{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "cecbf1a0",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:16:06.909304Z",
     "start_time": "2022-11-14T16:16:06.273610Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns \n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "96f03e29",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:11:20.720238Z",
     "start_time": "2022-11-14T16:11:20.684572Z"
    }
   },
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>51</th>\n",
       "      <th>52</th>\n",
       "      <th>53</th>\n",
       "      <th>54</th>\n",
       "      <th>55</th>\n",
       "      <th>56</th>\n",
       "      <th>57</th>\n",
       "      <th>58</th>\n",
       "      <th>59</th>\n",
       "      <th>60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0200</td>\n",
       "      <td>0.0371</td>\n",
       "      <td>0.0428</td>\n",
       "      <td>0.0207</td>\n",
       "      <td>0.0954</td>\n",
       "      <td>0.0986</td>\n",
       "      <td>0.1539</td>\n",
       "      <td>0.1601</td>\n",
       "      <td>0.3109</td>\n",
       "      <td>0.2111</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0027</td>\n",
       "      <td>0.0065</td>\n",
       "      <td>0.0159</td>\n",
       "      <td>0.0072</td>\n",
       "      <td>0.0167</td>\n",
       "      <td>0.0180</td>\n",
       "      <td>0.0084</td>\n",
       "      <td>0.0090</td>\n",
       "      <td>0.0032</td>\n",
       "      <td>R</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0453</td>\n",
       "      <td>0.0523</td>\n",
       "      <td>0.0843</td>\n",
       "      <td>0.0689</td>\n",
       "      <td>0.1183</td>\n",
       "      <td>0.2583</td>\n",
       "      <td>0.2156</td>\n",
       "      <td>0.3481</td>\n",
       "      <td>0.3337</td>\n",
       "      <td>0.2872</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0084</td>\n",
       "      <td>0.0089</td>\n",
       "      <td>0.0048</td>\n",
       "      <td>0.0094</td>\n",
       "      <td>0.0191</td>\n",
       "      <td>0.0140</td>\n",
       "      <td>0.0049</td>\n",
       "      <td>0.0052</td>\n",
       "      <td>0.0044</td>\n",
       "      <td>R</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0262</td>\n",
       "      <td>0.0582</td>\n",
       "      <td>0.1099</td>\n",
       "      <td>0.1083</td>\n",
       "      <td>0.0974</td>\n",
       "      <td>0.2280</td>\n",
       "      <td>0.2431</td>\n",
       "      <td>0.3771</td>\n",
       "      <td>0.5598</td>\n",
       "      <td>0.6194</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0232</td>\n",
       "      <td>0.0166</td>\n",
       "      <td>0.0095</td>\n",
       "      <td>0.0180</td>\n",
       "      <td>0.0244</td>\n",
       "      <td>0.0316</td>\n",
       "      <td>0.0164</td>\n",
       "      <td>0.0095</td>\n",
       "      <td>0.0078</td>\n",
       "      <td>R</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0100</td>\n",
       "      <td>0.0171</td>\n",
       "      <td>0.0623</td>\n",
       "      <td>0.0205</td>\n",
       "      <td>0.0205</td>\n",
       "      <td>0.0368</td>\n",
       "      <td>0.1098</td>\n",
       "      <td>0.1276</td>\n",
       "      <td>0.0598</td>\n",
       "      <td>0.1264</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0121</td>\n",
       "      <td>0.0036</td>\n",
       "      <td>0.0150</td>\n",
       "      <td>0.0085</td>\n",
       "      <td>0.0073</td>\n",
       "      <td>0.0050</td>\n",
       "      <td>0.0044</td>\n",
       "      <td>0.0040</td>\n",
       "      <td>0.0117</td>\n",
       "      <td>R</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0762</td>\n",
       "      <td>0.0666</td>\n",
       "      <td>0.0481</td>\n",
       "      <td>0.0394</td>\n",
       "      <td>0.0590</td>\n",
       "      <td>0.0649</td>\n",
       "      <td>0.1209</td>\n",
       "      <td>0.2467</td>\n",
       "      <td>0.3564</td>\n",
       "      <td>0.4459</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0031</td>\n",
       "      <td>0.0054</td>\n",
       "      <td>0.0105</td>\n",
       "      <td>0.0110</td>\n",
       "      <td>0.0015</td>\n",
       "      <td>0.0072</td>\n",
       "      <td>0.0048</td>\n",
       "      <td>0.0107</td>\n",
       "      <td>0.0094</td>\n",
       "      <td>R</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 61 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       0       1       2       3       4       5       6       7       8   \\\n",
       "0  0.0200  0.0371  0.0428  0.0207  0.0954  0.0986  0.1539  0.1601  0.3109   \n",
       "1  0.0453  0.0523  0.0843  0.0689  0.1183  0.2583  0.2156  0.3481  0.3337   \n",
       "2  0.0262  0.0582  0.1099  0.1083  0.0974  0.2280  0.2431  0.3771  0.5598   \n",
       "3  0.0100  0.0171  0.0623  0.0205  0.0205  0.0368  0.1098  0.1276  0.0598   \n",
       "4  0.0762  0.0666  0.0481  0.0394  0.0590  0.0649  0.1209  0.2467  0.3564   \n",
       "\n",
       "       9   ...      51      52      53      54      55      56      57  \\\n",
       "0  0.2111  ...  0.0027  0.0065  0.0159  0.0072  0.0167  0.0180  0.0084   \n",
       "1  0.2872  ...  0.0084  0.0089  0.0048  0.0094  0.0191  0.0140  0.0049   \n",
       "2  0.6194  ...  0.0232  0.0166  0.0095  0.0180  0.0244  0.0316  0.0164   \n",
       "3  0.1264  ...  0.0121  0.0036  0.0150  0.0085  0.0073  0.0050  0.0044   \n",
       "4  0.4459  ...  0.0031  0.0054  0.0105  0.0110  0.0015  0.0072  0.0048   \n",
       "\n",
       "       58      59  60  \n",
       "0  0.0090  0.0032   R  \n",
       "1  0.0052  0.0044   R  \n",
       "2  0.0095  0.0078   R  \n",
       "3  0.0040  0.0117   R  \n",
       "4  0.0107  0.0094   R  \n",
       "\n",
       "[5 rows x 61 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sonar_data = pd.read_csv('/Users/rishavdas/Downloads/Data/sonar_data.csv', header=None)\n",
    "sonar_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "5265f3b0",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:11:30.517652Z",
     "start_time": "2022-11-14T16:11:30.509443Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(208, 61)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sonar_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bb643596",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:11:53.467352Z",
     "start_time": "2022-11-14T16:11:53.456149Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "M    111\n",
       "R     97\n",
       "Name: 60, dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sonar_data[60].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5022feb5",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:13:31.950131Z",
     "start_time": "2022-11-14T16:13:31.926669Z"
    }
   },
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>50</th>\n",
       "      <th>51</th>\n",
       "      <th>52</th>\n",
       "      <th>53</th>\n",
       "      <th>54</th>\n",
       "      <th>55</th>\n",
       "      <th>56</th>\n",
       "      <th>57</th>\n",
       "      <th>58</th>\n",
       "      <th>59</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>M</th>\n",
       "      <td>0.034989</td>\n",
       "      <td>0.045544</td>\n",
       "      <td>0.050720</td>\n",
       "      <td>0.064768</td>\n",
       "      <td>0.086715</td>\n",
       "      <td>0.111864</td>\n",
       "      <td>0.128359</td>\n",
       "      <td>0.149832</td>\n",
       "      <td>0.213492</td>\n",
       "      <td>0.251022</td>\n",
       "      <td>...</td>\n",
       "      <td>0.019352</td>\n",
       "      <td>0.016014</td>\n",
       "      <td>0.011643</td>\n",
       "      <td>0.012185</td>\n",
       "      <td>0.009923</td>\n",
       "      <td>0.008914</td>\n",
       "      <td>0.007825</td>\n",
       "      <td>0.009060</td>\n",
       "      <td>0.008695</td>\n",
       "      <td>0.006930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>R</th>\n",
       "      <td>0.022498</td>\n",
       "      <td>0.030303</td>\n",
       "      <td>0.035951</td>\n",
       "      <td>0.041447</td>\n",
       "      <td>0.062028</td>\n",
       "      <td>0.096224</td>\n",
       "      <td>0.114180</td>\n",
       "      <td>0.117596</td>\n",
       "      <td>0.137392</td>\n",
       "      <td>0.159325</td>\n",
       "      <td>...</td>\n",
       "      <td>0.012311</td>\n",
       "      <td>0.010453</td>\n",
       "      <td>0.009640</td>\n",
       "      <td>0.009518</td>\n",
       "      <td>0.008567</td>\n",
       "      <td>0.007430</td>\n",
       "      <td>0.007814</td>\n",
       "      <td>0.006677</td>\n",
       "      <td>0.007078</td>\n",
       "      <td>0.006024</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 60 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          0         1         2         3         4         5         6   \\\n",
       "60                                                                         \n",
       "M   0.034989  0.045544  0.050720  0.064768  0.086715  0.111864  0.128359   \n",
       "R   0.022498  0.030303  0.035951  0.041447  0.062028  0.096224  0.114180   \n",
       "\n",
       "          7         8         9   ...        50        51        52        53  \\\n",
       "60                                ...                                           \n",
       "M   0.149832  0.213492  0.251022  ...  0.019352  0.016014  0.011643  0.012185   \n",
       "R   0.117596  0.137392  0.159325  ...  0.012311  0.010453  0.009640  0.009518   \n",
       "\n",
       "          54        55        56        57        58        59  \n",
       "60                                                              \n",
       "M   0.009923  0.008914  0.007825  0.009060  0.008695  0.006930  \n",
       "R   0.008567  0.007430  0.007814  0.006677  0.007078  0.006024  \n",
       "\n",
       "[2 rows x 60 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sonar_data.groupby(60).mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ba5d6b1e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:15:30.780755Z",
     "start_time": "2022-11-14T16:15:30.775524Z"
    }
   },
   "outputs": [],
   "source": [
    "x =sonar_data.drop(columns=60, axis=1)\n",
    "y = sonar_data[60]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "15d7f5ca",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:16:48.757586Z",
     "start_time": "2022-11-14T16:16:48.747482Z"
    }
   },
   "outputs": [],
   "source": [
    "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": 11,
   "id": "de53e35d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:16:53.768157Z",
     "start_time": "2022-11-14T16:16:53.762173Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(187, 60)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a96b6760",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:16:59.915019Z",
     "start_time": "2022-11-14T16:16:59.907292Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(21, 60)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "52afbcfc",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:22:06.869375Z",
     "start_time": "2022-11-14T16:22:06.864001Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "model = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "f24b1190",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:22:13.281423Z",
     "start_time": "2022-11-14T16:22:13.253601Z"
    }
   },
   "outputs": [],
   "source": [
    "model.fit(X_train, Y_train)\n",
    "y_pred = model.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "cc30be83",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:19:46.454625Z",
     "start_time": "2022-11-14T16:19:46.448714Z"
    }
   },
   "outputs": [],
   "source": [
    "training_data_accuracy = accuracy_score(y_pred, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "88cc423f",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:20:17.233636Z",
     "start_time": "2022-11-14T16:20:17.227732Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy on training data  0.8342245989304813\n"
     ]
    }
   ],
   "source": [
    "print(\"Accuracy on training data \", training_data_accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "96fe48f8",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-11-14T16:22:15.551420Z",
     "start_time": "2022-11-14T16:22:15.541970Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7619047619047619\n"
     ]
    }
   ],
   "source": [
    "y_pred_test = model.predict(X_test)\n",
    "test_data_accuracy = accuracy_score(y_pred_test, Y_test)\n",
    "print(test_data_accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d510eca7",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}