率%"         
     
     df=df.replace(0,'--')
     
@@ -676,6 +712,7 @@ def oef_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     """
     alignlist=['left','left']+['center']*(len(list(amac_sum_df.head(10)))-3)+['right']
     """
+    """
     print('')   #在标题与表格之间空一行
     alignlist=['right','left','center','center','right','center','center']
     try:   
@@ -693,6 +730,19 @@ def oef_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     import datetime
     today = datetime.date.today()
     print(texttranslate("数据来源：东方财富/天天基金,"),today)        
+    """
+    footnote1="披露净值的开放式基金数量："+str(len(dfprint))+'，'
+    footnote2="基金类型："+str(fund_type)+'\n'
+    footnote3="净值日期："+str(nvdate)+'，'
+    import datetime; todaydt = datetime.date.today()
+    footnote4="数据来源：东方财富/天天基金，"+str(todaydt)
+    footnote=footnote1+footnote2+footnote3+footnote4
+    
+    df_display_CSS(dfprint10,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=4, \
+                       first_col_align='left',second_col_align='right', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')
     
     return df
 
@@ -731,19 +781,20 @@ def get_oef_name_china(fund_code):
 if __name__=='__main__':
     fund='050111.SS'
     fund='000592.SS'
-    fromdate='2020-9-1'
-    todate='2021-9-1'
+    start='MRM'
+    end='today'
     trend_type='净值'
     power=0
     twinx=False
     zeroline=False
 
-def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
+def oef_trend_china(fund,start,end='today',trend_type='净值', \
                     power=0,twinx=False, \
                     loc1='upper left',loc2='lower left'):
     """
     功能：开放式基金业绩趋势，单位净值，累计净值，近三个月收益率，同类排名，总排名
     """
+    fromdate,todate=start_end_preprocess(start,end)
     #检查走势类型
     trendlist=["净值","收益率","排名"]
     if trend_type not in trendlist:
@@ -770,9 +821,10 @@ def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
     source=texttranslate("数据来源：东方财富/天天基金")
 
     fund1=fund[:6]
-    fund_name=ticker_name(fund1,ticker_type)
+    fund_name=ticker_name(fund1,'fund')
 
     #绘制单位/累计净值对比图
+    import pandas as pd
     if trend_type == '净值':
         df1 = ak.fund_open_fund_info_em(fund1, indicator="单位净值走势")
         df1.rename(columns={'净值日期':'date','单位净值':'单位净值'}, inplace=True)
@@ -784,8 +836,9 @@ def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
         df2.set_index(['date'],inplace=True)       
         
         #合并
-        import pandas as pd
         df = pd.merge(df1,df2,left_index=True,right_index=True,how='inner')
+        df['日期']=df['日期'].apply(lambda x: pd.to_datetime(x))
+        
         dfp=df[(df['日期'] >= start)]
         dfp=dfp[(dfp['日期'] <= end)]
         if len(dfp) == 0:
@@ -811,10 +864,11 @@ def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
     
     #绘制累计收益率单线图
     if trend_type == '收益率':
-        df = ak.fund_open_fund_info_em(fund=fund1, indicator="累计收益率走势")
-        df.rename(columns={'净值日期':'date','累计收益率':'累计收益率'}, inplace=True)
-        df['日期']=df['date']
+        df = ak.fund_open_fund_info_em(fund1, indicator="累计收益率走势")
+        #df.rename(columns={'净值日期':'date','累计收益率':'累计收益率'}, inplace=True)
+        df['date']=df['日期']
         df.set_index(['date'],inplace=True) 
+        df['日期']=df['日期'].apply(lambda x: pd.to_datetime(x))
         dfp=df[(df['日期'] >= start)]
         dfp=dfp[(dfp['日期'] <= end)]  
         if len(dfp) == 0:
@@ -830,7 +884,7 @@ def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
     
     #绘制同类排名图：近三个月收益率
     if trend_type == '排名':
-        df1 = ak.fund_open_fund_info_em(fund=fund1, indicator="同类排名走势")
+        df1 = ak.fund_open_fund_info_em(fund1, indicator="同类排名走势")
         df1.rename(columns={'报告日期':'date','同类型排名-每日近三月排名':'同类排名','总排名-每日近三月排名':'总排名'}, inplace=True)
         df1['日期']=df1['date']
         df1['总排名']=df1['总排名'].astype('int64')
@@ -841,8 +895,8 @@ def oef_trend_china(fund,fromdate,todate,trend_type='净值', \
         df2.set_index(['date'],inplace=True)       
         
         #合并
-        import pandas as pd
         df = pd.merge(df1,df2,left_index=True,right_index=True,how='inner')
+        df['日期']=df['日期'].apply(lambda x: pd.to_datetime(x))
         dfp=df[(df['日期'] >= start)]
         dfp=dfp[(dfp['日期'] <= end)]
         if len(dfp) == 0:
@@ -890,7 +944,9 @@ def mmf_rank_china(rank=10):
     #获取货币型基金实时信息
     df = ak.fund_money_fund_daily_em()
     collist=list(df)
-    nvname=collist[6]
+    nvname=collist[3]
+    if df[nvname].eq('').all():
+        nvname=collist[6]
     nvdate=nvname[:10]
     #修改列名
     df.rename(columns={nvname:'7日年化%'}, inplace=True) 
@@ -899,7 +955,8 @@ def mmf_rank_china(rank=10):
     
     dfb.sort_values(by=['7日年化%'],ascending=False,inplace=True)
     dfprint=dfb[['基金简称','基金代码','7日年化%','基金经理','手续费']]
-    print(texttranslate("\n======= 中国货币型基金排名：7日年化收益率 ======="))
+    #print(texttranslate("\n======= 中国货币型基金排名：7日年化收益率 ======="))
+    titletxt="中国货币型基金排名：7日年化收益率"
         
     #设置打印对齐
     import pandas as pd
@@ -921,6 +978,7 @@ def mmf_rank_china(rank=10):
     """
     print(dfprint10)
     """
+    """
     print('')   #在标题与表格之间空一行
     alignlist=['right','left','center','center','center','right']
     try:   
@@ -938,6 +996,18 @@ def mmf_rank_china(rank=10):
     import datetime
     today = datetime.date.today()
     print(texttranslate("数据来源：东方财富/天天基金,"),today)        
+    """
+    footnote1="披露收益率信息的货币型基金数量："+str(len(dfprint))+'\n'
+    footnote2="收益率日期："+str(nvdate)+'，'
+    import datetime; todaydt = datetime.date.today()
+    footnote3="数据来源：东方财富/天天基金，"+str(todaydt)
+    footnote=footnote1+footnote2+footnote3
+    
+    df_display_CSS(dfprint10,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=4, \
+                       first_col_align='left',second_col_align='right', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')    
     
     return df
 
@@ -951,11 +1021,11 @@ if __name__=='__main__':
     todate='2020-10-16'
     power=0
 
-def mmf_trend_china(fund,fromdate,todate,power=0):
+def mmf_trend_china(fund,start,end='today',power=0):
     """
     功能：货币型基金业绩趋势，7日年化收益率
     """
-    
+    fromdate,todate=start_end_preprocess(start,end)
     #检查日期
     result,start,end=check_period(fromdate,todate)
     if not result:
@@ -971,7 +1041,6 @@ def mmf_trend_china(fund,fromdate,todate,power=0):
     #基金历史数据
     import datetime; today = datetime.date.today()
     source=texttranslate("数据来源：东方财富/天天基金")
-
     
     #绘制收益率单线图
     fund1=fund[:6]
@@ -1029,8 +1098,12 @@ def etf_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     #提取净值日期
     collist=list(df2)
     nvname1=collist[3]
-    nvdate=nvname1[:10]
     nvname2=collist[4]
+    if df2[nvname1].eq('').all() or df2[nvname1].eq('---').all():
+        nvname1=collist[5]
+        nvname2=collist[6]
+    nvdate=nvname1[:10]
+    
     #修改列名
     df3=df2.rename(columns={nvname1:'单位净值',nvname2:'累计净值'}) 
     df=df3[['基金简称','基金代码','类型','单位净值','累计净值','增长率','市价']]
@@ -1064,27 +1137,35 @@ def etf_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
         df['单位净值']=df['单位净值'].astype(float)
         df.sort_values(by=['单位净值'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','类型','单位净值','市价']]
-        print(texttranslate("\n===== 中国ETF基金排名：单位净值 ====="))
+        #print(texttranslate("\n===== 中国ETF基金排名：单位净值 ====="))
+        titletxt="中国ETF基金排名：单位净值"
+        dfprint=dfprint[dfprint['单位净值'] != 0]
     
     if info_type == '累计净值':
         df=df.replace('---',0)
         df['累计净值']=df['累计净值'].astype(float)
         df.sort_values(by=['累计净值'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','类型','累计净值','单位净值']]
-        print(texttranslate("\n===== 中国ETF基金排名：累计净值 ====="))        
+        #print(texttranslate("\n===== 中国ETF基金排名：累计净值 ====="))  
+        titletxt="中国ETF基金排名：累计净值"
+        dfprint=dfprint[dfprint['累计净值'] != 0]
     
     if info_type == '市价':
         df=df.replace('---',0)
         df['市价']=df['市价'].astype(float)
         df.sort_values(by=['市价'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','类型','市价','单位净值']]
-        print(texttranslate("\n===== 中国ETF基金排名：市价 ====="))          
+        #print(texttranslate("\n===== 中国ETF基金排名：市价 ====="))  
+        titletxt="中国ETF基金排名：市价"   
+        dfprint=dfprint[dfprint['市价'] != 0]
     
     if info_type == '增长率':
         df['增长率']=df['增长率'].astype(str)
         df.sort_values(by=['增长率'],ascending=False,inplace=True)
         dfprint=df[['基金简称','基金代码','类型','增长率','市价','单位净值']]
-        print(texttranslate("\n===== 中国ETF基金排名：增长率 ====="))   
+        #print(texttranslate("\n===== 中国ETF基金排名：增长率 =====")) 
+        titletxt="中国ETF基金排名：增长率"
+        dfprint=dfprint[dfprint['增长率'] != 0]
         
     #设置打印对齐
     import pandas as pd
@@ -1106,6 +1187,7 @@ def etf_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     """
     print(dfprint10)
     """
+    """
     print('')   #在标题与表格之间空一行
     alignlist=['right','left','center','center','right','right']
     try:   
@@ -1124,6 +1206,19 @@ def etf_rank_china(info_type='单位净值',fund_type='全部类型',rank=10):
     import datetime
     today = datetime.date.today()
     print(texttranslate("数据来源：东方财富/天天基金,"),today)        
+    """
+    footnote1="披露净值信息的ETF基金数量："+str(len(dfprint))+'，'
+    footnote2="基金类型："+str(fund_type)+'\n'
+    footnote3="净值日期："+str(nvdate)+'，'
+    import datetime; todaydt = datetime.date.today()
+    footnote4="数据来源：东方财富/天天基金，"+str(todaydt)
+    footnote=footnote1+footnote2+footnote3+footnote4
+    
+    df_display_CSS(dfprint10,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=3, \
+                       first_col_align='left',second_col_align='right', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')
     
     return df
 
@@ -1138,10 +1233,12 @@ if __name__=='__main__':
     fromdate='2020-1-1'
     todate='2020-10-16'
 
-def etf_trend_china(fund,fromdate,todate,loc1='best',loc2='best',twinx=False,graph=True):
+def etf_trend_china(fund,start,end='today',loc1='best',loc2='best',twinx=False,graph=True):
     """
     功能：ETF基金业绩趋势，单位净值，累计净值
     """
+    fromdate,todate=start_end_preprocess(start,end='today')
+    
     #检查日期
     result,start,end=check_period(fromdate,todate)
     if not result:
@@ -1167,7 +1264,8 @@ def etf_trend_china(fund,fromdate,todate,loc1='best',loc2='best',twinx=False,gra
     df.set_index(['date'],inplace=True) 
     df['单位净值']=df['单位净值'].astype("float")
     df['累计净值']=df['累计净值'].astype("float")
-        
+    
+    df['净值日期']=df['净值日期'].apply(lambda x: pd.to_datetime(x))        
     dfp=df[(df['净值日期'] >= start)]
     dfp=dfp[(dfp['净值日期'] <= end)]
     if len(dfp) == 0:
@@ -1234,13 +1332,18 @@ def fund_summary_china():
     pd.set_option('display.width',1000)         # 设置宽度,就是说不换行,比较好看数据
     pd.set_option('display.max_rows',500)       # 设置行数的多少
     pd.set_option('display.colheader_justify','left')
-      
+    """  
     print(texttranslate("\n===== 中国基金投资机构概况 ====="))
     print(texttranslate("机构（会员）数量："),end='')
     num=len(list(set(list(amac_df["机构（会员）名称"]))))
     print("{:,}".format(num))
         
     print(texttranslate("其中包括："))
+    """
+    titletxt="中国基金投资机构概况"
+    num=len(list(set(list(amac_df["机构（会员）名称"]))))
+    footnote1="机构（会员）数量："+str(num)
+    
     amac_sum_df=pd.DataFrame(columns=['机构类型','数量','占比%'])
     for t in typelist:
         df_sub=amac_df[amac_df['机构类型']==t]
@@ -1270,6 +1373,7 @@ def fund_summary_china():
     """
     pandas2prettytable(amac_sum_df.head(10),titletxt='',firstColSpecial=True,leftColAlign='l',otherColAlign='c',tabborder=False)
     """
+    """
     alignlist=['left','left']+['center']*(len(list(amac_sum_df.head(10)))-3)+['right']
     try:   
         print(amac_sum_df.head(10).to_markdown(index=True,tablefmt='plain',colalign=alignlist))
@@ -1283,6 +1387,17 @@ def fund_summary_china():
     source=texttranslate("\n数据来源：中国证券投资基金业协会")
     footnote=source+', '+str(today)  
     print(footnote)
+    """
+    import datetime; todaydt = datetime.date.today()
+    footnote2="数据来源：中国证券投资基金业协会，"+str(todaydt)
+    footnote=footnote1+'\n'+footnote2
+    df10=amac_sum_df.head(10)
+    
+    df_display_CSS(df10,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=2, \
+                       first_col_align='left',second_col_align='right', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')
     
     """    
     print(texttranslate("\n===== 中国基金投资机构会员代表概况 ====="))
@@ -1495,12 +1610,13 @@ if __name__=='__main__':
     step_page_list=[100,10,1]
     DEBUG=True
 
-def get_pef_product_china(max_pages=2000,step_page_list=[200,10,1],DEBUG=True):   
+def get_pef_product_china(max_pages=2000,step_page_list=[100,20,1],DEBUG=True):   
     """
     功能：获取中国私募基金产品运营方式和状态信息，耗时较长
     注意：由于获取过程极易失败，因此分割为三个阶段进行下载，然后合成。
     """
-    print("  Searching pef info repeatedly, may need several hours, please wait ...")
+    print("  Downloading in pages, which takes long time upon network stability and speed")
+    print("  If a download is stuck, RESTART Python kernel or even Jupyter, then run again")
     import pandas as pd
     
     # 第1步：页数跨度最大
@@ -1559,88 +1675,134 @@ def get_pef_product_china(max_pages=2000,step_page_list=[200,10,1],DEBUG=True):
 #==============================================================================
 
 
-def pef_product_china(DEBUG=False):
+def pef_product_china(rank=20,facecolor='papayawhip',DEBUG=False):
     
     """
     功能：中国私募基金管理人的产品管理概况
     爬虫来源地址：https://zhuanlan.zhihu.com/p/97487003
+    注意：下载数据需要极长时间，极少完全成功，谨慎运行！
     """
-    print("Searching for private equity fund (PEF) info in China, it may take hours ...")
+    print("Searching for private equity fund (PEF) info in China ...")
     import akshare as ak
     import pandas as pd
 
     #私募基金管理人基金产品
-    product_df = get_pef_product_china(max_pages=2200,step_page_list=[200,10,1],DEBUG=False)
-    
-    print(texttranslate("\n== 中国私募基金管理人的产品与运营概况 =="))
-    print(texttranslate("产品数量："),end='')
-    num=len(list(product_df["基金名称"]))
-    print("{:,}".format(num))  
-        
-    #管理类型
-    print(texttranslate("产品的运营方式分布："))
-    #typelist=list(set(list(product_df['私募基金管理人类型'])))
-    typelist=['受托管理','顾问管理','自我管理']
+    product_df = get_pef_product_china(max_pages=2200,step_page_list=[100,22,1],DEBUG=False)
+    product_df['私募基金管理人类型']=product_df['私募基金管理人类型'].apply(lambda x: '方式不明' if x=='' or x is None else x)
+    product_df['运行状态']=product_df['运行状态'].apply(lambda x: '状态不明' if x=='' or x is None else x)
+    
+    #num=len(list(product_df["基金名称"])) #统计可能有问题，原因不明
+    #footnote1="找到产品数量："+str("{:,}".format(num))+'\n'
+    import datetime; todaydt = datetime.date.today()
+    footnote9="数据来源：中国证券投资基金业协会，"+str(todaydt)       
+    
+    # 产品运营方式==============================================================
+    titletxt="中国私募基金管理人的产品运营方式"
+
+    #typelist=['受托管理','顾问管理','自我管理']
+    typelist=list(set(list(product_df['私募基金管理人类型'])))
+    dfprint=pd.DataFrame(columns=['运营方式','产品数量','数量占比%'])
+    totalnum=0
     for t in typelist:
             df_sub=product_df[product_df['私募基金管理人类型']==t]
             n=len(list(set(list(df_sub['基金名称']))))
-            prefix=' '*4+t+':'
-            print(prefix,"{:,}".format(n),"\b,",round(n/num*100,2),'\b%')     
-        
-    #运行状态
-    print(texttranslate("产品的运营状态分布："))
-    """
+            totalnum=totalnum+n
+            
+            s=pd.Series({'运营方式':t,'产品数量':n})
+            try:
+                dfprint=dfprint.append(s,ignore_index=True)
+            except:
+                dfprint=dfprint._append(s,ignore_index=True) 
+                
+    dfprint['数量占比%']=dfprint['产品数量'].apply(lambda x: round(x/totalnum*100,3))
+    dfprint['产品数量']=dfprint['产品数量'].apply(lambda x: str("{:,}".format(x)))
+    
+    dfprint.sort_values(by=['数量占比%'],ascending=False,inplace=True)
+    dfprint.reset_index(drop=True,inplace=True)        
+    dfprint.index=dfprint.index + 1 
+    collist=list(dfprint)
+    dfprint['序号']=dfprint.index
+    dfprint=dfprint[['序号']+collist]
+
+    footnote1="找到管理产品"+str("{:,}".format(totalnum))+'个\n'
+    footnote=footnote1+footnote9
+
+    df_display_CSS(dfprint,titletxt=titletxt,footnote=footnote,facecolor=facecolor,decimals=3, \
+                       first_col_align='center',second_col_align='left', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')                
+                
+    #运营状态===================================================================
+    titletxt="中国私募基金管理人的产品运营状态"
     typelist=list(set(list(product_df['运行状态'])))
-    typelist=['状态不明' if i =='' else i for i in typelist]
-    """
-    typelist=['正在运作','提前清算','正常清算','延期清算','投顾协议已终止','']
-    maxlen=0
-    for t in typelist:
-            tlen=strlen(t)
-            if tlen > maxlen: maxlen=tlen
-    maxlen=maxlen+1 
-        
+    dfprint=pd.DataFrame(columns=['运营状态','产品数量','数量占比%'])  
+    totalnum=0
     for t in typelist:
             df_sub=product_df[product_df['运行状态']==t]
             n=len(list(set(list(df_sub['基金名称']))))
-            if t =='': t='状态不明'
-            tlen=strlen(t)
-            prefix=' '*4+t+' '*(maxlen-tlen)+':'
-            print(prefix,"{:,}".format(n),"\b,",round(n/num*100,2),'\b%')      
-
-    import datetime; today = datetime.date.today()
-    source=texttranslate("数据来源：中国证券投资基金业协会")
-    footnote=source+', '+str(today)       
-    print(footnote)
-        
-    #推出产品数量排行
-    print(texttranslate("\n===== 中国推出产品数量最多的私募基金管理人 ====="))
+            if n==0: continue
+            totalnum=totalnum+n
+            
+            s=pd.Series({'运营状态':t,'产品数量':n})
+            try:
+                dfprint=dfprint.append(s,ignore_index=True)
+            except:
+                dfprint=dfprint._append(s,ignore_index=True)               
+                
+    dfprint['数量占比%']=dfprint['产品数量'].apply(lambda x: round(x/totalnum*100,3))
+    dfprint['产品数量']=dfprint['产品数量'].apply(lambda x: str("{:,}".format(x)))
+    
+    dfprint.sort_values(by=['数量占比%'],ascending=False,inplace=True)
+    dfprint.reset_index(drop=True,inplace=True)        
+    dfprint.index=dfprint.index + 1 
+    collist=list(dfprint)
+    dfprint['序号']=dfprint.index
+    dfprint=dfprint[['序号']+collist]
+
+    footnote1="找到运营产品"+str("{:,}".format(totalnum))+'个\n'
+    footnote=footnote1+footnote9
+                
+    df_display_CSS(dfprint,titletxt=titletxt,footnote=footnote,facecolor=facecolor,decimals=3, \
+                       first_col_align='center',second_col_align='left', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')  
+        
+    #推出产品数量排行===========================================================
+    titletxt="中国推出产品数量最多的私募基金管理人（前"+str(rank)+"名）"
     subttl=pd.DataFrame(product_df.groupby(by=['私募基金管理人名称'])['基金名称'].count())
     subttl.rename(columns={'基金名称':'产品数量'}, inplace=True)
-    subttl['占比‰']=round(subttl['产品数量']/num*1000.0,2)
+    subttl['数量占比‰']=round(subttl['产品数量']/totalnum*1000.0,2)
     subttl.sort_values(by=['产品数量'],ascending=False,inplace=True)
     subttl.reset_index(inplace=True)
     
     subttl.index=subttl.index + 1
-    subttl10=subttl.head(10)
-        
-    #设置打印对齐
-    pd.set_option('display.max_columns', 1000)
-    pd.set_option('display.width', 1000)
-    pd.set_option('display.max_colwidth', 1000)
-    pd.set_option('display.unicode.ambiguous_as_wide', True)
-    pd.set_option('display.unicode.east_asian_width', True)
+    subttl10=subttl.head(rank)
     
-    print(subttl10)
+    dfprint=subttl10
+    dfprint.sort_values(by=['数量占比‰'],ascending=False,inplace=True)
+    dfprint.reset_index(drop=True,inplace=True)        
+    dfprint.index=dfprint.index + 1 
+    collist=list(dfprint)
+    dfprint['序号']=dfprint.index
+    dfprint=dfprint[['序号']+collist]
     
-    pctsum=round(subttl10['占比‰'].sum(),2)    
-    print(texttranslate("上述产品总计占比:"),pctsum,'\b‰')     
-    print(footnote)
-        
-    print(texttranslate("\n===== 中国私募基金管理人的产品托管概况 ====="))
-    #托管产品数量排行
+    pctsum=round(subttl10['数量占比‰'].sum(),2)   
+    footnote1="找到产品"+str("{:,}".format(totalnum))+"个，上述产品合计占比"+str(pctsum)+'%'+'\n'
+    footnote=footnote1+footnote9
+    
+    df_display_CSS(dfprint,titletxt=titletxt,footnote=footnote,facecolor=facecolor,decimals=2, \
+                       first_col_align='center',second_col_align='left', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')      
+    
+    
+    # 托管产品==================================================================
+    titletxt="中国私募基金管理人的产品托管概况（前"+str(rank)+"名）"
     tnum=len(list(set(list(product_df['托管人名称']))))
-    print(texttranslate("托管机构数量:"),"{:,}".format(tnum))
+    footnote1="找到产品"+str("{:,}".format(totalnum))+"个，托管机构"+str("{:,}".format(tnum))+'家\n'
     
     subttl=pd.DataFrame(product_df.groupby(by=['托管人名称'])['基金名称'].count())
     subttl.rename(columns={'基金名称':'产品数量'}, inplace=True)
@@ -1650,15 +1812,30 @@ def pef_product_china(DEBUG=False):
     subttl=subttl[subttl['托管人名称']!='']
     #subttl.drop(subttl.index[0], inplace=True)       # 删除第1行
     subttl.reset_index(drop=True,inplace=True)
-    subttl['占比%']=round(subttl['产品数量']/num*100.0,2)
+    subttl['数量占比%']=round(subttl['产品数量']/totalnum*100.0,3)
     
     subttl.index=subttl.index + 1
-    subttl10=subttl.head(10)
-        
-    pctsum=round(subttl10['占比%'].sum(),2)
-    print(subttl10)
-    print(texttranslate("上述金融机构托管产品总计占比:"),pctsum,'\b%')
-    print(footnote)     
+    subttl10=subttl.head(rank)
+        
+    pctsum=round(subttl10['数量占比%'].sum(),2)
+    #print(subttl10)
+    #print(texttranslate("上述金融机构托管产品总计占比:"),pctsum,'\b%')
+    footnote2="上述机构托管产品合计占比："+str(pctsum)+'%\n'
+    footnote=footnote1+footnote2+footnote9
+    
+    dfprint=subttl10
+    dfprint.sort_values(by=['数量占比%'],ascending=False,inplace=True)
+    dfprint.reset_index(drop=True,inplace=True)        
+    dfprint.index=dfprint.index + 1 
+    collist=list(dfprint)
+    dfprint['序号']=dfprint.index
+    dfprint=dfprint[['序号']+collist]    
+
+    df_display_CSS(dfprint,titletxt=titletxt,footnote=footnote,facecolor=facecolor,decimals=3, \
+                       first_col_align='center',second_col_align='left', \
+                       last_col_align='right',other_col_align='right', \
+                       titile_font_size='16px',heading_font_size='15px', \
+                       data_font_size='15px')  
         
     return product_df   
 

siat/security_prices.py

@@ -1244,8 +1244,8 @@ def get_prices_yahoo(ticker,start,end,retry_count=3,pause=1):
 
         print("  Successfully retrieved",len(p),"records for",ticker,ptname)
 
-    #去掉时区
-    p=df_index_timezone_remove(p)
+        #去掉时区
+        p=df_index_timezone_remove(p)
     
     return p
 
@@ -1331,13 +1331,13 @@ def get_prices_yf(ticker,start,end,threads=False):
             if ptname == ticker: ptname=''
 
             print("  Successfully retrieved",len(p),"records for",ticker1,ptname)  
+            
+            #去掉时区
+            p=df_index_timezone_remove(p)
     else:
         pass
         #print("  #Error(get_prices_yf):",ticker1,"not found or no prices in the period or inaccessible to yahoo")
 
-    #去掉时区
-    p=df_index_timezone_remove(p)
-
     return p
 
 if __name__=='__main__':

{siat-3.0.44.dist-info → siat-3.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: siat
-Version: 3.0.44
+Version: 3.1.1
 Summary: Securities Investment Analysis Tools (siat)
 Home-page: https://pypi.org/project/siat/
 Author: Prof. WANG Dehong, International Business School, Beijing Foreign Studies University

{siat-3.0.44.dist-info → siat-3.1.1.dist-info}/RECORD

@@ -52,7 +52,7 @@ siat/financials_test.py,sha256=HJ3CPo_Xckz2wXi3AEP6ZNWCF1Duc1pLi0Y10USiImc,23829
 siat/fred_test.py,sha256=KF50ssSbsfpa_kT6iuomD0vG4eXztAcOasZxg1OGX5w,1201
 siat/fund.py,sha256=wMDORsCBV8ZXfgwbtq-0bu3qqWY66dHnbqgllW0gWCo,24637
 siat/fund_china.pickle,sha256=QI3IjV46EeJ5ryO3xocmByc-6b_6_nDxgcXDhBHzop0,2380915
-siat/fund_china.py,sha256=vdri-FucJ39SDdnM0AWULN9biSaQVh-dnfM03AhOuZY,80880
+siat/fund_china.py,sha256=e-Ngpm34Kby8CFkso3M6KA4MWOPSi-M9FxS8Nv7Yr5M,90910
 siat/fund_china_test.py,sha256=-Bh6m0J0GPpIbYXx-H2vpzJoNFI6pE2C2jVPa8DazgE,6649
 siat/fund_test.py,sha256=V4ADb8Gsp8gyeFTwcgRsJBpnUih_O-Q2V1ILc5oKjK8,1116
 siat/future_china.py,sha256=F-HsIf2Op8Z22RzTjet1g8COzldgnMjFNSXsAkeGyWo,17595
@@ -95,7 +95,7 @@ siat/sector_china.py,sha256=QSNJclhzT6V9NidziMwwAs-Kk6f7nzdK6PiPGkKrBCk,111617
 siat/sector_china_test.py,sha256=1wq7ef8Bb_L8F0h0W6FvyBrIcBTEbrTV7hljtpj49U4,5843
 siat/security_price.py,sha256=2oHskgiw41KMGfqtnA0i2YjNNV6cYgtlUK0j3YeuXWs,29185
 siat/security_price2.py,sha256=kuYh0V5cqclkM6MjZUd-N361fv3oxGVVerYINuTzZrE,24622
-siat/security_prices.py,sha256=m_dWQ24Au9WMNOb1o0Igm6Sg1llz7kyIX3vSXrE5Jng,102705
+siat/security_prices.py,sha256=gubx-HrlnkSTByIhMC9qB2fxTMJTTxW1DH9KDGX22dY,102741
 siat/security_prices_test.py,sha256=OEphoJ87NPKoNow1QA8EU_5MUYrJF-qKoWKNapVfZNI,10779
 siat/security_trend.py,sha256=o0vpWdrJkmODCP94X-Bvn-w7efHhj9HpUYBHtLl55D0,17240
 siat/security_trend2.py,sha256=4yBY3ve0Kddu95JemS02gfLbrHVN2_gl_irr5pA4F6w,24626
@@ -132,7 +132,7 @@ siat/valuation.py,sha256=NKfeZMdDJOW42oLVHob6eSVBXUqlN1OCnnzwyGAst8c,48855
 siat/valuation_china.py,sha256=Tde2LzPDQy3Z7xOQQDw4ckQMPdROp_z0-GjFE6Z5_lI,67639
 siat/valuation_market_china_test.py,sha256=gbJ0ioauuo4koTPH6WKUkqcXiQPafnbhU5eKJ6lpdLA,1571
 siat/var_model_validation.py,sha256=f-oDewg7bPzyNanz_Y_jLH68NowAA3gXFehW_weKGG0,14898
-siat-3.0.44.dist-info/METADATA,sha256=lpYsF83FvwNlChiPm7slWucBOXtr6f2JcxFVEiMDSps,1448
-siat-3.0.44.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-siat-3.0.44.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
-siat-3.0.44.dist-info/RECORD,,
+siat-3.1.1.dist-info/METADATA,sha256=9fUOM1J5SJKvPEnZpip7QZ4nd_W7tCtWaK6kSPCphNQ,1447
+siat-3.1.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+siat-3.1.1.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
+siat-3.1.1.dist-info/RECORD,,