siat 3.7.8__py3-none-any.whl → 3.7.10__py3-none-any.whl

siat/event_study.py

@@ -118,17 +118,20 @@ def event_study(ticker,event_date, \
     功能：展示事件研究法的累计异常收益率CAR。
     参数：
     ticker：证券代码，可为股票、债券、基金、指数、国债收益率等。可为单个或多个。
-    event_date：事件发生日（注意时区的影响），以此日期为基期0，该日期可能在周末或假日。
+    event_date：事件发生日（注意时区的影响），以此日期为基期0，注意该日期可能在周末或假日。
         注意：允许标注多个事件日，但仅以第一个事件日计算相关日期。
     start/end：展示事件影响的起止日期，至少需要将事件日、事件窗口和事件后窗口包括在内，主要用于绘图。
         注意：如果不绘制AR仅绘制CAR，事件窗口前CAR均为空，start日期在绘图中将不起作用。
-    event_window：事件窗口的起止日期，为相对事件日的相对日期，默认[0,0]，即事件当日一天。
-        注意：事件窗口不一定包括事件日（适用于事件日在非交易日的情形，例如周末或假日）
+    event_window：事件窗口的起止日期，为相对事件日的相对日期
+        默认[0,0]，即事件当日一天。注意窗口期不宜过长，因为过长的期间中可能混杂其他事件的影响。
+        注意：事件窗口不一定包括事件日（适用于事件日在非交易日的情形，例如周末或假日，或者在当日闭市后发生）
         如果事件日为非交易日，事件窗口需要后移至事件日后的第一个交易日。
         如果怀疑市场提前对事件发生反应，可以考虑前移事件窗口的开始日期。
-    post_event_days：用于分析事件窗口后的漂移效应，取事件窗口后多少天。默认不分析，取0天。
-    method：估计事件窗口以及事件后窗口收益率预期值的方法，默认为CAPM（主要用于ticker为股票等）
-        如果ticker为股票等，也可以直接使用指数的收益率为其预期收益率，此时method为Market或Index。
+    post_event_days：用于分析事件窗口后的漂移效应，取事件窗口后多少天。
+        默认不分析，取0天。可以指定天数，注意是否跨过非交易日情形，过长的窗口期也可能混杂其他事件的影响。
+    method：估计事件窗口以及事件后窗口收益率预期值的方法
+        默认为CAPM（主要用于ticker为股票等），即通常所说的市场模型。
+        如果ticker为股票等，也可直接使用指数收益率为其预期收益率，此时method为Market或Index，即常说的市场调整模型。
         如果ticker为指数，无法再借助指数，method只能使用Random Walk，即使用前一个收益率为预期收益率。
         注意：不管多个ticker时里面的不同证券类型，仅按第一个ticker的类型判断，并使用同一种证券类型。
     early_response_days：默认为-2，即提前2天市场就开始有反应。
@@ -138,12 +141,15 @@ def event_study(ticker,event_date, \
         默认在事件窗口开始日期+提前反应天数前的365个自然日（约250个交易日）。
     market_index：当method为CAPM时，用于计算市场收益率。默认中国市场采用000300.SS。
         注意：需要根据不同市场采取不同的市场指数，例如香港市场为恒生指数，美国市场为标普500指数等。
-    RF：年化无风险收益率，默认使用市场模型"market index"，无需指定；可直接指定具体数值；
-        也可指定特定指标，例如一年期中国国债收益率"1YCNY.B"或一年期美债收益率"1YUSY.B"等。
+    RF：年化无风险收益率
+        默认使用市场模型"market index"自动计算，无需指定。
+        可直接指定具体数值。
+        也可指定特定指标替代，例如一年期中国国债收益率"1YCNY.B"或一年期美债收益率"1YUSY.B"等。
     show_RF：在使用市场模型或指定指标时是否显示计算出的RF均值，默认为False。
     ticker_type：显式指明ticker的证券类型，当siat误判其类型（中国内地股票/债券/基金）时使用，默认'auto'。
     facecolor：显式指定绘图背景颜色，默认"whitesmoke"。
-    show_AR：是否绘图时绘制异常收益率AR，默认'auto'（单个ticker时绘制，多个时不绘制）。
+    show_AR：是否绘图时绘制异常收益率AR
+        默认'auto'（单个ticker时绘制，多个时不绘制）。
         也可指定True/False强行绘制/不绘制。
     """
     
@@ -499,7 +505,8 @@ def event_study(ticker,event_date, \
     
     #显著性检验：异于零的t检验，事件窗口
     df_event_window=df0[(df0.index >=event_window_start) & (df0.index <=event_window_end)]
-    footnote5="事件窗口CAR(终值，p值)："
+    #footnote5="事件窗口CAR(终值，p值)："
+    footnote5="事件窗口CAR(均值，中位数，p值)："
     for c in list(df_event_window):
         if 'CAR' in c.upper():
             c_name=c[:-4]
@@ -507,11 +514,24 @@ def event_study(ticker,event_date, \
             event_window_endpd=pd.to_datetime(event_window_end)
             #car_value=df_event_window[df_event_window.index == event_window_endpd][c].values[0]
             car_value=df_event_window[c][-1]
+            car_mean=df_event_window[c].mean()
+            car_median=df_event_window[c].median()            
+            
             if car_value > 0:
                 car_value_str=str(round(car_value,4))[:6]
             else:
                 car_value_str=str(round(car_value,4))[:7]
             
+            if car_mean > 0:
+                car_mean_str=str(round(car_mean,4))[:6]
+            else:
+                car_mean_str=str(round(car_mean,4))[:7]
+            
+            if car_median > 0:
+                car_median_str=str(round(car_median,4))[:6]
+            else:
+                car_median_str=str(round(car_median,4))[:7]
+            
             if len(df_event_window[c])==1:
                 if  abs(df_event_window[c].values[0]) > 0.01:
                     p_value=0.0
@@ -524,18 +544,19 @@ def event_study(ticker,event_date, \
             else:
                 p_value_str=str(round(p_value,4))[:7]
             #footnote5=footnote5+c_name+p_value_str+"，"
-            footnote5=footnote5+"{0}({1}, {2}), ".format(c_name,car_value_str,p_value_str)
+            #footnote5=footnote5+"{0}({1}, {2}), ".format(c_name,car_value_str,p_value_str)
+            footnote5=footnote5+"{0}({1}, {2}, {3}), ".format(c_name,car_mean_str,car_median_str,p_value_str)
     footnote5=footnote5.strip(", ")
 
     #显著性检验：异于零的t检验，事件后窗口
     df_post_event_window=df0[(df0.index >event_window_end) & (df0.index <=post_event_end)]
     if len(df_post_event_window) == 0:
         footnote6=''
-
     elif len(df_post_event_window) == 0:
         footnote6=''
     else:
-        footnote6="事件后窗口CAR(终值，p值)："
+        #footnote6="事件后窗口CAR(终值，p值)："
+        footnote6="事件后窗口CAR(均值，中位数，p值)："
         for c in list(df_post_event_window):
             if 'CAR' in c.upper():
                 c_name=c[:-4]
@@ -544,11 +565,24 @@ def event_study(ticker,event_date, \
                     print("  DEBUG: c={0},post_event_end={1},df_post_event_window={2}".format(c,post_event_end,df_post_event_window))
                 #car_value=df_post_event_window[df_post_event_window.index == post_event_endpd][c].values[0]
                 car_value=df_post_event_window[c][-1]
+                car_mean=df_post_event_window[c].mean()
+                car_median=df_post_event_window[c].median()
+                
                 if car_value > 0:
                     car_value_str=str(round(car_value,4))[:6]
                 else:
                     car_value_str=str(round(car_value,4))[:7]
                 
+                if car_mean > 0:
+                    car_mean_str=str(round(car_mean,4))[:6]
+                else:
+                    car_mean_str=str(round(car_mean,4))[:7]
+                
+                if car_median > 0:
+                    car_median_str=str(round(car_median,4))[:6]
+                else:
+                    car_median_str=str(round(car_median,4))[:7]
+                
                 if len(df_post_event_window[c])==1:
                     if  abs(df_post_event_window[c].values[0]) > 0.01:
                         p_value=0.0
@@ -562,7 +596,7 @@ def event_study(ticker,event_date, \
                     p_value_str=str(round(p_value,4))[:7]
                     
                 #footnote6=footnote6+c[:-4]+str(p_value)[:6]+"，"
-                footnote6=footnote6+"{0}({1}, {2}), ".format(c_name,car_value_str,p_value_str)
+                footnote6=footnote6+"{0}({1}, {2}, {3}), ".format(c_name,car_mean_str,car_median_str,p_value_str)
         footnote6=footnote6.strip(", ")
     
     footnote7="数据来源：Sina/EM/Yahoo/Stooq/SWHY，"+stoday

siat/fin_stmt2_yahoo.py

@@ -19,6 +19,8 @@ SIAT：Security Investment Analysis Tool
 import warnings; warnings.filterwarnings('ignore')
 
 from siat.common import *
+from siat.translate import *
+
 import pandas as pd
 import numpy as np
 #==============================================================================
@@ -36,11 +38,11 @@ if __name__=='__main__':
     symbol='601398.SS'
     symbol='601328.SS'
     
-    max_count=3
-    max_sleep=30
-    
     report_type="balance sheet"
-    printout=True
+    report_period="all"
+    max_count=3; max_sleep=30
+    fix_entry=False; printout=False
+    auto_language=True
     
     bsdf_raw=get_1statement_yahoo2(symbol,report_type="balance sheet",fix_entry=False)
     bsdf_fix=get_1statement_yahoo2(symbol,report_type="balance sheet",fix_entry=True)
@@ -53,23 +55,27 @@ if __name__=='__main__':
 
 
 def get_1statement_yahoo2(symbol,report_type="balance sheet", \
-                          report_period="all", \
+                          report_period="annual", \
                           max_count=3,max_sleep=30, \
-                          fix_entry=True,printout=False):
+                          fix_entry=False,printout=False, \
+                          auto_language=False,language_engine='baidu', \
+                          entry_split=True,split_improve=True):
     """
     功能：获取雅虎财经上一只股票所有的年度和季度资产负债表，采用contains匹配法
     
     参数：
     symbol：股票代码，五位港股需要转换为四位
     report_type：需要抓取的财报类型，默认资产负债表"balance sheet"
-    report_period：财报期间，默认年报+季报all，可选单纯年报(annual)或单纯季报(quarterly)
+    report_period：财报期间，默认年报，可选年报+季报(all)或单纯季报(quarterly)
     max_count：抓取失败时的总尝试次数，默认3
     max_sleep=30：抓取失败时再次尝试间隔的随机秒数最大值
-    fix_entry：是否对重点科目进行检查和填充，默认是True
-    printout：是否打印赚取到的财报，默认否False
+    fix_entry：是否对重点科目进行检查和填充，默认是False
+    printout：是否打印抓取到的财报，默认否False
+    auto_language：是否自动进行翻译，默认否False，自动翻译True
     
     返回值：成功时返回df，失败时返回None
     """
+    
     report_type=report_type.lower()
     if 'balance' in report_type:
         report_type="balance sheet"
@@ -92,7 +98,7 @@ def get_1statement_yahoo2(symbol,report_type="balance sheet", \
     try:
         stock = Ticker(symbol)    
     except:
-        print("  #Warning(get_1statement_yahoo2): Yahoo Finance currently unaccessable")
+        print("  #Warning(get_1statement_yahoo2): currently unaccessable to Yahoo")
         return None
     
     if contains_any(report_period,['all','annual']):
@@ -102,6 +108,8 @@ def get_1statement_yahoo2(symbol,report_type="balance sheet", \
                 stmta=stock.balance_sheet()  # Defaults to Annual
             elif report_type=="income statement":
                 stmta=stock.income_statement()
+                #去掉TTM，数据不全
+                stmta=stmta[stmta['periodType'] != 'TTM']
             else:
                 stmta=stock.cash_flow()
                 
@@ -130,6 +138,8 @@ def get_1statement_yahoo2(symbol,report_type="balance sheet", \
                 stmtq=stock.balance_sheet(frequency="q")  # Defaults to Annual
             elif report_type=="income statement":
                 stmtq=stock.income_statement(frequency="q")
+                #去掉TTM，数据不全
+                stmtq=stmtq[stmtq['periodType'] != 'TTM']
             else:
                 stmtq=stock.cash_flow(frequency="q")
             
@@ -152,7 +162,7 @@ def get_1statement_yahoo2(symbol,report_type="balance sheet", \
         print("  #Error(get_1statement_yahoo2): retrieved no periodic reports for",symbol)
         return None    
 
-    #合并后排序+去重
+    #合并后排序+去重：季报中可能还含有年报
     stmt.sort_values(by=['asOfDate','periodType'],inplace=True)
     #去掉重复记录: 保留年报数据项多，去掉数据项少的季报
     stmt.drop_duplicates(subset=['asOfDate'],keep='first',inplace=True)
@@ -185,7 +195,9 @@ def get_1statement_yahoo2(symbol,report_type="balance sheet", \
     
     #是否打印供检查
     if printout:
-        print_stmt_yahoo2(stmt,title_prefix=report_type.title())
+        print_stmt_yahoo2(stmt,title_prefix=report_type.title(), \
+                          auto_language=auto_language,language_engine=language_engine, \
+                          entry_split=entry_split,split_improve=split_improve)
     
     return stmt    
     
@@ -454,13 +466,27 @@ def check_fill_cfs_yahoo(stmt):
 if __name__=='__main__':
     from yahooquery import Ticker
     stock = Ticker("AAPL")
-    stmt=stock.cash_flow()
+    stmt=stock.income_statement()
     
+    stmt=get_financial_statements2_yahoo('JD',printout=False)
+    
+    title_prefix="Balance Sheet"
     title_prefix="Cash Flow Statement"
+    title_prefix="Integrated Financial Statements"
+    
+    auto_language=True
+    entry_split=True
+    split_improve=True
+    language_engine=['baidu','sogou','bing','google']
+    
+    stmt=get_financial_statements2_yahoo('JD',printout=False)
     
     print_stmt_yahoo2(stmt,title_prefix)
     
-def print_stmt_yahoo2(stmt,title_prefix):
+def print_stmt_yahoo2(stmt,title_prefix, \
+                      auto_language=True, \
+                     #language_engine=['google','bing','sogou'], \
+                      entry_split=True,split_improve=True):
     """
     
     功能：打印雅虎抓取的财报
@@ -487,6 +513,7 @@ def print_stmt_yahoo2(stmt,title_prefix):
     for c in cols1:
         stmtprt1[c]=stmtprt1[c].apply(lambda x: round(x/million,2))
     
+    #科目分词处理与翻译
     stmtprt2=stmtprt1.T
     cols=list(stmtprt2)
     cols.sort(reverse=True)
@@ -494,14 +521,89 @@ def print_stmt_yahoo2(stmt,title_prefix):
     stmtprt2['Item']=stmtprt2.index
     stmtprt2=stmtprt2[['Item']+cols]
     
-    titletxt=f"{symbol}: {title_prefix}, in {currencyCode} millions"
-    footnote="Note: 12M indicates annual report, 3M quaterly reports"
-    df_display_CSS(stmtprt2,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='15px',heading_font_size='11px', \
-                   data_font_size='11px',footnote_font_size='13px')
+    lang=check_language()
+    
+    #科目分词，语言处理：英文
+    title_prefix=title_prefix.title()
+    titletxt=f"{ticker_name(symbol)}: {title_prefix}, in {currencyCode} millions"
+    
+    footnote1="Note: 12M = annual report, 3M = quaterly reports"
+    import datetime as dt; todaydt=dt.date.today()
+    footnote2=", data source: Yahoo, "+str(todaydt)
+    footnote=footnote1 + footnote2
+    
+    if (auto_language and lang=='English') or entry_split:
+        item_dict=dict(stmtprt2['Item'])
+        item_list=list(stmtprt2['Item'])
+        for i in item_list:
+            i2=words_split_yahoo(i,split_improve=split_improve)
+            item_dict[i]=i2
+        stmtprt2['Item']=stmtprt2['Item'].apply(lambda x: item_dict[x])
+        
+    
+    #语言处理：中文
+    if 'balance' in title_prefix.lower():
+        title_prefix_cn="资产负债表"
+    elif 'income' in title_prefix.lower():
+        title_prefix_cn="利润表" 
+    elif 'cash' in title_prefix.lower():
+        title_prefix_cn="现金流量表"
+    else:
+        title_prefix_cn="三大报表综合"
+    title_cn=f"{ticker_name(symbol)}: {title_prefix_cn}, 单位：百万{currencyCode}"
+    
+    footnote1_cn="注：12M表示年报，3M表示季报"
+    footnote2_cn="，数据来源：雅虎，"+str(todaydt)
+    footnote_cn=footnote1_cn + footnote2_cn
+    
+    if auto_language and lang=='Chinese':
+        print(f"  Translating into {lang} using AI, just for reference ...")
+        
+        item_dict=dict(stmtprt2['Item'])
+        item_list=list(stmtprt2['Item'])
+        for i in item_list:
+            print_progress_percent2(i,item_list,steps=10,leading_blanks=4)
+            
+            #i2=lang_auto2(i,language_engine=language_engine)
+            i2=lang_auto2(i)
+            #i2=lang_auto(i)
+            item_dict[i]=i2
+        
+        stmtprt2['Item']=stmtprt2['Item'].apply(lambda x: x+'('+item_dict[x]+')')
+        """
+        if 'bilingual' in str(auto_language).lower():
+            stmtprt2['Item']=stmtprt2['Item'].apply(lambda x: x+'('+item_dict[x]+')')
+        else:
+            stmtprt2['Item']=stmtprt2['Item'].apply(lambda x: item_dict[x])
+        """
+        
+    #语言合成
+    titletxt=text_lang(title_cn,titletxt)  
+    footnote=text_lang(footnote_cn,footnote)
+    
+    #删除全为零或空值的行：未做到！
+    stmtprt3=stmtprt2.copy()
+    cols3=list(stmtprt3)
+
+    stmtprt3.set_index('Item',inplace=True)
+    stmtprt3.replace(0,np.nan,inplace=True)
+    stmtprt3.dropna(how='all',axis=1,inplace=True)
+    stmtprt3['Item']=stmtprt3.index
+    stmtprt3=stmtprt3[cols3]
+    
+    #检测Item是否存在重复值，若存在则df_display_CSS会失败
+    index1=stmtprt3[stmtprt3[["Item"]].duplicated(keep="last")].index
+    index2=stmtprt3[stmtprt3[["Item"]].duplicated(keep="first")].index
+    if not len(index1)==0 and not len(index2)==0:
+        cross_index=stmtprt3.loc[index1 | index2,:]
+        print("  Unable to display becos of duplicate items [{list(cross_index['Item'])}]")
+    else:
+        df_display_CSS(stmtprt3,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='15px',heading_font_size='10px', \
+                       data_font_size='10px',footnote_font_size='13px')
 
     return
 
@@ -562,7 +664,7 @@ if __name__=='__main__':
     ticker='AAPL' 
     ticker='00700.HK' 
     
-    report_period="all"
+    report_period="annual"
     max_count=3; max_sleep=30
     pre_fix_entry=False; post_fix_entry=True
     pre_printout=False; printout=True
@@ -570,13 +672,34 @@ if __name__=='__main__':
     fsdf=get_financial_statements2_yahoo(ticker)
 
 def get_financial_statements2_yahoo(ticker, \
-                                    report_period="all", \
+                                    report_period="annual", \
                                     max_count=3,max_sleep=30, \
                                     pre_fix_entry=False,post_fix_entry=True, \
+                                    auto_language=False, \
+                                   #language_engine=['baidu','sogou','bing','google'], \
+                                    entry_split=True,split_improve=False, \
                                     pre_printout=False,printout=False):
     """
+    
     功能：获取雅虎财经上一只股票所有的年度和季度财务报表
+    参数：
+    ticker：一只股票的代码
+    report_period：报告期间，默认年报"annual"，可选季报"quarterly"或所有"all"
+    max_count：爬虫失败时的最大尝试次数，默认3
+    max_sleep：每次抓取数据的时间间隔，规避反爬虫，默认30秒
+    pre_fix_entry：抓取资产负债表、利润表、现金流量表时是否单独修复科目数据，默认否False
+    post_fix_entry：抓取资产负债表、利润表、现金流量表后是否统一修复科目数据，默认是True
+    auto_language：是否自动翻译科目语言，默认否False
+    language_engine：语言翻译引擎，默认'baidu'，可选必应"bing"、谷歌"google"等
+    entry_split：抓取数据后是否分拆科目名称单词，默认否False
+    split_improve：抓取数据后分拆科目单词时是否调整，默认否False
+    pre_printout：抓取资产负债表、利润表和现金流量表时是否单独显示，默认否False
+    printout：抓取资产负债表、利润表和现金流量表后是否统一显示，默认否False
     """
+    # 测试雅虎连通性
+    if not test_yahoo_access():
+        print("  Sorry, data source yahoo is inaccessible")
+        return None
     
     # 变换港股代码5位-->4位
     result,prefix,suffix=split_prefix_suffix(ticker)
@@ -591,6 +714,9 @@ def get_financial_statements2_yahoo(ticker, \
                               report_period=report_period, \
                               max_count=max_count,max_sleep=max_sleep, \
                               fix_entry=pre_fix_entry, \
+                              auto_language=False, \
+                             #language_engine=language_engine, \
+                              entry_split=entry_split,split_improve=split_improve, \
                               printout=pre_printout)
     
     
@@ -599,6 +725,9 @@ def get_financial_statements2_yahoo(ticker, \
                               report_period=report_period, \
                               max_count=max_count,max_sleep=max_sleep, \
                               fix_entry=pre_fix_entry, \
+                              auto_language=False, \
+                             #language_engine=language_engine, \
+                              entry_split=entry_split,split_improve=split_improve, \
                               printout=pre_printout)
     
     
@@ -607,6 +736,9 @@ def get_financial_statements2_yahoo(ticker, \
                               report_period=report_period, \
                               max_count=max_count,max_sleep=max_sleep, \
                               fix_entry=pre_fix_entry, \
+                              auto_language=False, \
+                             #language_engine=language_engine, \
+                              entry_split=entry_split,split_improve=split_improve, \
                               printout=pre_printout)
     
     #=====三表合并
@@ -618,19 +750,30 @@ def get_financial_statements2_yahoo(ticker, \
     df=pd.merge(df_bs_is,df_cfs,on=head_cols)
     df['ticker']=ticker
     
+    #合并后删除重复列
+    df.rename(columns={'NetIncome_x':'NetIncome'},inplace=True)
+    try:
+        del df['NetIncome_y']
+    except:
+        pass
+    
     #合成后填充缺失项
     if post_fix_entry:
         df1=check_fill_fs_yahoo(df)
     else:
         df1=df
         
-    print(f"  Successfully retrieved financial statements of {ticker}")    
+    #print(f"  Successfully retrieved 3 financial statements of {ticker}")    
     
     if printout:
         df2=df1.copy()
-        df2.replace(0,np.nan,inplace=True)
         title_prefix="Comprehensive Financial Statement"
-        print_stmt_yahoo2(df2,title_prefix)
+        
+        print_stmt_yahoo2(df2,title_prefix="Integrated Financial Statements", \
+                          auto_language=auto_language, \
+                         #language_engine=language_engine, \
+                          entry_split=entry_split,split_improve=split_improve)
+
     
     return df1    
     
@@ -668,16 +811,16 @@ def check_fill_fs_yahoo(stmt):
 
 """
 最终获得的表结构：
-['asOfDate',
- 'periodType',
+['asOfDate（截止日期）',
+ 'periodType（期间类型）',
  
  'AccountsPayable(应付账款)',
  'AccountsReceivable(应收账款)',
  'AccumulatedDepreciation（累计折旧）',
- 'AdditionalPaidInCapital（资本公积，资本溢价，附加资本；paid-in capital：实收资本；缴入资本）',
+ 'AdditionalPaidInCapital（资本公积，资本溢价；paid-in capital：实收资本；缴入资本）',
  'AllowanceForDoubtfulAccountsReceivable（备抵应收呆帐）',
  'AvailableForSaleSecurities（可供出售金融资产；trading securities: 交易性金融资产）',
- 'BuildingsAndImprovements（建筑物改良）',
+ 'BuildingsAndImprovements（建筑物及其改良）',
  'CapitalStock（股本）',
  'CashAndCashEquivalents（现金及现金等价物）',
  'CashCashEquivalentsAndShortTermInvestments（现金、现金等价物及短期投资）',
@@ -696,16 +839,16 @@ def check_fill_fs_yahoo(stmt):
  'InventoriesAdjustmentsAllowances（存货调整备抵）',
  'Inventory（存货）',
  'InvestedCapital（投入资本）',
- 'InvestmentinFinancialAssets（金融资产投资？）',
- 'LandAndImprovements（土地改良）',
- 'MachineryFurnitureEquipment（机械家具设备？）',
- 'MinorityInterest（少数股东损益？）',
+ 'InvestmentinFinancialAssets（金融资产投资）',
+ 'LandAndImprovements（土地及其改良）',
+ 'MachineryFurnitureEquipment（机械家具设备）',
+ 'MinorityInterest（少数股东利益）',
  'NetPPE（固定资产净值）',
  'NetTangibleAssets（有形资产净值）',
  'NonCurrentDeferredAssets（非流动递延资产）',
- 'NonCurrentDeferredTaxesAssets（非流动递延税项资产？）',
- 'NonCurrentDeferredTaxesLiabilities（非流动递延税金负债？）',
- 'OrdinarySharesNumber（普通股数量？）',
+ 'NonCurrentDeferredTaxesAssets（非流动递延税项资产）',
+ 'NonCurrentDeferredTaxesLiabilities（非流动递延税金负债）',
+ 'OrdinarySharesNumber（普通股？）',
  'OtherCurrentAssets（其他流动资产）',
  'OtherCurrentLiabilities（其他流动负债）',
  'OtherEquityInterest（其他股权）',
@@ -715,8 +858,8 @@ def check_fill_fs_yahoo(stmt):
  'OtherProperties（？）',
  'OtherReceivables（其他应收款）',
  'Payables（应付款项）',
- 'PrepaidAssets（预付资产；预付费用）',
- 'Properties（财产？）',
+ 'PrepaidAssets（预付资产）',
+ 'Properties（财产？物业？）',
  'RawMaterials（原材料）',
  'RetainedEarnings（留存收益）',
  'ShareIssued（股票发行）',
@@ -724,33 +867,33 @@ def check_fill_fs_yahoo(stmt):
  'TangibleBookValue（有形资产账面价值）',
  'TotalAssets（总资产）',
  'TotalCapitalization（资本总额？）',
- 'TotalEquityGrossMinorityInterest（少数股东权益总额）',
- 'TotalLiabilitiesNetMinorityInterest（？）',
+ 'TotalEquityGrossMinorityInterest（权益与少数股东利益总额）',
+ 'TotalLiabilitiesNetMinorityInterest（扣除少数股东利益的总负债）',
  'TotalNonCurrentAssets（非流动资产总额）',
- 'TotalNonCurrentLiabilitiesNetMinorityInterest（？）',
+ 'TotalNonCurrentLiabilitiesNetMinorityInterest（扣除少数股东利益的非流动负债总额）',
  'TotalTaxPayable（应缴税款总额）',
- 'TradeandOtherPayablesNonCurrent（？）',
+ 'TradeandOtherPayablesNonCurrent（贸易与其他非流动应付款）',
  'WorkInProcess（在制品）',
  'WorkingCapital（营运资本）',
  'Amortization（摊销）',
  
- 'BasicAverageShares（未稀释的平均股数？）',
- 'BasicEPS（ 基本每股收益，指属于普通股股东的当期净利润，除以发行在外普通股的加权平均数，可按存在月数加权）',
- 'CostOfRevenue（主营业务成本，营收成本）',
+ 'BasicAverageShares（未稀释的平均股数）',
+ 'BasicEPS（基本每股收益，指属于普通股股东的当期净利润，除以发行在外普通股的加权平均数，可按存在月数加权）',
+ 'CostOfRevenue（收入成本，营收成本）',
  'DepreciationAndAmortizationInIncomeStatement（损益表中的折旧和摊销）',
  'DepreciationIncomeStatement（损益表中的折旧）',
- 'DilutedAverageShares（稀释后平均股数？）',
+ 'DilutedAverageShares（稀释后的平均股数）',
  'DilutedEPS（考虑了可转换债券和股票期权可能行权对于流通在外股数的影响）',
  'EBIT（息税前利润）',
  'EBITDA（未计利息、税项、折旧及摊销前的利润）',
  'GeneralAndAdministrativeExpense（一般管理费用）',
- 'GrossProfit（营业毛利）',
+ 'GrossProfit（毛利润）',
  'ImpairmentOfCapitalAssets（资本资产减值）',
  'InterestExpense（利息费用）',
  'InterestExpenseNonOperating（非经营性利息费用）',
  'InterestIncome（利息收益）',
  'InterestIncomeNonOperating（非经营性利息收入）',
- 'MinorityInterests（少数股东权益）',
+ 'MinorityInterests（少数股东利益）',
  'NetIncome（净利润）',
  'NetIncomeCommonStockholders（归属于普通股股东的净利润，用于计算EPS和PE）',
  'NetIncomeContinuousOperations（扣非后净利润）',
@@ -758,45 +901,45 @@ def check_fill_fs_yahoo(stmt):
  'NetIncomeFromContinuingOperationNetMinorityInterest（不归属少数股东的扣非后净利润？）',
  'NetIncomeIncludingNoncontrollingInterests（包括非控股权的净收入？）',
  'NetInterestIncome（净利息收入）',
- 'NetNonOperatingInterestIncomeExpense（？）',
- 'NormalizedEBITDA（调整后EBITDA？）',
- 'NormalizedIncome（调整后利润？）',
+ 'NetNonOperatingInterestIncomeExpense（非营业外利息收入费用净值）',
+ 'NormalizedEBITDA（调整后EBITDA）',
+ 'NormalizedIncome（调整后利润）',
  'OperatingExpense（营业费用）',
  'OperatingIncome（营业利润）',
  'OperatingRevenue（营业收入）',
- 'OtherNonOperatingIncomeExpenses（其他营业外收入支出？）',
+ 'OtherNonOperatingIncomeExpenses（其他营业外收入支出）',
  'OtherOperatingExpenses（其它营业费用）',
  'OtherSpecialCharges（其他特殊费用）',
  'OtherunderPreferredStockDividend（优先股股利下的其他项目）',
  'PretaxIncome（税前利润）',
- 'ReconciledCostOfRevenue（对账后的经营收入成本？）',
+ 'ReconciledCostOfRevenue（对账后的经营收入成本）',
  'ReconciledDepreciation（对账后的折旧）',
- 'RentAndLandingFees（租金及土地费用？）',
- 'RentExpenseSupplemental（补充租金费用？）',
+ 'RentAndLandingFees（租金及土地费用）',
+ 'RentExpenseSupplemental（补充租金费用）',
  'ResearchAndDevelopment（研发费用）',
  'SellingAndMarketingExpense（销售和市场营销费用）',
  'SellingGeneralAndAdministration（销售及一般管理费用）',
  'SpecialIncomeCharges（特殊收入的手续费）',
  'TaxEffectOfUnusualItems（非常项目的税收影响）',
- 'TaxProvision（税金？）',
- 'TaxRateForCalcs（计算用的税率）',
+ 'TaxProvision（税金计提）',
+ 'TaxRateForCalcs（Calcs计算用的税率）',
  'TotalExpenses（总费用）',
  'TotalOperatingIncomeAsReported（报告的总营业利润）',
  'TotalOtherFinanceCost（其他财务成本合计）',
  'TotalRevenue（总收入）',
  'TotalUnusualItems（非经常性项目总计）',
  'TotalUnusualItemsExcludingGoodwill（不包括商誉的非经常项目合计）',
- 'WriteOff（冲销？）',
+ 'WriteOff（冲销，核销）',
  
  'BeginningCashPosition（期初现金头寸）',
  'CapitalExpenditure（资本支出）',
  'CashDividendsPaid（现金股利支付）',
- 'ChangeInCashSupplementalAsReported（现金补充变更报告？）',
+ 'ChangeInCashSupplementalAsReported（报告的补充现金变更）',
  'ChangeInInventory（存货变化）',
  'ChangeInWorkingCapital（营运资本的变动额）',
  'DepreciationAndAmortization（折旧摊销）',
  'EndCashPosition（期末现金头寸）',
- 'FreeCashFlow（自有现金流）',
+ 'FreeCashFlow（自由现金流）',
  'InvestingCashFlow（投资现金流）',
  'NetOtherFinancingCharges（其他融资费用净额）',
  'NetOtherInvestingChanges（其他投资变动净额）',
@@ -807,12 +950,12 @@ def check_fill_fs_yahoo(stmt):
 
 #==============================================================================
 if __name__ == '__main__':
-    fsdf=get_financial_statements('601398.SS')
+    fsdf=get_financial_statements2_yahoo('AAPL')
     account_entry='TotalAssets'
     
     fsdf1=fs_entry_begin(fsdf,account_entry='TotalAssets',suffix='_begin')
 
-def fs_entry_begin(fsdf,account_entry='TotalAssets',suffix='_begin'):
+def fs_entry_begin_yahoo(fsdf,account_entry='TotalAssets',suffix='_begin'):
     """
     功能：以上年年报期末科目数值作为本期年报和季报的期初，仅适用于雅虎财报！
     """

siat/financials2.py

@@ -104,17 +104,38 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
                 category='profile',business_period='annual', \
                 scale1=10,scale2=10,dupont_sort='PM',
                 printout=True, \
-                entry_sort=False, \
+               #entry_sort=False, \
                 facecolor='papayawhip',font_size='16px'
                 ):
     """
-    功能：tickers为股票列表，fsdates为财报日期，可为单个日期或日期列表
+    
+    功能：分析境外上市公司财报信息
+    
+    参数：
+    tickers：股票列表，对比分析时需要多个股票，单列财报时仅取第一个股票
+    fsdates：财报日期，可为单个日期或日期列表，注意境外上市公司财报日期与中国大陆的不同
+    
+    analysis_type：分析类型，可为企业概况('profile')、资产负债表简表('balance sheet')、
+    利润表简表('income statement')、现金流量表简表('cash flow')、财报概况('financial summary')、
+    财务比率('financial indicator')、杜邦分析('dupont identity')
+    
+    category：企业概况分类，，仅当analysis_type='profile'时有效，
+    可为基本信息'profile'、高管概况('officers')、分红('dividend')、股票分拆('split')、市场表现('market')、
+    财务状况('financial')、一般风险('risk')、ESG风险('esg')
+    
+    business_period：业务期间类型，可为季报'quarterly'，年报'annual'、最近的6次报告'recent', 所有'all' 
+    scale1：仅用于杜邦分析，放大倍数（以便缩小与EM之间的数量级差异），用于Profit Margin，默认10
+    scale2：仅用于杜邦分析，放大倍数，用于Total Asset Turnover，默认10
+    dupont_sort：仅用于杜邦分析，用于排序指标，默认净利润率'PM'，还可为总资产周转率'TAT'或权益乘数'EM'
+    printout：是否显示数据表，默认是True
+    facecolor：背景颜色，默认小麦黄'papayawhip'
+    font_size：标题字体大小，默认'16px'
+    
     注意1：仅从雅虎财经获取数据
     注意2：不同经济体上市公司报表币种可能不同，金额项目仅进行同公司对比，不进行公司间对比
-    注意3：公司间仅对比财务比率
+    注意3：公司间仅对比财务比率和杜邦分析
     注意4：不同经济体上市公司年报季报日期不同，需要列示报表日期和类型(年报或季报)
-    
-    business_period：取季报'quarterly'，年报'annual'，最近的6次报告'recent', 所有'all'    
+       
     """
     import numpy as np
 
@@ -177,9 +198,11 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
             info=get_stock_profile(tickers,info_type=category)
             
         elif contains_any(category,['risk']):
+            #这里的是风险指标，数值越大风险越高，数值越小越好
             category='risk_general'
             info=get_stock_profile(tickers,info_type=category)
         elif contains_any(category,['esg']):
+            #这里的ESG为风险指标，数值越大风险越高，数值越小越好
             category='risk_esg'
             info=get_stock_profile(tickers,info_type=category)
         else:
@@ -200,7 +223,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
         # 分析资产负债表       
         fsdf=get_balance_sheet(symbol=tickers)
         if fsdf is None:
-            print("  #Warning(fs_analysis): financial info unaccessible for",tickers,"\b, which needs connection to Yahoo Finance")
+            print("  #Warning(fs_analysis): financial info unaccessible for",tickers,"\b, which needs connection to Yahoo")
             return None
         
         fsdf['reportDate']=fsdf['asOfDate'].apply(lambda x: x.strftime('%y-%m-%d'))
@@ -245,7 +268,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
             fsdf4.replace(0,'---',inplace=True)
             
             #titletxt="\n***** "+ticker_name(tickers)+": BALANCE SHEET"+' *****\n'
-            titletxt=ticker_name(tickers,'stock')+": BALANCE SHEET"
+            titletxt=ticker_name(tickers,'stock')+text_lang("：资产负债简表",": BALANCE SHEET")
             #print(titletxt)
             """
             tablefmt_list=["plain","simple","github","grid","simple_grid","rounded_grid", \
@@ -347,7 +370,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
             fsdf4.replace(0,'---',inplace=True)
             
             #titletxt="\n***** "+ticker_name(tickers)+": INCOME STATEMENTS"+' *****\n'
-            titletxt=ticker_name(tickers,'stock')+": INCOME STATEMENTS"
+            titletxt=ticker_name(tickers,'stock')+text_lang("：利润简表",": INCOME STATEMENTS")
             #print(titletxt)
             
             collist=list(fsdf4)
@@ -427,7 +450,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
             fsdf4.replace(0,'---',inplace=True)
             
             #titletxt="\n***** "+ticker_name(tickers)+": CASHFLOW STATEMENTS"+' *****\n'
-            titletxt=ticker_name(tickers,'stock')+": CASHFLOW STATEMENTS"
+            titletxt=ticker_name(tickers,'stock')+text_lang("：现金流量简表",": CASHFLOW STATEMENTS")
             #print(titletxt)
             
             collist=list(fsdf4)
@@ -536,7 +559,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
                 fsdf4.replace(0,'---',inplace=True)
                 
                 #titletxt="\n***** "+ticker_name(tickers)+": FINANCIAL STATEMENT SUMMARY"+' *****\n'
-                titletxt=ticker_name(tickers,'stock')+": FINANCIAL STATEMENT SUMMARY"
+                titletxt=ticker_name(tickers,'stock')+text_lang("：财报摘要",": FINANCIAL STATEMENT SUMMARY")
                 #print(titletxt)
                 
                 collist=list(fsdf4)
@@ -638,7 +661,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
                 fsdf4.replace(0,'---',inplace=True)
                 
                 #titletxt="\n***** PEER COMPARISON OF FINANCIAL STATEMENT SUMMARY *****\n"
-                titletxt="FINANCIAL STATEMENT SUMMARY: PEER COMPARISON"
+                titletxt=text_lang("财报摘要对比","FINANCIAL STATEMENT SUMMARY: COMPARISON")
                 #print(titletxt)
                 
                 collist=list(fsdf4)
@@ -746,7 +769,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
                 fsdf4.replace(0,'---',inplace=True)
                 
                 #titletxt="\n***** "+ticker_name(tickers)+": FINANCIAL INDICATORS"+' *****\n'
-                titletxt=ticker_name(tickers,'stock')+": FINANCIAL INDICATORS"
+                titletxt=ticker_name(tickers,'stock')+text_lang("：财务比率",": FINANCIAL INDICATORS")
                 #print(titletxt)
                 
                 collist=list(fsdf4)
@@ -849,7 +872,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
                 fsdf4.replace(0,'---',inplace=True)
                 
                 #titletxt="\n***** PEER COMPARISON OF FINANCIAL INDICATORS *****\n"
-                titletxt="FINANCIAL INDICATORS: PEER COMPARISON"
+                titletxt=text_lang("财务比率对比","FINANCIAL INDICATORS: COMPARISON")
                 #print(titletxt)
                 
                 collist=list(fsdf4)
@@ -963,21 +986,21 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
         plt.ylabel("Items (Amplified)")
             
         footnote1="[Bar amplifier] "+name1+'：x'+str(scale1)+'，'+name2+'：x'+str(scale2)
-        footnote2='Financial statement period: '+fin_period+'. Bar height does not indicate ROE value.'
+        footnote2='Statement period: '+fin_period+'. Bar height does not indicate ROE value.'
         footnote3="Data source: Yahoo Finance，"+todaydt
         footnote ='\n'+footnote1+'\n'+footnote2+'\n'+footnote3
         plt.xlabel(footnote,fontsize=10)
         
         plt.legend(loc='best',fontsize=10)
-        plt.title("Dupont Identity Analysis")
+        plt.title(text_lang("杜邦分析对比","Dupont Identity Analysis"))
         plt.xlim([min(tick_pos)-w,max(tick_pos)+w])
         
-        plt.gca().set_facecolor('whitesmoke')
+        plt.gca().set_facecolor(facecolor)
         plt.show()    
         
         if printout:
             #title_txt="\n***** Dupont Identity Fact Sheet *****\n"
-            titletxt="Dupont Identity Fact Sheet"
+            titletxt=text_lang("杜邦分析数据表","Dupont Identity Fact Sheet")
             #print(titletxt)
             
             # 保留四位小数
@@ -998,7 +1021,7 @@ def fs_analysis(tickers,fsdates=[],analysis_type='balance sheet', \
             footnote2="Data source: Yahoo Finance, "+str(todaydt)
             footnote='Note:\n'+footnote1+'\n'+footnote2
             #print('\n',footnote1,'\b.',footnote2)               
-            df_display_CSS(df,titletxt=titletxt,footnote=footnote,facecolor=facecolor, \
+            df_display_CSS(df,titletxt=titletxt,footnote=footnote,facecolor=facecolor,decimals=4, \
                            titile_font_size=titile_font_size,heading_font_size=heading_font_size, \
                                data_font_size=data_font_size)        
         return  df2      

siat/grafix.py

@@ -1448,6 +1448,25 @@ def plot_line2_twinx2(df01,ticker1,colname1,label1, \
     return
 
 #==============================================================================
+if __name__ =="__main__":
+    df0=security_trend(['PDD','JD'],annotate=True,graph=False)
+    
+    y_label=''; x_label='Footnote'
+    axhline_value=0; axhline_label=''
+    title_txt='Title'
+    data_label=False
+    resample_freq='H'; smooth=True
+    linewidth=1.5
+    loc='best'
+    annotate=True; annotate_value=True
+    plus_sign=False
+    attention_value=''; attention_value_area=''
+    attention_point=''; attention_point_area=''
+    mark_top=False; mark_bottom=False; mark_end=False
+    ticker_type='auto'
+    facecolor='whitesmoke'
+
+
 def draw_lines(df0,y_label,x_label,axhline_value,axhline_label,title_txt, \
                data_label=True,resample_freq='H',smooth=True,linewidth=1.5, \
                loc='best',annotate=False,annotate_value=False,plus_sign=False, \
@@ -1758,8 +1777,24 @@ def draw_lines(df0,y_label,x_label,axhline_value,axhline_label,title_txt, \
         
     # 若不绘制annotate，则绘制图例
     #if not annotate:
-    plt.legend(loc=loc,fontsize=legend_txt_size)
+    #检查是否存在可绘制的标签，若有则绘制
+    if DEBUG:
+        have_label=False
+        for line in plt.gca().lines:
+            print(f"  DEBUG: plt.gca().lines, line={line.get_label()}")
+            if line.get_label() != '':
+                have_label=True
     
+    #plt.legend没有图例标签时会提示信息No artists...
+    if not annotate or attention_value !='' or attention_point !='':
+        plt.legend(loc=loc,fontsize=legend_txt_size)
+        
+    """
+    if any([line.get_label() != '' for line in plt.gca().lines]):
+        tuli=plt.legend(loc=loc,fontsize=legend_txt_size)
+        if DEBUG:
+            print(f"  DEBUG: result of plt.legend is {tuli}")
+    """
     if plus_sign:
         # 尝试改变纵轴刻度格式：给正数添加正号+，以便突出显示增减幅度
         import matplotlib.ticker as ticker
@@ -2072,7 +2107,9 @@ def draw_lines2(df0,y_label,x_label,axhline_value,axhline_label,title_txt, \
         plt.gca().set_facecolor("whitesmoke") 
         
     #if not annotate:
-    plt.legend(loc=loc,fontsize=legend_txt_size)
+    #plt.legend没有图例标签时会提示信息No artists...
+    if not annotate or attention_value !='' or attention_point !='':
+        plt.legend(loc=loc,fontsize=legend_txt_size)
         
     #设置绘图风格：关闭网格虚线
     plt.rcParams['axes.grid']=False

siat/translate.py

@@ -4554,6 +4554,306 @@ if __name__=='__main__':
     industry_sw_name(icode)
 
 #==============================================================================
-         
+#实现简单中英文短语互译
+#==============================================================================
+if __name__ == '__main__':
+    chntext='市盈率'
+    engtext="PE ratio"
+    engtext="P/E ratio"
+    
+    zh2en(chntext)
+    
+    en2zh(engtext)
+    
+
+def zh2en(text):
+    '''英文转换成中文'''
+    
+    from translate import Translator
+    translator = Translator(from_lang="zh", to_lang="en")
+    translation = translator.translate(text)
+
+    return translation
+
+def en2zh(text):
+    '''中文转换成英文'''
+    
+    from translate import Translator
+    translator = Translator(from_lang="en", to_lang="zh")
+    translation = translator.translate(text)
+    
+    return translation
+
+if __name__ == '__main__':
+    chntext='市盈率'
+    engtext1="PE ratio"
+    engtext2="P/E ratio"
+
+    lang_auto(chntext)
+    lang_auto(engtext1)
+    lang_auto(engtext2)
+    
+    lang_auto(text)
+
+
+def lang_auto(text):
+    '''转换字符串text至当前语言环境，基于translate'''
+    
+    #注意：这个翻译模块只能每天提供有限单词翻译服务
+    from translate import Translator
+    
+    lang_env=check_language()
+    lang_text=detect_language(text)
+    
+    #字符串语言与当前环境语言相同，无需翻译，节省运行时间
+    if lang_env==lang_text:
+        return text
+    
+    provider_list=['mymemory']
+    
+    if lang_env=='Chinese':
+        #translator = Translator(from_lang="en", to_lang="zh")
+        #translator = Translator(to_lang="zh")
+        translator = Translator(to_lang="zh",provider="mymemory")
+    elif lang_env=='English':
+        translator = Translator(to_lang="en")
+    else:
+        return text
+    
+    translation = translator.translate(text)
+    
+    return translation
+
+if __name__ == '__main__':
+    text='市盈率'
+    text='贵州茅台'
+    text='五粮液'
+    text='Dividend Payout Ratio'
+    text='asOfDate'
+    text='Cash And Cash Equivalents'
+    text='AccountsReceivableNetSalesAllowance'
+    text='Accounts Receivable Net of Sales Allowance'
+    text='Accounts Payable'
+    
+    language_detect=True
+    language_engine=['google','baidu','bing']
+    
+    chntext='市盈率'
+    engtext1="PE ratio"
+    engtext2="P/E ratio"
+
+    lang_auto2(text)
+    lang_auto2(text,language_detect=True)
+    
+    lang_auto2(chntext)
+    lang_auto2(engtext1)
+    lang_auto2(engtext2)
+
+
+def lang_auto2(text,language_detect=True,language_engine=['alibaba','google','bing','sogou']):
+    '''转换字符串text至当前语言环境，基于translators，可指定翻译服务器，准确度更高'''
+    
+    import translators as ts
+    
+    lang_env=check_language()
+    
+    if language_detect:
+        lang_text=detect_language(text)
+        
+        #字符串语言与当前环境语言相同，无需翻译，节省运行时间
+        if lang_env==lang_text:
+            return text
+    
+    success=False
+    if lang_env=='Chinese':
+        #translator支持baidu/bing/google
+        if isinstance(language_engine,str):
+            language_engine=[language_engine]
+            
+        for le in language_engine:
+            try:
+                translation = ts.translate_text(text,from_language='en',to_language='zh', translator=le)
+                success=True
+                break
+            except:
+                continue
+    elif lang_env=='English':
+        for le in language_engine:
+            try:
+                translation = ts.translate_text(text,from_language='zh',to_language='en', translator=le)
+                success=True
+                break
+            except:
+                continue
+    else:
+        return text
+    
+    if not success:
+        translation = text
+        
+    return translation
+
+
+if __name__ == '__main__':
+    chntext='市盈率'
+    engtext1="PE ratio"
+
+    detect_language(chntext)
+    detect_language(engtext)
+ 
+def detect_language(text):
+    '''判断字符串text是中文还是英文'''
+    
+    import re
+    chinese_pattern = re.compile(r'[\u4e00-\u9fa5]')
+    english_pattern = re.compile(r'[a-zA-Z]')
+    
+    chinese_count = len(chinese_pattern.findall(text))
+    english_count = len(english_pattern.findall(text))
+    total_count = chinese_count + english_count
+    
+    if total_count == 0:
+        result='Unknown'
+        
+    if chinese_count > english_count:
+        result='Chinese'
+    elif english_count > chinese_count:
+        result='English'
+    else:
+        result='Both'    
+    
+    return result
+
+
+if __name__ == '__main__':
+    text='DividendPayoutRatio'
+    text='CashAndCashEquivalents'
+    text='asOfDate'
+    
+    text='GrossPPE'
+    
+    text='Cash And Cash Equivalents'
+
+    words_split_yahoo(text)
+ 
+def words_split_yahoo(text,split_improve=True):
+    '''将雅虎英文财报术语拆分为带空格的词组'''
+
+    
+    #替换基于大写字母无法分词的短语
+    text=text.replace("periodType","PeriodType")
+    text=text.replace("Tradeand","TradeAnd")
+    
+    words_list=[]
+    start=0
+    
+    for i in range(len(text)):
+        c=text[i]
+        
+        if (c>='A' and c<='Z') or c==' ':
+            words_list=words_list+[text[start:i].strip(' ')]
+            start=i
+    
+    #添加最后一个单词
+    words_list=words_list+[text[start:i+1]]
+    
+    special_words=['and','of','in','at','as','for','non','from']
+    words_list2=[]
+    for w in words_list:
+        if text.index(w) == 0:
+            words_list2=words_list2+[w.title()]
+        elif w.lower() in special_words:
+            words_list2=words_list2+[w.lower()]
+        else:
+            words_list2=words_list2+[w]
+    
+    text_new=''
+    for w in words_list2:
+        text_new=text_new+' '+w
+    
+    #若出现多个空格则替换为单个空格
+    import re
+    text_new=re.sub(r' +', ' ', text_new)
+    
+    #去掉首尾的空格
+    text_new=text_new.strip(' ')
+    
+        
+    #判断大写字母缩写合并
+    prev_c1=''; prev_c2=''
+    text_new2=''
+    for c in text_new:
+        if c>='A' and c<='Z':
+            if prev_c1==' ' and (prev_c2>='A' and prev_c2<='Z'):
+                text_new2=text_new2.strip(' ')+c
+            else:
+                text_new2=text_new2+c
+        else:
+            text_new2=text_new2+c
+            
+        prev_c2=prev_c1; prev_c1=c
+    
+    #弥补大写字母合并后继词的逻辑缺陷
+    for upl in ['PPE']:
+        text_new2=text_new2.replace(upl,upl+' ')
+        text_new2=re.sub(r' +', ' ', text_new2)
+        text_new2=text_new2.strip(' ')
+    
+    
+    #替换缩写/简写/容易翻译出错的词，强行规避翻译错误。
+    #注意：不影响未拆分科目名称，仅为翻译用途
+    if split_improve:
+        text_new3=text_new2.replace("PPE","Plant Property and Equipment")
+        
+        text_new3=text_new3.replace("Treasury Shares Number","Treasury Shares")
+        text_new3=text_new3.replace("Ordinary Shares Number","Ordinary Shares")
+        text_new3=text_new3.replace(" Gross "," and ")
+        text_new3=text_new3.replace("non Current","Non-current")
+        text_new3=text_new3.replace("Non Current","Non-current")
+        text_new3=text_new3.replace("Short Term","Short-term")
+        text_new3=text_new3.replace("Long Term","Long-term")
+        text_new3=text_new3.replace("Available for Sale","Available-for-sale")
+    
+        text_new3=text_new3.replace(" Com "," Common ")
+        text_new3=text_new3.replace(" Net "," Net of ")
+        text_new3=text_new3.replace("Net Income","Net Profit")
+        
+        text_new3=text_new3.replace("EBITDA","XXX")
+        text_new3=text_new3.replace("EBIT","Earnings before Interest and Tax")
+        text_new3=text_new3.replace("XXX","EBITDA")
+        
+        text_new3=text_new3.replace("Tax Provision","Tax Accrued")
+        text_new3=text_new3.replace("non Operating","Non-operating")
+        
+        text_new3=text_new3.replace("Operating Income","Operating Profit")
+        text_new3=text_new3.replace("Pretax Income","Pretax Profit")
+        
+        text_new3=text_new3.replace("Current Provisions","Current Reserve")
+        
+        text_new3=text_new3.replace("Duefrom ","Due from ")
+        text_new3=text_new3.replace("Dueto ","Due to ")
+        
+        text_new3=text_new3.replace("Investmentin ","Investment in ")
+        text_new3=text_new3.replace("Diluted NIAvailto ","Diluted Net Profit Avail to ")
+        text_new3=text_new3.replace(" Noncontrolling "," Non-controlling ")
+        text_new3=text_new3.replace("Other Gand A","Other General and Administrative Expense")
+        text_new3=text_new3.replace("Otherunder ","Other under ")
+        text_new3=text_new3.replace("Mergern Acquisition","Merger and Acquisition")
+        text_new3=text_new3.replace("Write Off","Write-off")
+        
+        text_new3=text_new3.replace("Cash Flow From ","Cash Flow from ")
+        text_new3=text_new3.replace("Cash From ","Cash Flow from ")
+        text_new3=text_new3.replace(" From "," from ")
+        text_new3=text_new3.replace("Provisionand","Provision and")
+        text_new3=text_new3.replace("Write-offof","Write-off of")
+        text_new3=text_new3.replace("non Cash","non-Cash")
+        text_new3=text_new3.replace("Changein","Change in")
+        
+    else:
+        text_new3=text_new2
+        
+    return text_new3
+
+#==============================================================================
 #==============================================================================
 #==============================================================================

siat/valuation.py

@@ -1259,7 +1259,7 @@ def print_valuation(df,indicator='PE',base='',facecolor='whitesmoke'):
     df4=df3[['证券名称',col_mean,'均值排名',col_latest_date,'排名@'+col_latest_date,col_mean_rel,col_latest_rel,'均值对比','对比@'+col_latest_date]]
     
     #titletxt="估值对比："+ectranslate(indicator)+"，降序排列"
-    titletxt="估值对比：{0}({1})，降序排列".format(ectranslate(indicator),indicator)
+    titletxt="证券估值对比：{0}({1})，降序排列".format(ectranslate(indicator),indicator)
     """
     print("\n",titletxt,'\n')
     alignlist=['left','right','center','right','center']+['right']*(len(list(df4))-5)

{siat-3.7.8.dist-info → siat-3.7.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: siat
-Version: 3.7.8
+Version: 3.7.10
 Summary: Securities Investment Analysis Tools (siat)
 Home-page: https://pypi.org/project/siat/
 Author: Prof. WANG Dehong, International Business School, Beijing Foreign Studies University
@@ -35,6 +35,8 @@ Requires-Dist: pendulum
 Requires-Dist: itables
 Requires-Dist: py-trans
 Requires-Dist: bottleneck
+Requires-Dist: translate
+Requires-Dist: translators
 
 
 # What is siat?

{siat-3.7.8.dist-info → siat-3.7.10.dist-info}/RECORD

@@ -32,17 +32,17 @@ siat/economy.py,sha256=ijMAVA5ydghbQDgNDDdz8fz9NPd2eq90RzpJSRGWz5c,78638
 siat/economy_test.py,sha256=6vjNlPz7W125pJb7simCddobSEp3jmLIMvVkLRZ7zW8,13339
 siat/esg.py,sha256=GMhaonIKtvOK83rhpQUH5aJt2OL3HQBSVfD__Yw-0oo,19040
 siat/esg_test.py,sha256=Z9m6GUt8O7oHZSEG9aDYpGdvvrv2AiRJdHTiU6jqmZ0,2944
-siat/event_study.py,sha256=Q_AdnJzxxL6udCjn5LP6rdhOngsDRWPu5udFkK1CJZw,32223
+siat/event_study.py,sha256=aDq-mrwHw3qw0fDJbAWovz1kppwE6BSeuwoMfWdSYQY,33892
 siat/exchange_bond_china.pickle,sha256=zDqdPrFacQ0nqjP_SuF6Yy87EgijIRsFvFroW7FAYYY,1265092
 siat/fama_french.py,sha256=aUTC-67t_CEPbLk4u79woW_zfZ7OCP6Fo4z5EdWCSkQ,48051
 siat/fama_french_test.py,sha256=M4O23lBKsJxhWHRluwCb3l7HSEn3OFTjzGMpehcevRg,4678
-siat/fin_stmt2_yahoo.py,sha256=q4oNv-Wc30Kyuq_lRB0ZMINd33pusxQ3H2BecoFATqo,34297
+siat/fin_stmt2_yahoo.py,sha256=LGmspk0nKyz4X87MtcovZXUfMQkAvrWINuxR4HQ8PI8,41178
 siat/financial_base.py,sha256=5u298_1OSlgLnDmhXxqvo4WgMM0JKSa_4jBYF-Ilx38,41097
 siat/financial_statements.py,sha256=xx0SMpFqAMKm6cj8uYeG2RpJE6G-RoJ3NWa33UyaVMk,25414
 siat/financial_statements_test.py,sha256=FLhx8JD-tVVWSBGux6AMz1jioXX4U4bp9DmgFHYXb_w,716
 siat/financials.py,sha256=6WOWYift3MpKkNBnvnBFASXy9nKKC6DzAr8rg2XyNtw,80646
 siat/financials2 - 副本.py,sha256=dKlNjIfKeoSy055fQ6E6TUj9HEoO5Ney9grD84J5kfk,14389
-siat/financials2.py,sha256=A6gjqbdNVgA0hloglhPlDR82mHjb3rSskD-s0T8LKg0,47289
+siat/financials2.py,sha256=Se99o3nDn6Tvbpa-oYAWiIAQrQmEDrur2GkSXNElJIc,49125
 siat/financials_china.py,sha256=Y9QHyJKDgVbkb5L1f65BAiNxLIDmasRUN9_ju4Yby_c,191925
 siat/financials_china2.py,sha256=NZzpS1eCaxEClOhh8dvfdn88NhIULqeb9E0GUDUiG4U,92892
 siat/financials_china2_test.py,sha256=Erz5k4LyOplBBvYls2MypuqHpVNJ3daiLdyeJezNPu0,2722
@@ -62,7 +62,7 @@ siat/future_china.py,sha256=F-HsIf2Op8Z22RzTjet1g8COzldgnMjFNSXsAkeGyWo,17595
 siat/future_china_test.py,sha256=BrSzmDVaOHki6rntOtosmRn-6dkfOBuLulJNqh7MOpc,1163
 siat/global_index_test.py,sha256=hnFp3wqqzzL-kAP8mgxDZ54Bd5Ijf6ENi5YJlGBgcXw,2402
 siat/google_authenticator.py,sha256=ZUbZR8OW0IAKDbcYtlqGqIpZdERpFor9NccFELxg9yI,1637
-siat/grafix.py,sha256=EYgRBCfUTgJ9B5rTCzhO9UoABM1amTPUVXkOeKWpgGg,108806
+siat/grafix.py,sha256=WH_-a-R-zyKhT4t4NM24gYZWKyvIexN9LfXVQf-1zxA,110166
 siat/grafix_test.py,sha256=kXvcpLgQNO7wd30g_bWljLj5UH7bIVI0_dUtXbfiKR0,3150
 siat/holding_risk.py,sha256=G3wpaewAKF9CwEqRpr4khyuDu9SU2EGyQUHdk7cmHOA,30693
 siat/holding_risk_test.py,sha256=FRlw_9wFG98BYcg_cSj95HX5WZ1TvkGaOUdXD7-V86s,474
@@ -133,17 +133,17 @@ siat/transaction_test.py,sha256=Z8g1LJCN4-mnUByXMUMoFmN0t105cbmsz2QmvSuIkbU,1858
 siat/translate-20230125.py,sha256=NPPSXhT38s5t9fzMvl_fvi4ckSB73ThLmZetVI-xGdU,117953
 siat/translate-20230206.py,sha256=-vtI125WyaJhmPotOpDAmclt_XnYVaWU9ByLWZ6FyYE,118133
 siat/translate-20230215.py,sha256=TJgtPE3n8IjljmZ4Pefy8dmHoNdFF-1zpML6BhA9FKE,121657
-siat/translate.py,sha256=aAWk9museEsdxDstXjEy_SXiEzvKD_6fDi0W4TrBiwI,241364
+siat/translate.py,sha256=TJKbh9vU-ifEN1V9DnyojJ00qcT_fioooTAa8wrml_s,250970
 siat/translate_20240606.py,sha256=63IyHWEU3Uz9mjwyuAX3fqY4nUMdwh0ICQAgmgPXP7Y,215121
 siat/translate_241003_keep.py,sha256=un7Fqe1v35MXsja5exZgjmLzrZtt66NARZIGlyFuGGU,218747
 siat/universal_test.py,sha256=CDAOffW1Rvs-TcNN5giWVvHMlch1w4dp-w5SIV9jXL0,3936
-siat/valuation.py,sha256=DF-THR8AOPFtbMG58g9coqrfnzeBIhX3PW7ZhU6WbEo,50821
+siat/valuation.py,sha256=XdfTivpr652hRnI6yaB9mpA0JlXFJphJsTqcw2_FnMM,50827
 siat/valuation_china.py,sha256=CVp1IwIsF3Om0J29RGkyxZLt4n9Ug-ua_RKhLwL9fUQ,69624
 siat/valuation_market_china_test.py,sha256=gbJ0ioauuo4koTPH6WKUkqcXiQPafnbhU5eKJ6lpdLA,1571
 siat/var_model_validation.py,sha256=R0caWnuZarrRg9939hxh3vJIIpIyPfvelYmzFNZtPbo,14910
 siat/yf_name.py,sha256=r0Q67cSMMlfebEkI9h9pdGlJCooEq7hw_3M5IUs4cSI,20081
-siat-3.7.8.dist-info/LICENSE,sha256=NTEMMROY9_4U1szoKC3N2BLHcDd_o5uTgqdVH8tbApw,1071
-siat-3.7.8.dist-info/METADATA,sha256=eDkDeMALXeeUIhn3YcgdI7vzLy2P4qCAR8ErzLuv5p4,8009
-siat-3.7.8.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-siat-3.7.8.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
-siat-3.7.8.dist-info/RECORD,,
+siat-3.7.10.dist-info/LICENSE,sha256=NTEMMROY9_4U1szoKC3N2BLHcDd_o5uTgqdVH8tbApw,1071
+siat-3.7.10.dist-info/METADATA,sha256=nY3QaZF7WEgmuQ6z6eucsLYyrHlhX-BiCYsY97jrMEQ,8064
+siat-3.7.10.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+siat-3.7.10.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
+siat-3.7.10.dist-info/RECORD,,