Patient Diagnosis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ea1394d3-28b8-45c4-a15f-c9c736b90920",
   "metadata": {},
   "source": [
    "# Project - Classification\n",
    "\n",
    "For this project, I will be using the Breast Cancer Wisconsin (Diagnostic) Database to create a classifier that can help diagnose patients."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "376fad11-8187-404f-9c2a-daee4e3049ec",
   "metadata": {},
   "source": [
    "### Note: Comments at the end of the notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "108eda99-5351-457b-bdd7-375a8dd8a6f3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ".. _breast_cancer_dataset:\n",
      "\n",
      "Breast cancer wisconsin (diagnostic) dataset\n",
      "--------------------------------------------\n",
      "\n",
      "**Data Set Characteristics:**\n",
      "\n",
      "    :Number of Instances: 569\n",
      "\n",
      "    :Number of Attributes: 30 numeric, predictive attributes and the class\n",
      "\n",
      "    :Attribute Information:\n",
      "        - radius (mean of distances from center to points on the perimeter)\n",
      "        - texture (standard deviation of gray-scale values)\n",
      "        - perimeter\n",
      "        - area\n",
      "        - smoothness (local variation in radius lengths)\n",
      "        - compactness (perimeter^2 / area - 1.0)\n",
      "        - concavity (severity of concave portions of the contour)\n",
      "        - concave points (number of concave portions of the contour)\n",
      "        - symmetry\n",
      "        - fractal dimension (\"coastline approximation\" - 1)\n",
      "\n",
      "        The mean, standard error, and \"worst\" or largest (mean of the three\n",
      "        worst/largest values) of these features were computed for each image,\n",
      "        resulting in 30 features.  For instance, field 0 is Mean Radius, field\n",
      "        10 is Radius SE, field 20 is Worst Radius.\n",
      "\n",
      "        - class:\n",
      "                - WDBC-Malignant\n",
      "                - WDBC-Benign\n",
      "\n",
      "    :Summary Statistics:\n",
      "\n",
      "    ===================================== ====== ======\n",
      "                                           Min    Max\n",
      "    ===================================== ====== ======\n",
      "    radius (mean):                        6.981  28.11\n",
      "    texture (mean):                       9.71   39.28\n",
      "    perimeter (mean):                     43.79  188.5\n",
      "    area (mean):                          143.5  2501.0\n",
      "    smoothness (mean):                    0.053  0.163\n",
      "    compactness (mean):                   0.019  0.345\n",
      "    concavity (mean):                     0.0    0.427\n",
      "    concave points (mean):                0.0    0.201\n",
      "    symmetry (mean):                      0.106  0.304\n",
      "    fractal dimension (mean):             0.05   0.097\n",
      "    radius (standard error):              0.112  2.873\n",
      "    texture (standard error):             0.36   4.885\n",
      "    perimeter (standard error):           0.757  21.98\n",
      "    area (standard error):                6.802  542.2\n",
      "    smoothness (standard error):          0.002  0.031\n",
      "    compactness (standard error):         0.002  0.135\n",
      "    concavity (standard error):           0.0    0.396\n",
      "    concave points (standard error):      0.0    0.053\n",
      "    symmetry (standard error):            0.008  0.079\n",
      "    fractal dimension (standard error):   0.001  0.03\n",
      "    radius (worst):                       7.93   36.04\n",
      "    texture (worst):                      12.02  49.54\n",
      "    perimeter (worst):                    50.41  251.2\n",
      "    area (worst):                         185.2  4254.0\n",
      "    smoothness (worst):                   0.071  0.223\n",
      "    compactness (worst):                  0.027  1.058\n",
      "    concavity (worst):                    0.0    1.252\n",
      "    concave points (worst):               0.0    0.291\n",
      "    symmetry (worst):                     0.156  0.664\n",
      "    fractal dimension (worst):            0.055  0.208\n",
      "    ===================================== ====== ======\n",
      "\n",
      "    :Missing Attribute Values: None\n",
      "\n",
      "    :Class Distribution: 212 - Malignant, 357 - Benign\n",
      "\n",
      "    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n",
      "\n",
      "    :Donor: Nick Street\n",
      "\n",
      "    :Date: November, 1995\n",
      "\n",
      "This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\n",
      "https://goo.gl/U2Uwz2\n",
      "\n",
      "Features are computed from a digitized image of a fine needle\n",
      "aspirate (FNA) of a breast mass.  They describe\n",
      "characteristics of the cell nuclei present in the image.\n",
      "\n",
      "Separating plane described above was obtained using\n",
      "Multisurface Method-Tree (MSM-T) [K. P. Bennett, \"Decision Tree\n",
      "Construction Via Linear Programming.\" Proceedings of the 4th\n",
      "Midwest Artificial Intelligence and Cognitive Science Society,\n",
      "pp. 97-101, 1992], a classification method which uses linear\n",
      "programming to construct a decision tree.  Relevant features\n",
      "were selected using an exhaustive search in the space of 1-4\n",
      "features and 1-3 separating planes.\n",
      "\n",
      "The actual linear program used to obtain the separating plane\n",
      "in the 3-dimensional space is that described in:\n",
      "[K. P. Bennett and O. L. Mangasarian: \"Robust Linear\n",
      "Programming Discrimination of Two Linearly Inseparable Sets\",\n",
      "Optimization Methods and Software 1, 1992, 23-34].\n",
      "\n",
      "This database is also available through the UW CS ftp server:\n",
      "\n",
      "ftp ftp.cs.wisc.edu\n",
      "cd math-prog/cpo-dataset/machine-learn/WDBC/\n",
      "\n",
      ".. topic:: References\n",
      "\n",
      "   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n",
      "     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n",
      "     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n",
      "     San Jose, CA, 1993.\n",
      "   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n",
      "     prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n",
      "     July-August 1995.\n",
      "   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n",
      "     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n",
      "     163-171.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "\n",
    "cancer = load_breast_cancer()\n",
    "\n",
    "print(cancer.DESCR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "aedab8ee-5450-4025-a538-b378efb4974b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_zero():\n",
    "    return len(cancer['feature_names'])\n",
    "step_zero()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c23bb99f-e1d4-4a3d-bd6b-940513e5816f",
   "metadata": {},
   "source": [
    "### Step 1\n",
    "We will create a classifier with a pandas DataFrame. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cad841ea-0e74-42ae-86a7-1d0b65a83ae9",
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17.99</td>\n",
       "      <td>10.38</td>\n",
       "      <td>122.80</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>0.11840</td>\n",
       "      <td>0.27760</td>\n",
       "      <td>0.30010</td>\n",
       "      <td>0.14710</td>\n",
       "      <td>0.2419</td>\n",
       "      <td>0.07871</td>\n",
       "      <td>...</td>\n",
       "      <td>17.33</td>\n",
       "      <td>184.60</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>0.16220</td>\n",
       "      <td>0.66560</td>\n",
       "      <td>0.7119</td>\n",
       "      <td>0.2654</td>\n",
       "      <td>0.4601</td>\n",
       "      <td>0.11890</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20.57</td>\n",
       "      <td>17.77</td>\n",
       "      <td>132.90</td>\n",
       "      <td>1326.0</td>\n",
       "      <td>0.08474</td>\n",
       "      <td>0.07864</td>\n",
       "      <td>0.08690</td>\n",
       "      <td>0.07017</td>\n",
       "      <td>0.1812</td>\n",
       "      <td>0.05667</td>\n",
       "      <td>...</td>\n",
       "      <td>23.41</td>\n",
       "      <td>158.80</td>\n",
       "      <td>1956.0</td>\n",
       "      <td>0.12380</td>\n",
       "      <td>0.18660</td>\n",
       "      <td>0.2416</td>\n",
       "      <td>0.1860</td>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.08902</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.69</td>\n",
       "      <td>21.25</td>\n",
       "      <td>130.00</td>\n",
       "      <td>1203.0</td>\n",
       "      <td>0.10960</td>\n",
       "      <td>0.15990</td>\n",
       "      <td>0.19740</td>\n",
       "      <td>0.12790</td>\n",
       "      <td>0.2069</td>\n",
       "      <td>0.05999</td>\n",
       "      <td>...</td>\n",
       "      <td>25.53</td>\n",
       "      <td>152.50</td>\n",
       "      <td>1709.0</td>\n",
       "      <td>0.14440</td>\n",
       "      <td>0.42450</td>\n",
       "      <td>0.4504</td>\n",
       "      <td>0.2430</td>\n",
       "      <td>0.3613</td>\n",
       "      <td>0.08758</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.42</td>\n",
       "      <td>20.38</td>\n",
       "      <td>77.58</td>\n",
       "      <td>386.1</td>\n",
       "      <td>0.14250</td>\n",
       "      <td>0.28390</td>\n",
       "      <td>0.24140</td>\n",
       "      <td>0.10520</td>\n",
       "      <td>0.2597</td>\n",
       "      <td>0.09744</td>\n",
       "      <td>...</td>\n",
       "      <td>26.50</td>\n",
       "      <td>98.87</td>\n",
       "      <td>567.7</td>\n",
       "      <td>0.20980</td>\n",
       "      <td>0.86630</td>\n",
       "      <td>0.6869</td>\n",
       "      <td>0.2575</td>\n",
       "      <td>0.6638</td>\n",
       "      <td>0.17300</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20.29</td>\n",
       "      <td>14.34</td>\n",
       "      <td>135.10</td>\n",
       "      <td>1297.0</td>\n",
       "      <td>0.10030</td>\n",
       "      <td>0.13280</td>\n",
       "      <td>0.19800</td>\n",
       "      <td>0.10430</td>\n",
       "      <td>0.1809</td>\n",
       "      <td>0.05883</td>\n",
       "      <td>...</td>\n",
       "      <td>16.67</td>\n",
       "      <td>152.20</td>\n",
       "      <td>1575.0</td>\n",
       "      <td>0.13740</td>\n",
       "      <td>0.20500</td>\n",
       "      <td>0.4000</td>\n",
       "      <td>0.1625</td>\n",
       "      <td>0.2364</td>\n",
       "      <td>0.07678</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>564</th>\n",
       "      <td>21.56</td>\n",
       "      <td>22.39</td>\n",
       "      <td>142.00</td>\n",
       "      <td>1479.0</td>\n",
       "      <td>0.11100</td>\n",
       "      <td>0.11590</td>\n",
       "      <td>0.24390</td>\n",
       "      <td>0.13890</td>\n",
       "      <td>0.1726</td>\n",
       "      <td>0.05623</td>\n",
       "      <td>...</td>\n",
       "      <td>26.40</td>\n",
       "      <td>166.10</td>\n",
       "      <td>2027.0</td>\n",
       "      <td>0.14100</td>\n",
       "      <td>0.21130</td>\n",
       "      <td>0.4107</td>\n",
       "      <td>0.2216</td>\n",
       "      <td>0.2060</td>\n",
       "      <td>0.07115</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>565</th>\n",
       "      <td>20.13</td>\n",
       "      <td>28.25</td>\n",
       "      <td>131.20</td>\n",
       "      <td>1261.0</td>\n",
       "      <td>0.09780</td>\n",
       "      <td>0.10340</td>\n",
       "      <td>0.14400</td>\n",
       "      <td>0.09791</td>\n",
       "      <td>0.1752</td>\n",
       "      <td>0.05533</td>\n",
       "      <td>...</td>\n",
       "      <td>38.25</td>\n",
       "      <td>155.00</td>\n",
       "      <td>1731.0</td>\n",
       "      <td>0.11660</td>\n",
       "      <td>0.19220</td>\n",
       "      <td>0.3215</td>\n",
       "      <td>0.1628</td>\n",
       "      <td>0.2572</td>\n",
       "      <td>0.06637</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>16.60</td>\n",
       "      <td>28.08</td>\n",
       "      <td>108.30</td>\n",
       "      <td>858.1</td>\n",
       "      <td>0.08455</td>\n",
       "      <td>0.10230</td>\n",
       "      <td>0.09251</td>\n",
       "      <td>0.05302</td>\n",
       "      <td>0.1590</td>\n",
       "      <td>0.05648</td>\n",
       "      <td>...</td>\n",
       "      <td>34.12</td>\n",
       "      <td>126.70</td>\n",
       "      <td>1124.0</td>\n",
       "      <td>0.11390</td>\n",
       "      <td>0.30940</td>\n",
       "      <td>0.3403</td>\n",
       "      <td>0.1418</td>\n",
       "      <td>0.2218</td>\n",
       "      <td>0.07820</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>20.60</td>\n",
       "      <td>29.33</td>\n",
       "      <td>140.10</td>\n",
       "      <td>1265.0</td>\n",
       "      <td>0.11780</td>\n",
       "      <td>0.27700</td>\n",
       "      <td>0.35140</td>\n",
       "      <td>0.15200</td>\n",
       "      <td>0.2397</td>\n",
       "      <td>0.07016</td>\n",
       "      <td>...</td>\n",
       "      <td>39.42</td>\n",
       "      <td>184.60</td>\n",
       "      <td>1821.0</td>\n",
       "      <td>0.16500</td>\n",
       "      <td>0.86810</td>\n",
       "      <td>0.9387</td>\n",
       "      <td>0.2650</td>\n",
       "      <td>0.4087</td>\n",
       "      <td>0.12400</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>7.76</td>\n",
       "      <td>24.54</td>\n",
       "      <td>47.92</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.05263</td>\n",
       "      <td>0.04362</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.1587</td>\n",
       "      <td>0.05884</td>\n",
       "      <td>...</td>\n",
       "      <td>30.37</td>\n",
       "      <td>59.16</td>\n",
       "      <td>268.6</td>\n",
       "      <td>0.08996</td>\n",
       "      <td>0.06444</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.2871</td>\n",
       "      <td>0.07039</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>569 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       "0          17.99         10.38          122.80     1001.0          0.11840   \n",
       "1          20.57         17.77          132.90     1326.0          0.08474   \n",
       "2          19.69         21.25          130.00     1203.0          0.10960   \n",
       "3          11.42         20.38           77.58      386.1          0.14250   \n",
       "4          20.29         14.34          135.10     1297.0          0.10030   \n",
       "..           ...           ...             ...        ...              ...   \n",
       "564        21.56         22.39          142.00     1479.0          0.11100   \n",
       "565        20.13         28.25          131.20     1261.0          0.09780   \n",
       "566        16.60         28.08          108.30      858.1          0.08455   \n",
       "567        20.60         29.33          140.10     1265.0          0.11780   \n",
       "568         7.76         24.54           47.92      181.0          0.05263   \n",
       "\n",
       "     mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       "0             0.27760         0.30010              0.14710         0.2419   \n",
       "1             0.07864         0.08690              0.07017         0.1812   \n",
       "2             0.15990         0.19740              0.12790         0.2069   \n",
       "3             0.28390         0.24140              0.10520         0.2597   \n",
       "4             0.13280         0.19800              0.10430         0.1809   \n",
       "..                ...             ...                  ...            ...   \n",
       "564           0.11590         0.24390              0.13890         0.1726   \n",
       "565           0.10340         0.14400              0.09791         0.1752   \n",
       "566           0.10230         0.09251              0.05302         0.1590   \n",
       "567           0.27700         0.35140              0.15200         0.2397   \n",
       "568           0.04362         0.00000              0.00000         0.1587   \n",
       "\n",
       "     mean fractal dimension  ...  worst texture  worst perimeter  worst area  \\\n",
       "0                   0.07871  ...          17.33           184.60      2019.0   \n",
       "1                   0.05667  ...          23.41           158.80      1956.0   \n",
       "2                   0.05999  ...          25.53           152.50      1709.0   \n",
       "3                   0.09744  ...          26.50            98.87       567.7   \n",
       "4                   0.05883  ...          16.67           152.20      1575.0   \n",
       "..                      ...  ...            ...              ...         ...   \n",
       "564                 0.05623  ...          26.40           166.10      2027.0   \n",
       "565                 0.05533  ...          38.25           155.00      1731.0   \n",
       "566                 0.05648  ...          34.12           126.70      1124.0   \n",
       "567                 0.07016  ...          39.42           184.60      1821.0   \n",
       "568                 0.05884  ...          30.37            59.16       268.6   \n",
       "\n",
       "     worst smoothness  worst compactness  worst concavity  \\\n",
       "0             0.16220            0.66560           0.7119   \n",
       "1             0.12380            0.18660           0.2416   \n",
       "2             0.14440            0.42450           0.4504   \n",
       "3             0.20980            0.86630           0.6869   \n",
       "4             0.13740            0.20500           0.4000   \n",
       "..                ...                ...              ...   \n",
       "564           0.14100            0.21130           0.4107   \n",
       "565           0.11660            0.19220           0.3215   \n",
       "566           0.11390            0.30940           0.3403   \n",
       "567           0.16500            0.86810           0.9387   \n",
       "568           0.08996            0.06444           0.0000   \n",
       "\n",
       "     worst concave points  worst symmetry  worst fractal dimension  target  \n",
       "0                  0.2654          0.4601                  0.11890       0  \n",
       "1                  0.1860          0.2750                  0.08902       0  \n",
       "2                  0.2430          0.3613                  0.08758       0  \n",
       "3                  0.2575          0.6638                  0.17300       0  \n",
       "4                  0.1625          0.2364                  0.07678       0  \n",
       "..                    ...             ...                      ...     ...  \n",
       "564                0.2216          0.2060                  0.07115       0  \n",
       "565                0.1628          0.2572                  0.06637       0  \n",
       "566                0.1418          0.2218                  0.07820       0  \n",
       "567                0.2650          0.4087                  0.12400       0  \n",
       "568                0.0000          0.2871                  0.07039       1  \n",
       "\n",
       "[569 rows x 31 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_one():\n",
    "    \n",
    "    df=pd.DataFrame(cancer['data'], columns = cancer['feature_names'])\n",
    "    df['target']=cancer.target\n",
    "    \n",
    "    return df\n",
    "step_one()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87d616ff-fb51-4596-9a50-068555477aba",
   "metadata": {},
   "source": [
    "### Step 2\n",
    "We will now compute the class distribution (how many instances of `malignant` and how many `benign`?)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "82359282-847d-4f25-9b26-94464d9a4d39",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "malignant    212\n",
       "benign       357\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_two():\n",
    "    \n",
    "    cancerdf=step_one()\n",
    "    index= ['malignant','benign']\n",
    "    malignants= np.where(cancer['target'] == 0.0)\n",
    "    benigns= np.where(cancer['target'] == 1.0)\n",
    "    \n",
    "    data=[np.size(malignants),np.size(benigns)]\n",
    "    \n",
    "    series=pd.Series(data, index=index)\n",
    "    return series\n",
    "    \n",
    "step_two()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe0d9972-8a69-4a0d-8d1f-ac3481cc408f",
   "metadata": {},
   "source": [
    "### Step 3\n",
    "We will now split the DataFrame into `X` (the data) and `y` (the labels)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "091d3b23-999e-480f-a82c-9e1393eaf9ea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(     mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       " 0          17.99         10.38          122.80     1001.0          0.11840   \n",
       " 1          20.57         17.77          132.90     1326.0          0.08474   \n",
       " 2          19.69         21.25          130.00     1203.0          0.10960   \n",
       " 3          11.42         20.38           77.58      386.1          0.14250   \n",
       " 4          20.29         14.34          135.10     1297.0          0.10030   \n",
       " ..           ...           ...             ...        ...              ...   \n",
       " 564        21.56         22.39          142.00     1479.0          0.11100   \n",
       " 565        20.13         28.25          131.20     1261.0          0.09780   \n",
       " 566        16.60         28.08          108.30      858.1          0.08455   \n",
       " 567        20.60         29.33          140.10     1265.0          0.11780   \n",
       " 568         7.76         24.54           47.92      181.0          0.05263   \n",
       " \n",
       "      mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       " 0             0.27760         0.30010              0.14710         0.2419   \n",
       " 1             0.07864         0.08690              0.07017         0.1812   \n",
       " 2             0.15990         0.19740              0.12790         0.2069   \n",
       " 3             0.28390         0.24140              0.10520         0.2597   \n",
       " 4             0.13280         0.19800              0.10430         0.1809   \n",
       " ..                ...             ...                  ...            ...   \n",
       " 564           0.11590         0.24390              0.13890         0.1726   \n",
       " 565           0.10340         0.14400              0.09791         0.1752   \n",
       " 566           0.10230         0.09251              0.05302         0.1590   \n",
       " 567           0.27700         0.35140              0.15200         0.2397   \n",
       " 568           0.04362         0.00000              0.00000         0.1587   \n",
       " \n",
       "      mean fractal dimension  ...  worst radius  worst texture  \\\n",
       " 0                   0.07871  ...        25.380          17.33   \n",
       " 1                   0.05667  ...        24.990          23.41   \n",
       " 2                   0.05999  ...        23.570          25.53   \n",
       " 3                   0.09744  ...        14.910          26.50   \n",
       " 4                   0.05883  ...        22.540          16.67   \n",
       " ..                      ...  ...           ...            ...   \n",
       " 564                 0.05623  ...        25.450          26.40   \n",
       " 565                 0.05533  ...        23.690          38.25   \n",
       " 566                 0.05648  ...        18.980          34.12   \n",
       " 567                 0.07016  ...        25.740          39.42   \n",
       " 568                 0.05884  ...         9.456          30.37   \n",
       " \n",
       "      worst perimeter  worst area  worst smoothness  worst compactness  \\\n",
       " 0             184.60      2019.0           0.16220            0.66560   \n",
       " 1             158.80      1956.0           0.12380            0.18660   \n",
       " 2             152.50      1709.0           0.14440            0.42450   \n",
       " 3              98.87       567.7           0.20980            0.86630   \n",
       " 4             152.20      1575.0           0.13740            0.20500   \n",
       " ..               ...         ...               ...                ...   \n",
       " 564           166.10      2027.0           0.14100            0.21130   \n",
       " 565           155.00      1731.0           0.11660            0.19220   \n",
       " 566           126.70      1124.0           0.11390            0.30940   \n",
       " 567           184.60      1821.0           0.16500            0.86810   \n",
       " 568            59.16       268.6           0.08996            0.06444   \n",
       " \n",
       "      worst concavity  worst concave points  worst symmetry  \\\n",
       " 0             0.7119                0.2654          0.4601   \n",
       " 1             0.2416                0.1860          0.2750   \n",
       " 2             0.4504                0.2430          0.3613   \n",
       " 3             0.6869                0.2575          0.6638   \n",
       " 4             0.4000                0.1625          0.2364   \n",
       " ..               ...                   ...             ...   \n",
       " 564           0.4107                0.2216          0.2060   \n",
       " 565           0.3215                0.1628          0.2572   \n",
       " 566           0.3403                0.1418          0.2218   \n",
       " 567           0.9387                0.2650          0.4087   \n",
       " 568           0.0000                0.0000          0.2871   \n",
       " \n",
       "      worst fractal dimension  \n",
       " 0                    0.11890  \n",
       " 1                    0.08902  \n",
       " 2                    0.08758  \n",
       " 3                    0.17300  \n",
       " 4                    0.07678  \n",
       " ..                       ...  \n",
       " 564                  0.07115  \n",
       " 565                  0.06637  \n",
       " 566                  0.07820  \n",
       " 567                  0.12400  \n",
       " 568                  0.07039  \n",
       " \n",
       " [569 rows x 30 columns],\n",
       " 0      0\n",
       " 1      0\n",
       " 2      0\n",
       " 3      0\n",
       " 4      0\n",
       "       ..\n",
       " 564    0\n",
       " 565    0\n",
       " 566    0\n",
       " 567    0\n",
       " 568    1\n",
       " Name: target, Length: 569, dtype: int64)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_three():\n",
    "    \n",
    "    _df= step_one()\n",
    "    \n",
    "    X = _df.iloc[:,:-1]\n",
    "    y = _df.iloc[:,-1]\n",
    "    return (X,y)\n",
    "\n",
    "step_three()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8b324e19-7316-46d3-877d-a2d2915cf038",
   "metadata": {},
   "source": [
    "### Step 4\n",
    "We will now use `train_test_split`, split `X` and `y` into training and test sets `(X_train, X_test, y_train, and y_test)`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ee1a5dbd-c6cb-4441-acee-7124297fdc89",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(     mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       " 293       11.850         17.46           75.54      432.7          0.08372   \n",
       " 332       11.220         19.86           71.94      387.3          0.10540   \n",
       " 565       20.130         28.25          131.20     1261.0          0.09780   \n",
       " 278       13.590         17.84           86.24      572.3          0.07948   \n",
       " 489       16.690         20.20          107.10      857.6          0.07497   \n",
       " ..           ...           ...             ...        ...              ...   \n",
       " 277       18.810         19.98          120.90     1102.0          0.08923   \n",
       " 9         12.460         24.04           83.97      475.9          0.11860   \n",
       " 359        9.436         18.32           59.82      278.6          0.10090   \n",
       " 192        9.720         18.22           60.73      288.1          0.06950   \n",
       " 559       11.510         23.93           74.52      403.5          0.09261   \n",
       " \n",
       "      mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       " 293           0.05642        0.026880             0.022800         0.1875   \n",
       " 332           0.06779        0.005006             0.007583         0.1940   \n",
       " 565           0.10340        0.144000             0.097910         0.1752   \n",
       " 278           0.04052        0.019970             0.012380         0.1573   \n",
       " 489           0.07112        0.036490             0.023070         0.1846   \n",
       " ..                ...             ...                  ...            ...   \n",
       " 277           0.05884        0.080200             0.058430         0.1550   \n",
       " 9             0.23960        0.227300             0.085430         0.2030   \n",
       " 359           0.05956        0.027100             0.014060         0.1506   \n",
       " 192           0.02344        0.000000             0.000000         0.1653   \n",
       " 559           0.10210        0.111200             0.041050         0.1388   \n",
       " \n",
       "      mean fractal dimension  ...  worst radius  worst texture  \\\n",
       " 293                 0.05715  ...        13.060          25.75   \n",
       " 332                 0.06028  ...        11.980          25.78   \n",
       " 565                 0.05533  ...        23.690          38.25   \n",
       " 278                 0.05520  ...        15.500          26.10   \n",
       " 489                 0.05325  ...        19.180          26.56   \n",
       " ..                      ...  ...           ...            ...   \n",
       " 277                 0.04996  ...        19.960          24.30   \n",
       " 9                   0.08243  ...        15.090          40.68   \n",
       " 359                 0.06959  ...        12.020          25.02   \n",
       " 192                 0.06447  ...         9.968          20.83   \n",
       " 559                 0.06570  ...        12.480          37.16   \n",
       " \n",
       "      worst perimeter  worst area  worst smoothness  worst compactness  \\\n",
       " 293            84.35       517.8           0.13690            0.17580   \n",
       " 332            76.91       436.1           0.14240            0.09669   \n",
       " 565           155.00      1731.0           0.11660            0.19220   \n",
       " 278            98.91       739.1           0.10500            0.07622   \n",
       " 489           127.30      1084.0           0.10090            0.29200   \n",
       " ..               ...         ...               ...                ...   \n",
       " 277           129.00      1236.0           0.12430            0.11600   \n",
       " 9              97.65       711.4           0.18530            1.05800   \n",
       " 359            75.79       439.6           0.13330            0.10490   \n",
       " 192            62.25       303.8           0.07117            0.02729   \n",
       " 559            82.28       474.2           0.12980            0.25170   \n",
       " \n",
       "      worst concavity  worst concave points  worst symmetry  \\\n",
       " 293          0.13160               0.09140          0.3101   \n",
       " 332          0.01335               0.02022          0.3292   \n",
       " 565          0.32150               0.16280          0.2572   \n",
       " 278          0.10600               0.05185          0.2335   \n",
       " 489          0.24770               0.08737          0.4677   \n",
       " ..               ...                   ...             ...   \n",
       " 277          0.22100               0.12940          0.2567   \n",
       " 9            1.10500               0.22100          0.4366   \n",
       " 359          0.11440               0.05052          0.2454   \n",
       " 192          0.00000               0.00000          0.1909   \n",
       " 559          0.36300               0.09653          0.2112   \n",
       " \n",
       "      worst fractal dimension  \n",
       " 293                  0.07007  \n",
       " 332                  0.06522  \n",
       " 565                  0.06637  \n",
       " 278                  0.06263  \n",
       " 489                  0.07623  \n",
       " ..                       ...  \n",
       " 277                  0.05737  \n",
       " 9                    0.20750  \n",
       " 359                  0.08136  \n",
       " 192                  0.06559  \n",
       " 559                  0.08732  \n",
       " \n",
       " [426 rows x 30 columns],\n",
       "      mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       " 512        13.40         20.52           88.64      556.7          0.11060   \n",
       " 457        13.21         25.25           84.10      537.9          0.08791   \n",
       " 439        14.02         15.66           89.59      606.5          0.07966   \n",
       " 298        14.26         18.17           91.22      633.1          0.06576   \n",
       " 37         13.03         18.42           82.61      523.8          0.08983   \n",
       " ..           ...           ...             ...        ...              ...   \n",
       " 236        23.21         26.97          153.50     1670.0          0.09509   \n",
       " 113        10.51         20.19           68.64      334.2          0.11220   \n",
       " 527        12.34         12.27           78.94      468.5          0.09003   \n",
       " 76         13.53         10.94           87.91      559.2          0.12910   \n",
       " 162        19.59         18.15          130.70     1214.0          0.11200   \n",
       " \n",
       "      mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       " 512           0.14690         0.14450              0.08172         0.2116   \n",
       " 457           0.05205         0.02772              0.02068         0.1619   \n",
       " 439           0.05581         0.02087              0.02652         0.1589   \n",
       " 298           0.05220         0.02475              0.01374         0.1635   \n",
       " 37            0.03766         0.02562              0.02923         0.1467   \n",
       " ..                ...             ...                  ...            ...   \n",
       " 236           0.16820         0.19500              0.12370         0.1909   \n",
       " 113           0.13030         0.06476              0.03068         0.1922   \n",
       " 527           0.06307         0.02958              0.02647         0.1689   \n",
       " 76            0.10470         0.06877              0.06556         0.2403   \n",
       " 162           0.16660         0.25080              0.12860         0.2027   \n",
       " \n",
       "      mean fractal dimension  ...  worst radius  worst texture  \\\n",
       " 512                 0.07325  ...         16.41          29.66   \n",
       " 457                 0.05584  ...         14.35          34.23   \n",
       " 439                 0.05586  ...         14.91          19.31   \n",
       " 298                 0.05586  ...         16.22          25.26   \n",
       " 37                  0.05863  ...         13.30          22.81   \n",
       " ..                      ...  ...           ...            ...   \n",
       " 236                 0.06309  ...         31.01          34.51   \n",
       " 113                 0.07782  ...         11.16          22.75   \n",
       " 527                 0.05808  ...         13.61          19.27   \n",
       " 76                  0.06641  ...         14.08          12.49   \n",
       " 162                 0.06082  ...         26.73          26.39   \n",
       " \n",
       "      worst perimeter  worst area  worst smoothness  worst compactness  \\\n",
       " 512           113.30       844.4           0.15740            0.38560   \n",
       " 457            91.29       632.9           0.12890            0.10630   \n",
       " 439            96.53       688.9           0.10340            0.10170   \n",
       " 298           105.80       819.7           0.09445            0.21670   \n",
       " 37             84.46       545.9           0.09701            0.04619   \n",
       " ..               ...         ...               ...                ...   \n",
       " 236           206.00      2944.0           0.14810            0.41260   \n",
       " 113            72.62       374.4           0.13000            0.20490   \n",
       " 527            87.22       564.9           0.12920            0.20740   \n",
       " 76             91.36       605.5           0.14510            0.13790   \n",
       " 162           174.90      2232.0           0.14380            0.38460   \n",
       " \n",
       "      worst concavity  worst concave points  worst symmetry  \\\n",
       " 512          0.51060               0.20510          0.3585   \n",
       " 457          0.13900               0.06005          0.2444   \n",
       " 439          0.06260               0.08216          0.2136   \n",
       " 298          0.15650               0.07530          0.2636   \n",
       " 37           0.04833               0.05013          0.1987   \n",
       " ..               ...                   ...             ...   \n",
       " 236          0.58200               0.25930          0.3103   \n",
       " 113          0.12950               0.06136          0.2383   \n",
       " 527          0.17910               0.10700          0.3110   \n",
       " 76           0.08539               0.07407          0.2710   \n",
       " 162          0.68100               0.22470          0.3643   \n",
       " \n",
       "      worst fractal dimension  \n",
       " 512                  0.11090  \n",
       " 457                  0.06788  \n",
       " 439                  0.06710  \n",
       " 298                  0.07676  \n",
       " 37                   0.06169  \n",
       " ..                       ...  \n",
       " 236                  0.08677  \n",
       " 113                  0.09026  \n",
       " 527                  0.07592  \n",
       " 76                   0.07191  \n",
       " 162                  0.09223  \n",
       " \n",
       " [143 rows x 30 columns],\n",
       " 293    1\n",
       " 332    1\n",
       " 565    0\n",
       " 278    1\n",
       " 489    0\n",
       "       ..\n",
       " 277    0\n",
       " 9      0\n",
       " 359    1\n",
       " 192    1\n",
       " 559    1\n",
       " Name: target, Length: 426, dtype: int64,\n",
       " 512    0\n",
       " 457    1\n",
       " 439    1\n",
       " 298    1\n",
       " 37     1\n",
       "       ..\n",
       " 236    0\n",
       " 113    1\n",
       " 527    1\n",
       " 76     1\n",
       " 162    0\n",
       " Name: target, Length: 143, dtype: int64)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "def step_four():\n",
    "    \n",
    "    X,y = step_three()\n",
    "    X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.25, random_state=0)\n",
    "    return ( X_train, X_test, y_train, y_test)\n",
    "\n",
    "step_four()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af9e2e05-b16f-4809-99dd-a62cdddb6303",
   "metadata": {},
   "source": [
    "### Step 5\n",
    "Using KNeighborsClassifier, we will fit a k-nearest neighbors (knn) classifier with `X_train`, `y_train` and using one nearest neighbor (`n_neighbors = 1`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "6f3ecb7a-b58a-4355-8f3a-975d06e63b59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(n_neighbors=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier(n_neighbors=1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=1)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "def step_five():\n",
    "    \n",
    "    knn = KNeighborsClassifier(n_neighbors = 1)\n",
    "    X_train, X_test, y_train, y_test = step_four()\n",
    "    knn.fit(X_train, y_train)\n",
    "    \n",
    "    return knn\n",
    "step_five()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f41701a-8383-41c2-a1e5-d3eb501d9d23",
   "metadata": {},
   "source": [
    "### Step 6\n",
    "Using the knn classifier, we will now predict the class label using the mean value for each feature."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5b7388e6-4432-4fd0-9033-878045f91f73",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_six():\n",
    "    \n",
    "    cancerdf= step_one()\n",
    "    means= cancerdf.mean()[:-1].values.reshape(1, -1)\n",
    "    knn=step_five()\n",
    "    \n",
    "    return knn.predict(means)\n",
    "\n",
    "step_six()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a70983cb-ec80-481b-933d-d6882202abbc",
   "metadata": {},
   "source": [
    "### Step 7\n",
    "Using the knn classifier, we will now predict the class labels for the test set `X_test`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "eb5c1b66-b6e9-4112-a887-e3ba599957cf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,\n",
       "       0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1,\n",
       "       0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1,\n",
       "       1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1,\n",
       "       1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_seven():\n",
    "    knn= step_five()\n",
    "    X_train, X_test, y_train, y_test = step_four()\n",
    "    return knn.predict(X_test)\n",
    "\n",
    "step_seven()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0c9dae41-23b3-4f8e-aef5-79f6bb58bd98",
   "metadata": {},
   "source": [
    "### Step 8\n",
    "We will now compute the score (mean accuracy) of the knn classifier using `X_test` and `y_test`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "af4cfdce-079f-4838-9756-af6f9779acf6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.916083916083916"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def step_eight():\n",
    "    \n",
    "    knn=step_five()\n",
    "    X_train, X_test, y_train, y_test = step_four()\n",
    "    knn.score(X_test, y_test)\n",
    "    \n",
    "    return knn.score(X_test, y_test)\n",
    "    \n",
    "step_eight()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5edc879-164f-48dd-bef5-42bdfe6f47bf",
   "metadata": {},
   "source": [
    "### Data Plotting and Visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "85f715a0-7c76-4caa-a30b-190d752c3858",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def accuracy_plot():\n",
    "    import matplotlib.pyplot as plt\n",
    "\n",
    "    %matplotlib inline\n",
    "    \n",
    "    \n",
    "    X_train, X_test, y_train, y_test = step_four()\n",
    "    \n",
    "    mal_train_X = X_train[y_train==0]\n",
    "    mal_train_y = y_train[y_train==0]\n",
    "    ben_train_X = X_train[y_train==1]\n",
    "    ben_train_y = y_train[y_train==1]\n",
    "\n",
    "    mal_test_X = X_test[y_test==0]\n",
    "    mal_test_y = y_test[y_test==0]\n",
    "    ben_test_X = X_test[y_test==1]\n",
    "    ben_test_y = y_test[y_test==1]\n",
    "    \n",
    "    knn = step_five()\n",
    "\n",
    "    scores = [knn.score(mal_train_X, mal_train_y), knn.score(ben_train_X, ben_train_y), \n",
    "              knn.score(mal_test_X, mal_test_y), knn.score(ben_test_X, ben_test_y)]\n",
    "    \n",
    "    plt.figure()\n",
    "    bars = plt.bar(np.arange(4), scores, color=['#4c72b0','#4c72b0','#55a868','#55a868'])\n",
    "    for bar in bars:\n",
    "        height = bar.get_height()\n",
    "        plt.gca().text(bar.get_x() + bar.get_width()/2, height*.90, '{0:.{1}f}'.format(height, 2), \n",
    "                       ha='center', color='w', fontsize=11)\n",
    "    \n",
    "    plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')\n",
    "    \n",
    "    for spine in plt.gca().spines.values():\n",
    "        spine.set_visible(False)\n",
    "        \n",
    "    plt.xticks([0,1,2,3], ['Malignant\\nTraining', 'Benign\\nTraining', 'Malignant\\nTest', 'Benign\\nTest'], alpha=0.8);\n",
    "    plt.title('Training and Test Accuracies for Malignant and Benign Cells', alpha=0.8)\n",
    "    \n",
    "accuracy_plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b48f7bb-eff2-40be-920d-0f45cfad22f9",
   "metadata": {},
   "source": [
    "# Comment 1:\n",
    "The perfect training accuracies indicate potential overfitting to the training data, especially for malignant cases where the test accuracy drops to 87%. Let's move to a new model and test if it shows it can generalize better"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c253cee6-e143-4213-8374-6a698c0101aa",
   "metadata": {},
   "source": [
    "### Exploring different ML models "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9fe890cd-7241-475d-bf26-cb9bb39bff02",
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib notebook\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sn\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from matplotlib.colors import ListedColormap\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "\n",
    "cmap_bold = ListedColormap(['#FFFF00', '#00FF00', '#0000FF','#000000'])\n",
    "\n",
    "cancer = load_breast_cancer()\n",
    "(X_cancer, y_cancer) = load_breast_cancer(return_X_y = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c9f6513-3d59-41f3-8549-48e88f2f2501",
   "metadata": {},
   "source": [
    "**Logistic Regression**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9693a6e3-e5e2-4a38-8572-b49587877189",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breast cancer dataset\n",
      "Accuracy of Logistic regression classifier on training set: 0.95\n",
      "Accuracy of Logistic regression classifier on test set: 0.94\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_cancer, y_cancer, random_state = 0)\n",
    "\n",
    "clf = LogisticRegression().fit(X_train, y_train)\n",
    "print('Breast cancer dataset')\n",
    "print('Accuracy of Logistic regression classifier on training set: {:.2f}'\n",
    "     .format(clf.score(X_train, y_train)))\n",
    "print('Accuracy of Logistic regression classifier on test set: {:.2f}'\n",
    "     .format(clf.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba3e2159-c078-40aa-88bf-1dbd0ae4a84e",
   "metadata": {},
   "source": [
    "# Comment 2: \n",
    "The logistic regression model shows strong and consistent performance between the training and test sets, which in other words shows: good generalization without significant overfitting. The slight difference between training and test accuracy is normal! "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51aef942-ae24-4943-9bbc-bb2df5abcb30",
   "metadata": {},
   "source": [
    "### Using Support Vector Machines"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9e1a017-6989-49f1-98e1-ccd0c1b4101b",
   "metadata": {},
   "source": [
    "**Linear SVC vs RBF Kernel SVC**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0ea3a3c8-3a69-4151-900c-fd9586c14423",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breast cancer dataset\n",
      "Accuracy of Linear SVC classifier on training set: 0.93\n",
      "Accuracy of Linear SVC classifier on test set: 0.94\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import LinearSVC\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_cancer, y_cancer, random_state = 0)\n",
    "\n",
    "clf = LinearSVC().fit(X_train, y_train)\n",
    "print('Breast cancer dataset')\n",
    "print('Accuracy of Linear SVC classifier on training set: {:.2f}'\n",
    "     .format(clf.score(X_train, y_train)))\n",
    "print('Accuracy of Linear SVC classifier on test set: {:.2f}'\n",
    "     .format(clf.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a21315aa-3a8a-406d-a220-2544a15e3ae9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breast cancer dataset (unnormalized features)\n",
      "Accuracy of RBF-kernel SVC on training set: 0.92\n",
      "Accuracy of RBF-kernel SVC on test set: 0.94\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_cancer, y_cancer,\n",
    "                                                   random_state = 0)\n",
    "\n",
    "clf = SVC(C=10).fit(X_train, y_train)\n",
    "print('Breast cancer dataset (unnormalized features)')\n",
    "print('Accuracy of RBF-kernel SVC on training set: {:.2f}'\n",
    "     .format(clf.score(X_train, y_train)))\n",
    "print('Accuracy of RBF-kernel SVC on test set: {:.2f}'\n",
    "     .format(clf.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5202999-d5af-44e1-b2db-e6193f8e7b5a",
   "metadata": {},
   "source": [
    "**We can see that the accuracy is consistent across training and test sets for both models**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09a7718f-18cb-4041-a4dc-a75e48850ed4",
   "metadata": {},
   "source": [
    "### Re-computing scores after feature preprocessing using minmax scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4125d343-dae6-4f35-b86c-80813fbffe1e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Breast cancer dataset (normalized with MinMax scaling)\n",
      "RBF-kernel SVC (with MinMax scaling) training set accuracy: 0.99\n",
      "RBF-kernel SVC (with MinMax scaling) test set accuracy: 0.97\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "scaler = MinMaxScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "clf = SVC(C=10).fit(X_train_scaled, y_train)\n",
    "print('Breast cancer dataset (normalized with MinMax scaling)')\n",
    "print('RBF-kernel SVC (with MinMax scaling) training set accuracy: {:.2f}'\n",
    "     .format(clf.score(X_train_scaled, y_train)))\n",
    "print('RBF-kernel SVC (with MinMax scaling) test set accuracy: {:.2f}'\n",
    "     .format(clf.score(X_test_scaled, y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "28f75c86-903b-437f-848a-fcd63a9b3f7f",
   "metadata": {},
   "source": [
    "# Comment 3:\n",
    "This improvement shows that feature scaling helped in normalizing the data,improving the SVM’s ability to classify more effectively, which as you would imagine, is important given the varying scales of raw data features in medical datasets.**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c059f3b5-75ba-4791-b36b-59fb54be1fba",
   "metadata": {},
   "source": [
    "\n",
    "**Thank You for Reviewing This Project**\n",
    "\n",
    "I appreciate you taking the time to go through my work. Please feel free to reach out if you have any questions, suggestions, or would like to discuss any aspects of this project further.\n",
    "\n",
    "Best Regards,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ea3b2d43-604b-43f9-840a-1b00a0614610",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}