mirror of
https://github.com/reiyua/HospitalCancerClassification.git
synced 2026-11-17 06:12:06 +11:00
3602 lines
392 KiB
Text
3602 lines
392 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": 53,
|
||
"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\n",
|
||
"import matplotlib"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"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": 3,
|
||
"id": "10d93e7f-9ba8-45a4-831d-7ba48046fea7",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"np.int64(10)"
|
||
]
|
||
},
|
||
"execution_count": 3,
|
||
"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": 4,
|
||
"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": 4,
|
||
"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": 15,
|
||
"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>1.000000e+03</td>\n",
|
||
" <td>1.000000e+03</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>mean</th>\n",
|
||
" <td>-4.618528e-17</td>\n",
|
||
" <td>-3.552714e-17</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>std</th>\n",
|
||
" <td>1.000500e+00</td>\n",
|
||
" <td>1.000500e+00</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>min</th>\n",
|
||
" <td>-1.684915e+00</td>\n",
|
||
" <td>-1.703831e+00</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25%</th>\n",
|
||
" <td>-8.885765e-01</td>\n",
|
||
" <td>-8.621512e-01</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50%</th>\n",
|
||
" <td>3.871853e-03</td>\n",
|
||
" <td>-1.077505e-02</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>75%</th>\n",
|
||
" <td>8.860227e-01</td>\n",
|
||
" <td>8.687217e-01</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>max</th>\n",
|
||
" <td>1.733849e+00</td>\n",
|
||
" <td>1.775369e+00</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" bmi blood_pressure\n",
|
||
"count 1.000000e+03 1.000000e+03\n",
|
||
"mean -4.618528e-17 -3.552714e-17\n",
|
||
"std 1.000500e+00 1.000500e+00\n",
|
||
"min -1.684915e+00 -1.703831e+00\n",
|
||
"25% -8.885765e-01 -8.621512e-01\n",
|
||
"50% 3.871853e-03 -1.077505e-02\n",
|
||
"75% 8.860227e-01 8.687217e-01\n",
|
||
"max 1.733849e+00 1.775369e+00"
|
||
]
|
||
},
|
||
"execution_count": 15,
|
||
"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": 16,
|
||
"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>0.484421</td>\n",
|
||
" <td>1.631857</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>-1.492695</td>\n",
|
||
" <td>1.399135</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>0.525611</td>\n",
|
||
" <td>0.569092</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>1.665199</td>\n",
|
||
" <td>-0.101925</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>-1.451505</td>\n",
|
||
" <td>0.650544</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 0.484421 1.631857 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 -1.492695 1.399135 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 0.525611 0.569092 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 1.665199 -0.101925 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 -1.451505 0.650544 212.8 yes 5 moderate False False False False True False False False True False False False False False True"
|
||
]
|
||
},
|
||
"execution_count": 16,
|
||
"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": 17,
|
||
"id": "a5174be9-c40b-457e-afd5-1ec97c70ed0a",
|
||
"metadata": {
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"((693, 23), (148, 23), (149, 23))"
|
||
]
|
||
},
|
||
"execution_count": 17,
|
||
"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": 18,
|
||
"id": "c94e2161-e95d-4a84-864d-bc1388bd4d48",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"(693, 21)"
|
||
]
|
||
},
|
||
"execution_count": 18,
|
||
"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 - MLPClassifier"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"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": 20,
|
||
"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": 20,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# BUG FIXING: List any non numerical rows\n",
|
||
"X_train.dtypes"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "f16e2e40-e065-44ca-b944-e9a2921d89db",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/tmp/ipykernel_81/146862157.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": 21,
|
||
"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": 22,
|
||
"id": "f62a9503-664a-43d9-9afa-0029695acce8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# BUG FIXING\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": 23,
|
||
"id": "cfcddd52-1a78-4c07-8f5d-036682a8cad6",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<style>#sk-container-id-2 {\n",
|
||
" /* Definition of color scheme common for light and dark mode */\n",
|
||
" --sklearn-color-text: #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-2.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-2.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-2 {\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 pre {\n",
|
||
" padding: 0;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 input.sk-hidden--visually {\n",
|
||
" border: 0;\n",
|
||
" clip: rect(1px 1px 1px 1px);\n",
|
||
" clip: rect(1px, 1px, 1px, 1px);\n",
|
||
" height: 1px;\n",
|
||
" margin: -1px;\n",
|
||
" overflow: hidden;\n",
|
||
" padding: 0;\n",
|
||
" position: absolute;\n",
|
||
" width: 1px;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-dashed-wrapped {\n",
|
||
" border: 1px dashed var(--sklearn-color-line);\n",
|
||
" margin: 0 0.4em 0.5em 0.4em;\n",
|
||
" box-sizing: border-box;\n",
|
||
" padding-bottom: 0.4em;\n",
|
||
" background-color: var(--sklearn-color-background);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-container {\n",
|
||
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
||
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
||
" so we also need the `!important` here to be able to override the\n",
|
||
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
||
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
||
" display: inline-block !important;\n",
|
||
" position: relative;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-text-repr-fallback {\n",
|
||
" display: none;\n",
|
||
"}\n",
|
||
"\n",
|
||
"div.sk-parallel-item,\n",
|
||
"div.sk-serial,\n",
|
||
"div.sk-item {\n",
|
||
" /* draw centered vertical line to link estimators */\n",
|
||
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
||
" background-size: 2px 100%;\n",
|
||
" background-repeat: no-repeat;\n",
|
||
" background-position: center center;\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Parallel-specific style estimator block */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel-item::after {\n",
|
||
" content: \"\";\n",
|
||
" width: 100%;\n",
|
||
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
||
" flex-grow: 1;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel {\n",
|
||
" display: flex;\n",
|
||
" align-items: stretch;\n",
|
||
" justify-content: center;\n",
|
||
" background-color: var(--sklearn-color-background);\n",
|
||
" position: relative;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel-item {\n",
|
||
" display: flex;\n",
|
||
" flex-direction: column;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
|
||
" align-self: flex-end;\n",
|
||
" width: 50%;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
|
||
" align-self: flex-start;\n",
|
||
" width: 50%;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
|
||
" width: 0;\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Serial-specific style estimator block */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-serial {\n",
|
||
" display: flex;\n",
|
||
" flex-direction: column;\n",
|
||
" align-items: center;\n",
|
||
" background-color: var(--sklearn-color-background);\n",
|
||
" padding-right: 1em;\n",
|
||
" padding-left: 1em;\n",
|
||
"}\n",
|
||
"\n",
|
||
"\n",
|
||
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
||
"clickable and can be expanded/collapsed.\n",
|
||
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
||
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
||
"*/\n",
|
||
"\n",
|
||
"/* Pipeline and ColumnTransformer style (default) */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-toggleable {\n",
|
||
" /* Default theme specific background. It is overwritten whether we have a\n",
|
||
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
||
" background-color: var(--sklearn-color-background);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Toggleable label */\n",
|
||
"#sk-container-id-2 label.sk-toggleable__label {\n",
|
||
" cursor: pointer;\n",
|
||
" display: 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-2 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-2 label.sk-toggleable__label-arrow:before {\n",
|
||
" /* Arrow on the left of the label */\n",
|
||
" content: \"▸\";\n",
|
||
" float: left;\n",
|
||
" margin-right: 0.25em;\n",
|
||
" color: var(--sklearn-color-icon);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Toggleable content - dropdown */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-toggleable__content {\n",
|
||
" display: none;\n",
|
||
" text-align: left;\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
|
||
" /* fitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-toggleable__content pre {\n",
|
||
" margin: 0.2em;\n",
|
||
" border-radius: 0.25em;\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
||
" /* Expand drop-down */\n",
|
||
" display: block;\n",
|
||
" width: 100%;\n",
|
||
" overflow: visible;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
||
" content: \"▾\";\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Pipeline/ColumnTransformer-specific style */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Estimator-specific style */\n",
|
||
"\n",
|
||
"/* Colorize estimator box */\n",
|
||
"#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
" /* fitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
|
||
"#sk-container-id-2 div.sk-label label {\n",
|
||
" /* The background is the default theme color */\n",
|
||
" color: var(--sklearn-color-text-on-default-background);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* On hover, darken the color of the background */\n",
|
||
"#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Label box, darken color on hover, fitted */\n",
|
||
"#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
||
" color: var(--sklearn-color-text);\n",
|
||
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Estimator label */\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-label label {\n",
|
||
" font-family: monospace;\n",
|
||
" font-weight: bold;\n",
|
||
" line-height: 1.2em;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-label-container {\n",
|
||
" text-align: center;\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Estimator-specific */\n",
|
||
"#sk-container-id-2 div.sk-estimator {\n",
|
||
" font-family: monospace;\n",
|
||
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
||
" border-radius: 0.25em;\n",
|
||
" box-sizing: border-box;\n",
|
||
" margin-bottom: 0.5em;\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-estimator.fitted {\n",
|
||
" /* fitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* on hover */\n",
|
||
"#sk-container-id-2 div.sk-estimator:hover {\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
|
||
" /* fitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
"}\n",
|
||
"\n",
|
||
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
||
"\n",
|
||
"/* Common style for \"i\" and \"?\" */\n",
|
||
"\n",
|
||
".sk-estimator-doc-link,\n",
|
||
"a:link.sk-estimator-doc-link,\n",
|
||
"a:visited.sk-estimator-doc-link {\n",
|
||
" float: right;\n",
|
||
" font-size: smaller;\n",
|
||
" line-height: 1em;\n",
|
||
" font-family: monospace;\n",
|
||
" background-color: var(--sklearn-color-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-2 a.estimator_doc_link {\n",
|
||
" float: right;\n",
|
||
" font-size: 1rem;\n",
|
||
" line-height: 1em;\n",
|
||
" font-family: monospace;\n",
|
||
" background-color: var(--sklearn-color-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-2 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-2 a.estimator_doc_link:hover {\n",
|
||
" /* unfitted */\n",
|
||
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
||
" color: var(--sklearn-color-background);\n",
|
||
" text-decoration: none;\n",
|
||
"}\n",
|
||
"\n",
|
||
"#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
|
||
" /* fitted */\n",
|
||
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
||
"}\n",
|
||
"\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-2\" 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-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" 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-2');</script></body>"
|
||
],
|
||
"text/plain": [
|
||
"MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)"
|
||
]
|
||
},
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Train model 1 on generated data\n",
|
||
"mlp_model_1.fit(X_train, y_train)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"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": 24,
|
||
"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": "code",
|
||
"execution_count": 25,
|
||
"id": "b6521a2a-d843-4788-854b-a025ba5f234c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.6216216216216216"
|
||
]
|
||
},
|
||
"execution_count": 25,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating accuracy - Metric Calculation\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": 26,
|
||
"id": "a1c05820-0b69-4c8f-bfdd-5c51607c6b58",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.8325664811379098"
|
||
]
|
||
},
|
||
"execution_count": 26,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating ROC‑AUC (multi‑class) - Metrics Calculation\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 - Metrics calculation\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"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "32ec34ef-21ca-4ddb-94ec-ac66d794dcf2",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Part 3: Train and evaluate ML model - Task 1: Train ML model 2"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 37,
|
||
"id": "15b5b7f9-3411-4743-906f-539d8e8cc4e2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Select an appropriate initial model size by setting the number of layers and neurons.\n",
|
||
"\n",
|
||
"from sklearn.neural_network import MLPClassifier\n",
|
||
"\n",
|
||
"mlp_model_2 = MLPClassifier(\n",
|
||
" hidden_layer_sizes=(128, 64),\n",
|
||
" max_iter=500,\n",
|
||
" random_state=42\n",
|
||
")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 38,
|
||
"id": "5077d71c-8216-4f70-906a-435535b61733",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Refine hyperparameters separately to layers and neurons\n",
|
||
"mlp_model_2 = MLPClassifier(\n",
|
||
" hidden_layer_sizes=(128, 64),\n",
|
||
" max_iter=500, # increased training iterations\n",
|
||
" random_state=42\n",
|
||
")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 39,
|
||
"id": "a32d6252-87af-4361-9d07-718a845f9588",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"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>MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=500, 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-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" 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\">(128, ...)</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\">500</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-3');</script></body>"
|
||
],
|
||
"text/plain": [
|
||
"MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=500, random_state=42)"
|
||
]
|
||
},
|
||
"execution_count": 39,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Retrain the refined Model 2 using training data\n",
|
||
"mlp_model_2.fit(X_train, y_train)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 43,
|
||
"id": "8dc73f03-b890-454c-9a23-5964b2a215ed",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# BUG FIXING: Create model 2 prediction variables.\n",
|
||
"y_val_pred_2 = mlp_model_2.predict(X_val)\n",
|
||
"y_val_proba_2 = mlp_model_2.predict_proba(X_val)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 45,
|
||
"id": "69207f42-89e4-4bb6-ba2a-e9415e032508",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.7027027027027027"
|
||
]
|
||
},
|
||
"execution_count": 45,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating accuracy - Metric Calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import accuracy_score\n",
|
||
"\n",
|
||
"accuracy_2 = accuracy_score(y_val, y_val_pred_2)\n",
|
||
"accuracy_2"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"id": "735c89d9-b79c-454b-a8bf-a344d4b4bb72",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.8668102796674225"
|
||
]
|
||
},
|
||
"execution_count": 46,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating ROC‑AUC (multi‑class) - Metrics Calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import roc_auc_score\n",
|
||
"\n",
|
||
"roc_auc_2 = roc_auc_score(\n",
|
||
" y_val,\n",
|
||
" y_val_proba_2,\n",
|
||
" multi_class='ovr'\n",
|
||
")\n",
|
||
"roc_auc_2\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 47,
|
||
"id": "58527a3f-7dbf-4304-ab7c-fbc94d5dcf51",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[39, 0, 10],\n",
|
||
" [ 1, 35, 13],\n",
|
||
" [14, 6, 30]])"
|
||
]
|
||
},
|
||
"execution_count": 47,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#Calculating confusion matrix - Metrics calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import confusion_matrix\n",
|
||
"\n",
|
||
"conf_matrix_2 = confusion_matrix(y_val, y_val_pred_2)\n",
|
||
"conf_matrix_2"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9dae3ddf-0262-4c36-a378-a9fcbd13150b",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Graphic results of ML Model Metrics"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 49,
|
||
"id": "a5d55430-2952-4835-96bd-fdb46203870b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Import required libraries\n",
|
||
"\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"from sklearn.preprocessing import label_binarize\n",
|
||
"from sklearn.metrics import roc_curve, auc\n",
|
||
"import numpy as np\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 50,
|
||
"id": "93707da7-68af-45ac-8d37-61b9479d8388",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#Convert labels to binary format for Matplotlib\n",
|
||
"\n",
|
||
"classes = y_val.unique()\n",
|
||
"y_val_bin = label_binarize(y_val, classes=classes)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 51,
|
||
"id": "b285c94b-960b-4933-82a0-cf40f448725e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Generate ROC‑AUC graph for Model 1\n",
|
||
"\n",
|
||
"plt.figure()\n",
|
||
"\n",
|
||
"for i in range(len(classes)):\n",
|
||
" fpr, tpr, _ = roc_curve(y_val_bin[:, i], y_val_proba_1[:, i])\n",
|
||
" roc_auc = auc(fpr, tpr)\n",
|
||
" plt.plot(fpr, tpr, label=f\"{classes[i]} (AUC = {roc_auc:.2f})\")\n",
|
||
"\n",
|
||
"plt.plot([0, 1], [0, 1], 'k--')\n",
|
||
"plt.xlabel(\"False Positive Rate\")\n",
|
||
"plt.ylabel(\"True Positive Rate\")\n",
|
||
"plt.title(\"ROC-AUC Curve - Model 1 - Rayyan Hodges\")\n",
|
||
"plt.legend()\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 52,
|
||
"id": "ae527403-001c-41d2-a04f-1dfe9efca07e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Generate ROC‑AUC graph for Model 2\n",
|
||
"\n",
|
||
"plt.figure()\n",
|
||
"\n",
|
||
"for i in range(len(classes)):\n",
|
||
" fpr, tpr, _ = roc_curve(y_val_bin[:, i], y_val_proba_2[:, i])\n",
|
||
" roc_auc = auc(fpr, tpr)\n",
|
||
" plt.plot(fpr, tpr, label=f\"{classes[i]} (AUC = {roc_auc:.2f})\")\n",
|
||
"\n",
|
||
"plt.plot([0, 1], [0, 1], 'k--')\n",
|
||
"plt.xlabel(\"False Positive Rate\")\n",
|
||
"plt.ylabel(\"True Positive Rate\")\n",
|
||
"plt.title(\"ROC-AUC Curve - Model 2 - Rayyan Hodges\")\n",
|
||
"plt.legend()\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 61,
|
||
"id": "12619e3d-5e73-410c-9bc5-24edfa528731",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Geenrate ROC-AUC graph for Final Model\n",
|
||
"\n",
|
||
"plt.figure()\n",
|
||
"\n",
|
||
"for i in range(len(classes)):\n",
|
||
" fpr, tpr, _ = roc_curve(y_val_bin[:, i], y_val_proba_2[:, i])\n",
|
||
" roc_auc = auc(fpr, tpr)\n",
|
||
" plt.plot(fpr, tpr, label=f\"{classes[i]} (AUC = {roc_auc:.2f})\")\n",
|
||
"\n",
|
||
"plt.plot([0, 1], [0, 1], 'k--')\n",
|
||
"plt.xlabel(\"False Positive Rate\")\n",
|
||
"plt.ylabel(\"True Positive Rate\")\n",
|
||
"plt.title(\"ROC-AUC Curve - Final - Rayyan Hodges\")\n",
|
||
"plt.legend()\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 54,
|
||
"id": "7d70268f-48e7-4b9c-a162-cdb6ae27727f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Import additional required libraries\n",
|
||
"\n",
|
||
"from sklearn.metrics import ConfusionMatrixDisplay\n",
|
||
"import matplotlib.pyplot as plt\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 59,
|
||
"id": "fa792a8e-682e-4eda-9a15-9495f1c5e6c6",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 2 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Generate Confusion matrix graph for Model 1\n",
|
||
"\n",
|
||
"ConfusionMatrixDisplay.from_predictions(\n",
|
||
" y_val,\n",
|
||
" y_val_pred_1,\n",
|
||
" cmap=\"Reds\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.title(\"Confusion Matrix - Model 1 - Rayyan Hodges\")\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 58,
|
||
"id": "b4918222-c0ef-48ce-a29e-3c467e016f0f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 2 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Generate Confusion matrix graph for Model 2\n",
|
||
"\n",
|
||
"ConfusionMatrixDisplay.from_predictions(\n",
|
||
" y_val,\n",
|
||
" y_val_pred_2,\n",
|
||
" cmap=\"Blues\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.title(\"Confusion Matrix - Model 2 - Rayyan Hodges\")\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 60,
|
||
"id": "d69efb54-713d-4495-95da-6730ab2381ea",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 2 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"#Generate confusion matrix for final model\n",
|
||
"\n",
|
||
"# Confusion matrix\n",
|
||
"\n",
|
||
"ConfusionMatrixDisplay.from_predictions(\n",
|
||
" y_val,\n",
|
||
" y_val_pred_2,\n",
|
||
" cmap=\"Greens\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.title(\"Confusion Matrix - Final model - Rayyan Hodges\")\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 63,
|
||
"id": "1f3e3092-d82f-4560-b4fe-d21cd15aa044",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array(['low', 'moderate', 'high', 'low', 'high', 'high', 'low',\n",
|
||
" 'moderate', 'high', 'moderate'], dtype='<U8')"
|
||
]
|
||
},
|
||
"execution_count": 63,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Run test data through the final (best) model\n",
|
||
"y_test_pred = mlp_model_2.predict(X_test)\n",
|
||
"y_test_proba = mlp_model_2.predict_proba(X_test)\n",
|
||
"\n",
|
||
"# Display sample output for evidence\n",
|
||
"y_test_pred[:10]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0d31bef2-75be-45b3-b0bc-c33221e74957",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Final model metrics - Rayyan Hodges"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 64,
|
||
"id": "c44ed94e-9417-44b9-863a-b62c452ced48",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.7027027027027027"
|
||
]
|
||
},
|
||
"execution_count": 64,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating accuracy - Metric Calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import accuracy_score\n",
|
||
"\n",
|
||
"accuracy_2 = accuracy_score(y_val, y_val_pred_2)\n",
|
||
"accuracy_2"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 65,
|
||
"id": "bb270cc6-bf9d-4555-8914-59fe4589e5c2",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0.8668102796674225"
|
||
]
|
||
},
|
||
"execution_count": 65,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# Calculating ROC‑AUC (multi‑class) - Metrics Calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import roc_auc_score\n",
|
||
"\n",
|
||
"roc_auc_2 = roc_auc_score(\n",
|
||
" y_val,\n",
|
||
" y_val_proba_2,\n",
|
||
" multi_class='ovr'\n",
|
||
")\n",
|
||
"roc_auc_2\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 66,
|
||
"id": "99676265-d2a0-4f36-a384-a0bba44f6f44",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"array([[39, 0, 10],\n",
|
||
" [ 1, 35, 13],\n",
|
||
" [14, 6, 30]])"
|
||
]
|
||
},
|
||
"execution_count": 66,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#Calculating confusion matrix - Metrics calculation\n",
|
||
"\n",
|
||
"from sklearn.metrics import confusion_matrix\n",
|
||
"\n",
|
||
"conf_matrix_2 = confusion_matrix(y_val, y_val_pred_2)\n",
|
||
"conf_matrix_2"
|
||
]
|
||
}
|
||
],
|
||
"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
|
||
}
|