{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f12d3a3c",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd \n",
"import numpy as np\n",
"from datetime import datetime, timedelta, date\n",
"\n",
"'''\n",
"Raw factors and sector classification\n",
"'''\n",
"factors = pd.read_csv('factors.csv', index_col=None)\n",
"sector = pd.read_csv('sector.csv', index_col=None)\n",
"\n",
"'''\n",
"Market data\n",
"'''\n",
"op = pd.read_csv('./openadj.csv',index_col=0)\n",
"cp = pd.read_csv('./closeadj.csv',index_col=0) \n",
"adv = pd.read_csv('./adv.csv',index_col=0)\n",
"\n",
"adv = adv.reset_index()\n",
"op = op.reset_index()\n",
"cp = cp.reset_index()\n",
"\n",
"adv['Date'] = adv['Date'].apply(lambda x : datetime.strptime(str(x), '%Y%m%d'))\n",
"op['Date'] = op['Date'].apply(lambda x : datetime.strptime(str(x), '%Y%m%d'))\n",
"cp['Date'] = cp['Date'].apply(lambda x : datetime.strptime(str(x), '%Y%m%d'))\n",
"\n",
"adv = adv.set_index('Date')\n",
"op = op.set_index('Date')\n",
"cp = cp.set_index('Date')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "41428853",
"metadata": {},
"outputs": [
{
"data": {
   "text/plain": [
   "7    6.000000\n",
   "47 40.461538\n",
   "43 6.000000\n",
   "89 6.000000\n",
   "78 6.000000\n",
   "    ... \n",
   "65 6.000000\n",
   "81 6.000000\n",
   "32 31.230769\n",
   "27 6.000000\n",
   "44 6.000000\n",
   "Length: 100, dtype: float64"
   ]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(op.apply(lambda x : sum(x.isna()))/len(op)*100)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "02be87fc",
"metadata": {},
"outputs": [
{
"data": {
   "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>9</th>\n",
   "    <th>48</th>\n",
   "    <th>44</th>\n",
   "    <th>100</th>\n",
   "    <th>83</th>\n",
   "    <th>2</th>\n",
   "    <th>67</th>\n",
   "    <th>73</th>\n",
   "    <th>60</th>\n",
   "    <th>56</th>\n",
   "    <th>...</th>\n",
   "    <th>35</th>\n",
   "    <th>86</th>\n",
   "    <th>82</th>\n",
   "    <th>38</th>\n",
   "    <th>87</th>\n",
   "    <th>66</th>\n",
   "    <th>80</th>\n",
   "    <th>33</th>\n",
   "    <th>45</th>\n",
   "    <th>43</th>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>Date</th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   "    <th></th>\n",
   " </tr>\n",
   " </thead>\n",
   " <tbody>\n",
   " <tr>\n",
   "    <th>2011-06-28</th>\n",
   "    <td>3011131.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>6279554.0</td>\n",
   "    <td>2465377.0</td>\n",
   "    <td>7387614.0</td>\n",
   "    <td>36951890.0</td>\n",
   "    <td>60531910.0</td>\n",
   "    <td>16469940.0</td>\n",
   "    <td>10225800.0</td>\n",
   "    <td>23700900.0</td>\n",
   "    <td>...</td>\n",
   "    <td>9449860.0</td>\n",
   "    <td>15753890.0</td>\n",
   "    <td>6547555.0</td>\n",
   "    <td>64955320.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>16366510.0</td>\n",
   "    <td>9911693.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>25966750.0</td>\n",
   "    <td>12986800.0</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2011-06-29</th>\n",
   "    <td>3051924.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>6305580.0</td>\n",
   "    <td>2465377.0</td>\n",
   "    <td>7387614.0</td>\n",
   "    <td>36951890.0</td>\n",
   "    <td>60531910.0</td>\n",
   "    <td>16469940.0</td>\n",
   "    <td>10225800.0</td>\n",
   "    <td>23898430.0</td>\n",
   "    <td>...</td>\n",
   "    <td>9449860.0</td>\n",
   "    <td>15753890.0</td>\n",
   "    <td>6811846.0</td>\n",
   "    <td>64955320.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>16366510.0</td>\n",
   "    <td>9911693.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>25966750.0</td>\n",
   "    <td>12986800.0</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2011-06-30</th>\n",
   "    <td>3011131.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>6279554.0</td>\n",
   "    <td>2465377.0</td>\n",
   "    <td>7387614.0</td>\n",
   "    <td>36951890.0</td>\n",
   "    <td>59286670.0</td>\n",
   "    <td>16377320.0</td>\n",
   "    <td>10225800.0</td>\n",
   "    <td>23898430.0</td>\n",
   "    <td>...</td>\n",
   "    <td>9449860.0</td>\n",
   "    <td>14695030.0</td>\n",
   "    <td>6811846.0</td>\n",
   "    <td>64955320.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>16366510.0</td>\n",
   "    <td>9582925.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>25704030.0</td>\n",
   "    <td>12668220.0</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2011-07-01</th>\n",
   "    <td>3011131.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>6305580.0</td>\n",
   "    <td>2495445.0</td>\n",
   "    <td>7391484.0</td>\n",
   "    <td>36951890.0</td>\n",
   "    <td>59286670.0</td>\n",
   "    <td>16469940.0</td>\n",
   "    <td>10571900.0</td>\n",
   "    <td>23898430.0</td>\n",
   "    <td>...</td>\n",
   "    <td>9714047.0</td>\n",
   "    <td>15753890.0</td>\n",
   "    <td>7032208.0</td>\n",
   "    <td>65768010.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>16484780.0</td>\n",
   "    <td>9911693.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>25704030.0</td>\n",
   "    <td>12668220.0</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2011-07-04</th>\n",
   "    <td>2935905.0</td>\n",
   "    <td>NaN</td>\n",
   "    <td>6279554.0</td>\n",
   "    <td>2566692.0</td>\n",
   "    <td>7391484.0</td>\n",
   "    <td>36788640.0</td>\n",
   "    <td>59286670.0</td>\n",
   "    <td>16469940.0</td>\n",
   "    <td>10225800.0</td>\n",
   "    <td>23700900.0</td>\n",
   "    <td>...</td>\n",
   "    <td>9449860.0</td>\n",
   "    <td>15753890.0</td>\n",
   "    <td>7032208.0</td>\n",
   "    <td>65768010.0</td>\n",
   "    <td>NaN</td>\n",

The Scenario &nbsp; &nbsp; You are a financial planner who is inv...

The Scenario You are a financial planner who is inv...