Remove fnlwgt and use PCA instead of TSNE

Author: rohanchopra

Chapter 6/Activity 1 - Train and predict the income of a person.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,18 +15,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = pd.read_csv(\"../data/adult-data.csv\", names=['age', 'workclass', 'fnlwgt', 'education-num',\n",
+    "data = pd.read_csv(\"data/adult-data.csv\", names=['age', 'workclass', 'education-num',\n",
     "                                                 'occupation', 'capital-gain', 'capital-loss',\n",
     "                                                 'hours-per-week', 'income'])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
@@ -52,7 +52,6 @@
        "      <th></th>\n",
        "      <th>age</th>\n",
        "      <th>workclass</th>\n",
-       "      <th>fnlwgt</th>\n",
        "      <th>education-num</th>\n",
        "      <th>occupation</th>\n",
        "      <th>capital-gain</th>\n",
@@ -66,7 +65,6 @@
        "      <th>32556</th>\n",
        "      <td>27</td>\n",
        "      <td>Private</td>\n",
-       "      <td>257302</td>\n",
        "      <td>12</td>\n",
        "      <td>Tech-support</td>\n",
        "      <td>0</td>\n",
@@ -78,7 +76,6 @@
        "      <th>32557</th>\n",
        "      <td>40</td>\n",
        "      <td>Private</td>\n",
-       "      <td>154374</td>\n",
        "      <td>9</td>\n",
        "      <td>Machine-op-inspct</td>\n",
        "      <td>0</td>\n",
@@ -90,7 +87,6 @@
        "      <th>32558</th>\n",
        "      <td>58</td>\n",
        "      <td>Private</td>\n",
-       "      <td>151910</td>\n",
        "      <td>9</td>\n",
        "      <td>Adm-clerical</td>\n",
        "      <td>0</td>\n",
@@ -102,7 +98,6 @@
        "      <th>32559</th>\n",
        "      <td>22</td>\n",
        "      <td>Private</td>\n",
-       "      <td>201490</td>\n",
        "      <td>9</td>\n",
        "      <td>Adm-clerical</td>\n",
        "      <td>0</td>\n",
@@ -114,7 +109,6 @@
        "      <th>32560</th>\n",
        "      <td>52</td>\n",
        "      <td>Self-emp-inc</td>\n",
-       "      <td>287927</td>\n",
        "      <td>9</td>\n",
        "      <td>Exec-managerial</td>\n",
        "      <td>15024</td>\n",
@@ -127,22 +121,22 @@
        "</div>"
       ],
       "text/plain": [
-       "       age      workclass  fnlwgt  education-num          occupation  \\\n",
-       "32556   27        Private  257302             12        Tech-support   \n",
-       "32557   40        Private  154374              9   Machine-op-inspct   \n",
-       "32558   58        Private  151910              9        Adm-clerical   \n",
-       "32559   22        Private  201490              9        Adm-clerical   \n",
-       "32560   52   Self-emp-inc  287927              9     Exec-managerial   \n",
+       "       age      workclass  education-num          occupation  capital-gain  \\\n",
+       "32556   27        Private             12        Tech-support             0   \n",
+       "32557   40        Private              9   Machine-op-inspct             0   \n",
+       "32558   58        Private              9        Adm-clerical             0   \n",
+       "32559   22        Private              9        Adm-clerical             0   \n",
+       "32560   52   Self-emp-inc              9     Exec-managerial         15024   \n",
        "\n",
-       "       capital-gain  capital-loss  hours-per-week  income  \n",
-       "32556             0             0              38   <=50K  \n",
-       "32557             0             0              40    >50K  \n",
-       "32558             0             0              40   <=50K  \n",
-       "32559             0             0              20   <=50K  \n",
-       "32560         15024             0              40    >50K  "
+       "       capital-loss  hours-per-week  income  \n",
+       "32556             0              38   <=50K  \n",
+       "32557             0              40    >50K  \n",
+       "32558             0              40   <=50K  \n",
+       "32559             0              20   <=50K  \n",
+       "32560             0              40    >50K  "
       ]
      },
-     "execution_count": 33,
+     "execution_count": 37,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -153,7 +147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -164,7 +158,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -175,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -185,7 +179,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -195,7 +189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -206,7 +200,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -215,14 +209,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Accuracy: 83.63%\n"
+      "Accuracy: 83.66%\n"
      ]
     }
    ],