mirror of
https://github.com/mudabbir-ahmad/UNI-PROG3-CW2-MLWP.git
synced 2026-10-07 20:10:20 +00:00
2095 lines
95 KiB
Plaintext
2095 lines
95 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"metadata": {
|
|
"collapsed": true
|
|
},
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## This is the Q2 Notebook!\n",
|
|
"\n",
|
|
"It's tracked via GitHub! hence the need for this line for the init commit"
|
|
],
|
|
"id": "bb3519b1aa083259"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.826174300Z",
|
|
"start_time": "2026-04-25T21:15:54.817214200Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from sklearn.preprocessing import StandardScaler\n",
|
|
"from sklearn.linear_model import LogisticRegression\n",
|
|
"from sklearn.neighbors import KNeighborsClassifier\n",
|
|
"from sklearn.metrics import accuracy_score, f1_score, confusion_matrix, ConfusionMatrixDisplay\n",
|
|
"import matplotlib.pyplot as plt"
|
|
],
|
|
"id": "76e70b2ed9af0b56",
|
|
"outputs": [],
|
|
"execution_count": 19
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.842931600Z",
|
|
"start_time": "2026-04-25T21:15:54.827174Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "df = pd.read_csv('data/googleplaystore_new_new.csv')",
|
|
"id": "f44380615d3aba25",
|
|
"outputs": [],
|
|
"execution_count": 20
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Part A\n",
|
|
"\n",
|
|
"Q: A. Using (Rating + Reviews + Content Rating + Size in Bytes +\n",
|
|
"Installs_Num), using Logistic regression and KNN, find and discuss the best\n",
|
|
"classification model to predict “Category” (use the training/validation/test\n",
|
|
"partition without cross-validation). **[8 marks]**\n"
|
|
],
|
|
"id": "1baa7daa49445720"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.857539500Z",
|
|
"start_time": "2026-04-25T21:15:54.844931800Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"columns_to_keep = ['Rating', 'Reviews', 'Content Rating', 'Size in bytes', 'Numeric Installs', 'Category']\n",
|
|
"df_part_a = df[columns_to_keep]"
|
|
],
|
|
"id": "f6fd7137bf91f31e",
|
|
"outputs": [],
|
|
"execution_count": 21
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.877630200Z",
|
|
"start_time": "2026-04-25T21:15:54.857539500Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"X_raw = df_part_a.drop('Category', axis=1)\n",
|
|
"y = df_part_a['Category']"
|
|
],
|
|
"id": "b5daf475a5d5ca15",
|
|
"outputs": [],
|
|
"execution_count": 22
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.890619Z",
|
|
"start_time": "2026-04-25T21:15:54.878630300Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "X = pd.get_dummies(X_raw, columns=['Content Rating'])",
|
|
"id": "99a441c665dcc19b",
|
|
"outputs": [],
|
|
"execution_count": 23
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.896884800Z",
|
|
"start_time": "2026-04-25T21:15:54.891625500Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "X_temp, X_test, y_temp, y_test = train_test_split(X, y, test_size=0.2, random_state=101)",
|
|
"id": "c6eb622c0f7ec63c",
|
|
"outputs": [],
|
|
"execution_count": 24
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.904746500Z",
|
|
"start_time": "2026-04-25T21:15:54.897883400Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "X_train, X_val, y_train, y_val = train_test_split(X_temp, y_temp, test_size=0.25, random_state=101)",
|
|
"id": "89e8f117f057e0e2",
|
|
"outputs": [],
|
|
"execution_count": 25
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.914005600Z",
|
|
"start_time": "2026-04-25T21:15:54.905746300Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"scaler = StandardScaler()\n",
|
|
"scaled_X_train = scaler.fit_transform(X_train)\n",
|
|
"scaled_X_val = scaler.transform(X_val)\n",
|
|
"scaled_X_test = scaler.transform(X_test)"
|
|
],
|
|
"id": "d529991171fafb3e",
|
|
"outputs": [],
|
|
"execution_count": 26
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"cell_type": "markdown",
|
|
"source": "## Logistic Regression",
|
|
"id": "66dc17cdf1a00a06"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.935689400Z",
|
|
"start_time": "2026-04-25T21:15:54.915006600Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"log_model = LogisticRegression(max_iter=1000)\n",
|
|
"log_model.fit(scaled_X_train, y_train)"
|
|
],
|
|
"id": "84128fa4e7823565",
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"LogisticRegression(max_iter=1000)"
|
|
],
|
|
"text/html": [
|
|
"<style>#sk-container-id-3 {\n",
|
|
" /* Definition of color scheme common for light and dark mode */\n",
|
|
" --sklearn-color-text: #000;\n",
|
|
" --sklearn-color-text-muted: #666;\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",
|
|
"\n",
|
|
"#sk-container-id-3.light {\n",
|
|
" /* Specific color for light theme */\n",
|
|
" --sklearn-color-text-on-default-background: black;\n",
|
|
" --sklearn-color-background: white;\n",
|
|
" --sklearn-color-border-box: black;\n",
|
|
" --sklearn-color-icon: #696969;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3.dark {\n",
|
|
" --sklearn-color-text-on-default-background: white;\n",
|
|
" --sklearn-color-background: #111;\n",
|
|
" --sklearn-color-border-box: white;\n",
|
|
" --sklearn-color-icon: #878787;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 {\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 pre {\n",
|
|
" padding: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-3 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-3 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-3 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-3 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-3 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-3 div.sk-parallel-item {\n",
|
|
" display: flex;\n",
|
|
" flex-direction: column;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
|
|
" align-self: flex-end;\n",
|
|
" width: 50%;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
|
|
" align-self: flex-start;\n",
|
|
" width: 50%;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
|
|
" width: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Serial-specific style estimator block */\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-3 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-3 label.sk-toggleable__label {\n",
|
|
" cursor: pointer;\n",
|
|
" display: flex;\n",
|
|
" width: 100%;\n",
|
|
" margin-bottom: 0;\n",
|
|
" padding: 0.5em;\n",
|
|
" box-sizing: border-box;\n",
|
|
" text-align: center;\n",
|
|
" align-items: center;\n",
|
|
" justify-content: center;\n",
|
|
" gap: 0.5em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 label.sk-toggleable__label .caption {\n",
|
|
" font-size: 0.6rem;\n",
|
|
" font-weight: lighter;\n",
|
|
" color: var(--sklearn-color-text-muted);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-3 label.sk-toggleable__label-arrow:hover:before {\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Toggleable content - dropdown */\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-toggleable__content {\n",
|
|
" display: none;\n",
|
|
" text-align: left;\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-3 div.sk-toggleable__content.fitted pre {\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
|
" /* Expand drop-down */\n",
|
|
" display: block;\n",
|
|
" width: 100%;\n",
|
|
" overflow: visible;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-3 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-3 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-3 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-3 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-3 div.sk-label label.sk-toggleable__label,\n",
|
|
"#sk-container-id-3 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-3 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-3 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-3 div.sk-label label {\n",
|
|
" font-family: monospace;\n",
|
|
" font-weight: bold;\n",
|
|
" line-height: 1.2em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 div.sk-label-container {\n",
|
|
" text-align: center;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Estimator-specific */\n",
|
|
"#sk-container-id-3 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-3 div.sk-estimator.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* on hover */\n",
|
|
"#sk-container-id-3 div.sk-estimator:hover {\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-3 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-unfitted-level-0);\n",
|
|
" border-radius: 1em;\n",
|
|
" height: 1em;\n",
|
|
" width: 1em;\n",
|
|
" text-decoration: none !important;\n",
|
|
" margin-left: 0.5em;\n",
|
|
" text-align: center;\n",
|
|
" /* unfitted */\n",
|
|
" border: var(--sklearn-color-unfitted-level-3) 1pt solid;\n",
|
|
" color: var(--sklearn-color-unfitted-level-3);\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",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
" border: var(--sklearn-color-fitted-level-3) 1pt solid;\n",
|
|
" color: var(--sklearn-color-fitted-level-3);\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",
|
|
" border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
|
|
" color: var(--sklearn-color-unfitted-level-0);\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",
|
|
" border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
|
|
" color: var(--sklearn-color-fitted-level-0);\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-3 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-unfitted-level-0);\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-3 a.estimator_doc_link.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\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-3 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-3 a.estimator_doc_link.fitted:hover {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table {\n",
|
|
" font-family: monospace;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table summary {\n",
|
|
" padding: .5rem;\n",
|
|
" cursor: pointer;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table summary::marker {\n",
|
|
" font-size: 0.7rem;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table details[open] {\n",
|
|
" padding-left: 0.1rem;\n",
|
|
" padding-right: 0.1rem;\n",
|
|
" padding-bottom: 0.3rem;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table {\n",
|
|
" margin-left: auto !important;\n",
|
|
" margin-right: auto !important;\n",
|
|
" margin-top: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:nth-child(odd) {\n",
|
|
" background-color: #fff;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:nth-child(even) {\n",
|
|
" background-color: #f6f6f6;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:hover {\n",
|
|
" background-color: #e0e0e0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table table td {\n",
|
|
" border: 1px solid rgba(106, 105, 104, 0.232);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/*\n",
|
|
" `table td`is set in notebook with right text-align.\n",
|
|
" We need to overwrite it.\n",
|
|
"*/\n",
|
|
".estimator-table table td.param {\n",
|
|
" text-align: left;\n",
|
|
" position: relative;\n",
|
|
" padding: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td {\n",
|
|
" color:rgb(255, 94, 0);\n",
|
|
" text-align: left !important;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td.value {\n",
|
|
" color:rgb(255, 94, 0);\n",
|
|
" background-color: transparent;\n",
|
|
"}\n",
|
|
"\n",
|
|
".default td {\n",
|
|
" color: black;\n",
|
|
" text-align: left !important;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td i,\n",
|
|
".default td i {\n",
|
|
" color: black;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/*\n",
|
|
" Styles for parameter documentation links\n",
|
|
" We need styling for visited so jupyter doesn't overwrite it\n",
|
|
"*/\n",
|
|
"a.param-doc-link,\n",
|
|
"a.param-doc-link:link,\n",
|
|
"a.param-doc-link:visited {\n",
|
|
" text-decoration: underline dashed;\n",
|
|
" text-underline-offset: .3em;\n",
|
|
" color: inherit;\n",
|
|
" display: block;\n",
|
|
" padding: .5em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* \"hack\" to make the entire area of the cell containing the link clickable */\n",
|
|
"a.param-doc-link::before {\n",
|
|
" position: absolute;\n",
|
|
" content: \"\";\n",
|
|
" inset: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".param-doc-description {\n",
|
|
" display: none;\n",
|
|
" position: absolute;\n",
|
|
" z-index: 9999;\n",
|
|
" left: 0;\n",
|
|
" padding: .5ex;\n",
|
|
" margin-left: 1.5em;\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
" box-shadow: .3em .3em .4em #999;\n",
|
|
" width: max-content;\n",
|
|
" text-align: left;\n",
|
|
" max-height: 10em;\n",
|
|
" overflow-y: auto;\n",
|
|
"\n",
|
|
" /* unfitted */\n",
|
|
" background: var(--sklearn-color-unfitted-level-0);\n",
|
|
" border: thin solid var(--sklearn-color-unfitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Fitted state for parameter tooltips */\n",
|
|
".fitted .param-doc-description {\n",
|
|
" /* fitted */\n",
|
|
" background: var(--sklearn-color-fitted-level-0);\n",
|
|
" border: thin solid var(--sklearn-color-fitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
".param-doc-link:hover .param-doc-description {\n",
|
|
" display: block;\n",
|
|
"}\n",
|
|
"\n",
|
|
".copy-paste-icon {\n",
|
|
" background-image: url(data:image/svg+xml;base64,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);\n",
|
|
" background-repeat: no-repeat;\n",
|
|
" background-size: 14px 14px;\n",
|
|
" background-position: 0;\n",
|
|
" display: inline-block;\n",
|
|
" width: 14px;\n",
|
|
" height: 14px;\n",
|
|
" cursor: pointer;\n",
|
|
"}\n",
|
|
"</style><body><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(max_iter=1000)</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-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
|
|
" <div class=\"estimator-table\">\n",
|
|
" <details>\n",
|
|
" <summary>Parameters</summary>\n",
|
|
" <table class=\"parameters-table\">\n",
|
|
" <tbody>\n",
|
|
" \n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('penalty',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=penalty,-%7B%27l1%27%2C%20%27l2%27%2C%20%27elasticnet%27%2C%20None%7D%2C%20default%3D%27l2%27\">\n",
|
|
" penalty\n",
|
|
" <span class=\"param-doc-description\">penalty: {'l1', 'l2', 'elasticnet', None}, default='l2'<br><br>Specify the norm of the penalty:<br><br>- `None`: no penalty is added;<br>- `'l2'`: add a L2 penalty term and it is the default choice;<br>- `'l1'`: add a L1 penalty term;<br>- `'elasticnet'`: both L1 and L2 penalty terms are added.<br><br>.. warning::<br> Some penalties may not work with some solvers. See the parameter<br> `solver` below, to know the compatibility between the penalty and<br> solver.<br><br>.. versionadded:: 0.19<br> l1 penalty with SAGA solver (allowing 'multinomial' + L1)<br><br>.. deprecated:: 1.8<br> `penalty` was deprecated in version 1.8 and will be removed in 1.10.<br> Use `l1_ratio` instead. `l1_ratio=0` for `penalty='l2'`, `l1_ratio=1` for<br> `penalty='l1'` and `l1_ratio` set to any float between 0 and 1 for<br> `'penalty='elasticnet'`.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">'deprecated'</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('C',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=C,-float%2C%20default%3D1.0\">\n",
|
|
" C\n",
|
|
" <span class=\"param-doc-description\">C: float, default=1.0<br><br>Inverse of regularization strength; must be a positive float.<br>Like in support vector machines, smaller values specify stronger<br>regularization. `C=np.inf` results in unpenalized logistic regression.<br>For a visual example on the effect of tuning the `C` parameter<br>with an L1 penalty, see:<br>:ref:`sphx_glr_auto_examples_linear_model_plot_logistic_path.py`.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">1.0</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('l1_ratio',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=l1_ratio,-float%2C%20default%3D0.0\">\n",
|
|
" l1_ratio\n",
|
|
" <span class=\"param-doc-description\">l1_ratio: float, default=0.0<br><br>The Elastic-Net mixing parameter, with `0 <= l1_ratio <= 1`. Setting<br>`l1_ratio=1` gives a pure L1-penalty, setting `l1_ratio=0` a pure L2-penalty.<br>Any value between 0 and 1 gives an Elastic-Net penalty of the form<br>`l1_ratio * L1 + (1 - l1_ratio) * L2`.<br><br>.. warning::<br> Certain values of `l1_ratio`, i.e. some penalties, may not work with some<br> solvers. See the parameter `solver` below, to know the compatibility between<br> the penalty and solver.<br><br>.. versionchanged:: 1.8<br> Default value changed from None to 0.0.<br><br>.. deprecated:: 1.8<br> `None` is deprecated and will be removed in version 1.10. Always use<br> `l1_ratio` to specify the penalty type.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">0.0</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('dual',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=dual,-bool%2C%20default%3DFalse\">\n",
|
|
" dual\n",
|
|
" <span class=\"param-doc-description\">dual: bool, default=False<br><br>Dual (constrained) or primal (regularized, see also<br>:ref:`this equation <regularized-logistic-loss>`) formulation. Dual formulation<br>is only implemented for l2 penalty with liblinear solver. Prefer `dual=False`<br>when n_samples > n_features.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">False</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('tol',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=tol,-float%2C%20default%3D1e-4\">\n",
|
|
" tol\n",
|
|
" <span class=\"param-doc-description\">tol: float, default=1e-4<br><br>Tolerance for stopping criteria.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">0.0001</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('fit_intercept',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=fit_intercept,-bool%2C%20default%3DTrue\">\n",
|
|
" fit_intercept\n",
|
|
" <span class=\"param-doc-description\">fit_intercept: bool, default=True<br><br>Specifies if a constant (a.k.a. bias or intercept) should be<br>added to the decision function.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">True</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('intercept_scaling',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=intercept_scaling,-float%2C%20default%3D1\">\n",
|
|
" intercept_scaling\n",
|
|
" <span class=\"param-doc-description\">intercept_scaling: float, default=1<br><br>Useful only when the solver `liblinear` is used<br>and `self.fit_intercept` is set to `True`. In this case, `x` becomes<br>`[x, self.intercept_scaling]`,<br>i.e. a \"synthetic\" feature with constant value equal to<br>`intercept_scaling` is appended to the instance vector.<br>The intercept becomes<br>``intercept_scaling * synthetic_feature_weight``.<br><br>.. note::<br> The synthetic feature weight is subject to L1 or L2<br> regularization as all other features.<br> To lessen the effect of regularization on synthetic feature weight<br> (and therefore on the intercept) `intercept_scaling` has to be increased.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">1</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('class_weight',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=class_weight,-dict%20or%20%27balanced%27%2C%20default%3DNone\">\n",
|
|
" class_weight\n",
|
|
" <span class=\"param-doc-description\">class_weight: dict or 'balanced', default=None<br><br>Weights associated with classes in the form ``{class_label: weight}``.<br>If not given, all classes are supposed to have weight one.<br><br>The \"balanced\" mode uses the values of y to automatically adjust<br>weights inversely proportional to class frequencies in the input data<br>as ``n_samples / (n_classes * np.bincount(y))``.<br><br>Note that these weights will be multiplied with sample_weight (passed<br>through the fit method) if sample_weight is specified.<br><br>.. versionadded:: 0.17<br> *class_weight='balanced'*</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">None</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('random_state',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=random_state,-int%2C%20RandomState%20instance%2C%20default%3DNone\">\n",
|
|
" random_state\n",
|
|
" <span class=\"param-doc-description\">random_state: int, RandomState instance, default=None<br><br>Used when ``solver`` == 'sag', 'saga' or 'liblinear' to shuffle the<br>data. See :term:`Glossary <random_state>` for details.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">None</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('solver',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=solver,-%7B%27lbfgs%27%2C%20%27liblinear%27%2C%20%27newton-cg%27%2C%20%27newton-cholesky%27%2C%20%27sag%27%2C%20%27saga%27%7D%2C%20%20%20%20%20%20%20%20%20%20%20%20%20default%3D%27lbfgs%27\">\n",
|
|
" solver\n",
|
|
" <span class=\"param-doc-description\">solver: {'lbfgs', 'liblinear', 'newton-cg', 'newton-cholesky', 'sag', 'saga'}, default='lbfgs'<br><br>Algorithm to use in the optimization problem. Default is 'lbfgs'.<br>To choose a solver, you might want to consider the following aspects:<br><br>- 'lbfgs' is a good default solver because it works reasonably well for a wide<br> class of problems.<br>- For :term:`multiclass` problems (`n_classes >= 3`), all solvers except<br> 'liblinear' minimize the full multinomial loss, 'liblinear' will raise an<br> error.<br>- 'newton-cholesky' is a good choice for<br> `n_samples` >> `n_features * n_classes`, especially with one-hot encoded<br> categorical features with rare categories. Be aware that the memory usage<br> of this solver has a quadratic dependency on `n_features * n_classes`<br> because it explicitly computes the full Hessian matrix.<br>- For small datasets, 'liblinear' is a good choice, whereas 'sag'<br> and 'saga' are faster for large ones;<br>- 'liblinear' can only handle binary classification by default. To apply a<br> one-versus-rest scheme for the multiclass setting one can wrap it with the<br> :class:`~sklearn.multiclass.OneVsRestClassifier`.<br><br>.. warning::<br> The choice of the algorithm depends on the penalty chosen (`l1_ratio=0`<br> for L2-penalty, `l1_ratio=1` for L1-penalty and `0 < l1_ratio < 1` for<br> Elastic-Net) and on (multinomial) multiclass support:<br><br> ================= ======================== ======================<br> solver l1_ratio multinomial multiclass<br> ================= ======================== ======================<br> 'lbfgs' l1_ratio=0 yes<br> 'liblinear' l1_ratio=1 or l1_ratio=0 no<br> 'newton-cg' l1_ratio=0 yes<br> 'newton-cholesky' l1_ratio=0 yes<br> 'sag' l1_ratio=0 yes<br> 'saga' 0<=l1_ratio<=1 yes<br> ================= ======================== ======================<br><br>.. note::<br> 'sag' and 'saga' fast convergence is only guaranteed on features<br> with approximately the same scale. You can preprocess the data with<br> a scaler from :mod:`sklearn.preprocessing`.<br><br>.. seealso::<br> Refer to the :ref:`User Guide <Logistic_regression>` for more<br> information regarding :class:`LogisticRegression` and more specifically the<br> :ref:`Table <logistic_regression_solvers>`<br> summarizing solver/penalty supports.<br><br>.. versionadded:: 0.17<br> Stochastic Average Gradient (SAG) descent solver. Multinomial support in<br> version 0.18.<br>.. versionadded:: 0.19<br> SAGA solver.<br>.. versionchanged:: 0.22<br> The default solver changed from 'liblinear' to 'lbfgs' in 0.22.<br>.. versionadded:: 1.2<br> newton-cholesky solver. Multinomial support in version 1.6.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">'lbfgs'</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"user-set\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('max_iter',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=max_iter,-int%2C%20default%3D100\">\n",
|
|
" max_iter\n",
|
|
" <span class=\"param-doc-description\">max_iter: int, default=100<br><br>Maximum number of iterations taken for the solvers to converge.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">1000</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('verbose',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=verbose,-int%2C%20default%3D0\">\n",
|
|
" verbose\n",
|
|
" <span class=\"param-doc-description\">verbose: int, default=0<br><br>For the liblinear and lbfgs solvers set verbose to any positive<br>number for verbosity.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">0</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('warm_start',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=warm_start,-bool%2C%20default%3DFalse\">\n",
|
|
" warm_start\n",
|
|
" <span class=\"param-doc-description\">warm_start: bool, default=False<br><br>When set to True, reuse the solution of the previous call to fit as<br>initialization, otherwise, just erase the previous solution.<br>Useless for liblinear solver. See :term:`the Glossary <warm_start>`.<br><br>.. versionadded:: 0.17<br> *warm_start* to support *lbfgs*, *newton-cg*, *sag*, *saga* solvers.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">False</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('n_jobs',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=n_jobs,-int%2C%20default%3DNone\">\n",
|
|
" n_jobs\n",
|
|
" <span class=\"param-doc-description\">n_jobs: int, default=None<br><br>Does not have any effect.<br><br>.. deprecated:: 1.8<br> `n_jobs` is deprecated in version 1.8 and will be removed in 1.10.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">None</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
" </tbody>\n",
|
|
" </table>\n",
|
|
" </details>\n",
|
|
" </div>\n",
|
|
" </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
|
|
" // Get the parameter prefix from the closest toggleable content\n",
|
|
" const toggleableContent = element.closest('.sk-toggleable__content');\n",
|
|
" const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
|
|
" const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
|
|
"\n",
|
|
" const originalStyle = element.style;\n",
|
|
" const computedStyle = window.getComputedStyle(element);\n",
|
|
" const originalWidth = computedStyle.width;\n",
|
|
" const originalHTML = element.innerHTML.replace('Copied!', '');\n",
|
|
"\n",
|
|
" navigator.clipboard.writeText(fullParamName)\n",
|
|
" .then(() => {\n",
|
|
" element.style.width = originalWidth;\n",
|
|
" element.style.color = 'green';\n",
|
|
" element.innerHTML = \"Copied!\";\n",
|
|
"\n",
|
|
" setTimeout(() => {\n",
|
|
" element.innerHTML = originalHTML;\n",
|
|
" element.style = originalStyle;\n",
|
|
" }, 2000);\n",
|
|
" })\n",
|
|
" .catch(err => {\n",
|
|
" console.error('Failed to copy:', err);\n",
|
|
" element.style.color = 'red';\n",
|
|
" element.innerHTML = \"Failed!\";\n",
|
|
" setTimeout(() => {\n",
|
|
" element.innerHTML = originalHTML;\n",
|
|
" element.style = originalStyle;\n",
|
|
" }, 2000);\n",
|
|
" });\n",
|
|
" return false;\n",
|
|
"}\n",
|
|
"\n",
|
|
"document.querySelectorAll('.copy-paste-icon').forEach(function(element) {\n",
|
|
" const toggleableContent = element.closest('.sk-toggleable__content');\n",
|
|
" const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
|
|
" const paramName = element.parentElement.nextElementSibling\n",
|
|
" .textContent.trim().split(' ')[0];\n",
|
|
" const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
|
|
"\n",
|
|
" element.setAttribute('title', fullParamName);\n",
|
|
"});\n",
|
|
"\n",
|
|
"\n",
|
|
"/**\n",
|
|
" * Adapted from Skrub\n",
|
|
" * https://github.com/skrub-data/skrub/blob/403466d1d5d4dc76a7ef569b3f8228db59a31dc3/skrub/_reporting/_data/templates/report.js#L789\n",
|
|
" * @returns \"light\" or \"dark\"\n",
|
|
" */\n",
|
|
"function detectTheme(element) {\n",
|
|
" const body = document.querySelector('body');\n",
|
|
"\n",
|
|
" // Check VSCode theme\n",
|
|
" const themeKindAttr = body.getAttribute('data-vscode-theme-kind');\n",
|
|
" const themeNameAttr = body.getAttribute('data-vscode-theme-name');\n",
|
|
"\n",
|
|
" if (themeKindAttr && themeNameAttr) {\n",
|
|
" const themeKind = themeKindAttr.toLowerCase();\n",
|
|
" const themeName = themeNameAttr.toLowerCase();\n",
|
|
"\n",
|
|
" if (themeKind.includes(\"dark\") || themeName.includes(\"dark\")) {\n",
|
|
" return \"dark\";\n",
|
|
" }\n",
|
|
" if (themeKind.includes(\"light\") || themeName.includes(\"light\")) {\n",
|
|
" return \"light\";\n",
|
|
" }\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Check Jupyter theme\n",
|
|
" if (body.getAttribute('data-jp-theme-light') === 'false') {\n",
|
|
" return 'dark';\n",
|
|
" } else if (body.getAttribute('data-jp-theme-light') === 'true') {\n",
|
|
" return 'light';\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Guess based on a parent element's color\n",
|
|
" const color = window.getComputedStyle(element.parentNode, null).getPropertyValue('color');\n",
|
|
" const match = color.match(/^rgb\\s*\\(\\s*(\\d+)\\s*,\\s*(\\d+)\\s*,\\s*(\\d+)\\s*\\)\\s*$/i);\n",
|
|
" if (match) {\n",
|
|
" const [r, g, b] = [\n",
|
|
" parseFloat(match[1]),\n",
|
|
" parseFloat(match[2]),\n",
|
|
" parseFloat(match[3])\n",
|
|
" ];\n",
|
|
"\n",
|
|
" // https://en.wikipedia.org/wiki/HSL_and_HSV#Lightness\n",
|
|
" const luma = 0.299 * r + 0.587 * g + 0.114 * b;\n",
|
|
"\n",
|
|
" if (luma > 180) {\n",
|
|
" // If the text is very bright we have a dark theme\n",
|
|
" return 'dark';\n",
|
|
" }\n",
|
|
" if (luma < 75) {\n",
|
|
" // If the text is very dark we have a light theme\n",
|
|
" return 'light';\n",
|
|
" }\n",
|
|
" // Otherwise fall back to the next heuristic.\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Fallback to system preference\n",
|
|
" return window.matchMedia('(prefers-color-scheme: dark)').matches ? 'dark' : 'light';\n",
|
|
"}\n",
|
|
"\n",
|
|
"\n",
|
|
"function forceTheme(elementId) {\n",
|
|
" const estimatorElement = document.querySelector(`#${elementId}`);\n",
|
|
" if (estimatorElement === null) {\n",
|
|
" console.error(`Element with id ${elementId} not found.`);\n",
|
|
" } else {\n",
|
|
" const theme = detectTheme(estimatorElement);\n",
|
|
" estimatorElement.classList.add(theme);\n",
|
|
" }\n",
|
|
"}\n",
|
|
"\n",
|
|
"forceTheme('sk-container-id-3');</script></body>"
|
|
]
|
|
},
|
|
"execution_count": 27,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"execution_count": 27
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.948876Z",
|
|
"start_time": "2026-04-25T21:15:54.937689300Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "y_val_pred_log = log_model.predict(scaled_X_val)",
|
|
"id": "965e16ce48443c97",
|
|
"outputs": [],
|
|
"execution_count": 28
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.976908500Z",
|
|
"start_time": "2026-04-25T21:15:54.948876Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"log_val_f1 = f1_score(y_val, y_val_pred_log, average='weighted')\n",
|
|
"print(f\"Validation Accuracy: {accuracy_score(y_val, y_val_pred_log):.4f}\")\n",
|
|
"print(f\"Validation F1-Score: {log_val_f1:.4f}\")"
|
|
],
|
|
"id": "9be803af2f34cd6",
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Validation Accuracy: 0.3333\n",
|
|
"Validation F1-Score: 0.3069\n"
|
|
]
|
|
}
|
|
],
|
|
"execution_count": 29
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"cell_type": "markdown",
|
|
"source": "## KNN",
|
|
"id": "2b7b85284cddecb2"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:54.988744700Z",
|
|
"start_time": "2026-04-25T21:15:54.977907500Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"best_k = 1\n",
|
|
"best_f1 = 0"
|
|
],
|
|
"id": "8c4835d7a413a6e6",
|
|
"outputs": [],
|
|
"execution_count": 30
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:55.029426700Z",
|
|
"start_time": "2026-04-25T21:15:54.989744500Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"for k in range(1, 15, 2):\n",
|
|
" knn_temp = KNeighborsClassifier(n_neighbors=k)\n",
|
|
" knn_temp.fit(scaled_X_train, y_train)\n",
|
|
" y_val_pred_knn = knn_temp.predict(scaled_X_val)\n",
|
|
"\n",
|
|
" current_f1 = f1_score(y_val, y_val_pred_knn, average='weighted')\n",
|
|
" print(f\"KNN (K={k}) Validation F1-Score: {current_f1:.4f}\")\n",
|
|
"\n",
|
|
" if current_f1 > best_f1:\n",
|
|
" best_f1 = current_f1\n",
|
|
" best_k = k"
|
|
],
|
|
"id": "a8d69c56d1a21825",
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"KNN (K=1) Validation F1-Score: 0.3201\n",
|
|
"KNN (K=3) Validation F1-Score: 0.3245\n",
|
|
"KNN (K=5) Validation F1-Score: 0.2939\n",
|
|
"KNN (K=7) Validation F1-Score: 0.2916\n",
|
|
"KNN (K=9) Validation F1-Score: 0.3120\n",
|
|
"KNN (K=11) Validation F1-Score: 0.3097\n",
|
|
"KNN (K=13) Validation F1-Score: 0.3181\n"
|
|
]
|
|
}
|
|
],
|
|
"execution_count": 31
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:55.045639100Z",
|
|
"start_time": "2026-04-25T21:15:55.030432300Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": [
|
|
"knn_final = KNeighborsClassifier(n_neighbors=best_k)\n",
|
|
"knn_final.fit(scaled_X_train, y_train)"
|
|
],
|
|
"id": "9644f7a78b4ff687",
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"KNeighborsClassifier(n_neighbors=3)"
|
|
],
|
|
"text/html": [
|
|
"<style>#sk-container-id-4 {\n",
|
|
" /* Definition of color scheme common for light and dark mode */\n",
|
|
" --sklearn-color-text: #000;\n",
|
|
" --sklearn-color-text-muted: #666;\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",
|
|
"\n",
|
|
"#sk-container-id-4.light {\n",
|
|
" /* Specific color for light theme */\n",
|
|
" --sklearn-color-text-on-default-background: black;\n",
|
|
" --sklearn-color-background: white;\n",
|
|
" --sklearn-color-border-box: black;\n",
|
|
" --sklearn-color-icon: #696969;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4.dark {\n",
|
|
" --sklearn-color-text-on-default-background: white;\n",
|
|
" --sklearn-color-background: #111;\n",
|
|
" --sklearn-color-border-box: white;\n",
|
|
" --sklearn-color-icon: #878787;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 {\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 pre {\n",
|
|
" padding: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-4 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-4 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-4 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-4 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-4 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-4 div.sk-parallel-item {\n",
|
|
" display: flex;\n",
|
|
" flex-direction: column;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-parallel-item:first-child::after {\n",
|
|
" align-self: flex-end;\n",
|
|
" width: 50%;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-parallel-item:last-child::after {\n",
|
|
" align-self: flex-start;\n",
|
|
" width: 50%;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-parallel-item:only-child::after {\n",
|
|
" width: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Serial-specific style estimator block */\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-4 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-4 label.sk-toggleable__label {\n",
|
|
" cursor: pointer;\n",
|
|
" display: flex;\n",
|
|
" width: 100%;\n",
|
|
" margin-bottom: 0;\n",
|
|
" padding: 0.5em;\n",
|
|
" box-sizing: border-box;\n",
|
|
" text-align: center;\n",
|
|
" align-items: center;\n",
|
|
" justify-content: center;\n",
|
|
" gap: 0.5em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 label.sk-toggleable__label .caption {\n",
|
|
" font-size: 0.6rem;\n",
|
|
" font-weight: lighter;\n",
|
|
" color: var(--sklearn-color-text-muted);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-4 label.sk-toggleable__label-arrow:hover:before {\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Toggleable content - dropdown */\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-toggleable__content {\n",
|
|
" display: none;\n",
|
|
" text-align: left;\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-toggleable__content.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-4 div.sk-toggleable__content.fitted pre {\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
|
" /* Expand drop-down */\n",
|
|
" display: block;\n",
|
|
" width: 100%;\n",
|
|
" overflow: visible;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-4 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-4 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-4 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-4 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-4 div.sk-label label.sk-toggleable__label,\n",
|
|
"#sk-container-id-4 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-4 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-4 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-4 div.sk-label label {\n",
|
|
" font-family: monospace;\n",
|
|
" font-weight: bold;\n",
|
|
" line-height: 1.2em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 div.sk-label-container {\n",
|
|
" text-align: center;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Estimator-specific */\n",
|
|
"#sk-container-id-4 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-4 div.sk-estimator.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* on hover */\n",
|
|
"#sk-container-id-4 div.sk-estimator:hover {\n",
|
|
" /* unfitted */\n",
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
"}\n",
|
|
"\n",
|
|
"#sk-container-id-4 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-unfitted-level-0);\n",
|
|
" border-radius: 1em;\n",
|
|
" height: 1em;\n",
|
|
" width: 1em;\n",
|
|
" text-decoration: none !important;\n",
|
|
" margin-left: 0.5em;\n",
|
|
" text-align: center;\n",
|
|
" /* unfitted */\n",
|
|
" border: var(--sklearn-color-unfitted-level-3) 1pt solid;\n",
|
|
" color: var(--sklearn-color-unfitted-level-3);\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",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
" border: var(--sklearn-color-fitted-level-3) 1pt solid;\n",
|
|
" color: var(--sklearn-color-fitted-level-3);\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",
|
|
" border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
|
|
" color: var(--sklearn-color-unfitted-level-0);\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",
|
|
" border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
|
|
" color: var(--sklearn-color-fitted-level-0);\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-4 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-unfitted-level-0);\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-4 a.estimator_doc_link.fitted {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-0);\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-4 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-4 a.estimator_doc_link.fitted:hover {\n",
|
|
" /* fitted */\n",
|
|
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table {\n",
|
|
" font-family: monospace;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table summary {\n",
|
|
" padding: .5rem;\n",
|
|
" cursor: pointer;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table summary::marker {\n",
|
|
" font-size: 0.7rem;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table details[open] {\n",
|
|
" padding-left: 0.1rem;\n",
|
|
" padding-right: 0.1rem;\n",
|
|
" padding-bottom: 0.3rem;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table {\n",
|
|
" margin-left: auto !important;\n",
|
|
" margin-right: auto !important;\n",
|
|
" margin-top: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:nth-child(odd) {\n",
|
|
" background-color: #fff;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:nth-child(even) {\n",
|
|
" background-color: #f6f6f6;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table .parameters-table tr:hover {\n",
|
|
" background-color: #e0e0e0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".estimator-table table td {\n",
|
|
" border: 1px solid rgba(106, 105, 104, 0.232);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/*\n",
|
|
" `table td`is set in notebook with right text-align.\n",
|
|
" We need to overwrite it.\n",
|
|
"*/\n",
|
|
".estimator-table table td.param {\n",
|
|
" text-align: left;\n",
|
|
" position: relative;\n",
|
|
" padding: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td {\n",
|
|
" color:rgb(255, 94, 0);\n",
|
|
" text-align: left !important;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td.value {\n",
|
|
" color:rgb(255, 94, 0);\n",
|
|
" background-color: transparent;\n",
|
|
"}\n",
|
|
"\n",
|
|
".default td {\n",
|
|
" color: black;\n",
|
|
" text-align: left !important;\n",
|
|
"}\n",
|
|
"\n",
|
|
".user-set td i,\n",
|
|
".default td i {\n",
|
|
" color: black;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/*\n",
|
|
" Styles for parameter documentation links\n",
|
|
" We need styling for visited so jupyter doesn't overwrite it\n",
|
|
"*/\n",
|
|
"a.param-doc-link,\n",
|
|
"a.param-doc-link:link,\n",
|
|
"a.param-doc-link:visited {\n",
|
|
" text-decoration: underline dashed;\n",
|
|
" text-underline-offset: .3em;\n",
|
|
" color: inherit;\n",
|
|
" display: block;\n",
|
|
" padding: .5em;\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* \"hack\" to make the entire area of the cell containing the link clickable */\n",
|
|
"a.param-doc-link::before {\n",
|
|
" position: absolute;\n",
|
|
" content: \"\";\n",
|
|
" inset: 0;\n",
|
|
"}\n",
|
|
"\n",
|
|
".param-doc-description {\n",
|
|
" display: none;\n",
|
|
" position: absolute;\n",
|
|
" z-index: 9999;\n",
|
|
" left: 0;\n",
|
|
" padding: .5ex;\n",
|
|
" margin-left: 1.5em;\n",
|
|
" color: var(--sklearn-color-text);\n",
|
|
" box-shadow: .3em .3em .4em #999;\n",
|
|
" width: max-content;\n",
|
|
" text-align: left;\n",
|
|
" max-height: 10em;\n",
|
|
" overflow-y: auto;\n",
|
|
"\n",
|
|
" /* unfitted */\n",
|
|
" background: var(--sklearn-color-unfitted-level-0);\n",
|
|
" border: thin solid var(--sklearn-color-unfitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
"/* Fitted state for parameter tooltips */\n",
|
|
".fitted .param-doc-description {\n",
|
|
" /* fitted */\n",
|
|
" background: var(--sklearn-color-fitted-level-0);\n",
|
|
" border: thin solid var(--sklearn-color-fitted-level-3);\n",
|
|
"}\n",
|
|
"\n",
|
|
".param-doc-link:hover .param-doc-description {\n",
|
|
" display: block;\n",
|
|
"}\n",
|
|
"\n",
|
|
".copy-paste-icon {\n",
|
|
" background-image: url(data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCA0NDggNTEyIj48IS0tIUZvbnQgQXdlc29tZSBGcmVlIDYuNy4yIGJ5IEBmb250YXdlc29tZSAtIGh0dHBzOi8vZm9udGF3ZXNvbWUuY29tIExpY2Vuc2UgLSBodHRwczovL2ZvbnRhd2Vzb21lLmNvbS9saWNlbnNlL2ZyZWUgQ29weXJpZ2h0IDIwMjUgRm9udGljb25zLCBJbmMuLS0+PHBhdGggZD0iTTIwOCAwTDMzMi4xIDBjMTIuNyAwIDI0LjkgNS4xIDMzLjkgMTQuMWw2Ny45IDY3LjljOSA5IDE0LjEgMjEuMiAxNC4xIDMzLjlMNDQ4IDMzNmMwIDI2LjUtMjEuNSA0OC00OCA0OGwtMTkyIDBjLTI2LjUgMC00OC0yMS41LTQ4LTQ4bDAtMjg4YzAtMjYuNSAyMS41LTQ4IDQ4LTQ4ek00OCAxMjhsODAgMCAwIDY0LTY0IDAgMCAyNTYgMTkyIDAgMC0zMiA2NCAwIDAgNDhjMCAyNi41LTIxLjUgNDgtNDggNDhMNDggNTEyYy0yNi41IDAtNDgtMjEuNS00OC00OEwwIDE3NmMwLTI2LjUgMjEuNS00OCA0OC00OHoiLz48L3N2Zz4=);\n",
|
|
" background-repeat: no-repeat;\n",
|
|
" background-size: 14px 14px;\n",
|
|
" background-position: 0;\n",
|
|
" display: inline-block;\n",
|
|
" width: 14px;\n",
|
|
" height: 14px;\n",
|
|
" cursor: pointer;\n",
|
|
"}\n",
|
|
"</style><body><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(n_neighbors=3)</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\"><div><div>KNeighborsClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html\">?<span>Documentation for KNeighborsClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
|
|
" <div class=\"estimator-table\">\n",
|
|
" <details>\n",
|
|
" <summary>Parameters</summary>\n",
|
|
" <table class=\"parameters-table\">\n",
|
|
" <tbody>\n",
|
|
" \n",
|
|
" <tr class=\"user-set\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('n_neighbors',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=n_neighbors,-int%2C%20default%3D5\">\n",
|
|
" n_neighbors\n",
|
|
" <span class=\"param-doc-description\">n_neighbors: int, default=5<br><br>Number of neighbors to use by default for :meth:`kneighbors` queries.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">3</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('weights',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=weights,-%7B%27uniform%27%2C%20%27distance%27%7D%2C%20callable%20or%20None%2C%20default%3D%27uniform%27\">\n",
|
|
" weights\n",
|
|
" <span class=\"param-doc-description\">weights: {'uniform', 'distance'}, callable or None, default='uniform'<br><br>Weight function used in prediction. Possible values:<br><br>- 'uniform' : uniform weights. All points in each neighborhood<br> are weighted equally.<br>- 'distance' : weight points by the inverse of their distance.<br> in this case, closer neighbors of a query point will have a<br> greater influence than neighbors which are further away.<br>- [callable] : a user-defined function which accepts an<br> array of distances, and returns an array of the same shape<br> containing the weights.<br><br>Refer to the example entitled<br>:ref:`sphx_glr_auto_examples_neighbors_plot_classification.py`<br>showing the impact of the `weights` parameter on the decision<br>boundary.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">'uniform'</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('algorithm',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=algorithm,-%7B%27auto%27%2C%20%27ball_tree%27%2C%20%27kd_tree%27%2C%20%27brute%27%7D%2C%20default%3D%27auto%27\">\n",
|
|
" algorithm\n",
|
|
" <span class=\"param-doc-description\">algorithm: {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'<br><br>Algorithm used to compute the nearest neighbors:<br><br>- 'ball_tree' will use :class:`BallTree`<br>- 'kd_tree' will use :class:`KDTree`<br>- 'brute' will use a brute-force search.<br>- 'auto' will attempt to decide the most appropriate algorithm<br> based on the values passed to :meth:`fit` method.<br><br>Note: fitting on sparse input will override the setting of<br>this parameter, using brute force.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">'auto'</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('leaf_size',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=leaf_size,-int%2C%20default%3D30\">\n",
|
|
" leaf_size\n",
|
|
" <span class=\"param-doc-description\">leaf_size: int, default=30<br><br>Leaf size passed to BallTree or KDTree. This can affect the<br>speed of the construction and query, as well as the memory<br>required to store the tree. The optimal value depends on the<br>nature of the problem.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">30</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('p',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=p,-float%2C%20default%3D2\">\n",
|
|
" p\n",
|
|
" <span class=\"param-doc-description\">p: float, default=2<br><br>Power parameter for the Minkowski metric. When p = 1, this is equivalent<br>to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2.<br>For arbitrary p, minkowski_distance (l_p) is used. This parameter is expected<br>to be positive.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">2</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('metric',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=metric,-str%20or%20callable%2C%20default%3D%27minkowski%27\">\n",
|
|
" metric\n",
|
|
" <span class=\"param-doc-description\">metric: str or callable, default='minkowski'<br><br>Metric to use for distance computation. Default is \"minkowski\", which<br>results in the standard Euclidean distance when p = 2. See the<br>documentation of `scipy.spatial.distance<br><https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and<br>the metrics listed in<br>:class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric<br>values.<br><br>If metric is \"precomputed\", X is assumed to be a distance matrix and<br>must be square during fit. X may be a :term:`sparse graph`, in which<br>case only \"nonzero\" elements may be considered neighbors.<br><br>If metric is a callable function, it takes two arrays representing 1D<br>vectors as inputs and must return one value indicating the distance<br>between those vectors. This works for Scipy's metrics, but is less<br>efficient than passing the metric name as a string.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">'minkowski'</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('metric_params',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=metric_params,-dict%2C%20default%3DNone\">\n",
|
|
" metric_params\n",
|
|
" <span class=\"param-doc-description\">metric_params: dict, default=None<br><br>Additional keyword arguments for the metric function.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">None</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
"\n",
|
|
" <tr class=\"default\">\n",
|
|
" <td><i class=\"copy-paste-icon\"\n",
|
|
" onclick=\"copyToClipboard('n_jobs',\n",
|
|
" this.parentElement.nextElementSibling)\"\n",
|
|
" ></i></td>\n",
|
|
" <td class=\"param\">\n",
|
|
" <a class=\"param-doc-link\"\n",
|
|
" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#:~:text=n_jobs,-int%2C%20default%3DNone\">\n",
|
|
" n_jobs\n",
|
|
" <span class=\"param-doc-description\">n_jobs: int, default=None<br><br>The number of parallel jobs to run for neighbors search.<br>``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.<br>``-1`` means using all processors. See :term:`Glossary <n_jobs>`<br>for more details.<br>Doesn't affect :meth:`fit` method.</span>\n",
|
|
" </a>\n",
|
|
" </td>\n",
|
|
" <td class=\"value\">None</td>\n",
|
|
" </tr>\n",
|
|
" \n",
|
|
" </tbody>\n",
|
|
" </table>\n",
|
|
" </details>\n",
|
|
" </div>\n",
|
|
" </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
|
|
" // Get the parameter prefix from the closest toggleable content\n",
|
|
" const toggleableContent = element.closest('.sk-toggleable__content');\n",
|
|
" const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
|
|
" const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
|
|
"\n",
|
|
" const originalStyle = element.style;\n",
|
|
" const computedStyle = window.getComputedStyle(element);\n",
|
|
" const originalWidth = computedStyle.width;\n",
|
|
" const originalHTML = element.innerHTML.replace('Copied!', '');\n",
|
|
"\n",
|
|
" navigator.clipboard.writeText(fullParamName)\n",
|
|
" .then(() => {\n",
|
|
" element.style.width = originalWidth;\n",
|
|
" element.style.color = 'green';\n",
|
|
" element.innerHTML = \"Copied!\";\n",
|
|
"\n",
|
|
" setTimeout(() => {\n",
|
|
" element.innerHTML = originalHTML;\n",
|
|
" element.style = originalStyle;\n",
|
|
" }, 2000);\n",
|
|
" })\n",
|
|
" .catch(err => {\n",
|
|
" console.error('Failed to copy:', err);\n",
|
|
" element.style.color = 'red';\n",
|
|
" element.innerHTML = \"Failed!\";\n",
|
|
" setTimeout(() => {\n",
|
|
" element.innerHTML = originalHTML;\n",
|
|
" element.style = originalStyle;\n",
|
|
" }, 2000);\n",
|
|
" });\n",
|
|
" return false;\n",
|
|
"}\n",
|
|
"\n",
|
|
"document.querySelectorAll('.copy-paste-icon').forEach(function(element) {\n",
|
|
" const toggleableContent = element.closest('.sk-toggleable__content');\n",
|
|
" const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
|
|
" const paramName = element.parentElement.nextElementSibling\n",
|
|
" .textContent.trim().split(' ')[0];\n",
|
|
" const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
|
|
"\n",
|
|
" element.setAttribute('title', fullParamName);\n",
|
|
"});\n",
|
|
"\n",
|
|
"\n",
|
|
"/**\n",
|
|
" * Adapted from Skrub\n",
|
|
" * https://github.com/skrub-data/skrub/blob/403466d1d5d4dc76a7ef569b3f8228db59a31dc3/skrub/_reporting/_data/templates/report.js#L789\n",
|
|
" * @returns \"light\" or \"dark\"\n",
|
|
" */\n",
|
|
"function detectTheme(element) {\n",
|
|
" const body = document.querySelector('body');\n",
|
|
"\n",
|
|
" // Check VSCode theme\n",
|
|
" const themeKindAttr = body.getAttribute('data-vscode-theme-kind');\n",
|
|
" const themeNameAttr = body.getAttribute('data-vscode-theme-name');\n",
|
|
"\n",
|
|
" if (themeKindAttr && themeNameAttr) {\n",
|
|
" const themeKind = themeKindAttr.toLowerCase();\n",
|
|
" const themeName = themeNameAttr.toLowerCase();\n",
|
|
"\n",
|
|
" if (themeKind.includes(\"dark\") || themeName.includes(\"dark\")) {\n",
|
|
" return \"dark\";\n",
|
|
" }\n",
|
|
" if (themeKind.includes(\"light\") || themeName.includes(\"light\")) {\n",
|
|
" return \"light\";\n",
|
|
" }\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Check Jupyter theme\n",
|
|
" if (body.getAttribute('data-jp-theme-light') === 'false') {\n",
|
|
" return 'dark';\n",
|
|
" } else if (body.getAttribute('data-jp-theme-light') === 'true') {\n",
|
|
" return 'light';\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Guess based on a parent element's color\n",
|
|
" const color = window.getComputedStyle(element.parentNode, null).getPropertyValue('color');\n",
|
|
" const match = color.match(/^rgb\\s*\\(\\s*(\\d+)\\s*,\\s*(\\d+)\\s*,\\s*(\\d+)\\s*\\)\\s*$/i);\n",
|
|
" if (match) {\n",
|
|
" const [r, g, b] = [\n",
|
|
" parseFloat(match[1]),\n",
|
|
" parseFloat(match[2]),\n",
|
|
" parseFloat(match[3])\n",
|
|
" ];\n",
|
|
"\n",
|
|
" // https://en.wikipedia.org/wiki/HSL_and_HSV#Lightness\n",
|
|
" const luma = 0.299 * r + 0.587 * g + 0.114 * b;\n",
|
|
"\n",
|
|
" if (luma > 180) {\n",
|
|
" // If the text is very bright we have a dark theme\n",
|
|
" return 'dark';\n",
|
|
" }\n",
|
|
" if (luma < 75) {\n",
|
|
" // If the text is very dark we have a light theme\n",
|
|
" return 'light';\n",
|
|
" }\n",
|
|
" // Otherwise fall back to the next heuristic.\n",
|
|
" }\n",
|
|
"\n",
|
|
" // Fallback to system preference\n",
|
|
" return window.matchMedia('(prefers-color-scheme: dark)').matches ? 'dark' : 'light';\n",
|
|
"}\n",
|
|
"\n",
|
|
"\n",
|
|
"function forceTheme(elementId) {\n",
|
|
" const estimatorElement = document.querySelector(`#${elementId}`);\n",
|
|
" if (estimatorElement === null) {\n",
|
|
" console.error(`Element with id ${elementId} not found.`);\n",
|
|
" } else {\n",
|
|
" const theme = detectTheme(estimatorElement);\n",
|
|
" estimatorElement.classList.add(theme);\n",
|
|
" }\n",
|
|
"}\n",
|
|
"\n",
|
|
"forceTheme('sk-container-id-4');</script></body>"
|
|
]
|
|
},
|
|
"execution_count": 32,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"execution_count": 32
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Part B\n",
|
|
"\n",
|
|
"Q: Using (Rating + Reviews + Category + Size in Bytes + Installs_Num),\n",
|
|
"using Logistic regression and KNN, find and discuss the best classification model\n",
|
|
"to predict “Content Rating” (use the training/validation/test partition without\n",
|
|
"cross-validation). **[7 marks]**"
|
|
],
|
|
"id": "f15aa6cca58826fc"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:55.065809200Z",
|
|
"start_time": "2026-04-25T21:15:55.059661900Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "",
|
|
"id": "65e55b70ad44b2dc",
|
|
"outputs": [],
|
|
"execution_count": 32
|
|
},
|
|
{
|
|
"metadata": {},
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Part C\n",
|
|
"\n",
|
|
"Q: By considering Installs_Num as categorical feature and using (Rating +\n",
|
|
"Reviews + Category + Size in Bytes + Content Rating), find and discuss the\n",
|
|
"best classification model to predict “Installs_Num” (using Logistic regression and\n",
|
|
"KNN) (use the training/test partition without cross-validation) **[8 marks]**"
|
|
],
|
|
"id": "86c040f5e043a39c"
|
|
},
|
|
{
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2026-04-25T21:15:55.070341Z",
|
|
"start_time": "2026-04-25T21:15:55.066313200Z"
|
|
}
|
|
},
|
|
"cell_type": "code",
|
|
"source": "",
|
|
"id": "f3535461938f94f5",
|
|
"outputs": [],
|
|
"execution_count": 32
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 2
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython2",
|
|
"version": "2.7.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|