siat 3.1.1__py3-none-any.whl → 3.1.2__py3-none-any.whl

siat/fund_china.py

@@ -481,7 +481,7 @@ if __name__=='__main__':
     fund_type='债券型'
     printout=True
 
-def pof_list_china(fund_type='全部类型',printout=True):
+def pof_list_china(rank=10,fund_type='全部类型',printout=True):
     """
     功能：抓取公募基金列表，按照基金类型列表，按照基金名称拼音排序
     """
@@ -517,6 +517,7 @@ def pof_list_china(fund_type='全部类型',printout=True):
         df2=df[df['基金类型'].apply(lambda x: fund_type in x)]
     else:
         df2=df
+        
     df3=df2[['基金简称','基金代码','基金类型']]
     df3.reset_index(drop=True,inplace=True) 
     
@@ -526,13 +527,9 @@ 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'
+        
+        titletxt="中国公募基金的类型与分布（前"+str(rank)+"名）"
+        footnote1="共有"+str(len(typelist))+"种类型，"+str("{:,}".format(num))+'支基金\n'
         
         maxlen=0
         for t in typelist:
@@ -541,8 +538,10 @@ def pof_list_china(fund_type='全部类型',printout=True):
         maxlen=maxlen+1
         
         #排序
-        dfg=pd.DataFrame(df.groupby("基金类型").size())
-        dfg.sort_values(by=[0], ascending=False, inplace=True)
+        dfg0=pd.DataFrame(df.groupby("基金类型").size())
+        dfg0.sort_values(by=[0], ascending=False, inplace=True)
+        dfg=dfg0.head(rank)
+        
         typelist2=list(dfg.index)
         try:
             typelist2.remove('')
@@ -556,11 +555,11 @@ def pof_list_china(fund_type='全部类型',printout=True):
         collist=list(dfg)
         dfg['序号']=dfg.index+1
         dfg=dfg[['序号']+collist]
-        
+
+        footnote2="表中类型的数量占比为"+str(round(dfg['基金数量'].sum()/num*100,2))+"%\n"        
         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
+        footnote9="数据来源：东方财富/天天基金，"+str(todaydt)
+        footnote=footnote1+footnote2+footnote9
         
         df_display_CSS(dfg,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=3, \
                            first_col_align='center',second_col_align='left', \
@@ -1292,12 +1291,12 @@ if __name__=='__main__':
     
 #==============================================================================
 
-def fund_summary_china():
+def fund_summary_china(rank=10):
     """
     功能：中国基金投资机构概况
     爬虫来源地址：https://zhuanlan.zhihu.com/p/97487003
     """
-    print("Searching for fund investment institutions in China ...")
+    print("Searching for investment fund institutions in China ...")
     import akshare as ak
 
     #会员机构综合查询：
@@ -1309,7 +1308,7 @@ def fund_summary_china():
     try:
         amac_df = ak.amac_member_info()
     except:
-        print("  #Error(): data source tentatively inaccessible, try later")
+        print("  #Error(fund_summary_china): data source tentatively inaccessible, try later")
         return None
     
     """    
@@ -1318,114 +1317,50 @@ def fund_summary_china():
                 '证券公司私募基金子公司','证券公司资管子公司','境外机构']
     """
     typelist=list(set(list(amac_df["机构类型"])))
-    """
-    maxlen=0
-    for t in typelist:
-        #tlen=strlen(t)
-        tlen=hzlen(t)
-        if tlen > maxlen: maxlen=tlen
-    maxlen=maxlen+1
-    """
     
     import pandas as pd
-    pd.set_option('display.max_columns',1000)   # 设置最大显示列数的多少
-    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%'])
+    titletxt="中国基金机构类型与分布（前"+str(rank)+"名）"
+    
+    amac_sum_df=pd.DataFrame(columns=['机构类型','机构数量','数量占比%'])
+    totalnum=0
     for t in typelist:
         df_sub=amac_df[amac_df['机构类型']==t]
         n=len(list(set(list(df_sub['机构（会员）名称']))))
-        pct=round(n/num*100,2)
+        if n==0: continue
+        totalnum=totalnum+n
         
-        s=pd.Series({'机构类型':t,'数量':n,'占比%':pct})
+        s=pd.Series({'机构类型':t,'机构数量':n})
         try:
             amac_sum_df=amac_sum_df.append(s,ignore_index=True)
         except:
             amac_sum_df=amac_sum_df._append(s,ignore_index=True)        
-        """
-        tlen=hzlen(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)),"{:,}".format(n),"\b,",round(n/num*100,2),'\b%')
-        #print('{t:<{len}}\t'.format(t=t,len=maxlen-len(t.encode('GBK'))+len(t)),str(n).rjust(6,' '),"\t",(str(round(n/num*100,2))+'%').rjust(6,' '))
     
-    amac_sum_df.sort_values(by=['数量'],ascending=False,inplace=True)
+    amac_sum_df['数量占比%']=amac_sum_df['机构数量'].apply(lambda x: round(x/totalnum*100,2))
+    
+    amac_sum_df.sort_values(by=['机构数量'],ascending=False,inplace=True)
     amac_sum_df.reset_index(drop=True,inplace=True)        
-    amac_sum_df.index=amac_sum_df.index + 1   
-    """
-    from IPython.display import display
-    display(amac_sum_df.head(10))
-    """
-    """
-    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))
-    except:
-        #解决汉字编码gbk出错问题
-        print_df=amac_sum_df.head(10).to_markdown(index=True,tablefmt='plain',colalign=alignlist)
-        print_df2=print_df.encode("utf-8",errors="strict")
-        print(print_df2)
+    amac_sum_df.index=amac_sum_df.index + 1  
+    
+    collist=list(amac_sum_df)
+    amac_sum_df['序号']=amac_sum_df.index
+    amac_sum_df=amac_sum_df[['序号']+collist]
+    
+    df10=amac_sum_df.head(rank)
+
+    footnote1="共有"+str(len(typelist))+'个类型，'
+    footnote2=str(totalnum)+'家机构；'
+    footnote3="表中类型数量占比"+str(round(df10['机构数量'].sum()/totalnum*100,2))+'%\n'
     
-    import datetime; today = datetime.date.today()
-    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)
+    footnote9="数据来源：中国证券投资基金业协会，"+str(todaydt)
+    footnote=footnote1+footnote2+footnote3+footnote9
     
     df_display_CSS(df10,titletxt=titletxt,footnote=footnote,facecolor='papayawhip',decimals=2, \
-                       first_col_align='left',second_col_align='right', \
+                       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')
     
-    """    
-    print(texttranslate("\n===== 中国基金投资机构会员代表概况 ====="))
-    print(texttranslate("会员代表人数："),end='')
-    num=len(list(set(list(amac_df["会员代表"]))))
-    print("{:,}".format(num))        
-        
-    print(texttranslate("其中工作在："))
-    amac_mbr_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]
-        n=len(list(set(list(df_sub['会员代表']))))
-        pct=round(n/num*100,2)
-        
-        s=pd.Series({'机构类型':t,'数量':n,'占比%':pct})
-        try:
-            amac_mbr_df=amac_sum_df.append(s,ignore_index=True)
-        except:
-            amac_mbr_df=amac_mbr_df._append(s,ignore_index=True)        
-
-    amac_mbr_df.sort_values(by=['数量'],ascending=False,inplace=True)
-    amac_mbr_df.reset_index(drop=True,inplace=True)        
-    amac_mbr_df.index=amac_mbr_df.index + 1  
-
-    pandas2prettytable(amac_mbr_df.head(10),titletxt='',firstColSpecial=True,leftColAlign='l',otherColAlign='c',tabborder=False)
-    print(footnote)        
-    """
-    
     return amac_df
 
 
@@ -1789,7 +1724,7 @@ def pef_product_china(rank=20,facecolor='papayawhip',DEBUG=False):
     dfprint=dfprint[['序号']+collist]
     
     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'
+    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, \

{siat-3.1.1.dist-info → siat-3.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: siat
-Version: 3.1.1
+Version: 3.1.2
 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-3.1.1.dist-info → siat-3.1.2.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=e-Ngpm34Kby8CFkso3M6KA4MWOPSi-M9FxS8Nv7Yr5M,90910
+siat/fund_china.py,sha256=RK2A111np2U8Jfi9S7Yt_yYa_iuxEy0mhTg24i3O4VU,87982
 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
@@ -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-3.1.1.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,,
+siat-3.1.2.dist-info/METADATA,sha256=22Vwc49Bl5YYuI9AR9Mgb8nqq7L8FwIvnFut8X854z8,1447
+siat-3.1.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+siat-3.1.2.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
+siat-3.1.2.dist-info/RECORD,,