Quant_Code/5.课程代码/4.Stock-Prediction-Models/使用文档/Stock-Prediction-Models-master/misc/which-stock.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['../dataset/AMD.csv',\n",
       " '../dataset/FB.csv',\n",
       " '../dataset/FSV.csv',\n",
       " '../dataset/INFY.csv',\n",
       " '../dataset/KNX.csv',\n",
       " '../dataset/MONDY.csv',\n",
       " '../dataset/MTDR.csv',\n",
       " '../dataset/SINA.csv',\n",
       " '../dataset/TMUS.csv',\n",
       " '../dataset/TSLA.csv',\n",
       " '../dataset/TWTR.csv']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "directory = '../dataset/'\n",
    "ori_name = ['AMD.csv', 'FB.csv', 'FSV.csv', 'INFY.csv', 'KNX.csv',\n",
    "          'MONDY.csv', 'MTDR.csv', 'SINA.csv', 'TMUS.csv', 'TSLA.csv', 'TWTR.csv']\n",
    "stocks = [directory + s for s in ori_name]\n",
    "stocks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfs = [pd.read_csv(s)[['Date', 'Close']] for s in stocks]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Close_x</th>\n",
       "      <th>Close_y</th>\n",
       "      <th>Close_x</th>\n",
       "      <th>Close_y</th>\n",
       "      <th>Close_x</th>\n",
       "      <th>Close_y</th>\n",
       "      <th>Close_x</th>\n",
       "      <th>Close_y</th>\n",
       "      <th>Close_x</th>\n",
       "      <th>Close_y</th>\n",
       "      <th>Close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>16.270000</td>\n",
       "      <td>207.320007</td>\n",
       "      <td>78.820000</td>\n",
       "      <td>9.710</td>\n",
       "      <td>37.910000</td>\n",
       "      <td>56.889999</td>\n",
       "      <td>31.809999</td>\n",
       "      <td>84.070000</td>\n",
       "      <td>61.680000</td>\n",
       "      <td>318.869995</td>\n",
       "      <td>44.490002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>16.580000</td>\n",
       "      <td>207.229996</td>\n",
       "      <td>78.250000</td>\n",
       "      <td>9.800</td>\n",
       "      <td>36.360001</td>\n",
       "      <td>56.639999</td>\n",
       "      <td>31.670000</td>\n",
       "      <td>83.949997</td>\n",
       "      <td>61.630001</td>\n",
       "      <td>310.100006</td>\n",
       "      <td>44.259998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>16.870001</td>\n",
       "      <td>209.990005</td>\n",
       "      <td>77.940002</td>\n",
       "      <td>9.950</td>\n",
       "      <td>36.279999</td>\n",
       "      <td>57.730000</td>\n",
       "      <td>32.020000</td>\n",
       "      <td>84.870003</td>\n",
       "      <td>61.209999</td>\n",
       "      <td>322.690002</td>\n",
       "      <td>44.709999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>16.850000</td>\n",
       "      <td>209.360001</td>\n",
       "      <td>77.940002</td>\n",
       "      <td>9.840</td>\n",
       "      <td>37.500000</td>\n",
       "      <td>57.810001</td>\n",
       "      <td>31.740000</td>\n",
       "      <td>83.989998</td>\n",
       "      <td>60.520000</td>\n",
       "      <td>323.850006</td>\n",
       "      <td>43.340000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>16.709999</td>\n",
       "      <td>208.089996</td>\n",
       "      <td>78.055000</td>\n",
       "      <td>9.855</td>\n",
       "      <td>37.990002</td>\n",
       "      <td>52.380001</td>\n",
       "      <td>32.330002</td>\n",
       "      <td>82.940002</td>\n",
       "      <td>59.410000</td>\n",
       "      <td>320.230011</td>\n",
       "      <td>43.439999</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Close_x     Close_y    Close_x  Close_y    Close_x    Close_y    Close_x  \\\n",
       "0  16.270000  207.320007  78.820000    9.710  37.910000  56.889999  31.809999   \n",
       "1  16.580000  207.229996  78.250000    9.800  36.360001  56.639999  31.670000   \n",
       "2  16.870001  209.990005  77.940002    9.950  36.279999  57.730000  32.020000   \n",
       "3  16.850000  209.360001  77.940002    9.840  37.500000  57.810001  31.740000   \n",
       "4  16.709999  208.089996  78.055000    9.855  37.990002  52.380001  32.330002   \n",
       "\n",
       "     Close_y    Close_x     Close_y      Close  \n",
       "0  84.070000  61.680000  318.869995  44.490002  \n",
       "1  83.949997  61.630001  310.100006  44.259998  \n",
       "2  84.870003  61.209999  322.690002  44.709999  \n",
       "3  83.989998  60.520000  323.850006  43.340000  \n",
       "4  82.940002  59.410000  320.230011  43.439999  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from functools import reduce\n",
    "data = reduce(lambda left,right: pd.merge(left,right,on='Date'), dfs).iloc[:, 1:]\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "returns = data.pct_change()\n",
    "mean_daily_returns = returns.mean()\n",
    "volatilities = returns.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Close_x    0.995185\n",
       "Close_y   -0.247949\n",
       "Close_x    0.119677\n",
       "Close_y    0.190845\n",
       "Close_x   -0.175416\n",
       "Close_y   -0.170502\n",
       "Close_x   -0.626256\n",
       "Close_y   -0.450914\n",
       "Close_x    0.252493\n",
       "Close_y   -0.069273\n",
       "Close     -0.273753\n",
       "dtype: float64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_daily_returns * 252"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Close_x    12.196632\n",
       "Close_y     6.637175\n",
       "Close_x     3.677834\n",
       "Close_y     3.572859\n",
       "Close_x     7.104904\n",
       "Close_y     7.909165\n",
       "Close_x     8.121732\n",
       "Close_y     6.948244\n",
       "Close_x     3.863498\n",
       "Close_y    10.213733\n",
       "Close       8.873234\n",
       "dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "volatilities * 252"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "combine = pd.DataFrame({'returns': mean_daily_returns * 252,\n",
    "                       'volatility': volatilities * 252})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.jointplot(\"volatility\", \"returns\", data=combine, kind=\"reg\",height=7)\n",
    "\n",
    "for i in range(combine.shape[0]):\n",
    "    plt.annotate(ori_name[i].replace('.csv',''), (combine.iloc[i, 1], combine.iloc[i, 0]))\n",
    "    \n",
    "plt.text(0, -1.5, 'SELL', fontsize=25)\n",
    "plt.text(0, 1.0, 'BUY', fontsize=25)\n",
    "    \n",
    "plt.show()"
   ]
  },
  {
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}