{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "EX6m-JG4-1E_"
   },
   "source": [
    "To standardize a feature means to shift all of its values so that their mean = 0 and to scale them so that their variance = 1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "p3Z6ftQr_V51"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "data = pd.read_csv(\"file_pe_headers.csv\", sep =\",\")\n",
    "X = data.drop([\"Name\", \"Malware\"], axis=1).to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(X.shape)\n",
    "print(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### standarize data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Next standarize x using StandardScaler instance\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "### standarize 1-dimension data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get e_lfanew\n",
    "data1st = X[:,16].reshape(-1, 1)\n",
    "print(data1st.shape)\n",
    "print(data1st)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data1st_standardized = StandardScaler().fit_transform(data1st)\n",
    "\n",
    "print(data1st_standardized.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(data1st_standardized)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### standarize multi-dimension data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "N1fKkOaj_2Qe"
   },
   "outputs": [],
   "source": [
    "X_standardized = StandardScaler().fit_transform(X)\n",
    "\n",
    "print(X_standardized.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dE5vcO6kAJ4f",
    "outputId": "9b5eea03-73dd-4b30-e266-e275e95ca32f"
   },
   "outputs": [],
   "source": [
    "print(X_standardized)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2eB22gEeAkRt"
   },
   "source": [
    "It is important to standardize features because performance is highly sensitive to the relative scale of features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Standardizing data Udemy.ipynb",
   "provenance": []
  },
  "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": "3.8.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}