Breast_Cancer_KNN.ipynb

{
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.6-final"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3.8.6 64-bit",
   "metadata": {
    "interpreter": {
     "hash": "965ba1120b0c101b3f715b6e258a73742ec1cf86f2c8b04492724c87d9f112c3"
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "source": [
    "# Breast Cancer using KNN Classifier"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "source": [
    "# import the packages\n",
    "import pandas as pd \n",
    "from sklearn.datasets import load_breast_cancer \n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.neighbors import KNeighborsClassifier\n"
   ],
   "cell_type": "code",
   "metadata": {},
   "execution_count": null,
   "outputs": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "{'data': array([[1.799e+01, 1.038e+01, 1.228e+02, ..., 2.654e-01, 4.601e-01,\n",
       "         1.189e-01],\n",
       "        [2.057e+01, 1.777e+01, 1.329e+02, ..., 1.860e-01, 2.750e-01,\n",
       "         8.902e-02],\n",
       "        [1.969e+01, 2.125e+01, 1.300e+02, ..., 2.430e-01, 3.613e-01,\n",
       "         8.758e-02],\n",
       "        ...,\n",
       "        [1.660e+01, 2.808e+01, 1.083e+02, ..., 1.418e-01, 2.218e-01,\n",
       "         7.820e-02],\n",
       "        [2.060e+01, 2.933e+01, 1.401e+02, ..., 2.650e-01, 4.087e-01,\n",
       "         1.240e-01],\n",
       "        [7.760e+00, 2.454e+01, 4.792e+01, ..., 0.000e+00, 2.871e-01,\n",
       "         7.039e-02]]),\n",
       " 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,\n",
       "        1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,\n",
       "        1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,\n",
       "        0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,\n",
       "        1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,\n",
       "        0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,\n",
       "        1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,\n",
       "        1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,\n",
       "        0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,\n",
       "        0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,\n",
       "        1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,\n",
       "        1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,\n",
       "        1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,\n",
       "        1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n",
       "        1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,\n",
       "        1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1]),\n",
       " 'frame': None,\n",
       " 'target_names': array(['malignant', 'benign'], dtype='<U9'),\n",
       " 'DESCR': '.. _breast_cancer_dataset:\\n\\nBreast 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\\nThis is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\\nhttps://goo.gl/U2Uwz2\\n\\nFeatures are computed from a digitized image of a fine needle\\naspirate (FNA) of a breast mass.  They describe\\ncharacteristics of the cell nuclei present in the image.\\n\\nSeparating plane described above was obtained using\\nMultisurface Method-Tree (MSM-T) [K. P. Bennett, \"Decision Tree\\nConstruction Via Linear Programming.\" Proceedings of the 4th\\nMidwest Artificial Intelligence and Cognitive Science Society,\\npp. 97-101, 1992], a classification method which uses linear\\nprogramming to construct a decision tree.  Relevant features\\nwere selected using an exhaustive search in the space of 1-4\\nfeatures and 1-3 separating planes.\\n\\nThe actual linear program used to obtain the separating plane\\nin the 3-dimensional space is that described in:\\n[K. P. Bennett and O. L. Mangasarian: \"Robust Linear\\nProgramming Discrimination of Two Linearly Inseparable Sets\",\\nOptimization Methods and Software 1, 1992, 23-34].\\n\\nThis database is also available through the UW CS ftp server:\\n\\nftp ftp.cs.wisc.edu\\ncd 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",
       " 'feature_names': array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',\n",
       "        'mean smoothness', 'mean compactness', 'mean concavity',\n",
       "        'mean concave points', 'mean symmetry', 'mean fractal dimension',\n",
       "        'radius error', 'texture error', 'perimeter error', 'area error',\n",
       "        'smoothness error', 'compactness error', 'concavity error',\n",
       "        'concave points error', 'symmetry error',\n",
       "        'fractal dimension error', 'worst radius', 'worst texture',\n",
       "        'worst perimeter', 'worst area', 'worst smoothness',\n",
       "        'worst compactness', 'worst concavity', 'worst concave points',\n",
       "        'worst symmetry', 'worst fractal dimension'], dtype='<U23'),\n",
       " 'filename': 'C:\\\\Users\\\\ASUS\\\\AppData\\\\Local\\\\Programs\\\\Python\\\\Python38\\\\lib\\\\site-packages\\\\sklearn\\\\datasets\\\\data\\\\breast_cancer.csv'}"
      ]
     },
     "metadata": {},
     "execution_count": 6
    }
   ],
   "source": [
    "# Load the breast cancer dataset\n",
    "breast_cancer = load_breast_cancer()\n",
    "breast_cancer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# define independent and dependent variable\n",
    "X = breast_cancer.data\n",
    "y = breast_cancer.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "((569, 30), (569,))"
      ]
     },
     "metadata": {},
     "execution_count": 8
    }
   ],
   "source": [
    "X.shape , y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# split the data into train and test\n",
    "X_train , X_test , y_train , y_test = train_test_split(X , y  , test_size = 0.1 , stratify = y , random_state = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=2)"
      ]
     },
     "metadata": {},
     "execution_count": 10
    }
   ],
   "source": [
    "# build and train the KNN\n",
    "k_neighbor = KNeighborsClassifier(n_neighbors=2)\n",
    "k_neighbor.fit(X_train , y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Accuracy on training data :- 0.96875\n"
     ]
    }
   ],
   "source": [
    "# Evaluate the model\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "predictions_on_training_data = k_neighbor.predict(X_train)\n",
    "accuracy_on_training_data = accuracy_score(y_train , predictions_on_training_data)\n",
    "\n",
    "print(f\"Accuracy on training data :- {accuracy_on_training_data}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Accuracy on the test data:- 0.9122807017543859\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "predictions = k_neighbor.predict(X_test)\n",
    "\n",
    "acc = accuracy_score(y_test , predictions)\n",
    "\n",
    "print(f\"Accuracy on the test data:- {acc}\")\n"
   ]
  },
  {
   "source": [
    "Let's make the predictions \n"
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "         id diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n",
       "0    842302         M        17.99         10.38          122.80     1001.0   \n",
       "1    842517         M        20.57         17.77          132.90     1326.0   \n",
       "2  84300903         M        19.69         21.25          130.00     1203.0   \n",
       "3  84348301         M        11.42         20.38           77.58      386.1   \n",
       "4  84358402         M        20.29         14.34          135.10     1297.0   \n",
       "\n",
       "   smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "0          0.11840           0.27760          0.3001              0.14710   \n",
       "1          0.08474           0.07864          0.0869              0.07017   \n",
       "2          0.10960           0.15990          0.1974              0.12790   \n",
       "3          0.14250           0.28390          0.2414              0.10520   \n",
       "4          0.10030           0.13280          0.1980              0.10430   \n",
       "\n",
       "   ...  texture_worst  perimeter_worst  area_worst  smoothness_worst  \\\n",
       "0  ...          17.33           184.60      2019.0            0.1622   \n",
       "1  ...          23.41           158.80      1956.0            0.1238   \n",
       "2  ...          25.53           152.50      1709.0            0.1444   \n",
       "3  ...          26.50            98.87       567.7            0.2098   \n",
       "4  ...          16.67           152.20      1575.0            0.1374   \n",
       "\n",
       "   compactness_worst  concavity_worst  concave points_worst  symmetry_worst  \\\n",
       "0             0.6656           0.7119                0.2654          0.4601   \n",
       "1             0.1866           0.2416                0.1860          0.2750   \n",
       "2             0.4245           0.4504                0.2430          0.3613   \n",
       "3             0.8663           0.6869                0.2575          0.6638   \n",
       "4             0.2050           0.4000                0.1625          0.2364   \n",
       "\n",
       "   fractal_dimension_worst  Unnamed: 32  \n",
       "0                  0.11890          NaN  \n",
       "1                  0.08902          NaN  \n",
       "2                  0.08758          NaN  \n",
       "3                  0.17300          NaN  \n",
       "4                  0.07678          NaN  \n",
       "\n",
       "[5 rows x 33 columns]"
      ],
      "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>id</th>\n      <th>diagnosis</th>\n      <th>radius_mean</th>\n      <th>texture_mean</th>\n      <th>perimeter_mean</th>\n      <th>area_mean</th>\n      <th>smoothness_mean</th>\n      <th>compactness_mean</th>\n      <th>concavity_mean</th>\n      <th>concave points_mean</th>\n      <th>...</th>\n      <th>texture_worst</th>\n      <th>perimeter_worst</th>\n      <th>area_worst</th>\n      <th>smoothness_worst</th>\n      <th>compactness_worst</th>\n      <th>concavity_worst</th>\n      <th>concave points_worst</th>\n      <th>symmetry_worst</th>\n      <th>fractal_dimension_worst</th>\n      <th>Unnamed: 32</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>842302</td>\n      <td>M</td>\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>0.3001</td>\n      <td>0.14710</td>\n      <td>...</td>\n      <td>17.33</td>\n      <td>184.60</td>\n      <td>2019.0</td>\n      <td>0.1622</td>\n      <td>0.6656</td>\n      <td>0.7119</td>\n      <td>0.2654</td>\n      <td>0.4601</td>\n      <td>0.11890</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>842517</td>\n      <td>M</td>\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>0.0869</td>\n      <td>0.07017</td>\n      <td>...</td>\n      <td>23.41</td>\n      <td>158.80</td>\n      <td>1956.0</td>\n      <td>0.1238</td>\n      <td>0.1866</td>\n      <td>0.2416</td>\n      <td>0.1860</td>\n      <td>0.2750</td>\n      <td>0.08902</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>84300903</td>\n      <td>M</td>\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>0.1974</td>\n      <td>0.12790</td>\n      <td>...</td>\n      <td>25.53</td>\n      <td>152.50</td>\n      <td>1709.0</td>\n      <td>0.1444</td>\n      <td>0.4245</td>\n      <td>0.4504</td>\n      <td>0.2430</td>\n      <td>0.3613</td>\n      <td>0.08758</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>84348301</td>\n      <td>M</td>\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>0.2414</td>\n      <td>0.10520</td>\n      <td>...</td>\n      <td>26.50</td>\n      <td>98.87</td>\n      <td>567.7</td>\n      <td>0.2098</td>\n      <td>0.8663</td>\n      <td>0.6869</td>\n      <td>0.2575</td>\n      <td>0.6638</td>\n      <td>0.17300</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>84358402</td>\n      <td>M</td>\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>0.1980</td>\n      <td>0.10430</td>\n      <td>...</td>\n      <td>16.67</td>\n      <td>152.20</td>\n      <td>1575.0</td>\n      <td>0.1374</td>\n      <td>0.2050</td>\n      <td>0.4000</td>\n      <td>0.1625</td>\n      <td>0.2364</td>\n      <td>0.07678</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 33 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 13
    }
   ],
   "source": [
    "# load the data for make predictions \n",
    "import pandas as pd \n",
    "\n",
    "df = pd.read_csv(\"data.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "   radius_mean  texture_mean  perimeter_mean  area_mean  smoothness_mean  \\\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",
       "   compactness_mean  concavity_mean  concave points_mean  symmetry_mean  \\\n",
       "0           0.27760          0.3001              0.14710         0.2419   \n",
       "1           0.07864          0.0869              0.07017         0.1812   \n",
       "2           0.15990          0.1974              0.12790         0.2069   \n",
       "3           0.28390          0.2414              0.10520         0.2597   \n",
       "4           0.13280          0.1980              0.10430         0.1809   \n",
       "\n",
       "   fractal_dimension_mean  ...  radius_worst  texture_worst  perimeter_worst  \\\n",
       "0                 0.07871  ...         25.38          17.33           184.60   \n",
       "1                 0.05667  ...         24.99          23.41           158.80   \n",
       "2                 0.05999  ...         23.57          25.53           152.50   \n",
       "3                 0.09744  ...         14.91          26.50            98.87   \n",
       "4                 0.05883  ...         22.54          16.67           152.20   \n",
       "\n",
       "   area_worst  smoothness_worst  compactness_worst  concavity_worst  \\\n",
       "0      2019.0            0.1622             0.6656           0.7119   \n",
       "1      1956.0            0.1238             0.1866           0.2416   \n",
       "2      1709.0            0.1444             0.4245           0.4504   \n",
       "3       567.7            0.2098             0.8663           0.6869   \n",
       "4      1575.0            0.1374             0.2050           0.4000   \n",
       "\n",
       "   concave points_worst  symmetry_worst  fractal_dimension_worst  \n",
       "0                0.2654          0.4601                  0.11890  \n",
       "1                0.1860          0.2750                  0.08902  \n",
       "2                0.2430          0.3613                  0.08758  \n",
       "3                0.2575          0.6638                  0.17300  \n",
       "4                0.1625          0.2364                  0.07678  \n",
       "\n",
       "[5 rows x 30 columns]"
      ],
      "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>radius_mean</th>\n      <th>texture_mean</th>\n      <th>perimeter_mean</th>\n      <th>area_mean</th>\n      <th>smoothness_mean</th>\n      <th>compactness_mean</th>\n      <th>concavity_mean</th>\n      <th>concave points_mean</th>\n      <th>symmetry_mean</th>\n      <th>fractal_dimension_mean</th>\n      <th>...</th>\n      <th>radius_worst</th>\n      <th>texture_worst</th>\n      <th>perimeter_worst</th>\n      <th>area_worst</th>\n      <th>smoothness_worst</th>\n      <th>compactness_worst</th>\n      <th>concavity_worst</th>\n      <th>concave points_worst</th>\n      <th>symmetry_worst</th>\n      <th>fractal_dimension_worst</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>0.3001</td>\n      <td>0.14710</td>\n      <td>0.2419</td>\n      <td>0.07871</td>\n      <td>...</td>\n      <td>25.38</td>\n      <td>17.33</td>\n      <td>184.60</td>\n      <td>2019.0</td>\n      <td>0.1622</td>\n      <td>0.6656</td>\n      <td>0.7119</td>\n      <td>0.2654</td>\n      <td>0.4601</td>\n      <td>0.11890</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>0.0869</td>\n      <td>0.07017</td>\n      <td>0.1812</td>\n      <td>0.05667</td>\n      <td>...</td>\n      <td>24.99</td>\n      <td>23.41</td>\n      <td>158.80</td>\n      <td>1956.0</td>\n      <td>0.1238</td>\n      <td>0.1866</td>\n      <td>0.2416</td>\n      <td>0.1860</td>\n      <td>0.2750</td>\n      <td>0.08902</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>0.1974</td>\n      <td>0.12790</td>\n      <td>0.2069</td>\n      <td>0.05999</td>\n      <td>...</td>\n      <td>23.57</td>\n      <td>25.53</td>\n      <td>152.50</td>\n      <td>1709.0</td>\n      <td>0.1444</td>\n      <td>0.4245</td>\n      <td>0.4504</td>\n      <td>0.2430</td>\n      <td>0.3613</td>\n      <td>0.08758</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>0.2414</td>\n      <td>0.10520</td>\n      <td>0.2597</td>\n      <td>0.09744</td>\n      <td>...</td>\n      <td>14.91</td>\n      <td>26.50</td>\n      <td>98.87</td>\n      <td>567.7</td>\n      <td>0.2098</td>\n      <td>0.8663</td>\n      <td>0.6869</td>\n      <td>0.2575</td>\n      <td>0.6638</td>\n      <td>0.17300</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>0.1980</td>\n      <td>0.10430</td>\n      <td>0.1809</td>\n      <td>0.05883</td>\n      <td>...</td>\n      <td>22.54</td>\n      <td>16.67</td>\n      <td>152.20</td>\n      <td>1575.0</td>\n      <td>0.1374</td>\n      <td>0.2050</td>\n      <td>0.4000</td>\n      <td>0.1625</td>\n      <td>0.2364</td>\n      <td>0.07678</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 30 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 27
    }
   ],
   "source": [
    "# Drop some unused features like (Categorical features) in the data \n",
    "df1 = df.drop([\"id\" , \"diagnosis\" , \"Unnamed: 32\"] , axis = 1)\n",
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "[1]\nThe Breast Cancer is Benign\n"
     ]
    }
   ],
   "source": [
    "import numpy as np \n",
    "input_data = (df1.iloc[455])\n",
    "\n",
    "# change the input_data to the numpy array to make predictions\n",
    "input_data_as_numpy_array = np.asarray(input_data)\n",
    "# print(input_data_as_numpy_array.shape)\n",
    "\n",
    "# Reshape the array as we are predicting the output for one instance\n",
    "input_data_reshape = input_data_as_numpy_array.reshape(1,-1)\n",
    "# print(input_data_reshape.shape)\n",
    "\n",
    "# predictions\n",
    "prediction = k_neighbor.predict(input_data_reshape)\n",
    "print(prediction) # returns a list with element [0] if malignant: return a listwith element [1] , if benign.\n",
    "\n",
    "if prediction[0] == 0:\n",
    "  print(\"The Breast Cancer is Malignant\")\n",
    "\n",
    "else:\n",
    "  print(\"The Breast Cancer is Benign\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ]
}