Bitcoin Daily Price Prediction Code.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Import libraries necessary for this dissertation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import precision_score,recall_score, confusion_matrix, classification_report,accuracy_score, f1_score\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib import style\n",
    "import datetime as dt1\n",
    "from datetime import datetime as dt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import warnings\n",
    "from matplotlib import pyplot\n",
    "#from pandas import read_csv, set_option\n",
    "from pandas import Series, datetime\n",
    "from pandas.tools.plotting import scatter_matrix, autocorrelation_plot\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.model_selection import train_test_split, KFold, cross_val_score, GridSearchCV, TimeSeriesSplit\n",
    "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, mean_squared_error\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis \n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import AdaBoostClassifier, GradientBoostingClassifier, RandomForestClassifier, ExtraTreesClassifier\n",
    "from sklearn.metrics import roc_curve, auc\n",
    "import matplotlib.pyplot as plt\n",
    "import random\n",
    "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
    "from statsmodels.tsa.arima_model import ARIMA\n",
    "from xgboost import XGBClassifier\n",
    "import seaborn as sns\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Loading Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"C:\\\\Users\\\\Sumit Ranjan\\\\Desktop\\\\pgdm\\\\semester 5\\\\new_final_data_daily.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Time', 'market capitalisation', 'mining _difficulty', 'block_size',\n",
       "       'number_of_transaction', 'hash_rate_via_BTC', 'Mempool_count',\n",
       "       'Mempool_size', 'Estimated_transaction_volume', 'Transaction_fee',\n",
       "       'Confirmed_Transaction', 'price', 'gold_price', 'google_trend'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Time'] = pd.to_datetime(df['Time'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": true
   },
   "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>Time</th>\n",
       "      <th>market capitalisation</th>\n",
       "      <th>mining _difficulty</th>\n",
       "      <th>block_size</th>\n",
       "      <th>number_of_transaction</th>\n",
       "      <th>hash_rate_via_BTC</th>\n",
       "      <th>Mempool_count</th>\n",
       "      <th>Mempool_size</th>\n",
       "      <th>Estimated_transaction_volume</th>\n",
       "      <th>Transaction_fee</th>\n",
       "      <th>Confirmed_Transaction</th>\n",
       "      <th>price</th>\n",
       "      <th>gold_price</th>\n",
       "      <th>google_trend</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2017-01-01</td>\n",
       "      <td>1.546251e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>698539.77</td>\n",
       "      <td>180502</td>\n",
       "      <td>4.710000e+16</td>\n",
       "      <td>3050.5</td>\n",
       "      <td>2571019.00</td>\n",
       "      <td>170022.22</td>\n",
       "      <td>100.32</td>\n",
       "      <td>286818</td>\n",
       "      <td>976.29</td>\n",
       "      <td>1145.90</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2017-02-01</td>\n",
       "      <td>1.598423e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>944877.64</td>\n",
       "      <td>290951</td>\n",
       "      <td>1.420000e+17</td>\n",
       "      <td>12487.5</td>\n",
       "      <td>13863326.00</td>\n",
       "      <td>170022.22</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1015.00</td>\n",
       "      <td>1145.90</td>\n",
       "      <td>12.021739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017-03-01</td>\n",
       "      <td>1.636965e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>906573.52</td>\n",
       "      <td>301664</td>\n",
       "      <td>1.420000e+17</td>\n",
       "      <td>54240.0</td>\n",
       "      <td>48447467.25</td>\n",
       "      <td>333533.01</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1021.52</td>\n",
       "      <td>1151.00</td>\n",
       "      <td>10.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2017-04-01</td>\n",
       "      <td>1.659189e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>986063.19</td>\n",
       "      <td>328642</td>\n",
       "      <td>1.580000e+17</td>\n",
       "      <td>8815.0</td>\n",
       "      <td>7978899.00</td>\n",
       "      <td>333533.01</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1079.07</td>\n",
       "      <td>1164.25</td>\n",
       "      <td>12.782609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2017-05-01</td>\n",
       "      <td>1.782475e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>984196.89</td>\n",
       "      <td>288501</td>\n",
       "      <td>1.570000e+17</td>\n",
       "      <td>2669.0</td>\n",
       "      <td>9774868.50</td>\n",
       "      <td>528064.19</td>\n",
       "      <td>114.99</td>\n",
       "      <td>288501</td>\n",
       "      <td>1046.26</td>\n",
       "      <td>1176.70</td>\n",
       "      <td>15.217391</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Time  market capitalisation  mining _difficulty  block_size  \\\n",
       "0 2017-01-01           1.546251e+10        3.180000e+11   698539.77   \n",
       "1 2017-02-01           1.598423e+10        3.180000e+11   944877.64   \n",
       "2 2017-03-01           1.636965e+10        3.180000e+11   906573.52   \n",
       "3 2017-04-01           1.659189e+10        3.180000e+11   986063.19   \n",
       "4 2017-05-01           1.782475e+10        3.180000e+11   984196.89   \n",
       "\n",
       "   number_of_transaction  hash_rate_via_BTC  Mempool_count  Mempool_size  \\\n",
       "0                 180502       4.710000e+16         3050.5    2571019.00   \n",
       "1                 290951       1.420000e+17        12487.5   13863326.00   \n",
       "2                 301664       1.420000e+17        54240.0   48447467.25   \n",
       "3                 328642       1.580000e+17         8815.0    7978899.00   \n",
       "4                 288501       1.570000e+17         2669.0    9774868.50   \n",
       "\n",
       "   Estimated_transaction_volume  Transaction_fee  Confirmed_Transaction  \\\n",
       "0                     170022.22           100.32                 286818   \n",
       "1                     170022.22           112.88                 290951   \n",
       "2                     333533.01           112.88                 290951   \n",
       "3                     333533.01           112.88                 290951   \n",
       "4                     528064.19           114.99                 288501   \n",
       "\n",
       "     price  gold_price  google_trend  \n",
       "0   976.29     1145.90      7.000000  \n",
       "1  1015.00     1145.90     12.021739  \n",
       "2  1021.52     1151.00     10.500000  \n",
       "3  1079.07     1164.25     12.782609  \n",
       "4  1046.26     1176.70     15.217391  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['gold_price']=df['gold_price'].fillna(method='ffill')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Time</th>\n",
       "      <th>market capitalisation</th>\n",
       "      <th>mining _difficulty</th>\n",
       "      <th>block_size</th>\n",
       "      <th>number_of_transaction</th>\n",
       "      <th>hash_rate_via_BTC</th>\n",
       "      <th>Mempool_count</th>\n",
       "      <th>Mempool_size</th>\n",
       "      <th>Estimated_transaction_volume</th>\n",
       "      <th>Transaction_fee</th>\n",
       "      <th>Confirmed_Transaction</th>\n",
       "      <th>price</th>\n",
       "      <th>gold_price</th>\n",
       "      <th>google_trend</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2017-01-01</td>\n",
       "      <td>1.546251e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>698539.77</td>\n",
       "      <td>180502</td>\n",
       "      <td>4.710000e+16</td>\n",
       "      <td>3050.5</td>\n",
       "      <td>2571019.00</td>\n",
       "      <td>170022.22</td>\n",
       "      <td>100.32</td>\n",
       "      <td>286818</td>\n",
       "      <td>976.29</td>\n",
       "      <td>1145.90</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2017-02-01</td>\n",
       "      <td>1.598423e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>944877.64</td>\n",
       "      <td>290951</td>\n",
       "      <td>1.420000e+17</td>\n",
       "      <td>12487.5</td>\n",
       "      <td>13863326.00</td>\n",
       "      <td>170022.22</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1015.00</td>\n",
       "      <td>1145.90</td>\n",
       "      <td>12.021739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2017-03-01</td>\n",
       "      <td>1.636965e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>906573.52</td>\n",
       "      <td>301664</td>\n",
       "      <td>1.420000e+17</td>\n",
       "      <td>54240.0</td>\n",
       "      <td>48447467.25</td>\n",
       "      <td>333533.01</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1021.52</td>\n",
       "      <td>1151.00</td>\n",
       "      <td>10.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2017-04-01</td>\n",
       "      <td>1.659189e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>986063.19</td>\n",
       "      <td>328642</td>\n",
       "      <td>1.580000e+17</td>\n",
       "      <td>8815.0</td>\n",
       "      <td>7978899.00</td>\n",
       "      <td>333533.01</td>\n",
       "      <td>112.88</td>\n",
       "      <td>290951</td>\n",
       "      <td>1079.07</td>\n",
       "      <td>1164.25</td>\n",
       "      <td>12.782609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2017-05-01</td>\n",
       "      <td>1.782475e+10</td>\n",
       "      <td>3.180000e+11</td>\n",
       "      <td>984196.89</td>\n",
       "      <td>288501</td>\n",
       "      <td>1.570000e+17</td>\n",
       "      <td>2669.0</td>\n",
       "      <td>9774868.50</td>\n",
       "      <td>528064.19</td>\n",
       "      <td>114.99</td>\n",
       "      <td>288501</td>\n",
       "      <td>1046.26</td>\n",
       "      <td>1176.70</td>\n",
       "      <td>15.217391</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Time  market capitalisation  mining _difficulty  block_size  \\\n",
       "0 2017-01-01           1.546251e+10        3.180000e+11   698539.77   \n",
       "1 2017-02-01           1.598423e+10        3.180000e+11   944877.64   \n",
       "2 2017-03-01           1.636965e+10        3.180000e+11   906573.52   \n",
       "3 2017-04-01           1.659189e+10        3.180000e+11   986063.19   \n",
       "4 2017-05-01           1.782475e+10        3.180000e+11   984196.89   \n",
       "\n",
       "   number_of_transaction  hash_rate_via_BTC  Mempool_count  Mempool_size  \\\n",
       "0                 180502       4.710000e+16         3050.5    2571019.00   \n",
       "1                 290951       1.420000e+17        12487.5   13863326.00   \n",
       "2                 301664       1.420000e+17        54240.0   48447467.25   \n",
       "3                 328642       1.580000e+17         8815.0    7978899.00   \n",
       "4                 288501       1.570000e+17         2669.0    9774868.50   \n",
       "\n",
       "   Estimated_transaction_volume  Transaction_fee  Confirmed_Transaction  \\\n",
       "0                     170022.22           100.32                 286818   \n",
       "1                     170022.22           112.88                 290951   \n",
       "2                     333533.01           112.88                 290951   \n",
       "3                     333533.01           112.88                 290951   \n",
       "4                     528064.19           114.99                 288501   \n",
       "\n",
       "     price  gold_price  google_trend  \n",
       "0   976.29     1145.90      7.000000  \n",
       "1  1015.00     1145.90     12.021739  \n",
       "2  1021.52     1151.00     10.500000  \n",
       "3  1079.07     1164.25     12.782609  \n",
       "4  1046.26     1176.70     15.217391  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>Time</th>\n",
       "      <th>market capitalisation</th>\n",
       "      <th>mining _difficulty</th>\n",
       "      <th>block_size</th>\n",
       "      <th>number_of_transaction</th>\n",
       "      <th>hash_rate_via_BTC</th>\n",
       "      <th>Mempool_count</th>\n",
       "      <th>Mempool_size</th>\n",
       "      <th>Estimated_transaction_volume</th>\n",
       "      <th>Transaction_fee</th>\n",
       "      <th>Confirmed_Transaction</th>\n",
       "      <th>price</th>\n",
       "      <th>gold_price</th>\n",
       "      <th>google_trend</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1090</th>\n",
       "      <td>2019-12-27</td>\n",
       "      <td>1.300000e+11</td>\n",
       "      <td>1.290000e+13</td>\n",
       "      <td>709355.78</td>\n",
       "      <td>322204</td>\n",
       "      <td>4.480000e+18</td>\n",
       "      <td>1853.0</td>\n",
       "      <td>569068.50</td>\n",
       "      <td>117903.83</td>\n",
       "      <td>17.12</td>\n",
       "      <td>322204</td>\n",
       "      <td>7243.86</td>\n",
       "      <td>1511.50</td>\n",
       "      <td>9.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1091</th>\n",
       "      <td>2019-12-28</td>\n",
       "      <td>1.310000e+11</td>\n",
       "      <td>1.290000e+13</td>\n",
       "      <td>625243.75</td>\n",
       "      <td>298287</td>\n",
       "      <td>4.500000e+18</td>\n",
       "      <td>3002.0</td>\n",
       "      <td>866469.00</td>\n",
       "      <td>117903.83</td>\n",
       "      <td>17.12</td>\n",
       "      <td>322204</td>\n",
       "      <td>7346.90</td>\n",
       "      <td>1511.50</td>\n",
       "      <td>8.826923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1092</th>\n",
       "      <td>2019-12-29</td>\n",
       "      <td>1.320000e+11</td>\n",
       "      <td>1.290000e+13</td>\n",
       "      <td>552962.35</td>\n",
       "      <td>279925</td>\n",
       "      <td>4.550000e+18</td>\n",
       "      <td>825.0</td>\n",
       "      <td>284464.00</td>\n",
       "      <td>51871.89</td>\n",
       "      <td>17.12</td>\n",
       "      <td>322204</td>\n",
       "      <td>7389.38</td>\n",
       "      <td>1511.50</td>\n",
       "      <td>9.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1093</th>\n",
       "      <td>2019-12-30</td>\n",
       "      <td>1.320000e+11</td>\n",
       "      <td>1.290000e+13</td>\n",
       "      <td>661408.61</td>\n",
       "      <td>324497</td>\n",
       "      <td>6.390000e+18</td>\n",
       "      <td>2041.0</td>\n",
       "      <td>656850.75</td>\n",
       "      <td>51871.89</td>\n",
       "      <td>15.90</td>\n",
       "      <td>324497</td>\n",
       "      <td>7339.95</td>\n",
       "      <td>1514.75</td>\n",
       "      <td>8.320755</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1094</th>\n",
       "      <td>2019-12-31</td>\n",
       "      <td>1.300000e+11</td>\n",
       "      <td>1.290000e+13</td>\n",
       "      <td>687147.37</td>\n",
       "      <td>293447</td>\n",
       "      <td>5.200000e+18</td>\n",
       "      <td>2847.0</td>\n",
       "      <td>1021121.50</td>\n",
       "      <td>118692.28</td>\n",
       "      <td>15.90</td>\n",
       "      <td>324497</td>\n",
       "      <td>7246.46</td>\n",
       "      <td>1514.75</td>\n",
       "      <td>8.490566</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Time  market capitalisation  mining _difficulty  block_size  \\\n",
       "1090 2019-12-27           1.300000e+11        1.290000e+13   709355.78   \n",
       "1091 2019-12-28           1.310000e+11        1.290000e+13   625243.75   \n",
       "1092 2019-12-29           1.320000e+11        1.290000e+13   552962.35   \n",
       "1093 2019-12-30           1.320000e+11        1.290000e+13   661408.61   \n",
       "1094 2019-12-31           1.300000e+11        1.290000e+13   687147.37   \n",
       "\n",
       "      number_of_transaction  hash_rate_via_BTC  Mempool_count  Mempool_size  \\\n",
       "1090                 322204       4.480000e+18         1853.0     569068.50   \n",
       "1091                 298287       4.500000e+18         3002.0     866469.00   \n",
       "1092                 279925       4.550000e+18          825.0     284464.00   \n",
       "1093                 324497       6.390000e+18         2041.0     656850.75   \n",
       "1094                 293447       5.200000e+18         2847.0    1021121.50   \n",
       "\n",
       "      Estimated_transaction_volume  Transaction_fee  Confirmed_Transaction  \\\n",
       "1090                     117903.83            17.12                 322204   \n",
       "1091                     117903.83            17.12                 322204   \n",
       "1092                      51871.89            17.12                 322204   \n",
       "1093                      51871.89            15.90                 324497   \n",
       "1094                     118692.28            15.90                 324497   \n",
       "\n",
       "        price  gold_price  google_trend  \n",
       "1090  7243.86     1511.50      9.000000  \n",
       "1091  7346.90     1511.50      8.826923  \n",
       "1092  7389.38     1511.50      9.000000  \n",
       "1093  7339.95     1514.75      8.320755  \n",
       "1094  7246.46     1514.75      8.490566  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Removing NAN value from data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.dropna()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dependent Variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = np.where(df['price'].shift(-1) > df['price'],1,-1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Features included in the models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df.drop(['Time'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\data.py:323: DataConversionWarning: Data with input dtype int64, float64 were all converted to float64 by MinMaxScaler.\n",
      "  return self.partial_fit(X, y)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "X= scaler.fit_transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Splitting the data as train and test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "t=.8\n",
    "t = int(t*len(df))\n",
    "# Train dataset\n",
    "X_train = X[:t]\n",
    "y_train = y[:t]\n",
    "# Test dataset\n",
    "X_test = X[t:]\n",
    "y_test = y[t:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "scoring = 'accuracy'\n",
    "# Append the models to the models list\n",
    "models = []\n",
    "models.append(('LR' , LogisticRegression()))\n",
    "models.append(('LDA' , LinearDiscriminantAnalysis()))\n",
    "models.append(('KNN' , KNeighborsClassifier()))\n",
    "models.append(('CART' , DecisionTreeClassifier()))\n",
    "models.append(('NB' , GaussianNB()))\n",
    "models.append(('SVM' , SVC()))\n",
    "models.append(('RF' , RandomForestClassifier(n_estimators=50)))\n",
    "models.append(('XGBoost', XGBClassifier()))\n",
    "models.append(('QDA' , QuadraticDiscriminantAnalysis()))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model :LR\n",
      "Accuracy Score : 0.6484018264840182\n",
      "f1: 0.631578947368421\n",
      "Recall: 0.6534653465346535\n",
      "precision: 0.6111111111111112\n",
      "Confusion Matrix :\n",
      "Predicted  -1   1\n",
      "Actual           \n",
      "-1         76  42\n",
      " 1         35  66\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.68      0.64      0.66       118\n",
      "           1       0.61      0.65      0.63       101\n",
      "\n",
      "   micro avg       0.65      0.65      0.65       219\n",
      "   macro avg       0.65      0.65      0.65       219\n",
      "weighted avg       0.65      0.65      0.65       219\n",
      "\n",
      "Model :LDA\n",
      "Accuracy Score : 0.5981735159817352\n",
      "f1: 0.37142857142857144\n",
      "Recall: 0.25742574257425743\n",
      "precision: 0.6666666666666666\n",
      "Confusion Matrix :\n",
      "Predicted   -1   1\n",
      "Actual            \n",
      "-1         105  13\n",
      " 1          75  26\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.58      0.89      0.70       118\n",
      "           1       0.67      0.26      0.37       101\n",
      "\n",
      "   micro avg       0.60      0.60      0.60       219\n",
      "   macro avg       0.62      0.57      0.54       219\n",
      "weighted avg       0.62      0.60      0.55       219\n",
      "\n",
      "Model :KNN\n",
      "Accuracy Score : 0.4703196347031963\n",
      "f1: 0.6133333333333333\n",
      "Recall: 0.9108910891089109\n",
      "precision: 0.4623115577889447\n",
      "Confusion Matrix :\n",
      "Predicted  -1    1\n",
      "Actual            \n",
      "-1         11  107\n",
      " 1          9   92\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.55      0.09      0.16       118\n",
      "           1       0.46      0.91      0.61       101\n",
      "\n",
      "   micro avg       0.47      0.47      0.47       219\n",
      "   macro avg       0.51      0.50      0.39       219\n",
      "weighted avg       0.51      0.47      0.37       219\n",
      "\n",
      "Model :CART\n",
      "Accuracy Score : 0.5159817351598174\n",
      "f1: 0.3977272727272727\n",
      "Recall: 0.3465346534653465\n",
      "precision: 0.4666666666666667\n",
      "Confusion Matrix :\n",
      "Predicted  -1   1\n",
      "Actual           \n",
      "-1         78  40\n",
      " 1         66  35\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.54      0.66      0.60       118\n",
      "           1       0.47      0.35      0.40       101\n",
      "\n",
      "   micro avg       0.52      0.52      0.52       219\n",
      "   macro avg       0.50      0.50      0.50       219\n",
      "weighted avg       0.51      0.52      0.50       219\n",
      "\n",
      "Model :NB\n",
      "Accuracy Score : 0.5251141552511416\n",
      "f1: 0.018867924528301886\n",
      "Recall: 0.009900990099009901\n",
      "precision: 0.2\n",
      "Confusion Matrix :\n",
      "Predicted   -1   1\n",
      "Actual            \n",
      "-1         114   4\n",
      " 1         100   1\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.53      0.97      0.69       118\n",
      "           1       0.20      0.01      0.02       101\n",
      "\n",
      "   micro avg       0.53      0.53      0.53       219\n",
      "   macro avg       0.37      0.49      0.35       219\n",
      "weighted avg       0.38      0.53      0.38       219\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\svm\\base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
      "  \"avoid this warning.\", FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model :SVM\n",
      "Accuracy Score : 0.4611872146118721\n",
      "f1: 0.63125\n",
      "Recall: 1.0\n",
      "precision: 0.4611872146118721\n",
      "Confusion Matrix :\n",
      "Predicted    1\n",
      "Actual        \n",
      "-1         118\n",
      " 1         101\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.00      0.00      0.00       118\n",
      "           1       0.46      1.00      0.63       101\n",
      "\n",
      "   micro avg       0.46      0.46      0.46       219\n",
      "   macro avg       0.23      0.50      0.32       219\n",
      "weighted avg       0.21      0.46      0.29       219\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1143: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n",
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1143: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n",
      "C:\\Users\\Sumit Ranjan\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1143: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model :RF\n",
      "Accuracy Score : 0.547945205479452\n",
      "f1: 0.543778801843318\n",
      "Recall: 0.5841584158415841\n",
      "precision: 0.5086206896551724\n",
      "Confusion Matrix :\n",
      "Predicted  -1   1\n",
      "Actual           \n",
      "-1         61  57\n",
      " 1         42  59\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.59      0.52      0.55       118\n",
      "           1       0.51      0.58      0.54       101\n",
      "\n",
      "   micro avg       0.55      0.55      0.55       219\n",
      "   macro avg       0.55      0.55      0.55       219\n",
      "weighted avg       0.55      0.55      0.55       219\n",
      "\n",
      "Model :XGBoost\n",
      "Accuracy Score : 0.4748858447488584\n",
      "f1: 0.6101694915254238\n",
      "Recall: 0.8910891089108911\n",
      "precision: 0.4639175257731959\n",
      "Confusion Matrix :\n",
      "Predicted  -1    1\n",
      "Actual            \n",
      "-1         14  104\n",
      " 1         11   90\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.56      0.12      0.20       118\n",
      "           1       0.46      0.89      0.61       101\n",
      "\n",
      "   micro avg       0.47      0.47      0.47       219\n",
      "   macro avg       0.51      0.50      0.40       219\n",
      "weighted avg       0.52      0.47      0.39       219\n",
      "\n",
      "Model :QDA\n",
      "Accuracy Score : 0.4474885844748858\n",
      "f1: 0.5663082437275986\n",
      "Recall: 0.7821782178217822\n",
      "precision: 0.4438202247191011\n",
      "Confusion Matrix :\n",
      "Predicted  -1   1\n",
      "Actual           \n",
      "-1         19  99\n",
      " 1         22  79\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          -1       0.46      0.16      0.24       118\n",
      "           1       0.44      0.78      0.57       101\n",
      "\n",
      "   micro avg       0.45      0.45      0.45       219\n",
      "   macro avg       0.45      0.47      0.40       219\n",
      "weighted avg       0.45      0.45      0.39       219\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sn\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report \n",
    "results = []\n",
    "names = []\n",
    "\n",
    "\n",
    "for name, model in models:\n",
    "    clf = model\n",
    "    clf.fit(X_train, y_train)\n",
    "    y_pred = clf.predict(X_test)\n",
    "    accu_score = accuracy_score(y_test, y_pred)\n",
    "    F1_score=f1_score(y_test, y_pred)\n",
    "    Recall=recall_score(y_test, y_pred)\n",
    "    Precision=precision_score(y_test, y_pred)\n",
    "    results= pd.crosstab(y_test, y_pred, rownames=['Actual'], colnames=['Predicted'], margins=False)\n",
    "    print( \"Model :\" + name)\n",
    "    print ('Accuracy Score :',accuracy_score(y_test,y_pred))\n",
    "    print('f1'+\": \" + str(F1_score))\n",
    "    print('Recall' + \": \" + str(Recall))\n",
    "    print('precision' + \": \" + str(Precision))\n",
    "    print ('Confusion Matrix :')\n",
    "    print (results)\n",
    "    plt.show() \n",
    "    print(classification_report(y_test,y_pred))\n",
    "    \n",
    "   \n",
    "    \n",
    "   \n",
    "   \n",
    "    "
   ]
  },
  {
   "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}