Day12_getting started with Linear Discriminant Analysis.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# importing libraries\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "#importing the dataset\n",
    "\n",
    "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'\n",
    "\n",
    "features = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'Class']\n",
    "\n",
    "df = pd.read_csv(url, names=features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     sepal-length  sepal-width  petal-length  petal-width           Class\n",
      "0             5.1          3.5           1.4          0.2     Iris-setosa\n",
      "1             4.9          3.0           1.4          0.2     Iris-setosa\n",
      "2             4.7          3.2           1.3          0.2     Iris-setosa\n",
      "3             4.6          3.1           1.5          0.2     Iris-setosa\n",
      "4             5.0          3.6           1.4          0.2     Iris-setosa\n",
      "..            ...          ...           ...          ...             ...\n",
      "145           6.7          3.0           5.2          2.3  Iris-virginica\n",
      "146           6.3          2.5           5.0          1.9  Iris-virginica\n",
      "147           6.5          3.0           5.2          2.0  Iris-virginica\n",
      "148           6.2          3.4           5.4          2.3  Iris-virginica\n",
      "149           5.9          3.0           5.1          1.8  Iris-virginica\n",
      "\n",
      "[150 rows x 5 columns]\n"
     ]
    }
   ],
   "source": [
    "#visualizing the imported data\n",
    "print (df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "#data preprocessing\n",
    "\n",
    "X = df.iloc[:, 0:4].values #features\n",
    "y = df.iloc[:, 4].values #outcomes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "#splitting the data into training and testing\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "#feature scaling for LDA\n",
    "\n",
    "#importing necessary libraries\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\n",
    "\n",
    "lda = LDA(n_components=1)\n",
    "X_train = lda.fit_transform(X_train, y_train)\n",
    "X_test = lda.transform(X_test)\n",
    "sc = StandardScaler()\n",
    "\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "#performing LDA\n",
    "\n",
    "#importing the neccessary libraries\n",
    "\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\n",
    "\n",
    "lda = LDA(n_components=1)\n",
    "X_train = lda.fit_transform(X_train, y_train)\n",
    "X_test = lda.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "actual output: \n",
      " \n",
      " ['Iris-versicolor' 'Iris-setosa' 'Iris-virginica' 'Iris-versicolor'\n",
      " 'Iris-versicolor' 'Iris-setosa' 'Iris-versicolor' 'Iris-virginica'\n",
      " 'Iris-versicolor' 'Iris-versicolor' 'Iris-virginica' 'Iris-setosa'\n",
      " 'Iris-setosa' 'Iris-setosa' 'Iris-setosa' 'Iris-versicolor'\n",
      " 'Iris-virginica' 'Iris-versicolor' 'Iris-versicolor' 'Iris-virginica'\n",
      " 'Iris-setosa' 'Iris-virginica' 'Iris-setosa' 'Iris-virginica'\n",
      " 'Iris-virginica' 'Iris-virginica' 'Iris-virginica' 'Iris-virginica'\n",
      " 'Iris-setosa' 'Iris-setosa']\n",
      "\n",
      " \n",
      " predicted output: \n",
      " \n",
      " ['Iris-versicolor' 'Iris-setosa' 'Iris-virginica' 'Iris-versicolor'\n",
      " 'Iris-versicolor' 'Iris-setosa' 'Iris-versicolor' 'Iris-virginica'\n",
      " 'Iris-virginica' 'Iris-versicolor' 'Iris-virginica' 'Iris-setosa'\n",
      " 'Iris-setosa' 'Iris-setosa' 'Iris-setosa' 'Iris-versicolor'\n",
      " 'Iris-virginica' 'Iris-versicolor' 'Iris-versicolor' 'Iris-virginica'\n",
      " 'Iris-setosa' 'Iris-virginica' 'Iris-setosa' 'Iris-virginica'\n",
      " 'Iris-virginica' 'Iris-virginica' 'Iris-virginica' 'Iris-virginica'\n",
      " 'Iris-setosa' 'Iris-setosa']\n"
     ]
    }
   ],
   "source": [
    "# training and making predictions\n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "classifier = RandomForestClassifier(max_depth = 2, random_state =0)\n",
    "\n",
    "classifier.fit(X_train, y_train)\n",
    "y_pred = classifier.predict(X_test)\n",
    "\n",
    "print('actual output: \\n \\n', y_test)\n",
    "\n",
    "print ('\\n \\n predicted output: \\n \\n', y_pred)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confusion matrix:  [[10  0  0]\n",
      " [ 0  8  1]\n",
      " [ 0  0 11]]\n",
      "\n",
      " accuracy:  0.9666666666666667\n"
     ]
    }
   ],
   "source": [
    "#evaluating the performance \n",
    "\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "print (\"confusion matrix: \", cm)\n",
    "\n",
    "print ('\\n accuracy: ', accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# now lets use LDA in yesterday's problem of heart failure prediction and compare its accuracy with that of SVM and KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. with SVM\n",
    "\n",
    "# link here: http://localhost:8888/notebooks/Day10%3A%20SVM%20with%20feature%20extraction-II.ipynb\n",
    "\n",
    "svm_accuracy = 0.8023255813953488\n",
    "\n",
    "# 2. with KNN\n",
    "\n",
    "knn_accuracy = 0.8111111111111111 \n",
    "# link here : http://localhost:8888/notebooks/Day11_Starting%20with%20KNN%20Algorithm.ipynb\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
      "0  75.0        0                       582         0                 20   \n",
      "1  55.0        0                      7861         0                 38   \n",
      "2  65.0        0                       146         0                 20   \n",
      "3  50.0        1                       111         0                 20   \n",
      "4  65.0        1                       160         1                 20   \n",
      "\n",
      "   high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
      "0                    1  265000.00               1.9           130    1   \n",
      "1                    0  263358.03               1.1           136    1   \n",
      "2                    0  162000.00               1.3           129    1   \n",
      "3                    0  210000.00               1.9           137    1   \n",
      "4                    0  327000.00               2.7           116    0   \n",
      "\n",
      "   smoking  time  DEATH_EVENT  \n",
      "0        0     4            1  \n",
      "1        0     6            1  \n",
      "2        1     7            1  \n",
      "3        0     7            1  \n",
      "4        0     8            1  \n"
     ]
    }
   ],
   "source": [
    "# 3. with LDA\n",
    "\n",
    "#importing the data set using pandas\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(r\"Heart Fail Prediction.csv\")\n",
    "\n",
    "print(df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "features = ['age', 'anaemia', 'creatinine_phosphokinase', 'diabetes', 'ejection_fraction', 'high_blood_pressure', 'platelets', \n",
    "           'serum_creatinine', 'serum_sodium', 'sex', 'smoking', 'time']\n",
    "X = df [features]\n",
    "y = df ['DEATH_EVENT']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " 6 Best Features are: \n",
      " \n",
      "               specifications         score\n",
      "6                  platelets  26135.771990\n",
      "11                      time   3826.892661\n",
      "2   creatinine_phosphokinase   1897.314839\n",
      "4          ejection_fraction     79.072541\n",
      "0                        age     44.619455\n",
      "7           serum_creatinine     19.814118\n"
     ]
    }
   ],
   "source": [
    "# feature selection\n",
    "\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.feature_selection import chi2\n",
    "\n",
    "bestfeatures = SelectKBest(score_func = chi2, k = 6)\n",
    "fit = bestfeatures.fit(X, y) #applying the chi2 rule\n",
    "dfcolumns = pd.DataFrame(X.columns)\n",
    "dfscores = pd.DataFrame(fit.scores_)\n",
    "\n",
    "#for better visualization, concatinating two dataframes\n",
    "\n",
    "featureScores = pd.concat([dfcolumns, dfscores], axis=1)\n",
    "featureScores.columns = ['specifications', 'score'] # naming the dataframe columns\n",
    "print('\\n 6 Best Features are: \\n \\n', featureScores.nlargest(6, 'score')) # printig best 6 features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     platelets  creatinine_phosphokinase  ejection_fraction   age\n",
      "0    265000.00                       582                 20  75.0\n",
      "1    263358.03                      7861                 38  55.0\n",
      "2    162000.00                       146                 20  65.0\n",
      "3    210000.00                       111                 20  50.0\n",
      "4    327000.00                       160                 20  65.0\n",
      "..         ...                       ...                ...   ...\n",
      "294  155000.00                        61                 38  62.0\n",
      "295  270000.00                      1820                 38  55.0\n",
      "296  742000.00                      2060                 60  45.0\n",
      "297  140000.00                      2413                 38  45.0\n",
      "298  395000.00                       196                 45  50.0\n",
      "\n",
      "[299 rows x 4 columns]\n"
     ]
    }
   ],
   "source": [
    "# selecting features \n",
    "\n",
    "\n",
    "features = ['platelets', 'creatinine_phosphokinase', 'ejection_fraction', 'age']\n",
    "X = df[features]\n",
    "# y is already defined, no need to change it here\n",
    "\n",
    "print(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age'>"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# box plotting\n",
    "\n",
    "import seaborn as sns\n",
    "sns.boxplot(x = df['age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='platelets'>"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(x = df['platelets'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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>age</th>\n",
       "      <th>anaemia</th>\n",
       "      <th>creatinine_phosphokinase</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>ejection_fraction</th>\n",
       "      <th>high_blood_pressure</th>\n",
       "      <th>platelets</th>\n",
       "      <th>serum_creatinine</th>\n",
       "      <th>serum_sodium</th>\n",
       "      <th>sex</th>\n",
       "      <th>smoking</th>\n",
       "      <th>time</th>\n",
       "      <th>DEATH_EVENT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>105</th>\n",
       "      <td>72.0</td>\n",
       "      <td>1</td>\n",
       "      <td>328</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>621000.0</td>\n",
       "      <td>1.7</td>\n",
       "      <td>138</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>88</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>109</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>292</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>850000.0</td>\n",
       "      <td>1.3</td>\n",
       "      <td>142</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>88</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>85.0</td>\n",
       "      <td>1</td>\n",
       "      <td>102</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>507000.0</td>\n",
       "      <td>3.2</td>\n",
       "      <td>138</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>94</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>224</th>\n",
       "      <td>58.0</td>\n",
       "      <td>0</td>\n",
       "      <td>582</td>\n",
       "      <td>1</td>\n",
       "      <td>25</td>\n",
       "      <td>0</td>\n",
       "      <td>504000.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>138</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>205</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>70.0</td>\n",
       "      <td>0</td>\n",
       "      <td>81</td>\n",
       "      <td>1</td>\n",
       "      <td>35</td>\n",
       "      <td>1</td>\n",
       "      <td>533000.0</td>\n",
       "      <td>1.3</td>\n",
       "      <td>139</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>212</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>287</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>582</td>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>0</td>\n",
       "      <td>543000.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>132</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2060</td>\n",
       "      <td>1</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>742000.0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>138</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>278</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
       "105  72.0        1                       328         0                 30   \n",
       "109  45.0        0                       292         1                 35   \n",
       "117  85.0        1                       102         0                 60   \n",
       "224  58.0        0                       582         1                 25   \n",
       "240  70.0        0                        81         1                 35   \n",
       "287  45.0        0                       582         1                 55   \n",
       "296  45.0        0                      2060         1                 60   \n",
       "\n",
       "     high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
       "105                    1   621000.0               1.7           138    0   \n",
       "109                    0   850000.0               1.3           142    1   \n",
       "117                    0   507000.0               3.2           138    0   \n",
       "224                    0   504000.0               1.0           138    1   \n",
       "240                    1   533000.0               1.3           139    0   \n",
       "287                    0   543000.0               1.0           132    0   \n",
       "296                    0   742000.0               0.8           138    0   \n",
       "\n",
       "     smoking  time  DEATH_EVENT  \n",
       "105        1    88            1  \n",
       "109        1    88            0  \n",
       "117        0    94            0  \n",
       "224        0   205            0  \n",
       "240        0   212            0  \n",
       "287        0   250            0  \n",
       "296        0   278            0  "
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets remove outliers reasonably\n",
    "df[df['platelets']>500000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# lets remove them\n",
    "\n",
    "df= df[df['platelets']<500000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='creatinine_phosphokinase'>"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets look into creatinine_phosphokinase\n",
    "\n",
    "sns.boxplot(x = df['creatinine_phosphokinase'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>age</th>\n",
       "      <th>anaemia</th>\n",
       "      <th>creatinine_phosphokinase</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>ejection_fraction</th>\n",
       "      <th>high_blood_pressure</th>\n",
       "      <th>platelets</th>\n",
       "      <th>serum_creatinine</th>\n",
       "      <th>serum_sodium</th>\n",
       "      <th>sex</th>\n",
       "      <th>smoking</th>\n",
       "      <th>time</th>\n",
       "      <th>DEATH_EVENT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55.0</td>\n",
       "      <td>0</td>\n",
       "      <td>7861</td>\n",
       "      <td>0</td>\n",
       "      <td>38</td>\n",
       "      <td>0</td>\n",
       "      <td>263358.03</td>\n",
       "      <td>1.10</td>\n",
       "      <td>136</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52</th>\n",
       "      <td>60.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3964</td>\n",
       "      <td>1</td>\n",
       "      <td>62</td>\n",
       "      <td>0</td>\n",
       "      <td>263358.03</td>\n",
       "      <td>6.80</td>\n",
       "      <td>146</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>43</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>7702</td>\n",
       "      <td>1</td>\n",
       "      <td>25</td>\n",
       "      <td>1</td>\n",
       "      <td>390000.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>139</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>85.0</td>\n",
       "      <td>0</td>\n",
       "      <td>5882</td>\n",
       "      <td>0</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>243000.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>132</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>72</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>103</th>\n",
       "      <td>42.0</td>\n",
       "      <td>0</td>\n",
       "      <td>5209</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>226000.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>140</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>87</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>4540</td>\n",
       "      <td>0</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>231000.00</td>\n",
       "      <td>1.18</td>\n",
       "      <td>137</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>107</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>171</th>\n",
       "      <td>52.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3966</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>325000.00</td>\n",
       "      <td>0.90</td>\n",
       "      <td>140</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>146</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
       "1    55.0        0                      7861         0                 38   \n",
       "52   60.0        0                      3964         1                 62   \n",
       "60   45.0        0                      7702         1                 25   \n",
       "72   85.0        0                      5882         0                 35   \n",
       "103  42.0        0                      5209         0                 30   \n",
       "134  81.0        0                      4540         0                 35   \n",
       "171  52.0        0                      3966         0                 40   \n",
       "\n",
       "     high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
       "1                      0  263358.03              1.10           136    1   \n",
       "52                     0  263358.03              6.80           146    0   \n",
       "60                     1  390000.00              1.00           139    1   \n",
       "72                     0  243000.00              1.00           132    1   \n",
       "103                    0  226000.00              1.00           140    1   \n",
       "134                    0  231000.00              1.18           137    1   \n",
       "171                    0  325000.00              0.90           140    1   \n",
       "\n",
       "     smoking  time  DEATH_EVENT  \n",
       "1          0     6            1  \n",
       "52         0    43            1  \n",
       "60         0    60            1  \n",
       "72         1    72            1  \n",
       "103        1    87            0  \n",
       "134        1   107            0  \n",
       "171        1   146            0  "
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# much more outliers\n",
    "df[df['creatinine_phosphokinase']>3000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "# lets remove them\n",
    "df = df[df['creatinine_phosphokinase']<3000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='ejection_fraction'>"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# for ejection_fraction\n",
    "\n",
    "sns.boxplot(df['ejection_fraction'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "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>age</th>\n",
       "      <th>anaemia</th>\n",
       "      <th>creatinine_phosphokinase</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>ejection_fraction</th>\n",
       "      <th>high_blood_pressure</th>\n",
       "      <th>platelets</th>\n",
       "      <th>serum_creatinine</th>\n",
       "      <th>serum_sodium</th>\n",
       "      <th>sex</th>\n",
       "      <th>smoking</th>\n",
       "      <th>time</th>\n",
       "      <th>DEATH_EVENT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>582</td>\n",
       "      <td>0</td>\n",
       "      <td>80</td>\n",
       "      <td>0</td>\n",
       "      <td>263358.03</td>\n",
       "      <td>1.18</td>\n",
       "      <td>137</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>63</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>217</th>\n",
       "      <td>54.0</td>\n",
       "      <td>1</td>\n",
       "      <td>427</td>\n",
       "      <td>0</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>151000.00</td>\n",
       "      <td>9.00</td>\n",
       "      <td>137</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>196</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
       "64   45.0        0                       582         0                 80   \n",
       "217  54.0        1                       427         0                 70   \n",
       "\n",
       "     high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
       "64                     0  263358.03              1.18           137    0   \n",
       "217                    1  151000.00              9.00           137    0   \n",
       "\n",
       "     smoking  time  DEATH_EVENT  \n",
       "64         0    63            0  \n",
       "217        0   196            1  "
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets remove outliers\n",
    "\n",
    "df[df['ejection_fraction']>=70]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "# lets remove them\n",
    "df = df[df['ejection_fraction']<70]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='ejection_fraction'>"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# lets cross check\n",
    "sns.boxplot(df['ejection_fraction'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "#we are good here! and we are done in data cleaning part\n",
    "\n",
    "# checking the accuracy again of the KNN model\n",
    "\n",
    "# spliting training and testing data\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "#feature scaling for LDA\n",
    "\n",
    "#importing necessary libraries\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "sc = StandardScaler()\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "#performing LDA\n",
    "\n",
    "#importing the neccessary libraries\n",
    "\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\n",
    "\n",
    "lda = LDA(n_components=1)\n",
    "X_train = lda.fit_transform(X_train, y_train)\n",
    "X_test = lda.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "actual output: \n",
      " \n",
      " 130    0\n",
      "77     0\n",
      "135    0\n",
      "156    0\n",
      "0      1\n",
      "      ..\n",
      "102    0\n",
      "124    1\n",
      "68     1\n",
      "65     1\n",
      "113    1\n",
      "Name: DEATH_EVENT, Length: 90, dtype: int64\n",
      "\n",
      " \n",
      " predicted output: \n",
      " \n",
      " [0 0 0 0 1 0 0 0 1 0 0 0 1 0 1 0 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 0 0 1 0 0 0\n",
      " 0 0 0 1 1 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 1 1 0 1 1 0 0 0 0 0 0 0 0 0 1 0 0\n",
      " 0 1 0 1 0 0 0 0 0 0 0 1 0 1 1 0]\n"
     ]
    }
   ],
   "source": [
    "# training and making predictions\n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "classifier = RandomForestClassifier(max_depth = 3, random_state =0)\n",
    "\n",
    "classifier.fit(X_train, y_train)\n",
    "y_pred = classifier.predict(X_test)\n",
    "\n",
    "print('actual output: \\n \\n', y_test)\n",
    "\n",
    "print ('\\n \\n predicted output: \\n \\n', y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confusion matrix:  [[53  9]\n",
      " [14 14]]\n",
      "\n",
      " accuracy:  0.7444444444444445\n"
     ]
    }
   ],
   "source": [
    "#evaluating the performance \n",
    "\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "print (\"confusion matrix: \", cm)\n",
    "\n",
    "print ('\\n accuracy: ', accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy with SVM:  0.8023255813953488\n",
      "accuracy with KNN:  0.8111111111111111\n",
      "accuracy with LDA:  0.7444444444444445\n"
     ]
    }
   ],
   "source": [
    "print ('accuracy with SVM: ', svm_accuracy)\n",
    "print ('accuracy with KNN: ', knn_accuracy)\n",
    "print ('accuracy with LDA: ', accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}