{
    "info": {
        "author": "Yili Peng",
        "author_email": "yili_peng@outlook.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "Barra Risk Model for China A market\n===================================\n\nThis is a self-build project for studying purpose only. Any commercial\nusage of this project is banned.\n\nDependencies\n------------\n\n-  python 3.5\n-  pandas 0.23.0\n-  spyder 3.2.8\n\nSample\n------\n\nDownload descriptors from Wind API and make factors\n\n.. code:: bash\n\n   path='your_source_file'\n\n               #########################\n               ## step1   wind update ##\n               #########################\n   from barra_risk_model.Wind_update.get_wind import update_wind\n   dt_range_dict={\n   #         'dt':(None,20181231)\n           'rf':(None,20181019)\n           ,'totalA':(None,20181019)\n           ,'descriptor_annually':None \n           ,'index':(None,20181019)\n           ,'descriptor_daily':(20181011,20181019)\n           ,'descriptor_seasonal':20180930\n           }\n\n   update_wind(path,dt_range_dict)\n\n\n                   #####################\n                   ## step1.5  growth ##\n                   #####################\n\n   # only at the beginning of each year when new growth is downloaded\n   from barra_risk_model.Factor_manufacture.make_growth import make_growth\n\n   # example for update growth_r of 20111231\n   year_range=(2011,2012)\n   make_growth(year_range,path)\n\n\n                   ########################\n                   ## step2  integration ##\n                   ########################\n   from barra_risk_model.Factor_manufacture.descriptor_integration import descriptor_integration\n\n   dt_range=(20181008,20181019)\n   warm_start_quarterly=20170930 # warm start should be 1 seasons before for annual reporting and 1 seasons before for quaterly reporting\n   warm_start_yearly=20161231 # 2 years before\n   descriptor_integration(path,dt_range,warm_start_quarterly,warm_start_yearly)\n\n\n                       ########################\n                       ## step3 make factors ##\n                       ########################\n   from barra_risk_model.Factor_manufacture.make_factor import manufacture\n\n   dt_range_dict={\n   #        'exr':(20181008,20181019) #should cover one more day before to create return from price\n   #        ,'srcap':(20181008,20181019)\n   #        ,'ind':(20181008,20181019)\n           'styl':(20120101,20181019)\n           }\n   history_start_date=20120101 #525 before styl starting date\n   manufacture(path,dt_range_dict,history_start_date,mapping=True,ind_mapping_exists=True)\n\nMake prediction of index volatility\n\n.. code:: bash\n\n                       #########################\n                       ## step4 factor return ##\n                       #########################\n   from barra_risk_model.Factor_return.Factor_return_core import factor_return_manufacture\n\n   ## start\n   #dt_range=(20120101,20181019)\n   #factor_return_manufacture(path,dt_range,pool='ZZ800',filter_stock_flag=True,filter_dt_flag=True)\n\n   # renewal (use more days to keep more stocks,suggest)\n   dt_range=(20180901,20181019)\n   factor_return_manufacture(path,dt_range,pool='ZZ800',filter_stock_flag=True,filter_dt_flag=False)\n\n\n                   #######################################\n                   ## step5 factor cov and specfic risk ##\n                   #######################################\n   import numpy as np\n   from RNWS import read,write\n   from barra_risk_model.Factor_matrix_core import cov_matrix_gen_range\n   from barra_risk_model.Specific_matrix_core import spc_matrix_gen_range\n\n\n   start=20140312\n   end=20181019\n\n   Fct_return= read.read_df(path+'/factor_return_data',file_pattern='Fct_return',start=start,end=end)\n   F_all= cov_matrix_gen_range(Fct_return)\n\n   Spc_return=read.read_df(path+'/factor_return_data',file_pattern='Spc_return',start=start,end=end)\n   SRCap=read.read_df(path+'/srcap','srcap',start=start,end=end)\n   stock_pool=read.read_srs(path+'/index/ZZ800','Stk_ZZ800',start=start,end=end)\n   X_all= read.read_dict(path+'/factor_return_data',file_pattern='X1',start=start,end=end)\n   S_all=spc_matrix_gen_range(Spc_return=Spc_return,X_all=X_all,stock_pool=stock_pool,cap=np.square(SRCap))\n\n   renewal_dt=20140312\n   F_all_tmp={dt:F_all[dt] for dt in read.reading_data.trading_dt[(read.reading_data.trading_dt>=renewal_dt)&(read.reading_data.trading_dt<=end)]}\n   S_all_tmp=S_all.loc[renewal_dt:]\n\n   write.write_dict(F_all_tmp,path=path+'/factor_cov_matrix',file_pattern='factor_cov')\n   write.write_df(S_all_tmp,path=path+'/specific_volatility',file_pattern='specofoc_vol')\n\n                           #############################\n                           # step6 one day prediction ##\n                           #############################\n   import numpy as np\n   from RNWS import read,write\n   from barra_risk_model.Factor_matrix_core import cov_matrix_oneday\n   from barra_risk_model.Specific_matrix_core import spc_matrix_oneday\n\n   start=20170508\n   end=20180508\n\n   Fct_return= read.read_df(path+'/factor_return_data',file_pattern='Fct_return',start=start,end=end)\n   F_one=cov_matrix_oneday(Fct_return,dt=20180508)\n\n   Spc_return=read.read_df(path+'/factor_return_data',file_pattern='Spc_return',start=start,end=end)\n   X_all= read.read_dict(path+'/factor_return_data',file_pattern='X1',start=start,end=end)\n   stock_pool=read.read_srs(path+'/index/ZZ800','Stk_ZZ800',start=start,end=end)\n   SRCap=read.read_df(path+'/srcap','srcap',start=start,end=end)\n   S_one=spc_matrix_oneday(Spc_return=Spc_return,dt=20180508,X_all=X_all,stock_pool=stock_pool,cap=np.square(SRCap))\n   # S_one predict one day specific volatility, requiring 128 days to preoduce.\n\n                           ###############################\n                           ## step7 evaluate prediction ##\n                           ###############################\n   from barra_risk_model.Bias_stats import bs_F,bs,bs_window,bs_f_window,real_std,predicted_std\n\n   import datetime\n   import matplotlib.pyplot as plt\n\n\n   start=20140312\n   end=20181019\n\n   F_all= read.read_dict(path+'/factor_cov_matrix',file_pattern='factor_cov',start=start,end=end)\n   R_all= read.read_df(path+'/factor_return_data',file_pattern='R',start=start,end=end)\n   X_all= read.read_dict(path+'/factor_return_data',file_pattern='X1',start=start,end=end)\n   S_all= read.read_df(path+'/specific_volatility',file_pattern='specofoc_vol',start=start,end=end)\n   W= read.read_df(path+'/index/HS300',file_pattern='Stk_HS300',start=start,end=end,dat_col=3,inx_col=1)\n   W=W.replace('None',np.nan).astype(float)\n   W2=W.fillna(0)\n   #W2=W2.where(W2==0)\n\n   def plot_bs(R_all,F_all,X_all,S_all,W):\n       bs_f=bs_F(R_all,F_all,X_all,W) \n       bs_fw=bs_f_window(R_all,F_all,X_all,W)\n       bs_=bs(R_all,F_all,X_all,S_all,W) \n       bs_w=bs_window(R_all,F_all,X_all,S_all,W)\n\n       bs_fw.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in bs_fw.index]\n       bs_w.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in bs_w.index]\n\n       plt.figure(figsize=(10,6))\n       plt.plot(bs_w,label='bs')\n       plt.plot(bs_fw,label='bs_f')\n       plt.gcf().autofmt_xdate()\n       plt.legend()\n       plt.show()\n       print(bs_f,bs_)\n\n   def plot_vol(R_all,F_all,X_all,S_all,W):\n       rv=real_std(R_all,W)\n       pv=predicted_std(F_all,S_all,X_all,W)\n\n       rv.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in rv.index]\n       pv.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in pv.index]\n\n       plt.figure(figsize=(10,6))\n       plt.plot(rv,label='real volatility')\n       plt.plot(pv,label='predicted volatility')\n       plt.gcf().autofmt_xdate()\n       plt.legend()\n       plt.show()\n\n   plot_vol(R_all,F_all,X_all,S_all,W2)\n\n   rv=real_std(R_all,W2)\n   pv=predicted_std(F_all,S_all,X_all,W2)\n   pv2=pv.reset_index()\n   rv2=rv.reset_index()\n   pv3=pv.iloc[np.where((pv2['index']//100).pct_change()!=0)]\n   rv3=rv.iloc[np.where((rv2['index']//100).pct_change()!=0)]\n   rv3.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in rv3.index]\n   pv3.index=[datetime.datetime.strptime(str(i),'%Y%m%d') for i in pv3.index]\n   plt.figure(figsize=(10,6))\n   plt.plot(rv3,label='real volatility')\n   plt.plot(pv3,label='predicted volatility')\n   plt.gcf().autofmt_xdate()\n   plt.legend()\n   plt.show()\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "",
        "keywords": "",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "barra-risk-model",
        "package_url": "https://pypi.org/project/barra-risk-model/",
        "platform": "",
        "project_url": "https://pypi.org/project/barra-risk-model/",
        "project_urls": null,
        "release_url": "https://pypi.org/project/barra-risk-model/0.1.5/",
        "requires_dist": [
            "RNWS (>=0.1.0)"
        ],
        "requires_python": "",
        "summary": "Barra Risk Model CN version",
        "version": "0.1.5"
    },
    "last_serial": 4908202,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f4964c703cb793005226d86ae7981e1a",
                    "sha256": "fd08aa3835afc43f8f25c4a38a1a537fc97b2ae1f1b4bc5d4f9e7c2d4d43cb6d"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.0-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "f4964c703cb793005226d86ae7981e1a",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 32847,
                "upload_time": "2018-10-09T05:31:57",
                "url": "https://files.pythonhosted.org/packages/9d/30/00b98f4a233d876fc811db392f82dd1073169df17f6851cf106a77099fa5/barra_risk_model-0.1.0-py3-none-any.whl"
            }
        ],
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "ed668eb93b2ec3a32794211a33d24507",
                    "sha256": "2982c510d89b949d08ee36d143b5f9a9c4a358d1eee3c8d5c4aae51ee4daa0d3"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "ed668eb93b2ec3a32794211a33d24507",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 36555,
                "upload_time": "2018-10-12T03:34:49",
                "url": "https://files.pythonhosted.org/packages/67/af/bb2595a2432536c8f313171df841352aece98728003319af2f332886afda/barra_risk_model-0.1.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "82190615ceb68ae1998e9274437cf46c",
                    "sha256": "2b8ca4432c5188030dbaad9a9edeed038315b0626ee704dcf6e6b546d630d051"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "82190615ceb68ae1998e9274437cf46c",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 22367,
                "upload_time": "2018-10-12T03:34:51",
                "url": "https://files.pythonhosted.org/packages/aa/e1/95112f3e061987fc046b1c30bb9f16165e15be019f56824ca9cf60149546/barra_risk_model-0.1.1.tar.gz"
            }
        ],
        "0.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "29e52ad870730b089a37567cd2281de8",
                    "sha256": "0057246585de60c960625091101675f96680573d12028ed16511777953e85f1c"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "29e52ad870730b089a37567cd2281de8",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 36578,
                "upload_time": "2018-10-15T10:09:01",
                "url": "https://files.pythonhosted.org/packages/60/5f/b70d2362238d996448204c46a2d6181aa94d32e220e6ef58db3bd53e3c9d/barra_risk_model-0.1.2-py3-none-any.whl"
            }
        ],
        "0.1.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7c8ded69b6d7c1b43d0f7f4a1729c271",
                    "sha256": "48153644a3bef777d71a2ce8939e4e8b41e8cca40ff8a54df49d3dc806ad87e9"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "7c8ded69b6d7c1b43d0f7f4a1729c271",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 40529,
                "upload_time": "2018-11-22T09:58:51",
                "url": "https://files.pythonhosted.org/packages/50/2a/b446a6680b10ecfe02254020e17e2a2c49733c8344e501610e9967658077/barra_risk_model-0.1.3-py3-none-any.whl"
            }
        ],
        "0.1.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4b9c81480243f62b3987535bb8a81892",
                    "sha256": "70d7267e2d0fab4f0834bdbb2bc373a04cd72924f97ee7029d1da328af258f28"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.4-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "4b9c81480243f62b3987535bb8a81892",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 40529,
                "upload_time": "2018-12-10T01:33:32",
                "url": "https://files.pythonhosted.org/packages/61/05/9118ce74aab65e995e6e18509cd206df93951f6a454e1372f8ddba0e20c0/barra_risk_model-0.1.4-py3-none-any.whl"
            }
        ],
        "0.1.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "685c8ed75e2c2f2cd169fb7372184252",
                    "sha256": "3ea41fa95fd26caca4b74c1b03a9c4c2b95c831c7f5125c14ac229ba43f8490d"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.5-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "685c8ed75e2c2f2cd169fb7372184252",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 40491,
                "upload_time": "2018-12-26T09:45:29",
                "url": "https://files.pythonhosted.org/packages/bb/07/4036154f91cc152f0beb3b1cc38c171efa46fc8e887be35ed050bf54c6cc/barra_risk_model-0.1.5-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "555e680ebb51ffe7360955b5a41e5059",
                    "sha256": "5ba26ccf4789b4b9f34d5891a86ba06f59417f12b4b66ea29800d831bdd811c3"
                },
                "downloads": -1,
                "filename": "barra_risk_model-0.1.5.tar.gz",
                "has_sig": false,
                "md5_digest": "555e680ebb51ffe7360955b5a41e5059",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 25051,
                "upload_time": "2019-03-07T03:15:55",
                "url": "https://files.pythonhosted.org/packages/db/f4/9ecfadf968762693fc670160c48b76606eb5d3af3ae2f217ee72c768154f/barra_risk_model-0.1.5.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "685c8ed75e2c2f2cd169fb7372184252",
                "sha256": "3ea41fa95fd26caca4b74c1b03a9c4c2b95c831c7f5125c14ac229ba43f8490d"
            },
            "downloads": -1,
            "filename": "barra_risk_model-0.1.5-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "685c8ed75e2c2f2cd169fb7372184252",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 40491,
            "upload_time": "2018-12-26T09:45:29",
            "url": "https://files.pythonhosted.org/packages/bb/07/4036154f91cc152f0beb3b1cc38c171efa46fc8e887be35ed050bf54c6cc/barra_risk_model-0.1.5-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "555e680ebb51ffe7360955b5a41e5059",
                "sha256": "5ba26ccf4789b4b9f34d5891a86ba06f59417f12b4b66ea29800d831bdd811c3"
            },
            "downloads": -1,
            "filename": "barra_risk_model-0.1.5.tar.gz",
            "has_sig": false,
            "md5_digest": "555e680ebb51ffe7360955b5a41e5059",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 25051,
            "upload_time": "2019-03-07T03:15:55",
            "url": "https://files.pythonhosted.org/packages/db/f4/9ecfadf968762693fc670160c48b76606eb5d3af3ae2f217ee72c768154f/barra_risk_model-0.1.5.tar.gz"
        }
    ]
}