data collection

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 데이터 수집\n",
+    "데이터 : 코스피200 지수 종가/오픈/고가/저가/거래량 <br>\n",
+    "수집 출처 : investing.com\n",
+    "\n",
+    "|<center>**Data Set**</center>|<center>**Period**</center>|<center>**Number of Data**</center>|\n",
+    "|------|---|:---|\n",
+    "|Training Data|2005/01/03 ~ 2018/12/28|3464|\n",
+    "|Test Data|2019/01/02 ~ 2019/12/30|246|\n",
+    "|Validation Data|2020/01/02 ~ 2020/09/29|188|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'date'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-2-7e78e5e4da43>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtqdm\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtqdm\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mdate\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'date'"
+     ]
+    }
+   ],
+   "source": [
+    "# module\n",
+    "\n",
+    "import pandas as pd\n",
+    "from tqdm import tqdm\n",
+    "import date"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data = pd.read_csv('/Users/yangyoonji/Documents/2020_2학기/캡스톤디자인/data/train_data.csv')\n",
+    "test_data = pd.read_csv('/Users/yangyoonji/Documents/2020_2학기/캡스톤디자인/data/test_data.csv')\n",
+    "validation_data = pd.read_csv('/Users/yangyoonji/Documents/2020_2학기/캡스톤디자인/data/validation_data.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in tqdm(range(len(train_data))):\n",
+    "    train_data['date'][i] = train_data['date'][i].replace(' ','-') "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(len(train_data)):\n",
+    "    train_data['date'][i] = datetime.datetime.strptime(train_data['date'][i],\"%Y-%m-%d\").date()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_data.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "validation_data.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

+,date,close,open,high,low,vol
+0,20200102,290.35,294.19,294.57,289.96,66160000.0
+1,20200103,290.74,293.1,294.88,289.04,79770000.0
+2,20200106,288.43,287.73,289.41,287.49,69960000.0
+3,20200107,291.23,290.01,292.26,289.64,65349999.99999999
+4,20200108,289.42,288.94,291.01,287.3,124530000.0
+5,20200109,294.41,293.83,294.41,292.1,111790000.0
+6,20200110,297.06,294.8,297.17,294.17,94160000.0
+7,20200113,300.13,296.62,300.31,296.53,81680000.0
+8,20200114,301.53,302.2,303.61,300.69,92120000.0
+9,20200115,299.74,299.91,301.13,298.82,71770000.0
+10,20200116,302.78,299.93,302.91,298.95,85710000.0
+11,20200117,303.3,305.07,306.05,302.51,81540000.0
+12,20200120,305.58,304.99,307.54,304.77,78040000.0
+13,20200121,302.11,304.94,306.09,301.85,67630000.0
+14,20200122,306.08,301.79,306.52,301.16,79330000.0
+15,20200123,302.33,303.77,304.72,301.71,86910000.0
+16,20200128,292.77,294.98,296.3,291.3,130169999.99999999
+17,20200129,293.98,294.38,295.67,292.45,85730000.0
+18,20200130,288.37,293.27,294.11,287.09,101540000.0
+19,20200131,284.53,290.24,291.47,284.53,101460000.0
+20,20200203,285.05,280.17,286.24,279.78,111060000.0
+21,20200204,290.68,285.19,291.38,285.11,105450000.0
+22,20200205,292.02,293.57,294.26,290.3,102640000.0
+23,20200206,300.65,294.74,300.98,294.32,110220000.0
+24,20200207,298.21,299.59,300.05,296.01,108110000.0
+25,20200210,296.24,294.07,296.73,293.33,72220000.0
+26,20200211,299.28,297.91,301.1,297.48,78350000.0
+27,20200212,301.54,299.83,302.2,298.09,110630000.0
+28,20200213,300.93,302.79,304.43,300.48,115070000.0
+29,20200214,303.01,300.95,304.2,299.18,80530000.0
+30,20200217,302.76,302.84,304.05,300.99,84280000.0
+31,20200218,297.74,300.26,301.29,297.2,84750000.0
+32,20200219,298.33,299.68,300.38,295.53,84260000.0
+33,20200220,296.65,300.34,301.35,295.01,90010000.0
+34,20200221,292.42,292.16,295.24,291.96,100710000.0
+35,20200224,281.02,285.51,286.62,281.02,132820000.0
+36,20200225,284.24,280.48,284.63,279.77,117030000.0
+37,20200226,279.94,278.45,281.98,277.68,119550000.0
+38,20200227,277.09,279.46,281.09,276.07,110500000.0
+39,20200228,268.02,272.33,273.98,267.23,202610000.0
+40,20200302,270.37,269.59,272.6,265.7,163720000.0
+41,20200303,271.56,277.44,277.54,270.79,146720000.0
+42,20200304,278.13,270.13,278.9,270.13,208460000.0
+43,20200305,281.38,280.66,282.05,277.91,147440000.0
+44,20200306,275.1,276.74,278.31,274.0,140900000.0
+45,20200309,263.11,266.39,267.75,261.76,182670000.0
+46,20200310,264.67,261.94,265.57,260.75,173090000.0
+47,20200311,257.01,264.63,265.04,255.69,194210000.0
+48,20200312,247.62,253.93,255.49,243.76,242470000.0
+49,20200313,240.65,231.71,246.19,227.36,298900000.0
+50,20200316,232.97,245.21,245.21,232.76,175050000.0
+51,20200317,226.89,222.94,234.56,222.46,216730000.0
+52,20200318,215.83,228.63,230.04,215.81,208040000.0
+53,20200319,199.28,220.72,220.85,196.27,303560000.0
+54,20200320,213.67,204.84,214.08,200.54,269350000.0
+55,20200323,201.87,200.8,206.66,198.67,210300000.0
+56,20200324,220.34,207.65,220.34,205.41,225730000.0
+57,20200325,232.89,228.37,233.42,224.74,306110000.0
+58,20200326,229.34,231.91,236.61,229.22,290840000.0
+59,20200327,233.79,239.11,239.48,227.01,249100000.0
+60,20200330,232.45,227.05,234.7,225.09,167230000.0
+61,20200331,236.82,235.2,237.47,232.5,240440000.0
+62,20200401,226.35,234.23,237.52,226.34,228580000.0
+63,20200402,231.84,227.47,232.22,223.6,181790000.0
+64,20200403,231.7,232.48,234.45,229.23,181040000.0
+65,20200406,240.81,234.4,241.19,233.75,190740000.0
+66,20200407,244.87,245.65,247.39,240.68,224450000.0
+67,20200408,241.89,243.71,246.99,241.77,173120000.0
+68,20200409,245.61,246.13,246.46,243.11,175940000.0
+69,20200410,248.0,245.14,248.21,244.02,286110000.0
+70,20200413,243.4,246.59,246.9,243.39,195900000.0
+71,20200414,247.45,246.2,248.55,244.58,193120000.0
+72,20200416,247.1,244.99,247.87,243.61,197540000.0
+73,20200417,255.02,252.52,257.37,252.38,287360000.0
+74,20200420,252.14,253.85,255.93,251.46,211000000.0
+75,20200421,249.4,250.26,251.88,245.11,257160000.00000003
+76,20200422,251.88,246.16,252.18,244.56,184500000.0
+77,20200423,253.74,253.42,255.22,251.58,163810000.0
+78,20200424,250.28,252.47,252.86,249.19,154310000.0
+79,20200427,254.84,251.18,255.79,250.61,151360000.0
+80,20200428,256.39,255.91,257.34,253.22,172420000.0
+81,20200429,258.15,256.58,259.67,256.04,184480000.0
+82,20200504,250.6,252.44,253.7,250.34,174040000.0
+83,20200506,255.0,253.76,255.01,251.26,133280000.0
+84,20200507,254.46,253.88,256.14,253.37,114360000.0
+85,20200508,256.62,256.66,258.29,256.23,125220000.0
+86,20200511,254.95,257.67,258.87,254.59,144300000.0
+87,20200512,253.37,255.33,255.56,250.98,166800000.0
+88,20200513,255.85,250.03,255.85,249.95,141250000.0
+89,20200514,253.65,253.26,254.39,252.09,167640000.0
+90,20200515,253.79,255.34,255.49,252.02,228900000.0
+91,20200518,255.44,254.55,256.31,252.95,223000000.0
+92,20200519,261.79,261.12,262.34,259.96,253330000.0
+93,20200520,262.72,260.48,263.25,260.48,140300000.0
+94,20200521,263.74,264.52,264.85,263.07,159480000.0
+95,20200522,259.62,263.82,264.07,258.34,166030000.0
+96,20200525,262.76,260.95,262.82,259.16,125430000.0
+97,20200526,267.31,263.48,267.31,262.95,175420000.0
+98,20200527,267.64,266.71,269.17,265.86,247180000.0
+99,20200528,268.29,270.17,271.44,264.85,248930000.0
+100,20200529,268.32,266.62,269.61,265.23,269470000.0
+101,20200601,273.19,269.29,273.39,268.93,171510000.0
+102,20200602,276.08,272.65,276.47,272.22,251030000.0
+103,20200603,285.91,279.14,287.49,278.98,476500000.0
+104,20200604,286.45,291.17,292.9,284.93,364580000.0
+105,20200605,290.62,286.3,291.5,284.5,282060000.0
+106,20200608,290.77,295.41,295.68,289.71,286660000.0
+107,20200609,291.32,293.96,294.87,287.83,268570000.0
+108,20200610,291.9,291.03,292.92,289.6,229070000.0
+109,20200611,288.62,289.98,292.08,284.29,275900000.0
+110,20200612,281.78,276.97,282.54,276.05,232830000.0
+111,20200615,267.95,278.61,280.87,267.95,262440000.0
+112,20200616,282.59,275.89,282.59,274.0,247890000.0
+113,20200617,283.02,282.08,284.9,278.33,337220000.0
+114,20200618,281.91,281.74,283.39,280.02,181590000.0
+115,20200619,283.37,284.56,284.7,278.53,189130000.0
+116,20200622,281.42,281.01,283.71,280.34,139840000.0
+117,20200623,281.94,284.64,286.04,279.26,163680000.0
+118,20200624,286.7,283.71,288.3,283.3,200570000.0
+119,20200625,279.73,282.38,284.36,279.73,152980000.0
+120,20200626,283.38,283.36,284.58,280.65,169010000.0
+121,20200629,278.04,279.36,281.77,277.06,137760000.0
+122,20200630,280.09,282.55,283.98,280.09,179500000.0
+123,20200701,280.26,283.1,283.84,279.44,133800000.00000001
+124,20200702,283.86,281.3,283.89,280.71,111370000.0
+125,20200703,285.89,285.59,286.09,283.36,100220000.0
+126,20200706,290.62,286.84,291.14,286.31,128120000.0
+127,20200707,286.77,292.74,292.98,286.76,156130000.0
+128,20200708,285.97,287.2,288.41,285.18,119450000.0
+129,20200709,287.25,287.8,289.41,287.08,140610000.0
+130,20200710,285.06,287.87,288.09,283.51,136770000.0
+131,20200713,289.84,287.92,290.49,286.86,127050000.0
+132,20200714,289.63,288.42,289.63,286.89,126300000.0
+133,20200715,292.27,292.94,294.42,290.89,168350000.0
+134,20200716,289.25,292.34,292.74,288.46,129449999.99999999
+135,20200717,291.57,289.9,292.1,289.9,118640000.0
+136,20200720,290.81,292.76,292.76,289.01,161820000.0
+137,20200721,295.16,294.03,296.11,293.2,366990000.0
+138,20200722,294.04,294.71,296.14,293.39,327320000.0
+139,20200723,292.37,293.62,293.62,290.49,250980000.0
+140,20200724,290.66,289.84,292.74,289.42,216210000.0
+141,20200727,293.51,291.03,295.26,290.82,193240000.0
+142,20200728,300.13,296.53,301.34,296.38,301280000.0
+143,20200729,301.25,300.57,303.51,299.61,264440000.0
+144,20200730,301.85,303.13,304.13,301.49,191760000.0
+145,20200731,299.32,303.69,304.16,298.89,201960000.0
+146,20200803,299.46,299.57,300.33,297.57,179730000.0
+147,20200804,303.04,302.5,304.27,301.48,219870000.0
+148,20200805,306.64,303.94,306.67,302.91,210810000.0
+149,20200806,311.32,307.88,312.84,307.88,254200000.0
+150,20200807,312.57,311.99,314.11,310.0,299120000.0
+151,20200810,316.77,312.75,317.84,312.08,261180000.0
+152,20200811,321.02,317.63,322.64,317.56,297600000.0
+153,20200812,322.68,320.31,322.68,317.3,293140000.0
+154,20200813,323.33,325.84,326.22,319.66,285740000.0
+155,20200814,319.24,321.59,322.66,316.28,260399999.99999997
+156,20200818,312.84,319.57,321.69,311.2,247520000.0
+157,20200819,313.54,315.96,316.82,313.18,159930000.0
+158,20200820,301.59,310.45,312.77,301.15,249740000.0
+159,20200821,306.16,306.17,309.88,303.15,166300000.0
+160,20200824,309.33,306.86,310.27,303.39,142210000.0
+161,20200825,313.59,312.45,314.14,310.57,197820000.0
+162,20200826,314.19,313.61,315.08,309.74,193540000.0
+163,20200827,311.38,314.46,315.17,311.37,175570000.0
+164,20200828,312.24,313.86,315.95,311.06,256410000.00000003
+165,20200831,307.14,315.46,316.11,307.12,312180000.0
+166,20200901,309.81,309.08,311.15,307.63,342810000.0
+167,20200902,311.5,311.69,312.92,308.52,337040000.0
+168,20200903,316.43,314.73,317.46,314.45,342180000.0
+169,20200904,312.03,308.25,312.64,308.04,408030000.0
+170,20200907,313.67,312.08,314.44,310.93,264670000.00000003
+171,20200908,317.38,316.31,317.43,314.56,227270000.0
+172,20200909,313.77,313.54,315.9,312.9,198500000.0
+173,20200910,316.53,317.92,318.38,315.46,234270000.0
+174,20200911,316.45,315.64,316.77,313.2,165160000.0
+175,20200914,320.98,319.83,321.22,318.54,176780000.0
+176,20200915,323.36,321.82,323.57,320.54,152450000.0
+177,20200916,322.31,323.14,324.19,321.52,146880000.0
+178,20200917,318.0,321.3,322.23,316.92,178300000.0
+179,20200918,318.39,319.2,319.81,316.62,153540000.0
+180,20200921,315.89,318.13,320.86,314.78,165860000.0
+181,20200922,308.82,315.53,316.02,307.4,304360000.0
+182,20200923,309.64,311.5,311.76,303.29,208050000.0
+183,20200924,302.48,304.85,306.98,301.95,181250000.0
+184,20200925,303.57,305.38,305.55,301.93,156860000.0
+185,20200928,307.03,306.49,308.34,304.64,173180000.0
+186,20200929,309.44,310.01,311.34,308.52,138820000.0