Datasets
Models
Downloads: 2
[06cc32]:
/
heart_disease.ipynb
1897 lines (1896 with data), 67.9 kB
{
"cells": [
{
"cell_type": "markdown",
"id": "41bc3d29-1e2f-41ec-b919-37d014f4769b",
"metadata": {},
"source": [
"HEART DISEASE\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "596f49af-da22-40fd-b931-972608d711f9",
"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>sex</th>\n",
" <th>cp</th>\n",
" <th>trestbps</th>\n",
" <th>chol</th>\n",
" <th>fbs</th>\n",
" <th>restecg</th>\n",
" <th>thalach</th>\n",
" <th>exang</th>\n",
" <th>oldpeak</th>\n",
" <th>slope</th>\n",
" <th>ca</th>\n",
" <th>thal</th>\n",
" <th>target</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>63</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>145</td>\n",
" <td>233</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>2.3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>37</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>130</td>\n",
" <td>250</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>187</td>\n",
" <td>0</td>\n",
" <td>3.5</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>41</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>130</td>\n",
" <td>204</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>172</td>\n",
" <td>0</td>\n",
" <td>1.4</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>56</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>120</td>\n",
" <td>236</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>178</td>\n",
" <td>0</td>\n",
" <td>0.8</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>57</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>120</td>\n",
" <td>354</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>163</td>\n",
" <td>1</td>\n",
" <td>0.6</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>57</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>140</td>\n",
" <td>192</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>148</td>\n",
" <td>0</td>\n",
" <td>0.4</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>56</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>140</td>\n",
" <td>294</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>153</td>\n",
" <td>0</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>44</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>120</td>\n",
" <td>263</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>173</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>52</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>172</td>\n",
" <td>199</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>162</td>\n",
" <td>0</td>\n",
" <td>0.5</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>57</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>150</td>\n",
" <td>168</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>174</td>\n",
" <td>0</td>\n",
" <td>1.6</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>54</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>140</td>\n",
" <td>239</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>160</td>\n",
" <td>0</td>\n",
" <td>1.2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>48</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>130</td>\n",
" <td>275</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>139</td>\n",
" <td>0</td>\n",
" <td>0.2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>49</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>130</td>\n",
" <td>266</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>171</td>\n",
" <td>0</td>\n",
" <td>0.6</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>64</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>110</td>\n",
" <td>211</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>144</td>\n",
" <td>1</td>\n",
" <td>1.8</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>58</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>150</td>\n",
" <td>283</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>162</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age sex cp trestbps chol fbs restecg thalach exang oldpeak \\\n",
"0 63 1 3 145 233 1 0 150 0 2.3 \n",
"1 37 1 2 130 250 0 1 187 0 3.5 \n",
"2 41 0 1 130 204 0 0 172 0 1.4 \n",
"3 56 1 1 120 236 0 1 178 0 0.8 \n",
"4 57 0 0 120 354 0 1 163 1 0.6 \n",
"5 57 1 0 140 192 0 1 148 0 0.4 \n",
"6 56 0 1 140 294 0 0 153 0 1.3 \n",
"7 44 1 1 120 263 0 1 173 0 0.0 \n",
"8 52 1 2 172 199 1 1 162 0 0.5 \n",
"9 57 1 2 150 168 0 1 174 0 1.6 \n",
"10 54 1 0 140 239 0 1 160 0 1.2 \n",
"11 48 0 2 130 275 0 1 139 0 0.2 \n",
"12 49 1 1 130 266 0 1 171 0 0.6 \n",
"13 64 1 3 110 211 0 0 144 1 1.8 \n",
"14 58 0 3 150 283 1 0 162 0 1.0 \n",
"\n",
" slope ca thal target \n",
"0 0 0 1 1 \n",
"1 0 0 2 1 \n",
"2 2 0 2 1 \n",
"3 2 0 2 1 \n",
"4 2 0 2 1 \n",
"5 1 0 1 1 \n",
"6 1 0 2 1 \n",
"7 2 0 3 1 \n",
"8 2 0 3 1 \n",
"9 2 0 2 1 \n",
"10 2 0 2 1 \n",
"11 2 0 2 1 \n",
"12 2 0 2 1 \n",
"13 1 0 2 1 \n",
"14 2 0 2 1 "
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"\n",
"df= pd.read_csv(r'C:\\Users\\Pranshu Saini\\Desktop\\disease-prediction-main\\docpat\\datasets\\heart.csv')\n",
"df.head(15)\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7bd28756",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(303, 14)"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3244edd5-3dd2-47f9-85da-b9cc26fed0d7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"age 0\n",
"sex 0\n",
"cp 0\n",
"trestbps 0\n",
"chol 0\n",
"fbs 0\n",
"restecg 0\n",
"thalach 0\n",
"exang 0\n",
"oldpeak 0\n",
"slope 0\n",
"ca 0\n",
"thal 0\n",
"target 0\n",
"dtype: int64"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "348dde1b-1ff9-4d98-91a9-29688f5b0933",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The reduced dataframe has 14 columns.\n"
]
}
],
"source": [
"# removing highly correlated features\n",
"\n",
"corr_matrix = df.corr().abs() \n",
"\n",
"mask = np.triu(np.ones_like(corr_matrix, dtype = bool))\n",
"tri_df = corr_matrix.mask(mask)\n",
"\n",
"to_drop = [x for x in tri_df.columns if any(tri_df[x] > 0.92)]\n",
"\n",
"df = df.drop(to_drop, axis = 1)\n",
"\n",
"print(f\"The reduced dataframe has {df.shape[1]} columns.\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "16a87f6e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(303, 14)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "ade36649-a20a-4bf2-8368-64f70cd000f2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(303, 13) (242, 13) (61, 13)\n"
]
}
],
"source": [
"A = df.drop(columns='target', axis=1)\n",
"B = df['target']\n",
"A_training, A_testing, B_training, B_testing = train_test_split(A, B, test_size=0.2, stratify=B, random_state=2)\n",
"\n",
"print(A.shape, A_training.shape, A_testing.shape)"
]
},
{
"cell_type": "markdown",
"id": "34f600fd-1faf-4a62-8aba-9a6d0fa38644",
"metadata": {},
"source": [
"LogisticRegression"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "fce2ced2-6375-4077-921e-2f568056fffe",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.8512396694214877\n",
"0.819672131147541\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\Pranshu Saini\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
"STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
"\n",
"Increase the number of iterations (max_iter) or scale the data as shown in:\n",
" https://scikit-learn.org/stable/modules/preprocessing.html\n",
"Please also refer to the documentation for alternative solver options:\n",
" https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
" n_iter_i = _check_optimize_result(\n"
]
}
],
"source": [
"# fitting data to model\n",
"\n",
"from sklearn.linear_model import LogisticRegression\n",
"\n",
"log_reg = LogisticRegression()\n",
"log_reg.fit(A_training, B_training)\n",
"B_pred = log_reg.predict(A_testing)\n",
"# accuracy score\n",
"\n",
"from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
"\n",
"print(accuracy_score(B_training, log_reg.predict(A_training)))\n",
"\n",
"log_reg_acc = accuracy_score(B_testing, log_reg.predict(A_testing))\n",
"print(log_reg_acc)"
]
},
{
"cell_type": "markdown",
"id": "f1a6ab2c-fc10-4f0b-8b07-1e01f8ce1243",
"metadata": {},
"source": [
"K Neighbors Classifier (KNN)\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f8aecca7-018d-41ba-bb3c-2a96cf73b007",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.78099173553719\n",
"0.6229508196721312\n"
]
}
],
"source": [
"from sklearn.neighbors import KNeighborsClassifier\n",
"\n",
"knn = KNeighborsClassifier()\n",
"knn.fit(A_training, B_training)\n",
"# model predictions \n",
"\n",
"B_pred = knn.predict(A_testing)\n",
"# accuracy score\n",
"\n",
"print(accuracy_score(B_training, knn.predict(A_training)))\n",
"\n",
"knn_acc = accuracy_score(B_testing, knn.predict(A_testing))\n",
"print(knn_acc)"
]
},
{
"cell_type": "markdown",
"id": "dd05e4cf-6aaf-468e-9eef-6f1b27d99560",
"metadata": {},
"source": [
"Support Vector Machine (SVM)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "35cc692b-d57f-4738-badf-5fd6c02c2889",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'C': 20, 'gamma': 0.0001}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.svm import SVC\n",
"from sklearn.model_selection import GridSearchCV\n",
"\n",
"svc = SVC(probability=True)\n",
"parameters = {\n",
" 'gamma' : [0.0001, 0.001, 0.01, 0.1],\n",
" 'C' : [0.01, 0.05, 0.5, 0.1, 1, 10, 15, 20]\n",
"}\n",
"\n",
"grid_search = GridSearchCV(svc, parameters)\n",
"grid_search.fit(A_training, B_training)\n",
"# best parameters\n",
"\n",
"grid_search.best_params_\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "cb090811-a42c-47ec-b7c7-43889430b93d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.6981292517006803"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# best score \n",
"\n",
"grid_search.best_score_\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "639e3132-7346-40d5-becf-6d230a9004fb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1.0\n",
"0.5409836065573771\n",
" precision recall f1-score support\n",
"\n",
" 0 0.50 0.43 0.46 28\n",
" 1 0.57 0.64 0.60 33\n",
"\n",
" accuracy 0.54 61\n",
" macro avg 0.53 0.53 0.53 61\n",
"weighted avg 0.54 0.54 0.54 61\n",
"\n"
]
}
],
"source": [
"svc = SVC(C = 10, gamma = 0.01, probability=True)\n",
"svc.fit(A_training, B_training)\n",
"# model predictions \n",
"\n",
"B_pred = svc.predict(A_testing)\n",
"# accuracy score\n",
"\n",
"print(accuracy_score(B_training, svc.predict(A_training)))\n",
"\n",
"svc_acc = accuracy_score(B_testing, svc.predict(A_testing))\n",
"print(svc_acc)\n",
"# classification report\n",
"\n",
"print(classification_report(B_testing, B_pred))"
]
},
{
"cell_type": "markdown",
"id": "0e3059b1-2e79-46bd-9195-98cbd044b75c",
"metadata": {},
"source": [
"DECISION TREE"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "79b6cc36-eab3-4502-861f-0c4576170ffd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fitting 5 folds for each of 8640 candidates, totalling 43200 fits\n"
]
},
{
"data": {
"text/html": [
"<style>#sk-container-id-1 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
" /* Definition of color scheme for unfitted estimators */\n",
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
" --sklearn-color-unfitted-level-3: chocolate;\n",
" /* Definition of color scheme for fitted estimators */\n",
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
" --sklearn-color-fitted-level-1: #d4ebff;\n",
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
"\n",
" /* Specific color for light theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-icon: #696969;\n",
"\n",
" @media (prefers-color-scheme: dark) {\n",
" /* Redefinition of color scheme for dark theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-icon: #878787;\n",
" }\n",
"}\n",
"\n",
"#sk-container-id-1 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-1 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
" height: 1px;\n",
" margin: -1px;\n",
" overflow: hidden;\n",
" padding: 0;\n",
" position: absolute;\n",
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
" padding-bottom: 0.4em;\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
" display: inline-block !important;\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
"div.sk-parallel-item,\n",
"div.sk-serial,\n",
"div.sk-item {\n",
" /* draw centered vertical line to link estimators */\n",
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
" background-size: 2px 100%;\n",
" background-repeat: no-repeat;\n",
" background-position: center center;\n",
"}\n",
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
" background-color: var(--sklearn-color-background);\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
" background-color: var(--sklearn-color-background);\n",
" padding-right: 1em;\n",
" padding-left: 1em;\n",
"}\n",
"\n",
"\n",
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
"clickable and can be expanded/collapsed.\n",
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
"*/\n",
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
"#sk-container-id-1 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
" margin-bottom: 0;\n",
" padding: 0.5em;\n",
" box-sizing: border-box;\n",
" text-align: center;\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
" margin-right: 0.25em;\n",
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
" text-align: left;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-1 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
"#sk-container-id-1 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-1 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
" box-sizing: border-box;\n",
" margin-bottom: 0.5em;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-1 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
"\n",
"/* Common style for \"i\" and \"?\" */\n",
"\n",
".sk-estimator-doc-link,\n",
"a:link.sk-estimator-doc-link,\n",
"a:visited.sk-estimator-doc-link {\n",
" float: right;\n",
" font-size: smaller;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1em;\n",
" height: 1em;\n",
" width: 1em;\n",
" text-decoration: none !important;\n",
" margin-left: 1ex;\n",
" /* unfitted */\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted,\n",
"a:link.sk-estimator-doc-link.fitted,\n",
"a:visited.sk-estimator-doc-link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"/* Span, style for the box shown on hovering the info icon */\n",
".sk-estimator-doc-link span {\n",
" display: none;\n",
" z-index: 9999;\n",
" position: relative;\n",
" font-weight: normal;\n",
" right: .2ex;\n",
" padding: .5ex;\n",
" margin: .5ex;\n",
" width: min-content;\n",
" min-width: 20ex;\n",
" max-width: 50ex;\n",
" color: var(--sklearn-color-text);\n",
" box-shadow: 2pt 2pt 4pt #999;\n",
" /* unfitted */\n",
" background: var(--sklearn-color-unfitted-level-0);\n",
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted span {\n",
" /* fitted */\n",
" background: var(--sklearn-color-fitted-level-0);\n",
" border: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link:hover span {\n",
" display: block;\n",
"}\n",
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1rem;\n",
" height: 1rem;\n",
" width: 1rem;\n",
" text-decoration: none;\n",
" /* unfitted */\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5, estimator=DecisionTreeClassifier(), n_jobs=-1,\n",
" param_grid={'criterion': ['gini', 'entropy'],\n",
" 'max_depth': range(2, 32),\n",
" 'min_samples_leaf': range(1, 10),\n",
" 'min_samples_split': range(2, 10),\n",
" 'splitter': ['best', 'random']},\n",
" verbose=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> GridSearchCV<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.model_selection.GridSearchCV.html\">?<span>Documentation for GridSearchCV</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>GridSearchCV(cv=5, estimator=DecisionTreeClassifier(), n_jobs=-1,\n",
" param_grid={'criterion': ['gini', 'entropy'],\n",
" 'max_depth': range(2, 32),\n",
" 'min_samples_leaf': range(1, 10),\n",
" 'min_samples_split': range(2, 10),\n",
" 'splitter': ['best', 'random']},\n",
" verbose=1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: DecisionTreeClassifier</label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeClassifier()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> DecisionTreeClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.tree.DecisionTreeClassifier.html\">?<span>Documentation for DecisionTreeClassifier</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeClassifier()</pre></div> </div></div></div></div></div></div></div></div></div>"
],
"text/plain": [
"GridSearchCV(cv=5, estimator=DecisionTreeClassifier(), n_jobs=-1,\n",
" param_grid={'criterion': ['gini', 'entropy'],\n",
" 'max_depth': range(2, 32),\n",
" 'min_samples_leaf': range(1, 10),\n",
" 'min_samples_split': range(2, 10),\n",
" 'splitter': ['best', 'random']},\n",
" verbose=1)"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.tree import DecisionTreeClassifier\n",
"\n",
"dtc = DecisionTreeClassifier()\n",
"\n",
"parameters = {\n",
" 'criterion' : ['gini', 'entropy'],\n",
" 'max_depth' : range(2, 32, 1),\n",
" 'min_samples_leaf' : range(1, 10, 1),\n",
" 'min_samples_split' : range(2, 10, 1),\n",
" 'splitter' : ['best', 'random']\n",
"}\n",
"\n",
"grid_search_dt = GridSearchCV(dtc, parameters, cv = 5, n_jobs = -1, verbose = 1)\n",
"grid_search_dt.fit(A_training, B_training)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "362b8867-1ec8-4eba-84b0-c98486db2d2f",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-2 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
" /* Definition of color scheme for unfitted estimators */\n",
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
" --sklearn-color-unfitted-level-3: chocolate;\n",
" /* Definition of color scheme for fitted estimators */\n",
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
" --sklearn-color-fitted-level-1: #d4ebff;\n",
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
"\n",
" /* Specific color for light theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-icon: #696969;\n",
"\n",
" @media (prefers-color-scheme: dark) {\n",
" /* Redefinition of color scheme for dark theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-icon: #878787;\n",
" }\n",
"}\n",
"\n",
"#sk-container-id-2 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-2 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-2 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
" height: 1px;\n",
" margin: -1px;\n",
" overflow: hidden;\n",
" padding: 0;\n",
" position: absolute;\n",
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
" padding-bottom: 0.4em;\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
" display: inline-block !important;\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
"div.sk-parallel-item,\n",
"div.sk-serial,\n",
"div.sk-item {\n",
" /* draw centered vertical line to link estimators */\n",
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
" background-size: 2px 100%;\n",
" background-repeat: no-repeat;\n",
" background-position: center center;\n",
"}\n",
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-2 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
" background-color: var(--sklearn-color-background);\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-2 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
" background-color: var(--sklearn-color-background);\n",
" padding-right: 1em;\n",
" padding-left: 1em;\n",
"}\n",
"\n",
"\n",
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
"clickable and can be expanded/collapsed.\n",
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
"*/\n",
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-2 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
"#sk-container-id-2 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
" margin-bottom: 0;\n",
" padding: 0.5em;\n",
" box-sizing: border-box;\n",
" text-align: center;\n",
"}\n",
"\n",
"#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
" margin-right: 0.25em;\n",
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-2 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
" text-align: left;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
"#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
"#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
"#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-2 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
"#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
"#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
"#sk-container-id-2 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-2 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
" box-sizing: border-box;\n",
" margin-bottom: 0.5em;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-2 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
"\n",
"/* Common style for \"i\" and \"?\" */\n",
"\n",
".sk-estimator-doc-link,\n",
"a:link.sk-estimator-doc-link,\n",
"a:visited.sk-estimator-doc-link {\n",
" float: right;\n",
" font-size: smaller;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1em;\n",
" height: 1em;\n",
" width: 1em;\n",
" text-decoration: none !important;\n",
" margin-left: 1ex;\n",
" /* unfitted */\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted,\n",
"a:link.sk-estimator-doc-link.fitted,\n",
"a:visited.sk-estimator-doc-link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"/* Span, style for the box shown on hovering the info icon */\n",
".sk-estimator-doc-link span {\n",
" display: none;\n",
" z-index: 9999;\n",
" position: relative;\n",
" font-weight: normal;\n",
" right: .2ex;\n",
" padding: .5ex;\n",
" margin: .5ex;\n",
" width: min-content;\n",
" min-width: 20ex;\n",
" max-width: 50ex;\n",
" color: var(--sklearn-color-text);\n",
" box-shadow: 2pt 2pt 4pt #999;\n",
" /* unfitted */\n",
" background: var(--sklearn-color-unfitted-level-0);\n",
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted span {\n",
" /* fitted */\n",
" background: var(--sklearn-color-fitted-level-0);\n",
" border: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link:hover span {\n",
" display: block;\n",
"}\n",
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-2 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1rem;\n",
" height: 1rem;\n",
" width: 1rem;\n",
" text-decoration: none;\n",
" /* unfitted */\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-2 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"#sk-container-id-2 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier(criterion='entropy', max_depth=19, min_samples_leaf=4,\n",
" min_samples_split=6, splitter='random')</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> DecisionTreeClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.tree.DecisionTreeClassifier.html\">?<span>Documentation for DecisionTreeClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeClassifier(criterion='entropy', max_depth=19, min_samples_leaf=4,\n",
" min_samples_split=6, splitter='random')</pre></div> </div></div></div></div>"
],
"text/plain": [
"DecisionTreeClassifier(criterion='entropy', max_depth=19, min_samples_leaf=4,\n",
" min_samples_split=6, splitter='random')"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"dtc = DecisionTreeClassifier(criterion= 'entropy', max_depth= 19, min_samples_leaf= 4, min_samples_split= 6, splitter= 'random')\n",
"dtc.fit(A_training, B_training)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "2ac9e062-42ce-4baa-81f6-b004efa79279",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.9132231404958677\n",
"0.6885245901639344\n"
]
}
],
"source": [
"B_pred = dtc.predict(A_testing)\n",
"# accuracy score\n",
"\n",
"print(accuracy_score(B_training, dtc.predict(A_training)))\n",
"\n",
"dtc_acc = accuracy_score(B_testing, dtc.predict(A_testing))\n",
"print(dtc_acc)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "23941f55-8363-4bdd-a552-1bbb83f1c206",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 0.67 0.64 0.65 28\n",
" 1 0.71 0.73 0.72 33\n",
"\n",
" accuracy 0.69 61\n",
" macro avg 0.69 0.69 0.69 61\n",
"weighted avg 0.69 0.69 0.69 61\n",
"\n"
]
}
],
"source": [
"# classification report\n",
"\n",
"print(classification_report(B_testing, B_pred))"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "029bfdba-3d0e-4d3a-9ce1-06fe8de61f82",
"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>Model</th>\n",
" <th>Score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Logistic Regression</td>\n",
" <td>81.97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Decision Tree Classifier</td>\n",
" <td>68.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>KNN</td>\n",
" <td>62.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>SVM</td>\n",
" <td>54.10</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model Score\n",
"0 Logistic Regression 81.97\n",
"3 Decision Tree Classifier 68.85\n",
"1 KNN 62.30\n",
"2 SVM 54.10"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"models = pd.DataFrame({\n",
" 'Model': ['Logistic Regression', 'KNN', 'SVM', 'Decision Tree Classifier'],\n",
" 'Score': [100*round(log_reg_acc,4), 100*round(knn_acc,4), 100*round(svc_acc,4), 100*round(dtc_acc,4)]\n",
"})\n",
"models.sort_values(by = 'Score', ascending = False)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "12de1159",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" age sex cp trestbps chol fbs restecg thalach exang oldpeak \\\n",
"165 67 1 0 160 286 0 0 108 1 1.5 \n",
"166 67 1 0 120 229 0 0 129 1 2.6 \n",
"167 62 0 0 140 268 0 0 160 0 3.6 \n",
"168 63 1 0 130 254 0 0 147 0 1.4 \n",
"169 53 1 0 140 203 1 0 155 1 3.1 \n",
".. ... ... .. ... ... ... ... ... ... ... \n",
"298 57 0 0 140 241 0 1 123 1 0.2 \n",
"299 45 1 3 110 264 0 1 132 0 1.2 \n",
"300 68 1 0 144 193 1 1 141 0 3.4 \n",
"301 57 1 0 130 131 0 1 115 1 1.2 \n",
"302 57 0 1 130 236 0 0 174 0 0.0 \n",
"\n",
" slope ca thal target \n",
"165 1 3 2 0 \n",
"166 1 2 3 0 \n",
"167 0 2 2 0 \n",
"168 1 1 3 0 \n",
"169 0 0 3 0 \n",
".. ... .. ... ... \n",
"298 1 0 3 0 \n",
"299 1 0 3 0 \n",
"300 1 2 3 0 \n",
"301 1 1 3 0 \n",
"302 1 1 2 0 \n",
"\n",
"[138 rows x 14 columns]\n"
]
}
],
"source": [
"filtered_df = df[df['target'] == 0]\n",
"C = pd.DataFrame(filtered_df) \n",
"print(C)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ea84040-eb10-42f2-97c7-f91b52129aef",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\Pranshu Saini\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\sklearn\\base.py:493: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
" warnings.warn(\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"a = [63, 1, 3, 145, 233, 1, 0, 150, 0, 2.3, 0, 0, 1]\n",
"b=[67 , 1, 0, 160, 286, 0, 0, 108, 1, 1.5, 1, 3, 2 ]\n",
"a_reshaped = np.array().reshape(1, -1)\n",
"\n",
"B = log_reg.predict(a_reshaped)\n",
"print(B)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e66f5d96-79a7-4ac9-a01b-e753181af587",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 20,
"id": "7552b5a0-d407-4bf9-98e0-56b8bd7c3245",
"metadata": {},
"outputs": [],
"source": [
"import pickle\n",
"filename = r'C:\\Users\\Pranshu Saini\\Desktop\\disease-prediction-main\\docpat\\model\\heart_disease_model.pkl'\n",
"pickle.dump(log_reg, open(filename, 'wb'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4f01bd6a-95cc-4383-a17c-0e0ae3ff2e69",
"metadata": {},
"outputs": [],
"source": [
"'''import pickle\n",
"def load_model(path):\n",
" with open(path, 'rb') as file:\n",
" model = pickle.load(file)\n",
"heart_model = load_model(r'C:\\Users\\DELL\\Desktop\\app\\heart_disease_model.pkl')\n",
"def predict(inputs):\n",
" return heart_model.predict(inputs)'''"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3765e3cf-d221-4413-a91e-9b7d4d49bd3c",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8fc26d0",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "66257935",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}