{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "983ff4f2",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.model_selection import train_test_split\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.preprocessing import normalize\n",
"from sklearn.linear_model import LogisticRegression\n",
"#import scikitplot as skplt"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "85a3861d",
"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>Seq#</th>\n",
   "    <th>ID#</th>\n",
   "    <th>Gender</th>\n",
   "    <th>M</th>\n",
   "    <th>R</th>\n",
   "    <th>F</th>\n",
   "    <th>FirstPurch</th>\n",
   "    <th>ChildBks</th>\n",
   "    <th>YouthBks</th>\n",
   "    <th>CookBks</th>\n",
   "    <th>...</th>\n",
   "    <th>ItalCook</th>\n",
   "    <th>ItalAtlas</th>\n",
   "    <th>ItalArt</th>\n",
   "    <th>Florence</th>\n",
   "    <th>Related Purchase</th>\n",
   "    <th>Mcode</th>\n",
   "    <th>Rcode</th>\n",
   "    <th>Fcode</th>\n",
   "    <th>Yes_Florence</th>\n",
   "    <th>No_Florence</th>\n",
   " </tr>\n",
   " </thead>\n",
   " <tbody>\n",
   " <tr>\n",
   "    <th>0</th>\n",
   "    <td>1</td>\n",
   "    <td>25</td>\n",
   "    <td>1</td>\n",
   "    <td>297</td>\n",
   "    <td>14</td>\n",
   "    <td>2</td>\n",
   "    <td>22</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   "    <td>1</td>\n",
   "    <td>...</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>5</td>\n",
   "    <td>4</td>\n",
   "    <td>2</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>1</th>\n",
   "    <td>2</td>\n",
   "    <td>29</td>\n",
   "    <td>0</td>\n",
   "    <td>128</td>\n",
   "    <td>8</td>\n",
   "    <td>2</td>\n",
   "    <td>10</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>...</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>4</td>\n",
   "    <td>3</td>\n",
   "    <td>2</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>2</th>\n",
   "    <td>3</td>\n",
   "    <td>46</td>\n",
   "    <td>1</td>\n",
   "    <td>138</td>\n",
   "    <td>22</td>\n",
   "    <td>7</td>\n",
   "    <td>56</td>\n",
   "    <td>2</td>\n",
   "    <td>1</td>\n",
   "    <td>2</td>\n",
   "    <td>...</td>\n",
   "    <td>1</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>2</td>\n",
   "    <td>4</td>\n",
   "    <td>4</td>\n",
   "    <td>3</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>3</th>\n",
   "    <td>4</td>\n",
   "    <td>47</td>\n",
   "    <td>1</td>\n",
   "    <td>228</td>\n",
   "    <td>2</td>\n",
   "    <td>1</td>\n",
   "    <td>2</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>...</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>5</td>\n",
   "    <td>1</td>\n",
   "    <td>1</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   " </tr>\n",
   " <tr>\n",
   "    <th>4</th>\n",
   "    <td>5</td>\n",
   "    <td>51</td>\n",
   "    <td>1</td>\n",
   "    <td>257</td>\n",
   "    <td>10</td>\n",
   "    <td>1</td>\n",
   "    <td>10</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>...</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>0</td>\n",
   "    <td>5</td>\n",
   "    <td>3</td>\n",
   "    <td>1</td>\n",
   "    <td>0</td>\n",
   "    <td>1</td>\n",
   " </tr>\n",
   " </tbody>\n",
   "</table>\n",
   "<p>5 rows Ã— 24 columns</p>\n",
   "</div>"
   ],
   "text/plain": [
   " Seq# ID# Gender M R F FirstPurch ChildBks YouthBks CookBks \\\n",
   "0 1 25    1 297 14 2       22       0       1    1 \n",
   "1 2 29    0 128 8 2       10       0       0    0 \n",
   "2 3 46    1 138 22 7       56       2       1    2 \n",
   "3 4 47    1 228 2 1       2       0       0    0 \n",
   "4 5 51    1 257 10 1       10       0       0    0 \n",
   "\n",
   " ... ItalCook ItalAtlas ItalArt Florence Related Purchase Mcode \\\n",
   "0 ...       0       0    0       0             0    5 \n",
   "1 ...       0       0    0       0             0    4 \n",
   "2 ...       1       0    0       0             2    4 \n",
   "3 ...       0       0    0       0             0    5 \n",
   "4 ...       0       0    0       0             0    5 \n",
   "\n",
   " Rcode Fcode Yes_Florence No_Florence \n",
   "0    4    2          0          1 \n",
   "1    3    2          0          1 \n",
   "2    4    3          0          1 \n",
   "3    1    1          0          1 \n",
   "4    3    1          0          1 \n",
   "\n",
   "[5 rows x 24 columns]"
   ]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = pd.read_csv(\"CharlesBookClub.csv\")\n",
"data.head()"
]
},
{
"cell_type": "markdown",
"id": "2506e007",
"metadata": {},
"source": [
"Here we don't see any NA's existing in our data"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "23e9b00f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
   "<class 'pandas.core.frame.DataFrame'>\n",
   "RangeIndex: 4000 entries, 0 to 3999\n",
   "Data columns (total 24 columns):\n",
   " # Column          Non-Null Count Dtype\n",
   "--- ------          -------------- -----\n",
   " 0 Seq#          4000 non-null int64\n",
   " 1 ID#             4000 non-null int64\n",
   " 2 Gender          4000 non-null int64\n",
   " 3 M             4000 non-null int64\n",
   " 4 R             4000 non-null int64\n",
   " 5 F             4000 non-null int64\n",
   " 6 FirstPurch    4000 non-null int64\n",
   " 7 ChildBks       4000 non-null int64\n",
   " 8 YouthBks       4000 non-null int64\n",
   " 9 CookBks       4000 non-null int64\n",
   " 10 DoItYBks       4000 non-null int64\n",
   " 11 RefBks          4000 non-null int64\n",
   " 12 ArtBks          4000 non-null int64\n",
   " 13 GeogBks       4000 non-null int64\n",
   " 14 ItalCook       4000 non-null int64\n",
   " 15 ItalAtlas       4000 non-null int64\n",
   " 16 ItalArt       4000 non-null int64\n",
   " 17 Florence       4000 non-null int64\n",
   " 18 Related Purchase 4000 non-null int64\n",
   " 19 Mcode          4000 non-null int64\n",
   " 20 Rcode          4000 non-null int64\n",
   " 21 Fcode          4000 non-null int64\n",
   " 22 Yes_Florence    4000 non-null int64\n",
   " 23 No_Florence    4000 non-null int64\n",
   "dtypes: int64(24)\n",
   "memory usage: 750.1 KB\n"
]
}
],
"source": [
"data.info()"
]
},
{
"cell_type": "markdown",

ASSIGNMENT part 2 use Jupyter notebook 1. Partition the data into...