siat 1.7.49__py3-none-any.whl → 1.7.51__py3-none-any.whl

siat/markowitz.py

@@ -2180,35 +2180,8 @@ def security_correlation(tickers,start,end,info_type='Close'):
     return df_coor
 
 #==============================================================================
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+#==============================================================================
+#==============================================================================
+#==============================================================================
 
 

siat/sector_china.py

@@ -20,6 +20,7 @@ from siat.translate import *
 from siat.bond_base import *
 from siat.stock import *
 from siat.risk_adjusted_return import *
+from siat.financials_china2 import *
 #==============================================================================
 
 if __name__=='__main__':
@@ -661,6 +662,7 @@ def print_industry_sw(itype='I',numberPerLine=5,colalign='left'):
 if __name__=='__main__':
     iname='食品饮料'
     iname='银行'
+    iname='汽车'
     numberPerLine=5
     colalign='right'
     
@@ -676,6 +678,9 @@ def print_industry_component_sw(iname,numberPerLine=5,colalign='left'):
     clist,cdf=industry_stock_sw(icode,top=1000)    
 
     cdf['icode']=cdf['证券代码'].apply(lambda x: x+'.SS' if x[:1] in ['6'] else (x+'.SZ' if x[:1] in ['0','3'] else x+'.BJ' ))
+    
+    # 删除'证券名称'为None的行
+    cdf=cdf.mask(cdf.eq('None')).dropna()
     cdf['name_code']=cdf.apply(lambda x: x['证券名称']+'('+x['icode']+')',axis=1)
     
     ilist=list(cdf['name_code'])
@@ -721,7 +726,7 @@ def industry_sw_code(iname):
         icode=industry[industry['name']==iname]['code'].values[0]
     except:
         #未查到
-        print("  #Warning(industry_sw_code): industry name not found",iname)
+        #print("  #Warning(industry_sw_code): industry name not found",iname)
         return None
    
     return icode
@@ -758,7 +763,7 @@ def industry_sw_codes(inamelist):
             if not (icode is None):
                 icodelist=icodelist+[icode]
             else:
-                print("  #Warning(industries_sw_code): industry code not found",i)
+                print("  #Warning(industries_sw_code): industry name not found",i)
                 return None
    
     return icodelist
@@ -1415,10 +1420,10 @@ def rank_industry_sw_sharpe(idfall,base_return='Exp Ret%',graph=True,axisamp=0.8
     
 #==============================================================================
 if __name__=='__main__':
-    industry='801843'
+    industry='801780'
     top=5
 
-def industry_stock_sw(industry='801270',top=5):
+def industry_stock_sw(industry='801270',top=5,printout=False):
     """
     功能：获取申万行业指数的成分股
     排序：按照权重从大到小，重仓优先
@@ -1456,6 +1461,12 @@ def industry_stock_sw(industry='801270',top=5):
         else:
             clist1=clist1+[c+'.SZ']
     
+    if printout:
+        title_txt="申万行业指数成分股排名与权重："+industry_sw_name(industry)+'指数('+industry+')'
+        import datetime as dt; today=str(dt.date.today())
+        footnote="*** 数据来源：sina/EM，"+str(today)
+        df_directprint(cdf1,title_txt,footnote)        
+    
     return clist1,cdf1
     
 if __name__=='__main__':
@@ -1582,6 +1593,162 @@ def rank_msecurity_performance(tickers,start,end, \
     
     return df1
 #==============================================================================
+#==============================================================================
+if __name__=='__main__':
+    tickers=['801160','801120','801170','801710','801890','801040','801130','801180','801720','801970']
+    start='2022-1-1'
+    end='2023-3-22'
+    info_type='Close'
+    
+    df=get_industry_sw('I')
+    df=industry_correlation_sw(df,tickers,start,end,info_type='Close')
+
+def cm2inch(x,y):
+    return x/2.54,y/2.54
+
+def industry_correlation_sw(df,tickers,start,end,info_type='Close'):
+    """
+    功能：股票/指数收盘价之间的相关性
+    info_type='Close': 默认Close, 还可为Open/High/Low/Volume
+    """
+    # 检查行业个数
+    if not isinstance(tickers,list) or len(tickers) < 2:
+        print("  #Error(industry_correlation_sw): number of industries too few",tickers)
+        return None
+    
+    # 检查信息类型
+    info_types=['Close','Open','High','Low','Volume']
+    info_types_cn=['收盘价','开盘价','最高价','最低价','成交量']
+    if not(info_type in info_types):
+        print("  #Error(industry_correlation_sw): invalid information type",info_type)
+        print("  Supported information type:",info_types)
+        return None
+    pos=info_types.index(info_type)
+    info_type_cn=info_types_cn[pos]
+    
+    # 检查日期
+    result,startdt,enddt=check_period(start,end)
+    if not result: 
+        print("  #Error(industry_correlation_sw): invalid period",start,end)
+        return None
+    
+    # 合成行业行情信息
+    print("  Consolidating industry performance, please wait ...")
+    import pandas as pd
+    
+    """
+    tickercodes=industry_sw_codes(tickers)
+    if tickercodes is None:
+        tickercodes=tickers
+    """
+    
+    dfs=None
+    for ind in tickers:
+        dft=df[df['ticker']==ind]
+        if dft is None: 
+            print("  #Warning(industry_correlation_sw): unknown industry code",ind)
+            continue
+    
+        dft2=dft[(dft.index >= startdt) & (dft.index <= enddt)]
+        dft3=pd.DataFrame(dft2[info_type])
+        dft3.rename(columns={info_type:industry_sw_name(ind)},inplace=True)
+        
+        if dfs is None:
+            dfs=dft3
+        else:
+            dfs=pd.merge(dfs,dft3,how='inner',left_index=True,right_index=True)
+    dfs.dropna(axis=0,inplace=True)
+
+    df_coor = dfs.corr()
+
+    print("  Preparing cross-industry correlations, please wait ...")
+    # here put the import lib
+    import seaborn as sns
+    sns.set(font='SimHei')  # 解决Seaborn中文显示问题
+
+    fig = plt.figure(figsize=(cm2inch(12,8)))
+    ax1 = plt.gca()
+    
+    #构造mask，去除重复数据显示
+    import numpy as np
+    mask = np.zeros_like(df_coor)
+    mask[np.triu_indices_from(mask)] = True
+    mask2 = mask
+    mask = (np.flipud(mask)-1)*(-1)
+    mask = np.rot90(mask,k = -1)
+    
+    im1 = sns.heatmap(df_coor,annot=True,cmap="YlGnBu"
+                        , mask=mask#构造mask，去除重复数据显示
+                        ,vmax=1,vmin=-1
+                        , fmt='.2f',ax = ax1,annot_kws={"size": 6})
+    
+    ax1.tick_params(axis = 'both', length=0)
+    
+    #计算相关性显著性并显示
+    from scipy.stats import pearsonr
+    rlist = []
+    plist = []
+    for i in dfs.columns.values:
+        for j in dfs.columns.values:
+            r,p = pearsonr(dfs[i],dfs[j])
+            rlist.append(r)
+            plist.append(p)
+    
+    rarr = np.asarray(rlist).reshape(len(dfs.columns.values),len(dfs.columns.values))
+    parr = np.asarray(plist).reshape(len(dfs.columns.values),len(dfs.columns.values))
+    xlist = ax1.get_xticks()
+    ylist = ax1.get_yticks()
+    
+    widthx = 0
+    widthy = -0.15
+    
+    # 星号的大小
+    font_dict={'size':5}
+    
+    for m in ax1.get_xticks():
+        for n in ax1.get_yticks():
+            pv = (parr[int(m),int(n)])
+            rv = (rarr[int(m),int(n)])
+            if mask2[int(m),int(n)]<1.:
+                #if abs(rv) > 0.5:
+                if rv > 0.3:
+                    if  pv< 0.05 and pv>= 0.01:
+                        ax1.text(n+widthx,m+widthy,'*',ha = 'center',color = 'white',fontdict=font_dict)
+                    if  pv< 0.01 and pv>= 0.001:
+                        ax1.text(n+widthx,m+widthy,'**',ha = 'center',color = 'white',fontdict=font_dict)
+                    if  pv< 0.001:
+                        #print([int(m),int(n)])
+                        ax1.text(n+widthx,m+widthy,'***',ha = 'center',color = 'white',fontdict=font_dict)
+                else: 
+                    if  pv< 0.05 and pv>= 0.01:
+                        ax1.text(n+widthx,m+widthy,'*',ha = 'center',color = 'k',fontdict=font_dict)
+                    elif  pv< 0.01 and pv>= 0.001:
+                        ax1.text(n+widthx,m+widthy,'**',ha = 'center',color = 'k',fontdict=font_dict)
+                    elif  pv< 0.001:
+                        ax1.text(n+widthx,m+widthy,'***',ha = 'center',color = 'k',fontdict=font_dict)
+    
+    plt.title("行业板块"+info_type_cn+"之间的相关性")
+    plt.tick_params(labelsize=6)
+    
+    footnote1="\n显著性数值：***非常显著(<0.001)，**很显著(<0.01)，*显著(<0.05)，其余为不显著"
+    footnote2="\n系数绝对值：>=0.8极强相关，0.6-0.8强相关，0.4-0.6相关，0.2-0.4弱相关，否则为极弱(不)相关"
+
+    footnote3="\n观察期间: "+start+'至'+end
+    import datetime as dt; stoday=dt.date.today()    
+    footnote4="；来源：Sina/EM，"+str(stoday)+"；基于申万行业分类"
+    
+    fontxlabel={'size':6}
+    plt.xlabel(footnote1+footnote2+footnote3+footnote4,fontxlabel)
+    plt.show()
+    
+    return df_coor
+
+#==============================================================================
+#==============================================================================
+#==============================================================================
+#==============================================================================
+
+
 
 #==============================================================================
 

{siat-1.7.49.dist-info → siat-1.7.51.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: siat
-Version: 1.7.49
+Version: 1.7.51
 Summary: Securities Investment Analysis Tools (siat)
 Home-page: https://pypi.org/project/siat/
 Author: Prof. WANG Dehong, Business School, BFSU (北京外国语大学 国际商学院 王德宏 教授)

{siat-1.7.49.dist-info → siat-1.7.51.dist-info}/RECORD

@@ -53,7 +53,7 @@ siat/holding_risk.py,sha256=108tiI7DDl8uUZkyUiq6Y-McKeim1mxYsgqgk7CcXw8,30544
 siat/holding_risk_test.py,sha256=FRlw_9wFG98BYcg_cSj95HX5WZ1TvkGaOUdXD7-V86s,474
 siat/local_debug_test.py,sha256=CDAOffW1Rvs-TcNN5giWVvHMlch1w4dp-w5SIV9jXL0,3936
 siat/market_china.py,sha256=2_ov1KQwRtHQ6PXNO1TS4-wUPhBuoWla326g0x_xUgQ,31158
-siat/markowitz.py,sha256=sIgfOUkD23CxKgEfBL9sidzpa36De49ufNd2XdrWdpQ,91344
+siat/markowitz.py,sha256=tCeWCz_KzkTD2ho1y3IrxY9-4IAn5BxVxDA2PlLdI2g,91527
 siat/markowitz_ccb_test.py,sha256=xBkkoaNHdq9KSUrNuHGgKTdNYUvgi84kNYcf719eoyE,1593
 siat/markowitz_ef_test.py,sha256=wjNlICkgRIqnonPeSIHo4Mu2GRtb9dr21wDt2kMNEcI,4032
 siat/markowitz_old.py,sha256=Lf7O_4QWT8RsdkHiUyc_7kKY3eZjKDtFR89Fz3pwYnY,33046
@@ -73,7 +73,7 @@ siat/risk_evaluation.py,sha256=lCDqCaSEppH0MFPFg-P14IYcF3IJqILbPfDmzf_AfcY,75061
 siat/risk_evaluation_test.py,sha256=YEXM96gKzTfwN4U61AS4Rr1tV7KgUvn4rRC6f3iMw9s,3731
 siat/risk_free_rate.py,sha256=r62zCl1qbI4lJU17GsgM-OmVx9oo3dltXeZVCNd6Uxg,12304
 siat/risk_free_rate_test.py,sha256=CpmhUf8aEAEZeNu4gvWP2Mz2dLoIgBX5bI41vfUBEr8,4285
-siat/sector_china.py,sha256=mTMspgBgd07pesdMhGm-SpTr-rcKts-kaEsIM3kXsjk,58803
+siat/sector_china.py,sha256=rpJ-HA14nb5pk6IRS7GTS3moRKhLQeC5-YlMkQJgfYo,65349
 siat/sector_china_test.py,sha256=tvFQYptmj7jq6H5kNaRJtcP5Wgb-eWvaoSl33Y47ZsM,4210
 siat/security_price.py,sha256=ibrdUJyt_n0c8oKRbVStE1_ptmWkzy4YIHjpc_fGiPQ,29148
 siat/security_prices.py,sha256=Xl7EHz16qCUIzuPGpEi-g-tLGQKk3MqHmic556-Vs7U,71984
@@ -104,7 +104,7 @@ siat/universal_test.py,sha256=CDAOffW1Rvs-TcNN5giWVvHMlch1w4dp-w5SIV9jXL0,3936
 siat/valuation_china.py,sha256=U9FQgFcbJcS-S0cwy8iJ9Z0Rf8sxCN5Pxhm1DItUUgQ,51206
 siat/valuation_market_china_test.py,sha256=gbJ0ioauuo4koTPH6WKUkqcXiQPafnbhU5eKJ6lpdLA,1571
 siat/var_model_validation.py,sha256=zB_Skk_tmzIR15l6oAW3am4HBGVIG-eZ8gJhCdXZ8Qw,14859
-siat-1.7.49.dist-info/METADATA,sha256=X2D3EGkVuQ5cx9rdtAx0Ipu74S_VraqWUmrUCP-bDNw,1400
-siat-1.7.49.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
-siat-1.7.49.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
-siat-1.7.49.dist-info/RECORD,,
+siat-1.7.51.dist-info/METADATA,sha256=SNhRr3owapwRinP3mPd2OG6wmJvFWBcya99n013Ruk8,1400
+siat-1.7.51.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
+siat-1.7.51.dist-info/top_level.txt,sha256=r1cVyL7AIKqeAmEJjNR8FMT20OmEzufDstC2gv3NvEY,5
+siat-1.7.51.dist-info/RECORD,,