1  {
   2   "cells": [
   3    {
   4     "cell_type": "code",
   5     "execution_count": null,
   6     "id": "89287518",
   7     "metadata": {},
   8     "outputs": [],
   9     "source": [
  10      "import datetime\n",
  11      "import pandas as pd\n",
  12      "import time\n",
  13      "import numpy as np\n",
  14      "import math"
  15     ]
  16    },
  17    {
  18     "cell_type": "code",
  19     "execution_count": null,
  20     "id": "ffc15a64",
  21     "metadata": {},
  22     "outputs": [],
  23     "source": [
  24      "name='%5ENSEI'\n",
  25      "days= 6000\n",
  26      "future_period=5\n",
  27      "input_period=60\n",
  28      "minimum_change=1.004\n",
  29      "validation_size=0.2"
  30     ]
  31    },
  32    {
  33     "cell_type": "code",
  34     "execution_count": null,
  35     "id": "51f00d62",
  36     "metadata": {
  37      "scrolled": true
  38     },
  39     "outputs": [],
  40     "source": [
  41      "t2=int(time.mktime((datetime.date.today() - datetime.timedelta(1)).timetuple())+19800)\n",
  42      "t1=int(time.mktime((datetime.date.today() - datetime.timedelta(days)).timetuple())+19800)\n",
  43      "url='https://query1.finance.yahoo.com/v7/finance/download/' \\\n",
  44      "                +name+'?period1='+str(t1)+'&period2='+str(t2)+'&interval=1d&events=history&includeAdjustedClose=true'\n",
  45      "\n",
  46      "df=  pd.read_csv(url).dropna(axis=0)\n",
  47      "df.Date=pd.to_datetime(df.Date)\n",
  48      "df.set_index('Date',inplace=True)\n",
  49      "df.drop(columns='Volume', inplace=True)"
  50     ]
  51    },
  52    {
  53     "cell_type": "code",
  54     "execution_count": null,
  55     "id": "e02a5f7e",
  56     "metadata": {},
  57     "outputs": [],
  58     "source": []
  59    },
  60    {
  61     "cell_type": "code",
  62     "execution_count": null,
  63     "id": "425b7d2b",
  64     "metadata": {},
  65     "outputs": [],
  66     "source": [
  67      "df['future']=(df['Adj Close'].shift(-future_period).div(df['Adj Close'])-1)*100"
  68     ]
  69    },
  70    {
  71     "cell_type": "code",
  72     "execution_count": null,
  73     "id": "a553a133",
  74     "metadata": {},
  75     "outputs": [],
  76     "source": [
  77      "df.iloc[:,:-1]=df.iloc[:,:-1].pct_change()"
  78     ]
  79    },
  80    {
  81     "cell_type": "code",
  82     "execution_count": null,
  83     "id": "7ee05964",
  84     "metadata": {},
  85     "outputs": [],
  86     "source": [
  87      "df.dropna(axis=0, inplace= True)"
  88     ]
  89    },
  90    {
  91     "cell_type": "code",
  92     "execution_count": null,
  93     "id": "22612f42",
  94     "metadata": {
  95      "scrolled": true
  96     },
  97     "outputs": [],
  98     "source": [
  99      "df"
 100     ]
 101    },
 102    {
 103     "cell_type": "code",
 104     "execution_count": null,
 105     "id": "bc61fea6",
 106     "metadata": {},
 107     "outputs": [],
 108     "source": [
 109      "from sklearn.preprocessing import MinMaxScaler\n",
 110      "scale=MinMaxScaler()\n",
 111      "x= df.iloc[:,:-1].values"
 112     ]
 113    },
 114    {
 115     "cell_type": "code",
 116     "execution_count": null,
 117     "id": "d4dbaed3",
 118     "metadata": {},
 119     "outputs": [],
 120     "source": [
 121      "x=[x[i:i+input_period] for i,j in enumerate(x) if len(x[i:i+input_period])==input_period]"
 122     ]
 123    },
 124    {
 125     "cell_type": "code",
 126     "execution_count": null,
 127     "id": "1a3608ba",
 128     "metadata": {},
 129     "outputs": [],
 130     "source": [
 131      "X= np.array([1])\n",
 132      "for i in x:\n",
 133      "    X=np.append(X,i)\n",
 134      "x=X[1:]\n",
 135      "del X"
 136     ]
 137    },
 138    {
 139     "cell_type": "code",
 140     "execution_count": null,
 141     "id": "04832c85",
 142     "metadata": {},
 143     "outputs": [],
 144     "source": []
 145    },
 146    {
 147     "cell_type": "code",
 148     "execution_count": null,
 149     "id": "104cc642",
 150     "metadata": {},
 151     "outputs": [],
 152     "source": [
 153      "x=x.reshape(-1,input_period, len(df.iloc[:,:-1].columns))"
 154     ]
 155    },
 156    {
 157     "cell_type": "code",
 158     "execution_count": null,
 159     "id": "db1826c7",
 160     "metadata": {},
 161     "outputs": [],
 162     "source": []
 163    },
 164    {
 165     "cell_type": "code",
 166     "execution_count": null,
 167     "id": "bbef5acc",
 168     "metadata": {},
 169     "outputs": [],
 170     "source": []
 171    },
 172    {
 173     "cell_type": "code",
 174     "execution_count": null,
 175     "id": "c40b993a",
 176     "metadata": {},
 177     "outputs": [],
 178     "source": []
 179    },
 180    {
 181     "cell_type": "code",
 182     "execution_count": null,
 183     "id": "f7bf8711",
 184     "metadata": {},
 185     "outputs": [],
 186     "source": []
 187    }
 188   ],
 189   "metadata": {
 190    "kernelspec": {
 191     "display_name": "Python 3",
 192     "language": "python",
 193     "name": "python3"
 194    },
 195    "language_info": {
 196     "codemirror_mode": {
 197      "name": "ipython",
 198      "version": 3
 199     },
 200     "file_extension": ".py",
 201     "mimetype": "text/x-python",
 202     "name": "python",
 203     "nbconvert_exporter": "python",
 204     "pygments_lexer": "ipython3",
 205     "version": "3.8.8"
 206    }
 207   },
 208   "nbformat": 4,
 209   "nbformat_minor": 5
 210  }
 211