mirror of
https://github.com/reiyua/HospitalCancerClassification.git
synced 2026-11-17 06:12:06 +11:00
2047 lines
84 KiB
Text
2047 lines
84 KiB
Text
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c01ffe8d-3916-478f-a9c5-f3b480e5e293",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Copyright Rayyan Hodges, TAFE NSW, Gelos Enterprises, Indigo Community Services and Health Hub © 2026"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b9f47b2c-6f01-479a-a87b-e698effc6edf",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Contact: rayyan.hodges@studytafensw.edu.au, rayyan.hodges@gelosmail.com.au indigoCSHH@hmail.com"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c49336b7-8ec3-4a18-8590-4cd6c02917cb",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Program Name: HopsitalCancerClassification.ipynb"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "59691122-a537-4615-8a65-f408eb6fcffb",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Purpose: To train and evaluate an ML model to automate the task of classifying clients as high, medium or low risk of developing cancer."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "1092545b-8be3-487b-87df-d8829e0a00eb",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Import required libraries\n",
|
||
"import joblib\n",
|
||
"import numpy\n",
|
||
"import pandas as pd\n",
|
||
"import sklearn # importing the scikit-learn project, different name due to syntax rules \n",
|
||
"import scipy\n",
|
||
"import threadpoolctl"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "3a05014a-200c-4bc6-9667-568898547852",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Set appropriate display options in Pandas\n",
|
||
"pd.set_option('display.max_rows', 10000)\n",
|
||
"pd.set_option('display.max_columns', 10000)\n",
|
||
"pd.set_option('display.width', 10000)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "95ffdbd6-b7e7-41b9-990f-932a05cae2e6",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Identify any datapoints with missing labels and remove them"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "10d93e7f-9ba8-45a4-831d-7ba48046fea7",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"np.int64(10)"
|
||
]
|
||
},
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Load the data set into memory and define it for further analysis.\n",
|
||
"df = pd.read_csv(\"data.csv\")\n",
|
||
"# Check for missing values in the target column, count them, and display them in a total number.\n",
|
||
"df['cancer_risk'].isnull().sum()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "3434f6bb-7cdb-4434-a948-1dc7d9e7d260",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"np.int64(0)"
|
||
]
|
||
},
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Remove the affected rows with missing data\n",
|
||
"df = df.dropna(subset=['cancer_risk'])\n",
|
||
"# Verify removal of said invalid data.\n",
|
||
"df['cancer_risk'].isnull().sum()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "44a9b1bc-0c6c-4e9e-95a7-03d3108b696b",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Categorise ages as required."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "a8887198-0dbd-471d-bd1e-836d34def83a",
|
||
"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>age_group</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>51</td>\n",
|
||
" <td>45-54</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>92</td>\n",
|
||
" <td>85+</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>14</td>\n",
|
||
" <td>0-14</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>71</td>\n",
|
||
" <td>65-74</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>60</td>\n",
|
||
" <td>55-64</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" age age_group\n",
|
||
"0 51 45-54\n",
|
||
"1 92 85+\n",
|
||
"2 14 0-14\n",
|
||
"3 71 65-74\n",
|
||
"4 60 55-64"
|
||
]
|
||
},
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Define age bins and labels for the groups\n",
|
||
"# Bins meaning boundaries \n",
|
||
"bins = [0, 14, 24, 34, 44, 54, 64, 74, 84, 120]\n",
|
||
"labels = ['0-14', '15-24', '25-34', '35-44', \n",
|
||
" '45-54', '55-64', '65-74', '75-84', '85+']\n",
|
||
"\n",
|
||
"# Categorise ages into age groups\n",
|
||
"df['age_group'] = pd.cut(df['age'], bins=bins, labels=labels, right=True)\n",
|
||
"\n",
|
||
"# Display the results in a table\n",
|
||
"df[['age', 'age_group']].head()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b2751d18-2580-453a-b0d9-70bc956f73cc",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Standardise numerical features using appropriate scaling techniques."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "f9beff06-ce08-479d-b63d-56ca8aaf6338",
|
||
"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>bmi</th>\n",
|
||
" <th>blood_pressure</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>count</th>\n",
|
||
" <td>9.900000e+02</td>\n",
|
||
" <td>9.900000e+02</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>mean</th>\n",
|
||
" <td>1.076580e-17</td>\n",
|
||
" <td>1.130409e-16</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>std</th>\n",
|
||
" <td>1.000505e+00</td>\n",
|
||
" <td>1.000505e+00</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>min</th>\n",
|
||
" <td>-1.679483e+00</td>\n",
|
||
" <td>-1.699762e+00</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25%</th>\n",
|
||
" <td>-8.839714e-01</td>\n",
|
||
" <td>-8.598235e-01</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50%</th>\n",
|
||
" <td>6.927133e-04</td>\n",
|
||
" <td>-1.794981e-02</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>75%</th>\n",
|
||
" <td>8.853568e-01</td>\n",
|
||
" <td>8.703721e-01</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>max</th>\n",
|
||
" <td>1.735732e+00</td>\n",
|
||
" <td>1.772241e+00</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" bmi blood_pressure\n",
|
||
"count 9.900000e+02 9.900000e+02\n",
|
||
"mean 1.076580e-17 1.130409e-16\n",
|
||
"std 1.000505e+00 1.000505e+00\n",
|
||
"min -1.679483e+00 -1.699762e+00\n",
|
||
"25% -8.839714e-01 -8.598235e-01\n",
|
||
"50% 6.927133e-04 -1.794981e-02\n",
|
||
"75% 8.853568e-01 8.703721e-01\n",
|
||
"max 1.735732e+00 1.772241e+00"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Import the scaling component from the SciKit Learning Library\n",
|
||
"from sklearn.preprocessing import StandardScaler\n",
|
||
"\n",
|
||
"# Select numerical features from the datasheet.\n",
|
||
"numerical_features = ['bmi', 'blood_pressure']\n",
|
||
"\n",
|
||
"# Initialise scaler component\n",
|
||
"scaler = StandardScaler()\n",
|
||
"\n",
|
||
"# Apply scaling and transformation to standardise the numbers.\n",
|
||
"df[numerical_features] = scaler.fit_transform(df[numerical_features])\n",
|
||
"\n",
|
||
"# Display results from the scaling and transformation.\n",
|
||
"df[numerical_features].describe()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2616a37d-bffd-4a8d-b648-24673a543e7d",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Encode categorical data using appropriate encoding techniques."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "8bc14115-e855-4233-9058-eff0ce5c9386",
|
||
"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>family_history</th>\n",
|
||
" <th>alcohol_consumption</th>\n",
|
||
" <th>bmi</th>\n",
|
||
" <th>blood_pressure</th>\n",
|
||
" <th>cholesterol_level</th>\n",
|
||
" <th>travelled_overseas</th>\n",
|
||
" <th>number_of_children</th>\n",
|
||
" <th>cancer_risk</th>\n",
|
||
" <th>age_group_15-24</th>\n",
|
||
" <th>age_group_25-34</th>\n",
|
||
" <th>age_group_35-44</th>\n",
|
||
" <th>age_group_45-54</th>\n",
|
||
" <th>age_group_55-64</th>\n",
|
||
" <th>age_group_65-74</th>\n",
|
||
" <th>age_group_75-84</th>\n",
|
||
" <th>age_group_85+</th>\n",
|
||
" <th>smoking_history_former</th>\n",
|
||
" <th>smoking_history_never</th>\n",
|
||
" <th>diet_good</th>\n",
|
||
" <th>diet_poor</th>\n",
|
||
" <th>exercise_frequency_low</th>\n",
|
||
" <th>exercise_frequency_moderate</th>\n",
|
||
" <th>exercise_frequency_none</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>51</td>\n",
|
||
" <td>no</td>\n",
|
||
" <td>low</td>\n",
|
||
" <td>0.487601</td>\n",
|
||
" <td>1.629026</td>\n",
|
||
" <td>226.4</td>\n",
|
||
" <td>no</td>\n",
|
||
" <td>5</td>\n",
|
||
" <td>moderate</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>92</td>\n",
|
||
" <td>no</td>\n",
|
||
" <td>moderate</td>\n",
|
||
" <td>-1.487463</td>\n",
|
||
" <td>1.396785</td>\n",
|
||
" <td>170.9</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>low</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>14</td>\n",
|
||
" <td>no</td>\n",
|
||
" <td>none</td>\n",
|
||
" <td>0.528748</td>\n",
|
||
" <td>0.568459</td>\n",
|
||
" <td>279.9</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>4</td>\n",
|
||
" <td>high</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>71</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>low</td>\n",
|
||
" <td>1.667153</td>\n",
|
||
" <td>-0.101170</td>\n",
|
||
" <td>280.7</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>moderate</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>60</td>\n",
|
||
" <td>no</td>\n",
|
||
" <td>none</td>\n",
|
||
" <td>-1.446316</td>\n",
|
||
" <td>0.649743</td>\n",
|
||
" <td>212.8</td>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>5</td>\n",
|
||
" <td>moderate</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>False</td>\n",
|
||
" <td>True</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" age family_history alcohol_consumption bmi blood_pressure cholesterol_level travelled_overseas number_of_children cancer_risk age_group_15-24 age_group_25-34 age_group_35-44 age_group_45-54 age_group_55-64 age_group_65-74 age_group_75-84 age_group_85+ smoking_history_former smoking_history_never diet_good diet_poor exercise_frequency_low exercise_frequency_moderate exercise_frequency_none\n",
|
||
"0 51 no low 0.487601 1.629026 226.4 no 5 moderate False False False True False False False False False True False True False False True\n",
|
||
"1 92 no moderate -1.487463 1.396785 170.9 yes 2 low False False False False False False False True False True False True False False False\n",
|
||
"2 14 no none 0.528748 0.568459 279.9 yes 4 high False False False False False False False False False False False False False False True\n",
|
||
"3 71 yes low 1.667153 -0.101170 280.7 yes 0 moderate False False False False False True False False True False False True False False False\n",
|
||
"4 60 no none -1.446316 0.649743 212.8 yes 5 moderate False False False False True False False False True False False False False False True"
|
||
]
|
||
},
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Identify categorical features from the dataset file to be referenced.\n",
|
||
"categorical_features = ['age_group', 'smoking_history', 'diet', 'exercise_frequency']\n",
|
||
"\n",
|
||
"# Apply one-hot encoding to convert the text categories into dummy numerical categories (specifically true or false)\n",
|
||
"df_encoded = pd.get_dummies(df, columns=categorical_features, drop_first=True)\n",
|
||
"\n",
|
||
"# Print the results to ensure the categorical features have been converted to variables such as true or false correctly.\n",
|
||
"df_encoded.head()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3b6926b7-31d0-4558-9695-c16570087104",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Divide and randomise the dataset into training"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "a5174be9-c40b-457e-afd5-1ec97c70ed0a",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"((693, 23), (148, 23), (149, 23))"
|
||
]
|
||
},
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"\n",
|
||
"# Remove rows with missing target labels (specifically, the 'cancer_risk' label, as it has missing data) \n",
|
||
"df_encoded = df_encoded.dropna(subset=['cancer_risk'])\n",
|
||
"\n",
|
||
"#Import the splitting model from the scikit-learn model.\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
"# Separate features and target\n",
|
||
"X = df_encoded.drop('cancer_risk', axis=1)\n",
|
||
"y = df_encoded['cancer_risk']\n",
|
||
"\n",
|
||
"# First split: 70% training, 30% temp\n",
|
||
"X_train, X_temp, y_train, y_temp = train_test_split(\n",
|
||
" X, y, test_size=0.30, random_state=42, stratify=y\n",
|
||
")\n",
|
||
"\n",
|
||
"# Second split: 15% validation, 15% test\n",
|
||
"X_val, X_test, y_val, y_test = train_test_split(\n",
|
||
" X_temp, y_temp, test_size=0.50, random_state=42, stratify=y_temp\n",
|
||
")\n",
|
||
"\n",
|
||
"# Print the results of said sizes to ensure it is working correctly.\n",
|
||
"X_train.shape, X_val.shape, X_test.shape\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b4c21ba9-b730-4150-8b38-dfb5b00f87c1",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Select the most important features in the training dataset that may influence cancer risk, dropping 2 unnecessary features."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "c94e2161-e95d-4a84-864d-bc1388bd4d48",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(693, 21)"
|
||
]
|
||
},
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Drop two unnecessary features/columns that aren't relevant to cancer risk evaluation and wouldn't affect if someone would be likely to have cancer.\n",
|
||
"X_train = X_train.drop(['travelled_overseas', 'number_of_children'], axis=1)\n",
|
||
"X_val = X_val.drop(['travelled_overseas', 'number_of_children'], axis=1)\n",
|
||
"X_test = X_test.drop(['travelled_overseas', 'number_of_children'], axis=1)\n",
|
||
"\n",
|
||
"# Print the results to allow the user to determine the changes have worked\n",
|
||
"X_train.shape\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "49174e92-2e15-461a-844f-ffa90c0d7c99",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Part 3: Train and evaluate ML model - Task 1: Train ML model 1"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "b95cb28a-5312-4f55-8485-61c4e95e782e",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Select an appropriate initial model size by setting the number of layers and neurons.\n",
|
||
"\n",
|
||
"\n",
|
||
"from sklearn.neural_network import MLPClassifier\n",
|
||
"\n",
|
||
"mlp_model_1 = MLPClassifier(\n",
|
||
" hidden_layer_sizes=(64, 32),\n",
|
||
" activation='relu',\n",
|
||
" solver='adam',\n",
|
||
" max_iter=300,\n",
|
||
" random_state=42\n",
|
||
")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"id": "9a44bcdd-8605-4e21-9a7a-1a3296f46909",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"age int64\n",
|
||
"family_history str\n",
|
||
"alcohol_consumption str\n",
|
||
"bmi float64\n",
|
||
"blood_pressure float64\n",
|
||
"cholesterol_level float64\n",
|
||
"age_group_15-24 bool\n",
|
||
"age_group_25-34 bool\n",
|
||
"age_group_35-44 bool\n",
|
||
"age_group_45-54 bool\n",
|
||
"age_group_55-64 bool\n",
|
||
"age_group_65-74 bool\n",
|
||
"age_group_75-84 bool\n",
|
||
"age_group_85+ bool\n",
|
||
"smoking_history_former bool\n",
|
||
"smoking_history_never bool\n",
|
||
"diet_good bool\n",
|
||
"diet_poor bool\n",
|
||
"exercise_frequency_low bool\n",
|
||
"exercise_frequency_moderate bool\n",
|
||
"exercise_frequency_none bool\n",
|
||
"dtype: object"
|
||
]
|
||
},
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# BUG FIXING: List any non numerical rows\n",
|
||
"X_train.dtypes"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "f16e2e40-e065-44ca-b944-e9a2921d89db",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/tmp/ipykernel_82/146862157.py:2: Pandas4Warning: For backward compatibility, 'str' dtypes are included by select_dtypes when 'object' dtype is specified. This behavior is deprecated and will be removed in a future version. Explicitly pass 'str' to `include` to select them, or to `exclude` to remove them and silence this warning.\n",
|
||
"See https://pandas.pydata.org/docs/user_guide/migration-3-strings.html#string-migration-select-dtypes for details on how to write code that works with pandas 2 and 3.\n",
|
||
" X_train.select_dtypes(include=['object']).head()\n"
|
||
]
|
||
},
|
||
{
|
||
"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>family_history</th>\n",
|
||
" <th>alcohol_consumption</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>494</th>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>none</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>379</th>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>high</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>220</th>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>none</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>732</th>\n",
|
||
" <td>yes</td>\n",
|
||
" <td>high</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>869</th>\n",
|
||
" <td>no</td>\n",
|
||
" <td>low</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" family_history alcohol_consumption\n",
|
||
"494 yes none\n",
|
||
"379 yes high\n",
|
||
"220 yes none\n",
|
||
"732 yes high\n",
|
||
"869 no low"
|
||
]
|
||
},
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# BUG FIXING: Check if the text value exists\n",
|
||
"X_train.select_dtypes(include=['object']).head()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 18,
|
||
"id": "f62a9503-664a-43d9-9afa-0029695acce8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# BUG FIXING - Rayyan Hodges\n",
|
||
"\n",
|
||
"# Force all non-numeric columns to be one-hot encoded\n",
|
||
"X_train = pd.get_dummies(X_train)\n",
|
||
"X_val = pd.get_dummies(X_val)\n",
|
||
"X_test = pd.get_dummies(X_test)\n",
|
||
"\n",
|
||
"# Align columns so they match exactly\n",
|
||
"X_train, X_val = X_train.align(X_val, join=\"left\", axis=1, fill_value=0)\n",
|
||
"X_train, X_test = X_train.align(X_test, join=\"left\", axis=1, fill_value=0)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"id": "cfcddd52-1a78-4c07-8f5d-036682a8cad6",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<style>#sk-container-id-1 {\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-1.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-1.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-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: 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-1 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-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",
|
||
" display: none;\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",
|
||
" display: block;\n",
|
||
" width: 100%;\n",
|
||
" overflow: visible;\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",
|
||
" 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-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-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-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-1 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-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",
|
||
"\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-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)</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-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>MLPClassifier</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.8/modules/generated/sklearn.neural_network.MLPClassifier.html\">?<span>Documentation for MLPClassifier</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('hidden_layer_sizes',\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.neural_network.MLPClassifier.html#:~:text=hidden_layer_sizes,-array-like%20of%20shape%28n_layers%20-%202%2C%29%2C%20default%3D%28100%2C%29\">\n",
|
||
" hidden_layer_sizes\n",
|
||
" <span class=\"param-doc-description\">hidden_layer_sizes: array-like of shape(n_layers - 2,), default=(100,)<br><br>The ith element represents the number of neurons in the ith<br>hidden layer.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">(64, ...)</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('activation',\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.neural_network.MLPClassifier.html#:~:text=activation,-%7B%27identity%27%2C%20%27logistic%27%2C%20%27tanh%27%2C%20%27relu%27%7D%2C%20default%3D%27relu%27\">\n",
|
||
" activation\n",
|
||
" <span class=\"param-doc-description\">activation: {'identity', 'logistic', 'tanh', 'relu'}, default='relu'<br><br>Activation function for the hidden layer.<br><br>- 'identity', no-op activation, useful to implement linear bottleneck,<br> returns f(x) = x<br><br>- 'logistic', the logistic sigmoid function,<br> returns f(x) = 1 / (1 + exp(-x)).<br><br>- 'tanh', the hyperbolic tan function,<br> returns f(x) = tanh(x).<br><br>- 'relu', the rectified linear unit function,<br> returns f(x) = max(0, x)</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">'relu'</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.neural_network.MLPClassifier.html#:~:text=solver,-%7B%27lbfgs%27%2C%20%27sgd%27%2C%20%27adam%27%7D%2C%20default%3D%27adam%27\">\n",
|
||
" solver\n",
|
||
" <span class=\"param-doc-description\">solver: {'lbfgs', 'sgd', 'adam'}, default='adam'<br><br>The solver for weight optimization.<br><br>- 'lbfgs' is an optimizer in the family of quasi-Newton methods.<br><br>- 'sgd' refers to stochastic gradient descent.<br><br>- 'adam' refers to a stochastic gradient-based optimizer proposed<br> by Kingma, Diederik, and Jimmy Ba<br><br>For a comparison between Adam optimizer and SGD, see<br>:ref:`sphx_glr_auto_examples_neural_networks_plot_mlp_training_curves.py`.<br><br>Note: The default solver 'adam' works pretty well on relatively<br>large datasets (with thousands of training samples or more) in terms of<br>both training time and validation score.<br>For small datasets, however, 'lbfgs' can converge faster and perform<br>better.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">'adam'</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('alpha',\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.neural_network.MLPClassifier.html#:~:text=alpha,-float%2C%20default%3D0.0001\">\n",
|
||
" alpha\n",
|
||
" <span class=\"param-doc-description\">alpha: float, default=0.0001<br><br>Strength of the L2 regularization term. The L2 regularization term<br>is divided by the sample size when added to the loss.<br><br>For an example usage and visualization of varying regularization, see<br>:ref:`sphx_glr_auto_examples_neural_networks_plot_mlp_alpha.py`.</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('batch_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.neural_network.MLPClassifier.html#:~:text=batch_size,-int%2C%20default%3D%27auto%27\">\n",
|
||
" batch_size\n",
|
||
" <span class=\"param-doc-description\">batch_size: int, default='auto'<br><br>Size of minibatches for stochastic optimizers.<br>If the solver is 'lbfgs', the classifier will not use minibatch.<br>When set to \"auto\", `batch_size=min(200, n_samples)`.</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('learning_rate',\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.neural_network.MLPClassifier.html#:~:text=learning_rate,-%7B%27constant%27%2C%20%27invscaling%27%2C%20%27adaptive%27%7D%2C%20default%3D%27constant%27\">\n",
|
||
" learning_rate\n",
|
||
" <span class=\"param-doc-description\">learning_rate: {'constant', 'invscaling', 'adaptive'}, default='constant'<br><br>Learning rate schedule for weight updates.<br><br>- 'constant' is a constant learning rate given by<br> 'learning_rate_init'.<br><br>- 'invscaling' gradually decreases the learning rate at each<br> time step 't' using an inverse scaling exponent of 'power_t'.<br> effective_learning_rate = learning_rate_init / pow(t, power_t)<br><br>- 'adaptive' keeps the learning rate constant to<br> 'learning_rate_init' as long as training loss keeps decreasing.<br> Each time two consecutive epochs fail to decrease training loss by at<br> least tol, or fail to increase validation score by at least tol if<br> 'early_stopping' is on, the current learning rate is divided by 5.<br><br>Only used when ``solver='sgd'``.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">'constant'</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('learning_rate_init',\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.neural_network.MLPClassifier.html#:~:text=learning_rate_init,-float%2C%20default%3D0.001\">\n",
|
||
" learning_rate_init\n",
|
||
" <span class=\"param-doc-description\">learning_rate_init: float, default=0.001<br><br>The initial learning rate used. It controls the step-size<br>in updating the weights. Only used when solver='sgd' or 'adam'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.001</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('power_t',\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.neural_network.MLPClassifier.html#:~:text=power_t,-float%2C%20default%3D0.5\">\n",
|
||
" power_t\n",
|
||
" <span class=\"param-doc-description\">power_t: float, default=0.5<br><br>The exponent for inverse scaling learning rate.<br>It is used in updating effective learning rate when the learning_rate<br>is set to 'invscaling'. Only used when solver='sgd'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.5</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.neural_network.MLPClassifier.html#:~:text=max_iter,-int%2C%20default%3D200\">\n",
|
||
" max_iter\n",
|
||
" <span class=\"param-doc-description\">max_iter: int, default=200<br><br>Maximum number of iterations. The solver iterates until convergence<br>(determined by 'tol') or this number of iterations. For stochastic<br>solvers ('sgd', 'adam'), note that this determines the number of epochs<br>(how many times each data point will be used), not the number of<br>gradient steps.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">300</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('shuffle',\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.neural_network.MLPClassifier.html#:~:text=shuffle,-bool%2C%20default%3DTrue\">\n",
|
||
" shuffle\n",
|
||
" <span class=\"param-doc-description\">shuffle: bool, default=True<br><br>Whether to shuffle samples in each iteration. Only used when<br>solver='sgd' or 'adam'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">True</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"user-set\">\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.neural_network.MLPClassifier.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>Determines random number generation for weights and bias<br>initialization, train-test split if early stopping is used, and batch<br>sampling when solver='sgd' or 'adam'.<br>Pass an int for reproducible results across multiple function calls.<br>See :term:`Glossary <random_state>`.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">42</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.neural_network.MLPClassifier.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 the optimization. When the loss or score is not improving<br>by at least ``tol`` for ``n_iter_no_change`` consecutive iterations,<br>unless ``learning_rate`` is set to 'adaptive', convergence is<br>considered to be reached and training stops.</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('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.neural_network.MLPClassifier.html#:~:text=verbose,-bool%2C%20default%3DFalse\">\n",
|
||
" verbose\n",
|
||
" <span class=\"param-doc-description\">verbose: bool, default=False<br><br>Whether to print progress messages to stdout.</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('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.neural_network.MLPClassifier.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<br>call to fit as initialization, otherwise, just erase the<br>previous solution. See :term:`the Glossary <warm_start>`.</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('momentum',\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.neural_network.MLPClassifier.html#:~:text=momentum,-float%2C%20default%3D0.9\">\n",
|
||
" momentum\n",
|
||
" <span class=\"param-doc-description\">momentum: float, default=0.9<br><br>Momentum for gradient descent update. Should be between 0 and 1. Only<br>used when solver='sgd'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.9</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('nesterovs_momentum',\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.neural_network.MLPClassifier.html#:~:text=nesterovs_momentum,-bool%2C%20default%3DTrue\">\n",
|
||
" nesterovs_momentum\n",
|
||
" <span class=\"param-doc-description\">nesterovs_momentum: bool, default=True<br><br>Whether to use Nesterov's momentum. Only used when solver='sgd' and<br>momentum > 0.</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('early_stopping',\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.neural_network.MLPClassifier.html#:~:text=early_stopping,-bool%2C%20default%3DFalse\">\n",
|
||
" early_stopping\n",
|
||
" <span class=\"param-doc-description\">early_stopping: bool, default=False<br><br>Whether to use early stopping to terminate training when validation<br>score is not improving. If set to True, it will automatically set<br>aside ``validation_fraction`` of training data as validation and<br>terminate training when validation score is not improving by at least<br>``tol`` for ``n_iter_no_change`` consecutive epochs. The split is<br>stratified, except in a multilabel setting.<br>If early stopping is False, then the training stops when the training<br>loss does not improve by more than ``tol`` for ``n_iter_no_change``<br>consecutive passes over the training set.<br>Only effective when solver='sgd' or 'adam'.</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('validation_fraction',\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.neural_network.MLPClassifier.html#:~:text=validation_fraction,-float%2C%20default%3D0.1\">\n",
|
||
" validation_fraction\n",
|
||
" <span class=\"param-doc-description\">validation_fraction: float, default=0.1<br><br>The proportion of training data to set aside as validation set for<br>early stopping. Must be between 0 and 1.<br>Only used if early_stopping is True.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.1</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('beta_1',\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.neural_network.MLPClassifier.html#:~:text=beta_1,-float%2C%20default%3D0.9\">\n",
|
||
" beta_1\n",
|
||
" <span class=\"param-doc-description\">beta_1: float, default=0.9<br><br>Exponential decay rate for estimates of first moment vector in adam,<br>should be in [0, 1). Only used when solver='adam'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.9</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('beta_2',\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.neural_network.MLPClassifier.html#:~:text=beta_2,-float%2C%20default%3D0.999\">\n",
|
||
" beta_2\n",
|
||
" <span class=\"param-doc-description\">beta_2: float, default=0.999<br><br>Exponential decay rate for estimates of second moment vector in adam,<br>should be in [0, 1). Only used when solver='adam'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">0.999</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('epsilon',\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.neural_network.MLPClassifier.html#:~:text=epsilon,-float%2C%20default%3D1e-8\">\n",
|
||
" epsilon\n",
|
||
" <span class=\"param-doc-description\">epsilon: float, default=1e-8<br><br>Value for numerical stability in adam. Only used when solver='adam'.</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">1e-08</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('n_iter_no_change',\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.neural_network.MLPClassifier.html#:~:text=n_iter_no_change,-int%2C%20default%3D10\">\n",
|
||
" n_iter_no_change\n",
|
||
" <span class=\"param-doc-description\">n_iter_no_change: int, default=10<br><br>Maximum number of epochs to not meet ``tol`` improvement.<br>Only effective when solver='sgd' or 'adam'.<br><br>.. versionadded:: 0.20</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">10</td>\n",
|
||
" </tr>\n",
|
||
" \n",
|
||
"\n",
|
||
" <tr class=\"default\">\n",
|
||
" <td><i class=\"copy-paste-icon\"\n",
|
||
" onclick=\"copyToClipboard('max_fun',\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.neural_network.MLPClassifier.html#:~:text=max_fun,-int%2C%20default%3D15000\">\n",
|
||
" max_fun\n",
|
||
" <span class=\"param-doc-description\">max_fun: int, default=15000<br><br>Only used when solver='lbfgs'. Maximum number of loss function calls.<br>The solver iterates until convergence (determined by 'tol'), number<br>of iterations reaches max_iter, or this number of loss function calls.<br>Note that number of loss function calls will be greater than or equal<br>to the number of iterations for the `MLPClassifier`.<br><br>.. versionadded:: 0.22</span>\n",
|
||
" </a>\n",
|
||
" </td>\n",
|
||
" <td class=\"value\">15000</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-1');</script></body>"
|
||
],
|
||
"text/plain": [
|
||
"MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)"
|
||
]
|
||
},
|
||
"execution_count": 19,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Train model 1 on generated data\n",
|
||
"mlp_model_1.fit(X_train, y_train)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "600e90f1-fc12-4300-ab60-76b4656bf5d8",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Run the validation data through the ML model."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "4d08a5ac-93cf-4da5-a266-7052ea31ac6a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array(['low', 'high', 'high', 'moderate', 'low', 'high', 'high', 'high',\n",
|
||
" 'low', 'low'], dtype='<U8')"
|
||
]
|
||
},
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Run validation data through the trained model\n",
|
||
"y_val_pred_1 = mlp_model_1.predict(X_val)\n",
|
||
"y_val_proba_1 = mlp_model_1.predict_proba(X_val)\n",
|
||
"\n",
|
||
"\n",
|
||
"# This script outputs nothing by default, so adding a line to display the first ten lines as evidence.\n",
|
||
"y_val_pred_1[:10]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ef0f7e01-0fe2-4c66-86eb-734d59280e85",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Metrics Calculation (Accuracy, ROC-AUC & Confusion matrix) - Rayyan Hodges"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 26,
|
||
"id": "b6521a2a-d843-4788-854b-a025ba5f234c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.6216216216216216"
|
||
]
|
||
},
|
||
"execution_count": 26,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating accuracy\n",
|
||
"\n",
|
||
"from sklearn.metrics import accuracy_score\n",
|
||
"\n",
|
||
"accuracy_1 = accuracy_score(y_val, y_val_pred_1)\n",
|
||
"accuracy_1\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"id": "a1c05820-0b69-4c8f-bfdd-5c51607c6b58",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.8328379028379028"
|
||
]
|
||
},
|
||
"execution_count": 27,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating ROC‑AUC (multi‑class)\n",
|
||
"\n",
|
||
"from sklearn.metrics import roc_auc_score\n",
|
||
"\n",
|
||
"roc_auc_1 = roc_auc_score(\n",
|
||
" y_val,\n",
|
||
" y_val_proba_1,\n",
|
||
" multi_class='ovr'\n",
|
||
")\n",
|
||
"roc_auc_1\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"id": "99e73c34-5650-42cc-9ed2-36a1f2fb044c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[35, 1, 13],\n",
|
||
" [ 1, 40, 8],\n",
|
||
" [14, 19, 17]])"
|
||
]
|
||
},
|
||
"execution_count": 25,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#Calculating confusion matrix\n",
|
||
"\n",
|
||
"from sklearn.metrics import confusion_matrix\n",
|
||
"\n",
|
||
"conf_matrix_1 = confusion_matrix(y_val, y_val_pred_1)\n",
|
||
"conf_matrix_1"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.13.12"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|