{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split, cross_val_score\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "import matplotlib.pyplot as plt\n",
    "test_inputs = pd.read_csv('Stockdaily%changeraw.csv', delimiter=',')\n",
    "test_inputs = np.asarray(test_inputs)\n",
    "test_inputs\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[-0.00155  0.00371  0.00399 -0.00111 -0.00094]\n",
      " [-0.00449 -0.00635 -0.00175 -0.00406 -0.00468]\n",
      " [ 0.00046 -0.00246  0.00224  0.00171 -0.00046]\n",
      " ...\n",
      " [-0.00119 -0.00086 -0.0025  -0.00078  0.00025]\n",
      " [-0.00716 -0.007   -0.00817 -0.00483 -0.00177]\n",
      " [ 0.00326  0.00073  0.00436  0.00166  0.00516]]\n"
     ]
    }
   ],
   "source": [
    "X = test_inputs[:,15:20] #data \n",
    "Y = test_inputs[:,21] #target\n",
    "X=X.astype('float')\n",
    "Y=Y.astype('float')\n",
    "\n",
    "print(X)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 1 ... 0 0 1]\n"
     ]
    }
   ],
   "source": [
    "#test_inputs[test_inputs == np.round(X)]\n",
    "#print(X)\n",
    "X_d = np.array(np.round(X*1000,decimals=0))\n",
    "Y_d = np.array(np.round(Y*1000,decimals=0))\n",
    "#print(X_d)\n",
    "#print(Y_d)\n",
    "X_d=X_d.astype('int')\n",
    "Y_d=Y_d.astype('int')\n",
    "Y_d = np.array( Y_d>=0, dtype='int')\n",
    "#print(X_d)\n",
    "print(Y_d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X_d, Y_d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1510, 1132, 378)"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(X_d),len(X_train),len(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {},
   "outputs": [],
   "source": [
    "estimator = KNeighborsClassifier(n_neighbors=40)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=40, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estimator.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy is 88.1%\n"
     ]
    }
   ],
   "source": [
    "y_predicted = estimator.predict(X_test)\n",
    "accuracy = np.mean(y_test == y_predicted) *100\n",
    "print(\"The accuracy is {0:.1f}%\".format(accuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy is 89.5%\n"
     ]
    }
   ],
   "source": [
    "\n",
    "from sklearn.model_selection import cross_val_score\n",
    "scores = cross_val_score(estimator, X_d, Y_d, scoring = 'accuracy')\n",
    "average_accuracy = np.mean(scores)*100\n",
    "print(\"The accuracy is {0:.1f}%\".format(average_accuracy))"
   ]
  },
  {
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}