siat 2.14.2__py3-none-any.whl → 3.0.1__py3-none-any.whl

siat/common.py

@@ -16,11 +16,11 @@ SIAT：Security Investment Analysis Tool
 #==============================================================================
 #关闭所有警告
 import warnings; warnings.filterwarnings('ignore')
-
-#==============================================================================
-SUFFIX_LIST_CN=['SS','SZ','BJ','NQ']
 import pandas as pd
 #==============================================================================
+SUFFIX_LIST_CN=['SS','SZ','BJ','SW','SH']
+SUFFIX_LIST_HK=['HK']
+#==============================================================================
 #设置全局语言环境
 import pickle
 
@@ -239,19 +239,26 @@ def check_period(fromdate, todate):
     try:
         start=pd.to_datetime(fromdate)
     except:
-        print("*** #Error(check_period), invalid date:",fromdate)
+        print("    #Error(check_period), invalid date:",fromdate)
+        return None, None, None         
+    
+    #开始日期不能晚于今日
+    import datetime
+    todaydt = pd.to_datetime(datetime.date.today())
+    if start > todaydt:
+        print("    #Error(check_period), invalid start date:",fromdate)
         return None, None, None         
     
     #测试结束日期的合理性
     try:
         end=pd.to_datetime(todate)
     except:
-        print("  #Error(check_period): invalid date:",todate)
+        print("    #Error(check_period): invalid date:",todate)
         return None, None, None          
     
     #测试日期期间的合理性
     if start > end:
-        print("  #Error(check_period): invalid period: from",fromdate,"to",todate)
+        print("    #Error(check_period): invalid period: from",fromdate,"to",todate)
         return None, None, None     
 
     return True, start, end
@@ -417,6 +424,8 @@ def date_adjust2(basedate,adjust_year=0,adjust_month=0,adjust_day=0, \
 #==============================================================================
 if __name__ =="__main__":
     portfolio={'Market':('US','^GSPC'),'EDU':0.4,'TAL':0.3,'TEDU':0.2}
+    
+    portfolio={'Market':('China','000001.SS','股债基组合'),'600519.SS':50,'sh010504':150,'sh010504':300}
 
 def decompose_portfolio(portfolio):
     """
@@ -426,7 +435,7 @@ def decompose_portfolio(portfolio):
     输出：市场，市场指数，股票代码列表和份额列表
     """
     #从字典中提取信息
-    keylist=list(portfolio.keys())
+    keylist=list(portfolio.keys()) #注意：字典中相同的键会被合并为一个
     scope=portfolio[keylist[0]][0]
     mktidx=portfolio[keylist[0]][1]
     
@@ -1468,7 +1477,7 @@ if __name__=='__main__':
     _,_,tickerlist,sharelist=decompose_portfolio(portfolio)
     leading_blanks=2
 
-def print_tickerlist_sharelist(tickerlist,sharelist,leading_blanks=2):
+def print_tickerlist_sharelist(tickerlist,sharelist,leading_blanks=2,ticker_type='auto'):
     """
     功能：纵向打印投资组合的成分股和持股比例
     输入：
@@ -1494,12 +1503,16 @@ def print_tickerlist_sharelist(tickerlist,sharelist,leading_blanks=2):
     sharelist_array = np.array(sharelist)
     total_shares=sharelist_array.sum()
     weights=sharelist_array/total_shares 
+
+    #预处理ticker_type
+    ticker_type_list=ticker_type_preprocess_mticker_mixed(tickerlist,ticker_type)
     
     import pandas as pd
     df=pd.DataFrame(columns=['证券代码','证券名称','持仓比例'])
     for t in tickerlist:
         pos=tickerlist.index(t)
-        tname=codetranslate(t)
+        tt=ticker_type_list[pos]
+        tname=ticker_name(t,tt)
         tweight=weights[pos]
         
         row=pd.Series({'证券代码':t,'证券名称':tname,'持仓比例':tweight})
@@ -2841,12 +2854,66 @@ def fix_package(file='stooq.py',package='pandas_datareader'):
         print("  Please RESTART your Python kernel before continue to use siat")
     
     return    
+
+#==============================================================================
+if __name__=='__main__':
+    file='stock_info.pickle'
+    package='siat'
+    developer=False
+    
+    file_position()
+
+def file_position(file='stock_info.pickle',package='siat',mode='read'):
+    """
+    功能：给定文件名file，返回其路径
+    注意：执行本程序可能需要系统管理员权限，可以系统管理员权限启动Jupyter或Spyder
+    
+    改进：建立一个Excel文件，记录需要修复的文件和包，例如：
+    file                package
+    stooq.py            pandas_datareader
+    bond_zh_sina.py     akshare
+    
+    """
+    #判断操作系统
+    import sys; czxt=sys.platform
+    if czxt in ['win32','win64']:
+        os='windows'
+    elif czxt in ['darwin']: #MacOSX
+        os='mac'
+    elif czxt in ['linux']: #linux
+        os='linux'
+    else:
+        os='windows'
+   
+    #目标地址
+    cmdstr1='import '+package
+    exec(cmdstr1)   #无返回值地执行字符串代码
+    #import pandas_datareader
+    #objpath=pandas_datareader.__path__[0]
+    cmdstr2=package+'.__path__[0]'
+    objpath=eval(cmdstr2)   #有返回值地执行字符串代码
     
+    if os == 'windows':
+        objpath1=objpath.replace("\\",'/')
+        objfile=objpath1+'/'+file
+    else:
+        objpath1=objpath
+        objfile=objpath1+'/'+file
+    
+    if mode=='read':
+        with open(objfile,'rb') as test:
+            df = pickle.load(test) 
+        return df
+    else:
+        return objfile    
+#==============================================================================
+
+
 #==============================================================================
 #==============================================================================
 
-def df_preprocess(dfs,measure,axhline_label,x_label,y_label,lang='Chinese', \
-                  preprocess='scaling',scaling_option='start'):
+def df_preprocess(dfs,measure,axhline_label,x_label,y_label, \
+                  preprocess='scaling',scaling_option='change%'):
     """
     功能：对于dfs中的数据进行预处理变换，以便克服数量级压制现象更好地展现多条曲线的趋势
     """
@@ -2862,9 +2929,6 @@ def df_preprocess(dfs,measure,axhline_label,x_label,y_label,lang='Chinese', \
         meanlist=[]
         for c in collist:
             
-            # 去掉缺失值
-            #dfs2[c].dropna(inplace=True)
-            
             if preprocess1 == 'standardize': #标准化
                 cmean=dfs2[c].mean()
                 cstd=dfs2[c].std()
@@ -2889,16 +2953,12 @@ def df_preprocess(dfs,measure,axhline_label,x_label,y_label,lang='Chinese', \
                     return None
                 if scaling_option == 'mean':
                     cmean=dfs2[c].mean()   #使用均值
-                    if lang == 'English':
-                        scalingOptionText='mean value'
-                    else:
-                        scalingOptionText='均值'
+                    scalingOptionText=text_lang('均值','mean value')
+                    
                 if scaling_option == 'min':
                     cmean=dfs2[c].min()    #使用最小值
-                    if lang == 'English':
-                        scalingOptionText='min value'
-                    else:
-                        scalingOptionText='最小值'
+                    scalingOptionText=text_lang('最小值','min value')
+                    
                 #if scaling_option == 'start':
                 if scaling_option in ['start','percentage','change%']:
                     # 从头寻找第一个非空数值
@@ -2909,11 +2969,13 @@ def df_preprocess(dfs,measure,axhline_label,x_label,y_label,lang='Chinese', \
                         else:
                             cmean=dfs2[c][n] #使用第一个非空值
                             break
-                        
-                    if lang == 'English':
-                        scalingOptionText='starting value'
+                    
+                    if scaling_option in ['start']:
+                        scalingOptionText=text_lang('起点值','starting value')  
+                    elif scaling_option in ['percentage']:
+                        scalingOptionText=text_lang('百分比','percentage') 
                     else:
-                        scalingOptionText='起点值'
+                        scalingOptionText=text_lang('变化率%','change%')
                     
                 meanlist=meanlist+[cmean]
             
@@ -2949,6 +3011,7 @@ def df_preprocess(dfs,measure,axhline_label,x_label,y_label,lang='Chinese', \
                     dfs2[c]=dfs2[c].apply(lambda x: (x/cfactor-1)*100)
                 
         #设置中英文的脚注和纵轴标记
+        lang=check_language()        
         if lang == 'English':
             if preprocess1 == 'standardize':
                 std_notes="Note: for ease of comparison, data are standardized "
@@ -3203,48 +3266,21 @@ def start_end_preprocess(start,end='today'):
     # 检查日期：开始日期
     start=start.lower()
     
-    """
-    if start in ['default','mrm','l1m']:  # 默认近一个月
-        fromdate=date_adjust(todate,adjust=-31-7) #多几天有利于绘图坐标标示
-    elif start in ['l2m']:  # 近2个月
-        fromdate=date_adjust(todate,adjust=-31*2-14)        
-    elif start in ['mrq','l3m']:  # 近三个月
-        fromdate=date_adjust(todate,adjust=-31*3-16) 
-    elif start in ['l6m','mrh']:  # 近6个月
-        fromdate=date_adjust(todate,adjust=-31*6-16)         
-    elif start in ['mry','l12m']:  # 近一年
-        fromdate=date_adjust(todate,adjust=-366-16)  
-    elif start in ['l2y']:  # 近两年以来
-        fromdate=date_adjust(todate,adjust=-366*2-15)  
-    elif start in ['l3y']:  # 近三年以来
-        fromdate=date_adjust(todate,adjust=-366*3-14)  
-    elif start in ['l5y']:  # 近五年以来
-        fromdate=date_adjust(todate,adjust=-366*5-13)  
-    elif start in ['l8y']:  # 近八年以来
-        fromdate=date_adjust(todate,adjust=-366*8-11)   
-    elif start in ['l10y']:  # 近十年以来
-        fromdate=date_adjust(todate,adjust=-366*10-9)  
-    elif start in ['l20y']:  # 近20年以来
-        fromdate=date_adjust(todate,adjust=-366*20-1)  
-    elif start in ['l30y']:  # 近30年以来
-        fromdate=date_adjust(todate,adjust=-366*30)           
-    elif start in ['ytd']:  # 今年以来
-        fromdate=str(todaydt.year-1)+'-12-1'        
-    else:
-        validdate,fromdate=check_date2(start)
-        if not validdate:
-            print("  #Warning(security_trend): invalid date for",start,"/b, reset to MRM")
-            fromdate=date_adjust(todate,adjust=-31-16)    
-    """
     if start in ['default','mrm','l1m']:  # 默认近一个月
         fromdate=date_adjust2(todate,adjust_month=-1,adjust_day=-1) #有利于绘图横坐标日期标示
+    elif start in ['mrw','l1w']:  # 近1个周
+        fromdate=date_adjust2(todate,adjust_month=0,adjust_day=-7-1)        
+    elif start in ['lhm','l2w']:  # 近2个周
+        fromdate=date_adjust2(todate,adjust_month=0,adjust_day=-7*2-1)        
+    elif start in ['l3w']:  # 近3个周
+        fromdate=date_adjust2(todate,adjust_month=0,adjust_day=-7*3-1)        
     elif start in ['l2m']:  # 近2个月
         fromdate=date_adjust2(todate,adjust_month=-2,adjust_day=-1)        
     elif start in ['mrq','l3m']:  # 近三个月
         fromdate=date_adjust2(todate,adjust_month=-3,adjust_day=-1) 
     elif start in ['l6m','mrh']:  # 近6个月
         fromdate=date_adjust2(todate,adjust_month=-6,adjust_day=-1)         
-    elif start in ['mry','l12m']:  # 近一年
+    elif start in ['mry','l12m','l1y']:  # 近一年
         fromdate=date_adjust2(todate,adjust_year=-1,to_prev_month_end=True)  
     elif start in ['l2y']:  # 近两年以来
         fromdate=date_adjust2(todate,adjust_year=-2,to_prev_month_end=True)  
@@ -3275,6 +3311,337 @@ def start_end_preprocess(start,end='today'):
         
     return fromdate,todate
 
+#==============================================================================
+if __name__=='__main__':
+    text_cn="这是中文"
+    text_en="This is in English"
+    
+    set_language('English')
+    set_language('Chinese')
+    
+    text_lang(text_cn, text_en)
+    
+def text_lang(text_cn, text_en):
+    """
+    功能：检测当前语言环境，若为中文返回text_cn，否则返回text_cn
+    """
+    lang=check_language()
+    
+    if lang == 'Chinese':
+        result=text_cn
+    else:
+        result=text_en
+        
+    return result
+
+#==============================================================================
+if __name__=='__main__':
+    df,_=get_price_1ticker('sh010504',fromdate='2024-1-1',todate='2024-4-6',fill=False)
+
+def df_have_data(df):
+    """
+    功能：判断df内是否有数据
+    返回：有数据-Found，df存在但无数据-Empty，其余-None
+    """
+    found=None
+    if df is None:
+        found='None'
+    elif len(df)==0:
+        found='Empty'
+    else:
+        found='Found'
+        
+    return found
+
+#==============================================================================
+if __name__=='__main__':
+    df,_=get_price_1ticker('sz149976',fromdate='2024-1-1',todate='2024-4-6',fill=False)
+    colname='Close'
+    extend_business_date=False
+    
+    df4=df_fill_extend(df,colname='Close',extend_business_date=False)
+
+def df_fill_extend(df,colname='Close',extend_business_date=False):
+    """
+    功能：对df进行填充
+    colname：基于此判断是否为空，默认为'Close'
+    extend_business_date：False=仅对df现有值进行填充，
+    True=对于现有开始结束日期之间的所有非周末日期进行扩展后填充
+    """
+    import numpy as np
+    
+    df1=df.copy()
+    #仅对现有数据中的缺失值进行填充
+    if not extend_business_date:
+        df1['filled']=df1[colname].apply(lambda x: True if np.isnan(x) else False)
+        df4=df1.ffill(axis=0) #从开始向尾部填充
+        #df5=df4.bfill(axis=0) #从尾部向开始填充，容易对后续的分析结果造成误导，慎用！
+    else:
+        fromdate=df1.head(1).index[0].strftime('%Y-%m-%d')
+        todate=df1.tail(1).index[0].strftime('%Y-%m-%d')
+        
+        df2dt=pd.bdate_range(start=fromdate,end=todate)
+        df2dt=pd.to_datetime(df2dt)
+        df2=pd.DataFrame(index=df2dt)
+        df3=pd.merge(df2,df1,how='outer',left_index=True,right_index=True)
+        
+        df3['filled']=df3[colname].apply(lambda x: True if np.isnan(x) else False)
+        df4=df3.ffill(axis=0) #从开始向尾部填充
+        #df5=df4.bfill(axis=0) #从尾部向开始填充
+ 
+    return df4
+    
+#==============================================================================
+if __name__=='__main__':
+    url="https://finance.yahoo.com"
+    url="https://finance.sina.com.cn"
+    
+    test_website(url)
+
+def test_website(url):
+    """
+    功能：测试一个网址是否可访问
+    """
+    import requests
+    try:
+        response = requests.get(url)
+        if response.status_code == 200:
+            #print(f"{url} is accessible.")
+            return True
+        else:
+            #print(f"{url} is not accessible. Status code: {response.status_code}")
+            return False
+    except requests.exceptions.RequestException:
+        #print(f"{url} is not accessible. Network error occurred.")
+        return False
+
+if __name__=='__main__':
+    test_yahoo_finance()
+    
+def test_yahoo_finance():
+    url="https://finance.yahoo.com"
+    return test_website(url) 
+       
+#==============================================================================
+if __name__=='__main__':
+    check_os()
+
+def check_os():
+    """
+    功能：检测操作系统的类型
+    """
+    import platform
+    system = platform.system()
+    if system == "Windows":
+        return "Windows"
+    elif system == "Linux":
+        return "Linux"
+    elif system == "Darwin":
+        return "Mac OSX"
+    else:
+        return "Unknown OS"  
+    
+#==============================================================================
+if __name__=='__main__':
+    check_python_version()
+
+def check_python_version():
+    """
+    功能：检测Python的版本号
+    """
+    import sys
+    python_version = sys.version_info
+    ver=f"{python_version.major}.{python_version.minor}.{python_version.micro}"
+    return ver
+
+#==============================================================================
+if __name__=='__main__':
+    ticker='AAPL'
+    fromdate='2011-1-1'
+    todate='2020-12-31'
+    retry_count=3
+    pause=1
+    
+    ticker='ABCD'
+    
+    ticker=['AAPL','MSFT']
+    ticker=['AAPL','MSFT','ABCD']
+    
+    ticker=['600011.SS']
+    fromdate='2020-1-1'
+    todate='2020-6-30'    
+
+def upper_ticker(ticker):
+    """
+    功能：改成大写，字符串或列表
+    """
+    if isinstance(ticker,str):
+        return ticker.upper()
+    elif isinstance(ticker,list):
+        tlist=[]
+        for t in ticker:
+            try:
+                tupper=t.upper()
+            except:
+                tupper=t
+            tlist=tlist+[tupper]
+        return tlist
+
+
+#==============================================================================
+if __name__=='__main__':
+    ticker='600519.SS'
+    ticker=['600519.SS','000858.SZ']
+    ticker=['600519.SS','000858.SZ',pf]
+    
+    ticker_type='auto'
+    ticker_type='bond'
+    ticker_type=['auto','bond']
+    ticker_type=['xyz','bond']
+    
+    ticker_type_preprocess_1str(ticker,ticker_type)
+    
+def ticker_type_preprocess_1str(ticker,ticker_type='auto'):
+    """
+    功能：根据ticker情况(单个原生证券)处理ticker_type，使之与ticker对应    
+    """
+    if isinstance(ticker,str):
+        if isinstance(ticker_type,str):
+            ticker_type9=ticker_type
+        if isinstance(ticker_type,list):
+            if len(ticker_type) >= 1:
+                ticker_type9=ticker_type[0]
+            else:
+                ticker_type9='auto'
+    else:
+        ticker_type9=ticker_type
+
+    if ticker_type9 not in ['auto','stock','fund','bond']:
+        ticker_type9='auto'
+            
+    return ticker_type9
+
+if __name__=='__main__':
+    pf={'Market':('China','000001.SS','股债基组合'),'600519.SS':50,'sh018003':150,'sh010504':300}
+    ticker=['600519.SS','000858.SZ','000002.SZ']
+    ticker=['600519.SS','000858.SZ',pf]
+    
+    ticker_type='auto'
+    ticker_type='bond'
+    ticker_type=['auto','bond']
+    ticker_type=['xyz','bond']
+    
+    ticker_type_preprocess_mstr(ticker,ticker_type)
+
+def ticker_type_preprocess_mstr(ticker,ticker_type='auto'):
+    """
+    功能：根据ticker情况(多个原生证券)处理ticker_type，使之与ticker对应    
+    """
+    if isinstance(ticker,list):
+        if isinstance(ticker_type,str):
+            ticker_type8=[ticker_type]*len(ticker)
+            
+        if isinstance(ticker_type,list):
+            if len(ticker) > len(ticker_type):
+                ticker_type8=ticker_type+[ticker_type[-1]]*(len(ticker)-len(ticker_type))
+            else:
+                ticker_type8=ticker_type
+                
+        ticker_type9=[]
+        for tt in ticker_type8:
+            if tt  not in ['auto','stock','fund','bond']:
+                tt='auto'
+            ticker_type9=ticker_type9+[tt]
+        
+    else:
+        ticker_type9=ticker_type
+        
+    return ticker_type9
+
+if __name__=='__main__':
+    ticker={'Market':('China','000001.SS','股债基组合'),'600519.SS':50,'sh018003':150,'sh010504':300}
+    
+    ticker_type='auto'
+    ticker_type='bond'
+    ticker_type=['auto','bond']
+    ticker_type=['xyz','bond']
+    
+    ticker_type_preprocess_1portfolio(ticker,ticker_type)
+
+def ticker_type_preprocess_1portfolio(ticker,ticker_type='auto'):
+    """
+    功能：根据ticker情况(单个投资组合)处理ticker_type，使之与ticker对应    
+    """    
+    if isinstance(ticker,dict):
+        _,_,tickerlist,_=decompose_portfolio(ticker)
+        if len(tickerlist)==1:
+            ticker_type9=ticker_type_preprocess_1str(tickerlist[0],ticker_type)
+        else:
+            ticker_type9=ticker_type_preprocess_mstr(tickerlist,ticker_type)
+    else:
+        ticker_type9=ticker_type
+        
+    return ticker_type9
+    
+if __name__=='__main__':
+    pf={'Market':('China','000001.SS','股债基组合'),'600519.SS':50,'sh018003':150,'sh010504':300}
+    ticker='600519.SS'
+    ticker=['600519.SS','000858.SZ','000002.SZ']
+    ticker={'Market':('China','000001.SS','股债基组合'),'600519.SS':50,'sh018003':150,'sh010504':300}
+
+    ticker=['600519.SS','000858.SZ',pf]
+    
+    ticker_type='auto'
+    ticker_type='bond'
+    ticker_type=['auto','bond']
+    ticker_type=['xyz','bond']
+    
+    ticker_type_preprocess_mticker_mixed(ticker,ticker_type)
+    
+def ticker_type_preprocess_mticker_mixed(ticker,ticker_type='auto'):
+    """
+    功能：根据ticker(可为列表，列表中可含有投资组合)情况处理ticker_type，使之与ticker对应    
+    """
+    #单个证券，非投资组合
+    if isinstance(ticker,str):
+        ticker_type9=ticker_type_preprocess_1str(ticker,ticker_type)  
+        return ticker_type9
+              
+    #单个证券，投资组合
+    if isinstance(ticker,dict):
+        ticker_type9=ticker_type_preprocess_1portfolio(ticker,ticker_type)
+        return ticker_type9
+        
+    #混合列表
+    if isinstance(ticker,list):
+        if isinstance(ticker_type,str):
+            ticker_type8=[ticker_type]*len(ticker)
+        if isinstance(ticker_type,list):
+            if len(ticker) > len(ticker_type):
+                ticker_type8=ticker_type+[ticker_type[-1]]*(len(ticker)-len(ticker_type))
+            else:
+                ticker_type8=ticker_type
+        
+        ticker_type9=[]
+        for t in ticker:
+            pos=ticker.index(t)
+            tt8=ticker_type8[pos]
+            tt9=tt8
+            
+            if isinstance(t,str):
+                tt9=ticker_type_preprocess_1str(t,tt8)
+            
+            if isinstance(t,dict):
+                tt9=ticker_type_preprocess_1portfolio(t,tt8)
+    
+            ticker_type9=ticker_type9+[tt9]    
+    else:
+        ticker_type9=ticker_type
+
+    return ticker_type9
+
+
+#==============================================================================
 #==============================================================================
 #==============================================================================