{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f52748d7",
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'defs'",
     "output_type": "error",
     "traceback": [
      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
      "\u001B[1;31mModuleNotFoundError\u001B[0m                       Traceback (most recent call last)",
      "Cell \u001B[1;32mIn[1], line 5\u001B[0m\n\u001B[0;32m      3\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mstatsmodels\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mapi\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m \u001B[38;5;21;01msm\u001B[39;00m\n\u001B[0;32m      4\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01mscipy\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mstats\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m f\n\u001B[1;32m----> 5\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mdefs\u001B[39;00m\n\u001B[0;32m      6\u001B[0m \u001B[38;5;28;01mimport\u001B[39;00m \u001B[38;5;21;01mlinearmodels\u001B[39;00m\n",
      "\u001B[1;31mModuleNotFoundError\u001B[0m: No module named 'defs'"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import statsmodels.api as sm\n",
    "from scipy.stats import f\n",
    "import defs\n",
    "import linearmodels"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "56199258",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'pd' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
      "\u001B[1;31mNameError\u001B[0m                                 Traceback (most recent call last)",
      "Cell \u001B[1;32mIn[1], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m data_factors \u001B[38;5;241m=\u001B[39m \u001B[43mpd\u001B[49m\u001B[38;5;241m.\u001B[39mread_csv(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mE:\u001B[39m\u001B[38;5;124m\\\u001B[39m\u001B[38;5;124m大三下study\u001B[39m\u001B[38;5;124m\\\u001B[39m\u001B[38;5;124m蒋志强\u001B[39m\u001B[38;5;124m\\\u001B[39m\u001B[38;5;124m実験3\u001B[39m\u001B[38;5;124m\\\u001B[39m\u001B[38;5;124m学习通资料\u001B[39m\u001B[38;5;124m\\\u001B[39m\u001B[38;5;124mData_FFFactors.csv\u001B[39m\u001B[38;5;124m'\u001B[39m, encoding\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mGB2312\u001B[39m\u001B[38;5;124m'\u001B[39m, usecols\u001B[38;5;241m=\u001B[39m[\u001B[38;5;241m2\u001B[39m, \u001B[38;5;241m6\u001B[39m, \u001B[38;5;241m7\u001B[39m, \u001B[38;5;241m8\u001B[39m])\u001B[38;5;66;03m##全部是总市值加权\u001B[39;00m\n\u001B[0;32m      2\u001B[0m data_factors\u001B[38;5;241m.\u001B[39mcolumns \u001B[38;5;241m=\u001B[39m [\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mdate\u001B[39m\u001B[38;5;124m'\u001B[39m, \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mmkt\u001B[39m\u001B[38;5;124m'\u001B[39m, \u001B[38;5;124m'\u001B[39m\u001B[38;5;124msmb\u001B[39m\u001B[38;5;124m'\u001B[39m, \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mhml\u001B[39m\u001B[38;5;124m'\u001B[39m]\n\u001B[0;32m      3\u001B[0m data_factors[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mdate\u001B[39m\u001B[38;5;124m'\u001B[39m]\u001B[38;5;241m=\u001B[39mpd\u001B[38;5;241m.\u001B[39mto_datetime(data_factors[\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mdate\u001B[39m\u001B[38;5;124m'\u001B[39m])\n",
      "\u001B[1;31mNameError\u001B[0m: name 'pd' is not defined"
     ]
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c27c9ae7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "      code       date  return\n0       32 2010-01-08 -0.0137\n1       32 2010-01-15 -0.0246\n2       32 2010-01-22 -0.0682\n3       32 2010-01-29 -0.0489\n4       32 2010-02-05 -0.0313\n...    ...        ...     ...\n4650    41 2022-12-02 -0.0073\n4651    41 2022-12-09 -0.0291\n4652    41 2022-12-16 -0.0112\n4653    41 2022-12-23 -0.0402\n4654    41 2022-12-30  0.0526\n\n[4655 rows x 3 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>code</th>\n      <th>date</th>\n      <th>return</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>32</td>\n      <td>2010-01-08</td>\n      <td>-0.0137</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>32</td>\n      <td>2010-01-15</td>\n      <td>-0.0246</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>32</td>\n      <td>2010-01-22</td>\n      <td>-0.0682</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>32</td>\n      <td>2010-01-29</td>\n      <td>-0.0489</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>32</td>\n      <td>2010-02-05</td>\n      <td>-0.0313</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>4650</th>\n      <td>41</td>\n      <td>2022-12-02</td>\n      <td>-0.0073</td>\n    </tr>\n    <tr>\n      <th>4651</th>\n      <td>41</td>\n      <td>2022-12-09</td>\n      <td>-0.0291</td>\n    </tr>\n    <tr>\n      <th>4652</th>\n      <td>41</td>\n      <td>2022-12-16</td>\n      <td>-0.0112</td>\n    </tr>\n    <tr>\n      <th>4653</th>\n      <td>41</td>\n      <td>2022-12-23</td>\n      <td>-0.0402</td>\n    </tr>\n    <tr>\n      <th>4654</th>\n      <td>41</td>\n      <td>2022-12-30</td>\n      <td>0.0526</td>\n    </tr>\n  </tbody>\n</table>\n<p>4655 rows × 3 columns</p>\n</div>"
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "index=pd.read_csv('index.csv',encoding='utf-8',usecols=[0,1,3])\n",
    "index.columns=['code','date','return']\n",
    "index['date']=pd.to_datetime(index['date'])\n",
    "index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d7674a90",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "array([32, 33, 34, 35, 38, 40, 41], dtype=int64)"
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "indexcode=np.unique(index['code'])\n",
    "indexcode"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "63a027b5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "     code       date  return32\n0      32 2010-01-08   -0.0137\n1      32 2010-01-15   -0.0246\n2      32 2010-01-22   -0.0682\n3      32 2010-01-29   -0.0489\n4      32 2010-02-05   -0.0313\n..    ...        ...       ...\n660    32 2022-12-02   -0.0100\n661    32 2022-12-09   -0.0068\n662    32 2022-12-16   -0.0216\n663    32 2022-12-23   -0.0488\n664    32 2022-12-30    0.0023\n\n[665 rows x 3 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>code</th>\n      <th>date</th>\n      <th>return32</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>32</td>\n      <td>2010-01-08</td>\n      <td>-0.0137</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>32</td>\n      <td>2010-01-15</td>\n      <td>-0.0246</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>32</td>\n      <td>2010-01-22</td>\n      <td>-0.0682</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>32</td>\n      <td>2010-01-29</td>\n      <td>-0.0489</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>32</td>\n      <td>2010-02-05</td>\n      <td>-0.0313</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>660</th>\n      <td>32</td>\n      <td>2022-12-02</td>\n      <td>-0.0100</td>\n    </tr>\n    <tr>\n      <th>661</th>\n      <td>32</td>\n      <td>2022-12-09</td>\n      <td>-0.0068</td>\n    </tr>\n    <tr>\n      <th>662</th>\n      <td>32</td>\n      <td>2022-12-16</td>\n      <td>-0.0216</td>\n    </tr>\n    <tr>\n      <th>663</th>\n      <td>32</td>\n      <td>2022-12-23</td>\n      <td>-0.0488</td>\n    </tr>\n    <tr>\n      <th>664</th>\n      <td>32</td>\n      <td>2022-12-30</td>\n      <td>0.0023</td>\n    </tr>\n  </tbody>\n</table>\n<p>665 rows × 3 columns</p>\n</div>"
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index32=index[index['code']==indexcode[0]]\n",
    "index32.columns=['code','date','return32']\n",
    "index32"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "2d59f930",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "      code       date  return34\n1330    34 2010-01-08   -0.0089\n1331    34 2010-01-15    0.0385\n1332    34 2010-01-22   -0.0274\n1333    34 2010-01-29   -0.0472\n1334    34 2010-02-05   -0.0242\n...    ...        ...       ...\n1990    34 2022-12-02    0.0083\n1991    34 2022-12-09    0.0050\n1992    34 2022-12-16   -0.0244\n1993    34 2022-12-23   -0.0516\n1994    34 2022-12-30    0.0226\n\n[665 rows x 3 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>code</th>\n      <th>date</th>\n      <th>return34</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1330</th>\n      <td>34</td>\n      <td>2010-01-08</td>\n      <td>-0.0089</td>\n    </tr>\n    <tr>\n      <th>1331</th>\n      <td>34</td>\n      <td>2010-01-15</td>\n      <td>0.0385</td>\n    </tr>\n    <tr>\n      <th>1332</th>\n      <td>34</td>\n      <td>2010-01-22</td>\n      <td>-0.0274</td>\n    </tr>\n    <tr>\n      <th>1333</th>\n      <td>34</td>\n      <td>2010-01-29</td>\n      <td>-0.0472</td>\n    </tr>\n    <tr>\n      <th>1334</th>\n      <td>34</td>\n      <td>2010-02-05</td>\n      <td>-0.0242</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>1990</th>\n      <td>34</td>\n      <td>2022-12-02</td>\n      <td>0.0083</td>\n    </tr>\n    <tr>\n      <th>1991</th>\n      <td>34</td>\n      <td>2022-12-09</td>\n      <td>0.0050</td>\n    </tr>\n    <tr>\n      <th>1992</th>\n      <td>34</td>\n      <td>2022-12-16</td>\n      <td>-0.0244</td>\n    </tr>\n    <tr>\n      <th>1993</th>\n      <td>34</td>\n      <td>2022-12-23</td>\n      <td>-0.0516</td>\n    </tr>\n    <tr>\n      <th>1994</th>\n      <td>34</td>\n      <td>2022-12-30</td>\n      <td>0.0226</td>\n    </tr>\n  </tbody>\n</table>\n<p>665 rows × 3 columns</p>\n</div>"
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index33=index[index['code']==indexcode[1]]\n",
    "index34=index[index['code']==indexcode[2]]\n",
    "index35=index[index['code']==indexcode[3]]\n",
    "index38=index[index['code']==indexcode[4]]\n",
    "index40=index[index['code']==indexcode[5]]\n",
    "index41=index[index['code']==indexcode[6]]\n",
    "index33.columns=['code','date','return33']\n",
    "index34.columns=['code','date','return34']\n",
    "index35.columns=['code','date','return35']\n",
    "index38.columns=['code','date','return38']\n",
    "index40.columns=['code','date','return40']\n",
    "index41.columns=['code','date','return41']\n",
    "index34"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "04d0190e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "        日期_Date  周无风险收益率_WkRFRet\n0    2010/01/01         0.000352\n1    2010/01/08         0.000352\n2    2010/01/15         0.000356\n3    2010/01/22         0.000361\n4    2010/01/29         0.000365\n..          ...              ...\n674  2022/12/02         0.000422\n675  2022/12/09         0.000429\n676  2022/12/16         0.000443\n677  2022/12/23         0.000457\n678  2022/12/30         0.000464\n\n[679 rows x 2 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>日期_Date</th>\n      <th>周无风险收益率_WkRFRet</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2010/01/01</td>\n      <td>0.000352</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2010/01/08</td>\n      <td>0.000352</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2010/01/15</td>\n      <td>0.000356</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2010/01/22</td>\n      <td>0.000361</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2010/01/29</td>\n      <td>0.000365</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>674</th>\n      <td>2022/12/02</td>\n      <td>0.000422</td>\n    </tr>\n    <tr>\n      <th>675</th>\n      <td>2022/12/09</td>\n      <td>0.000429</td>\n    </tr>\n    <tr>\n      <th>676</th>\n      <td>2022/12/16</td>\n      <td>0.000443</td>\n    </tr>\n    <tr>\n      <th>677</th>\n      <td>2022/12/23</td>\n      <td>0.000457</td>\n    </tr>\n    <tr>\n      <th>678</th>\n      <td>2022/12/30</td>\n      <td>0.000464</td>\n    </tr>\n  </tbody>\n</table>\n<p>679 rows × 2 columns</p>\n</div>"
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf=pd.read_csv('rfreturn.csv',encoding='utf-8',usecols=[0,2])\n",
    "rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "d6cdf89f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "          date  rfreturn\n0   2010-01-01  0.000352\n1   2010-01-08  0.000352\n2   2010-01-15  0.000356\n3   2010-01-22  0.000361\n4   2010-01-29  0.000365\n..         ...       ...\n674 2022-12-02  0.000422\n675 2022-12-09  0.000429\n676 2022-12-16  0.000443\n677 2022-12-23  0.000457\n678 2022-12-30  0.000464\n\n[679 rows x 2 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>date</th>\n      <th>rfreturn</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2010-01-01</td>\n      <td>0.000352</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2010-01-08</td>\n      <td>0.000352</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2010-01-15</td>\n      <td>0.000356</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2010-01-22</td>\n      <td>0.000361</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2010-01-29</td>\n      <td>0.000365</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>674</th>\n      <td>2022-12-02</td>\n      <td>0.000422</td>\n    </tr>\n    <tr>\n      <th>675</th>\n      <td>2022-12-09</td>\n      <td>0.000429</td>\n    </tr>\n    <tr>\n      <th>676</th>\n      <td>2022-12-16</td>\n      <td>0.000443</td>\n    </tr>\n    <tr>\n      <th>677</th>\n      <td>2022-12-23</td>\n      <td>0.000457</td>\n    </tr>\n    <tr>\n      <th>678</th>\n      <td>2022-12-30</td>\n      <td>0.000464</td>\n    </tr>\n  </tbody>\n</table>\n<p>679 rows × 2 columns</p>\n</div>"
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf.columns=['date','rfreturn']\n",
    "rf['date']=pd.to_datetime(rf['date'])\n",
    "rf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "eaeea2a4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "          date     mkt     smb     hml  rfreturn\n0   2010-01-08 -0.0256  0.0270 -0.0021  0.000352\n1   2010-01-15  0.0082  0.0362 -0.0087  0.000356\n2   2010-01-22 -0.0302  0.0068 -0.0137  0.000361\n3   2010-01-29 -0.0449  0.0040 -0.0178  0.000365\n4   2010-02-05 -0.0173  0.0193  0.0024  0.000367\n..         ...     ...     ...     ...       ...\n626 2022-12-02  0.0174  0.0125 -0.0153  0.000422\n627 2022-12-09  0.0178 -0.0163 -0.0080  0.000429\n628 2022-12-16 -0.0107 -0.0030 -0.0019  0.000443\n629 2022-12-23 -0.0364 -0.0118 -0.0014  0.000457\n630 2022-12-30  0.0125  0.0051 -0.0066  0.000464\n\n[631 rows x 5 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>date</th>\n      <th>mkt</th>\n      <th>smb</th>\n      <th>hml</th>\n      <th>rfreturn</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2010-01-08</td>\n      <td>-0.0256</td>\n      <td>0.0270</td>\n      <td>-0.0021</td>\n      <td>0.000352</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2010-01-15</td>\n      <td>0.0082</td>\n      <td>0.0362</td>\n      <td>-0.0087</td>\n      <td>0.000356</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2010-01-22</td>\n      <td>-0.0302</td>\n      <td>0.0068</td>\n      <td>-0.0137</td>\n      <td>0.000361</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2010-01-29</td>\n      <td>-0.0449</td>\n      <td>0.0040</td>\n      <td>-0.0178</td>\n      <td>0.000365</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2010-02-05</td>\n      <td>-0.0173</td>\n      <td>0.0193</td>\n      <td>0.0024</td>\n      <td>0.000367</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>626</th>\n      <td>2022-12-02</td>\n      <td>0.0174</td>\n      <td>0.0125</td>\n      <td>-0.0153</td>\n      <td>0.000422</td>\n    </tr>\n    <tr>\n      <th>627</th>\n      <td>2022-12-09</td>\n      <td>0.0178</td>\n      <td>-0.0163</td>\n      <td>-0.0080</td>\n      <td>0.000429</td>\n    </tr>\n    <tr>\n      <th>628</th>\n      <td>2022-12-16</td>\n      <td>-0.0107</td>\n      <td>-0.0030</td>\n      <td>-0.0019</td>\n      <td>0.000443</td>\n    </tr>\n    <tr>\n      <th>629</th>\n      <td>2022-12-23</td>\n      <td>-0.0364</td>\n      <td>-0.0118</td>\n      <td>-0.0014</td>\n      <td>0.000457</td>\n    </tr>\n    <tr>\n      <th>630</th>\n      <td>2022-12-30</td>\n      <td>0.0125</td>\n      <td>0.0051</td>\n      <td>-0.0066</td>\n      <td>0.000464</td>\n    </tr>\n  </tbody>\n</table>\n<p>631 rows × 5 columns</p>\n</div>"
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_factors = pd.read_csv('FFF3factors.csv', encoding='utf-8', usecols=[2, 6, 7, 8])##全部是总市值加权\n",
    "data_factors.columns = ['date', 'mkt', 'smb', 'hml']\n",
    "data_factors['date']=pd.to_datetime(data_factors['date'])\n",
    "data_factors\n",
    "data_matrix=pd.merge(left=data_factors,right=rf,on='date',how='inner')\n",
    "data_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "877f79a5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "          date     mkt     smb     hml  rfreturn  return32\n0   2010-01-08 -0.0256  0.0270 -0.0021  0.000352   -0.0137\n1   2010-01-15  0.0082  0.0362 -0.0087  0.000356   -0.0246\n2   2010-01-22 -0.0302  0.0068 -0.0137  0.000361   -0.0682\n3   2010-01-29 -0.0449  0.0040 -0.0178  0.000365   -0.0489\n4   2010-02-05 -0.0173  0.0193  0.0024  0.000367   -0.0313\n..         ...     ...     ...     ...       ...       ...\n626 2022-12-02  0.0174  0.0125 -0.0153  0.000422   -0.0100\n627 2022-12-09  0.0178 -0.0163 -0.0080  0.000429   -0.0068\n628 2022-12-16 -0.0107 -0.0030 -0.0019  0.000443   -0.0216\n629 2022-12-23 -0.0364 -0.0118 -0.0014  0.000457   -0.0488\n630 2022-12-30  0.0125  0.0051 -0.0066  0.000464    0.0023\n\n[631 rows x 6 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>date</th>\n      <th>mkt</th>\n      <th>smb</th>\n      <th>hml</th>\n      <th>rfreturn</th>\n      <th>return32</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2010-01-08</td>\n      <td>-0.0256</td>\n      <td>0.0270</td>\n      <td>-0.0021</td>\n      <td>0.000352</td>\n      <td>-0.0137</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2010-01-15</td>\n      <td>0.0082</td>\n      <td>0.0362</td>\n      <td>-0.0087</td>\n      <td>0.000356</td>\n      <td>-0.0246</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2010-01-22</td>\n      <td>-0.0302</td>\n      <td>0.0068</td>\n      <td>-0.0137</td>\n      <td>0.000361</td>\n      <td>-0.0682</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2010-01-29</td>\n      <td>-0.0449</td>\n      <td>0.0040</td>\n      <td>-0.0178</td>\n      <td>0.000365</td>\n      <td>-0.0489</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2010-02-05</td>\n      <td>-0.0173</td>\n      <td>0.0193</td>\n      <td>0.0024</td>\n      <td>0.000367</td>\n      <td>-0.0313</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>626</th>\n      <td>2022-12-02</td>\n      <td>0.0174</td>\n      <td>0.0125</td>\n      <td>-0.0153</td>\n      <td>0.000422</td>\n      <td>-0.0100</td>\n    </tr>\n    <tr>\n      <th>627</th>\n      <td>2022-12-09</td>\n      <td>0.0178</td>\n      <td>-0.0163</td>\n      <td>-0.0080</td>\n      <td>0.000429</td>\n      <td>-0.0068</td>\n    </tr>\n    <tr>\n      <th>628</th>\n      <td>2022-12-16</td>\n      <td>-0.0107</td>\n      <td>-0.0030</td>\n      <td>-0.0019</td>\n      <td>0.000443</td>\n      <td>-0.0216</td>\n    </tr>\n    <tr>\n      <th>629</th>\n      <td>2022-12-23</td>\n      <td>-0.0364</td>\n      <td>-0.0118</td>\n      <td>-0.0014</td>\n      <td>0.000457</td>\n      <td>-0.0488</td>\n    </tr>\n    <tr>\n      <th>630</th>\n      <td>2022-12-30</td>\n      <td>0.0125</td>\n      <td>0.0051</td>\n      <td>-0.0066</td>\n      <td>0.000464</td>\n      <td>0.0023</td>\n    </tr>\n  </tbody>\n</table>\n<p>631 rows × 6 columns</p>\n</div>"
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_matrix=pd.merge(left=data_matrix,right=index32[['date','return32']],on='date',how='inner')\n",
    "data_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "e2fcd7bd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "          date     mkt     smb     hml  rfreturn  return32  return33  \\\n0   2010-01-08 -0.0256  0.0270 -0.0021  0.000352   -0.0137   -0.0190   \n1   2010-01-15  0.0082  0.0362 -0.0087  0.000356   -0.0246    0.0016   \n2   2010-01-22 -0.0302  0.0068 -0.0137  0.000361   -0.0682   -0.0672   \n3   2010-01-29 -0.0449  0.0040 -0.0178  0.000365   -0.0489   -0.0556   \n4   2010-02-05 -0.0173  0.0193  0.0024  0.000367   -0.0313   -0.0318   \n..         ...     ...     ...     ...       ...       ...       ...   \n626 2022-12-02  0.0174  0.0125 -0.0153  0.000422   -0.0100    0.0108   \n627 2022-12-09  0.0178 -0.0163 -0.0080  0.000429   -0.0068    0.0376   \n628 2022-12-16 -0.0107 -0.0030 -0.0019  0.000443   -0.0216   -0.0305   \n629 2022-12-23 -0.0364 -0.0118 -0.0014  0.000457   -0.0488   -0.0441   \n630 2022-12-30  0.0125  0.0051 -0.0066  0.000464    0.0023    0.0121   \n\n     return34  return35  return38  return40  return41  \n0     -0.0089   -0.0317   -0.0378   -0.0002   -0.0152  \n1      0.0385    0.0548   -0.0329    0.0925    0.0205  \n2     -0.0274   -0.0227   -0.0003   -0.0636   -0.0218  \n3     -0.0472   -0.0441   -0.0696   -0.0230   -0.0436  \n4     -0.0242   -0.0154   -0.0003   -0.0700   -0.0054  \n..        ...       ...       ...       ...       ...  \n626    0.0083    0.0488    0.0144    0.0510   -0.0073  \n627    0.0050    0.0284    0.0394   -0.0145   -0.0291  \n628   -0.0244   -0.0067   -0.0087   -0.0220   -0.0112  \n629   -0.0516   -0.0290   -0.0253   -0.0223   -0.0402  \n630    0.0226    0.0004    0.0177    0.0148    0.0526  \n\n[631 rows x 12 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>date</th>\n      <th>mkt</th>\n      <th>smb</th>\n      <th>hml</th>\n      <th>rfreturn</th>\n      <th>return32</th>\n      <th>return33</th>\n      <th>return34</th>\n      <th>return35</th>\n      <th>return38</th>\n      <th>return40</th>\n      <th>return41</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2010-01-08</td>\n      <td>-0.0256</td>\n      <td>0.0270</td>\n      <td>-0.0021</td>\n      <td>0.000352</td>\n      <td>-0.0137</td>\n      <td>-0.0190</td>\n      <td>-0.0089</td>\n      <td>-0.0317</td>\n      <td>-0.0378</td>\n      <td>-0.0002</td>\n      <td>-0.0152</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2010-01-15</td>\n      <td>0.0082</td>\n      <td>0.0362</td>\n      <td>-0.0087</td>\n      <td>0.000356</td>\n      <td>-0.0246</td>\n      <td>0.0016</td>\n      <td>0.0385</td>\n      <td>0.0548</td>\n      <td>-0.0329</td>\n      <td>0.0925</td>\n      <td>0.0205</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2010-01-22</td>\n      <td>-0.0302</td>\n      <td>0.0068</td>\n      <td>-0.0137</td>\n      <td>0.000361</td>\n      <td>-0.0682</td>\n      <td>-0.0672</td>\n      <td>-0.0274</td>\n      <td>-0.0227</td>\n      <td>-0.0003</td>\n      <td>-0.0636</td>\n      <td>-0.0218</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2010-01-29</td>\n      <td>-0.0449</td>\n      <td>0.0040</td>\n      <td>-0.0178</td>\n      <td>0.000365</td>\n      <td>-0.0489</td>\n      <td>-0.0556</td>\n      <td>-0.0472</td>\n      <td>-0.0441</td>\n      <td>-0.0696</td>\n      <td>-0.0230</td>\n      <td>-0.0436</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2010-02-05</td>\n      <td>-0.0173</td>\n      <td>0.0193</td>\n      <td>0.0024</td>\n      <td>0.000367</td>\n      <td>-0.0313</td>\n      <td>-0.0318</td>\n      <td>-0.0242</td>\n      <td>-0.0154</td>\n      <td>-0.0003</td>\n      <td>-0.0700</td>\n      <td>-0.0054</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>626</th>\n      <td>2022-12-02</td>\n      <td>0.0174</td>\n      <td>0.0125</td>\n      <td>-0.0153</td>\n      <td>0.000422</td>\n      <td>-0.0100</td>\n      <td>0.0108</td>\n      <td>0.0083</td>\n      <td>0.0488</td>\n      <td>0.0144</td>\n      <td>0.0510</td>\n      <td>-0.0073</td>\n    </tr>\n    <tr>\n      <th>627</th>\n      <td>2022-12-09</td>\n      <td>0.0178</td>\n      <td>-0.0163</td>\n      <td>-0.0080</td>\n      <td>0.000429</td>\n      <td>-0.0068</td>\n      <td>0.0376</td>\n      <td>0.0050</td>\n      <td>0.0284</td>\n      <td>0.0394</td>\n      <td>-0.0145</td>\n      <td>-0.0291</td>\n    </tr>\n    <tr>\n      <th>628</th>\n      <td>2022-12-16</td>\n      <td>-0.0107</td>\n      <td>-0.0030</td>\n      <td>-0.0019</td>\n      <td>0.000443</td>\n      <td>-0.0216</td>\n      <td>-0.0305</td>\n      <td>-0.0244</td>\n      <td>-0.0067</td>\n      <td>-0.0087</td>\n      <td>-0.0220</td>\n      <td>-0.0112</td>\n    </tr>\n    <tr>\n      <th>629</th>\n      <td>2022-12-23</td>\n      <td>-0.0364</td>\n      <td>-0.0118</td>\n      <td>-0.0014</td>\n      <td>0.000457</td>\n      <td>-0.0488</td>\n      <td>-0.0441</td>\n      <td>-0.0516</td>\n      <td>-0.0290</td>\n      <td>-0.0253</td>\n      <td>-0.0223</td>\n      <td>-0.0402</td>\n    </tr>\n    <tr>\n      <th>630</th>\n      <td>2022-12-30</td>\n      <td>0.0125</td>\n      <td>0.0051</td>\n      <td>-0.0066</td>\n      <td>0.000464</td>\n      <td>0.0023</td>\n      <td>0.0121</td>\n      <td>0.0226</td>\n      <td>0.0004</td>\n      <td>0.0177</td>\n      <td>0.0148</td>\n      <td>0.0526</td>\n    </tr>\n  </tbody>\n</table>\n<p>631 rows × 12 columns</p>\n</div>"
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_matrix=pd.merge(left=data_matrix,right=index33[['date','return33']],on='date',how='inner')\n",
    "data_matrix=pd.merge(left=data_matrix,right=index34[['date','return34']],on='date',how='inner')\n",
    "data_matrix=pd.merge(left=data_matrix,right=index35[['date','return35']],on='date',how='inner')\n",
    "data_matrix=pd.merge(left=data_matrix,right=index38[['date','return38']],on='date',how='inner')\n",
    "data_matrix=pd.merge(left=data_matrix,right=index40[['date','return40']],on='date',how='inner')\n",
    "data_matrix=pd.merge(left=data_matrix,right=index41[['date','return41']],on='date',how='inner')\n",
    "data_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "ea7534ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "array([[-0.0256,  0.027 , -0.0021],\n       [ 0.0082,  0.0362, -0.0087],\n       [-0.0302,  0.0068, -0.0137],\n       ...,\n       [-0.0107, -0.003 , -0.0019],\n       [-0.0364, -0.0118, -0.0014],\n       [ 0.0125,  0.0051, -0.0066]])"
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = data_matrix.loc[:, ['mkt', 'smb', 'hml']].values\n",
    "ret_rf = data_matrix.loc[:, ['rfreturn']].values\n",
    "ret_stock = data_matrix.loc[:, ['return32']].values\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "a54afc33",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.754\n",
      "Model:                            OLS   Adj. R-squared:                  0.752\n",
      "Method:                 Least Squares   F-statistic:                     639.0\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          3.52e-190\n",
      "Time:                        17:41:34   Log-Likelihood:                 1622.8\n",
      "No. Observations:                 631   AIC:                            -3238.\n",
      "Df Residuals:                     627   BIC:                            -3220.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0006      0.001     -0.817      0.414      -0.002       0.001\n",
      "x1             1.1281      0.026     43.013      0.000       1.077       1.180\n",
      "x2             0.0830      0.040      2.063      0.040       0.004       0.162\n",
      "x3            -0.0648      0.044     -1.466      0.143      -0.152       0.022\n",
      "==============================================================================\n",
      "Omnibus:                       62.667   Durbin-Watson:                   2.078\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              150.548\n",
      "Skew:                           0.537   Prob(JB):                     2.04e-33\n",
      "Kurtosis:                       5.138   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "import statsmodels.api as sm\n",
    "X = sm.add_constant(x)##增加一列全为1的列向量，即为截距项。\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "180b333a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.754\n",
      "Model:                            OLS   Adj. R-squared:                  0.752\n",
      "Method:                 Least Squares   F-statistic:                     639.0\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          3.52e-190\n",
      "Time:                        17:43:29   Log-Likelihood:                 1622.8\n",
      "No. Observations:                 631   AIC:                            -3238.\n",
      "Df Residuals:                     627   BIC:                            -3220.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0006      0.001     -0.817      0.414      -0.002       0.001\n",
      "x1             1.1281      0.026     43.013      0.000       1.077       1.180\n",
      "x2             0.0830      0.040      2.063      0.040       0.004       0.162\n",
      "x3            -0.0648      0.044     -1.466      0.143      -0.152       0.022\n",
      "==============================================================================\n",
      "Omnibus:                       62.667   Durbin-Watson:                   2.078\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              150.548\n",
      "Skew:                           0.537   Prob(JB):                     2.04e-33\n",
      "Kurtosis:                       5.138   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return33']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "304fbab1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.797\n",
      "Model:                            OLS   Adj. R-squared:                  0.796\n",
      "Method:                 Least Squares   F-statistic:                     820.9\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          1.26e-216\n",
      "Time:                        17:48:12   Log-Likelihood:                 1720.8\n",
      "No. Observations:                 631   AIC:                            -3434.\n",
      "Df Residuals:                     627   BIC:                            -3416.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0003      0.001     -0.469      0.640      -0.002       0.001\n",
      "x1             1.1072      0.022     49.311      0.000       1.063       1.151\n",
      "x2            -0.0461      0.034     -1.339      0.181      -0.114       0.022\n",
      "x3             0.0345      0.038      0.910      0.363      -0.040       0.109\n",
      "==============================================================================\n",
      "Omnibus:                      309.540   Durbin-Watson:                   1.953\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             5270.758\n",
      "Skew:                           1.750   Prob(JB):                         0.00\n",
      "Kurtosis:                      16.719   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return34']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "ee839b5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.816\n",
      "Model:                            OLS   Adj. R-squared:                  0.815\n",
      "Method:                 Least Squares   F-statistic:                     928.5\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          3.79e-230\n",
      "Time:                        17:49:07   Log-Likelihood:                 1779.0\n",
      "No. Observations:                 631   AIC:                            -3550.\n",
      "Df Residuals:                     627   BIC:                            -3532.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0004      0.001     -0.626      0.531      -0.001       0.001\n",
      "x1             1.0230      0.020     49.959      0.000       0.983       1.063\n",
      "x2             0.0206      0.031      0.654      0.513      -0.041       0.082\n",
      "x3            -0.4994      0.035    -14.463      0.000      -0.567      -0.432\n",
      "==============================================================================\n",
      "Omnibus:                       27.815   Durbin-Watson:                   1.946\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               57.594\n",
      "Skew:                           0.248   Prob(JB):                     3.12e-13\n",
      "Kurtosis:                       4.395   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return35']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "3b95aa15",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.799\n",
      "Model:                            OLS   Adj. R-squared:                  0.798\n",
      "Method:                 Least Squares   F-statistic:                     828.4\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          1.31e-217\n",
      "Time:                        17:51:40   Log-Likelihood:                 1757.0\n",
      "No. Observations:                 631   AIC:                            -3506.\n",
      "Df Residuals:                     627   BIC:                            -3488.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const       6.727e-05      0.001      0.112      0.911      -0.001       0.001\n",
      "x1             1.0075      0.021     47.518      0.000       0.966       1.049\n",
      "x2            -0.3149      0.033     -9.685      0.000      -0.379      -0.251\n",
      "x3             0.3760      0.036     10.518      0.000       0.306       0.446\n",
      "==============================================================================\n",
      "Omnibus:                       28.040   Durbin-Watson:                   2.030\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               77.696\n",
      "Skew:                           0.078   Prob(JB):                     1.34e-17\n",
      "Kurtosis:                       4.712   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return38']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "e9fd7f11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.681\n",
      "Model:                            OLS   Adj. R-squared:                  0.679\n",
      "Method:                 Least Squares   F-statistic:                     446.0\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          4.92e-155\n",
      "Time:                        17:52:20   Log-Likelihood:                 1477.7\n",
      "No. Observations:                 631   AIC:                            -2947.\n",
      "Df Residuals:                     627   BIC:                            -2930.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0007      0.001     -0.777      0.438      -0.003       0.001\n",
      "x1             1.0021      0.033     30.359      0.000       0.937       1.067\n",
      "x2             0.6144      0.051     12.136      0.000       0.515       0.714\n",
      "x3            -0.4269      0.056     -7.670      0.000      -0.536      -0.318\n",
      "==============================================================================\n",
      "Omnibus:                      127.986   Durbin-Watson:                   2.077\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              580.694\n",
      "Skew:                           0.838   Prob(JB):                    8.02e-127\n",
      "Kurtosis:                       7.391   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return40']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "32dc363c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            OLS Regression Results                            \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   R-squared:                       0.651\n",
      "Model:                            OLS   Adj. R-squared:                  0.649\n",
      "Method:                 Least Squares   F-statistic:                     390.0\n",
      "Date:                Tue, 18 Apr 2023   Prob (F-statistic):          7.28e-143\n",
      "Time:                        17:57:13   Log-Likelihood:                 1650.5\n",
      "No. Observations:                 631   AIC:                            -3293.\n",
      "Df Residuals:                     627   BIC:                            -3275.\n",
      "Df Model:                           3                                         \n",
      "Covariance Type:            nonrobust                                         \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "const         -0.0007      0.001     -0.937      0.349      -0.002       0.001\n",
      "x1             0.7993      0.025     31.844      0.000       0.750       0.849\n",
      "x2             0.2669      0.038      6.932      0.000       0.191       0.342\n",
      "x3             0.3009      0.042      7.108      0.000       0.218       0.384\n",
      "==============================================================================\n",
      "Omnibus:                       89.501   Durbin-Watson:                   1.856\n",
      "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              532.758\n",
      "Skew:                           0.447   Prob(JB):                    2.06e-116\n",
      "Kurtosis:                       7.412   Cond. No.                         66.4\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "ret_stock = data_matrix.loc[:, ['return41']].values\n",
    "Y = ret_stock - ret_rf\n",
    "model = sm.OLS(Y, X)\n",
    "results = model.fit()\n",
    "print(results.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "cd55852e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "array([-1.09385290e-03, -6.05465781e-04, -2.97166333e-04, -3.62089810e-04,\n        6.72710287e-05, -7.23986734e-04, -6.64024956e-04])"
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "T = len(Y)##数据项数\n",
    "N = len(indexcode)\n",
    "K = 3\n",
    "y = data_matrix.iloc[:, 5:].values - data_matrix.loc[:, ['rfreturn']].values\n",
    "x = sm.add_constant(x)\n",
    "XTX = np.dot(np.transpose(X), X)\n",
    "yTX = np.dot(np.transpose(y),X)\n",
    "AB_hat = np.dot(yTX,np.linalg.inv(XTX))\n",
    "AB_hat=np.transpose(AB_hat)\n",
    "ALPHA=AB_hat[0]\n",
    "ALPHA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "47482709",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "三因子模型的多资产检验结果\n",
      " alpha1, alpha2, alpha3, alpha4, alpha5, alpha6, alpha7,    GRS, pvalue\n",
      "-0.0011,-0.0006,-0.0003,-0.0004, 0.0001,-0.0007,-0.0007, 0.6544, 0.7108\n"
     ]
    }
   ],
   "source": [
    "from scipy.stats import f\n",
    "RESD = y - np.dot(x, AB_hat)##np.dot(x, np.transpose(AB_hat))将每个时间点上，对于每个指数根据估计出来的系数计算出值\n",
    "COV = np.dot(np.transpose(RESD), RESD)/T\n",
    "invCOV = np.linalg.inv(COV)\n",
    "\n",
    "fs = x[:, [1, 2, 3]]\n",
    "muhat = np.mean(fs, axis=0).reshape((3, 1))##这里的reshape没有到作用了，因为np.mean(fs, axis=0)本来是1行*3列了\n",
    "# a = np.array([1, 2, 3, 4, 5, 6])  reshape用例\n",
    "# b = a.reshape((2, 3))\n",
    "# print(b)\n",
    "fs = fs - np.mean(fs, axis=0)##这里是对fs中的每一行进行减的操作\n",
    "omegahat = np.dot(np.transpose(fs), fs)/T\n",
    "invOMG = np.linalg.inv(omegahat)\n",
    "xxx = np.dot(np.dot(np.transpose(muhat), invOMG), muhat)\n",
    "yyy = np.dot(np.dot(np.transpose(ALPHA), invCOV), ALPHA)\n",
    "GRS = (T-N-K)/N*(1/(1+xxx))*yyy\n",
    "pvalue = 1 - f.cdf(GRS[0][0], N, T-N-K)\n",
    "print('三因子模型的多资产检验结果')\n",
    "print('{:>7s},{:>7s},{:>7s},{:>7s},{:>7s},{:>7s},{:>7s},{:>7s},{:>7s}'.format('alpha1', 'alpha2', 'alpha3', 'alpha4', 'alpha5', 'alpha6', 'alpha7', 'GRS', 'pvalue'))\n",
    "print('{:7.4f},{:7.4f},{:7.4f},{:7.4f},{:7.4f},{:7.4f},{:7.4f},{:7.4f},{:7.4f}'.format(ALPHA[0], ALPHA[1], ALPHA[2], ALPHA[3], ALPHA[4], ALPHA[5], ALPHA[6], GRS[0][0], pvalue))"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "5ed828da",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "[{1}, {2}, {3}, {4}]"
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rows = sum([[var, f'{var}_t'] for var in ['const'] + ['reg_order']],[])\n",
    "reg_names=None\n",
    "if reg_names is None:\n",
    "        reg_names = [f'({i+1})' for i in range(4)]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "b790610c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "name": "python3",
   "language": "python",
   "display_name": "Python 3 (ipykernel)"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}