Skip to content

D
Data Science
Commit ccce059a authored by Anurag Kumar's avatar Anurag Kumar
Browse files
Options

Upload New File

parent 081ff745
Show whitespace changes
Inline Side-by-side
Showing with 417 additions and 0 deletions
ML_Models/Logistic_Regression.ipynb 0 → 100644
View file @ ccce059a
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Logistic Regression"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"dataset/breast_cancer.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"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>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>"
],
"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]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['id', 'diagnosis', 'radius_mean', 'texture_mean', 'perimeter_mean',\n",
" 'area_mean', 'smoothness_mean', 'compactness_mean', 'concavity_mean',\n",
" 'concave points_mean', 'symmetry_mean', 'fractal_dimension_mean',\n",
" 'radius_se', 'texture_se', 'perimeter_se', 'area_se', 'smoothness_se',\n",
" 'compactness_se', 'concavity_se', 'concave points_se', 'symmetry_se',\n",
" 'fractal_dimension_se', 'radius_worst', 'texture_worst',\n",
" 'perimeter_worst', 'area_worst', 'smoothness_worst',\n",
" 'compactness_worst', 'concavity_worst', 'concave points_worst',\n",
" 'symmetry_worst', 'fractal_dimension_worst', 'Unnamed: 32'],\n",
" dtype='object')"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# converting text value into classifier (or, number)\n",
"from sklearn import preprocessing\n",
"Label = preprocessing.LabelEncoder()\n",
"\n",
"diagnosis = Label.fit_transform(df['diagnosis'])\n",
"# diagnosis"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"train, test = train_test_split(df, random_state = 40)\n",
"x_train = train[train.columns[2:30]]\n",
"y_train = train['diagnosis']\n",
"\n",
"x_test = test[test.columns[2:30]]\n",
"y_test = test['diagnosis']"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"scaler = StandardScaler()\n",
"\n",
"scaler.fit(x_train)\n",
"\n",
"x_train = scaler.transform(x_train)\n",
"x_test = scaler.transform(x_test)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"lr = LogisticRegression()\n",
"lr.fit(x_train, y_train)\n",
"y_pred = lr.predict(x_test)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[96 2]\n",
" [ 2 43]]\n",
" precision recall f1-score support\n",
"\n",
" B 0.98 0.98 0.98 98\n",
" M 0.96 0.96 0.96 45\n",
"\n",
"avg / total 0.97 0.97 0.97 143\n",
"\n"
]
}
],
"source": [
"# accuracy\n",
"from sklearn.metrics import confusion_matrix, classification_report\n",
"print(confusion_matrix(y_test, y_pred))\n",
"print(classification_report(y_test, y_pred))"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['M'], dtype=object)"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# predicting one perticular output\n",
"x_test1 = scaler.transform(df.iloc[0:1, 2:30])\n",
"pred = lr.predict(x_test1)\n",
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment