{ "cells": [ { "cell_type": "markdown", "id": "c01ffe8d-3916-478f-a9c5-f3b480e5e293", "metadata": {}, "source": [ "# Copyright Rayyan Hodges, TAFE NSW, Gelos Enterprises, Indigo Community Services and Health Hub © 2026" ] }, { "cell_type": "markdown", "id": "b9f47b2c-6f01-479a-a87b-e698effc6edf", "metadata": {}, "source": [ "# Contact: rayyan.hodges@studytafensw.edu.au, rayyan.hodges@gelosmail.com.au indigoCSHH@hmail.com" ] }, { "cell_type": "markdown", "id": "c49336b7-8ec3-4a18-8590-4cd6c02917cb", "metadata": {}, "source": [ "# Program Name: HopsitalCancerClassification.ipynb" ] }, { "cell_type": "markdown", "id": "59691122-a537-4615-8a65-f408eb6fcffb", "metadata": {}, "source": [ "# Purpose: To train and evaluate an ML model to automate the task of classifying clients as high, medium or low risk of developing cancer." ] }, { "cell_type": "code", "execution_count": 1, "id": "1092545b-8be3-487b-87df-d8829e0a00eb", "metadata": {}, "outputs": [], "source": [ "# Import required libraries\n", "import joblib\n", "import numpy\n", "import pandas as pd\n", "import sklearn # importing the scikit-learn project, different name due to syntax rules \n", "import scipy\n", "import threadpoolctl" ] }, { "cell_type": "code", "execution_count": 3, "id": "3a05014a-200c-4bc6-9667-568898547852", "metadata": {}, "outputs": [], "source": [ "# Set appropriate display options in Pandas\n", "pd.set_option('display.max_rows', 10000)\n", "pd.set_option('display.max_columns', 10000)\n", "pd.set_option('display.width', 10000)" ] }, { "cell_type": "markdown", "id": "95ffdbd6-b7e7-41b9-990f-932a05cae2e6", "metadata": {}, "source": [ "# Identify any datapoints with missing labels and remove them" ] }, { "cell_type": "code", "execution_count": 4, "id": "10d93e7f-9ba8-45a4-831d-7ba48046fea7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "np.int64(10)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Load the data set into memory and define it for further analysis.\n", "df = pd.read_csv(\"data.csv\")\n", "# Check for missing values in the target column, count them, and display them in a total number.\n", "df['cancer_risk'].isnull().sum()" ] }, { "cell_type": "code", "execution_count": 5, "id": "3434f6bb-7cdb-4434-a948-1dc7d9e7d260", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "np.int64(0)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Remove the affected rows with missing data\n", "df = df.dropna(subset=['cancer_risk'])\n", "# Verify removal of said invalid data.\n", "df['cancer_risk'].isnull().sum()" ] }, { "cell_type": "markdown", "id": "44a9b1bc-0c6c-4e9e-95a7-03d3108b696b", "metadata": {}, "source": [ "# Categorise ages as required." ] }, { "cell_type": "code", "execution_count": 6, "id": "a8887198-0dbd-471d-bd1e-836d34def83a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ageage_group
05145-54
19285+
2140-14
37165-74
46055-64
\n", "
" ], "text/plain": [ " age age_group\n", "0 51 45-54\n", "1 92 85+\n", "2 14 0-14\n", "3 71 65-74\n", "4 60 55-64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Define age bins and labels for the groups\n", "# Bins meaning boundaries \n", "bins = [0, 14, 24, 34, 44, 54, 64, 74, 84, 120]\n", "labels = ['0-14', '15-24', '25-34', '35-44', \n", " '45-54', '55-64', '65-74', '75-84', '85+']\n", "\n", "# Categorise ages into age groups\n", "df['age_group'] = pd.cut(df['age'], bins=bins, labels=labels, right=True)\n", "\n", "# Display the results in a table\n", "df[['age', 'age_group']].head()\n" ] }, { "cell_type": "markdown", "id": "b2751d18-2580-453a-b0d9-70bc956f73cc", "metadata": {}, "source": [ "# Standardise numerical features using appropriate scaling techniques." ] }, { "cell_type": "code", "execution_count": 7, "id": "f9beff06-ce08-479d-b63d-56ca8aaf6338", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
bmiblood_pressure
count9.900000e+029.900000e+02
mean1.076580e-171.130409e-16
std1.000505e+001.000505e+00
min-1.679483e+00-1.699762e+00
25%-8.839714e-01-8.598235e-01
50%6.927133e-04-1.794981e-02
75%8.853568e-018.703721e-01
max1.735732e+001.772241e+00
\n", "
" ], "text/plain": [ " bmi blood_pressure\n", "count 9.900000e+02 9.900000e+02\n", "mean 1.076580e-17 1.130409e-16\n", "std 1.000505e+00 1.000505e+00\n", "min -1.679483e+00 -1.699762e+00\n", "25% -8.839714e-01 -8.598235e-01\n", "50% 6.927133e-04 -1.794981e-02\n", "75% 8.853568e-01 8.703721e-01\n", "max 1.735732e+00 1.772241e+00" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Import the scaling component from the SciKit Learning Library\n", "from sklearn.preprocessing import StandardScaler\n", "\n", "# Select numerical features from the datasheet.\n", "numerical_features = ['bmi', 'blood_pressure']\n", "\n", "# Initialise scaler component\n", "scaler = StandardScaler()\n", "\n", "# Apply scaling and transformation to standardise the numbers.\n", "df[numerical_features] = scaler.fit_transform(df[numerical_features])\n", "\n", "# Display results from the scaling and transformation.\n", "df[numerical_features].describe()\n" ] }, { "cell_type": "markdown", "id": "2616a37d-bffd-4a8d-b648-24673a543e7d", "metadata": {}, "source": [ "# Encode categorical data using appropriate encoding techniques." ] }, { "cell_type": "code", "execution_count": 8, "id": "8bc14115-e855-4233-9058-eff0ce5c9386", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agefamily_historyalcohol_consumptionbmiblood_pressurecholesterol_leveltravelled_overseasnumber_of_childrencancer_riskage_group_15-24age_group_25-34age_group_35-44age_group_45-54age_group_55-64age_group_65-74age_group_75-84age_group_85+smoking_history_formersmoking_history_neverdiet_gooddiet_poorexercise_frequency_lowexercise_frequency_moderateexercise_frequency_none
051nolow0.4876011.629026226.4no5moderateFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseTrueFalseFalseTrue
192nomoderate-1.4874631.396785170.9yes2lowFalseFalseFalseFalseFalseFalseFalseTrueFalseTrueFalseTrueFalseFalseFalse
214nonone0.5287480.568459279.9yes4highFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseFalseTrue
371yeslow1.667153-0.101170280.7yes0moderateFalseFalseFalseFalseFalseTrueFalseFalseTrueFalseFalseTrueFalseFalseFalse
460nonone-1.4463160.649743212.8yes5moderateFalseFalseFalseFalseTrueFalseFalseFalseTrueFalseFalseFalseFalseFalseTrue
\n", "
" ], "text/plain": [ " age family_history alcohol_consumption bmi blood_pressure cholesterol_level travelled_overseas number_of_children cancer_risk age_group_15-24 age_group_25-34 age_group_35-44 age_group_45-54 age_group_55-64 age_group_65-74 age_group_75-84 age_group_85+ smoking_history_former smoking_history_never diet_good diet_poor exercise_frequency_low exercise_frequency_moderate exercise_frequency_none\n", "0 51 no low 0.487601 1.629026 226.4 no 5 moderate False False False True False False False False False True False True False False True\n", "1 92 no moderate -1.487463 1.396785 170.9 yes 2 low False False False False False False False True False True False True False False False\n", "2 14 no none 0.528748 0.568459 279.9 yes 4 high False False False False False False False False False False False False False False True\n", "3 71 yes low 1.667153 -0.101170 280.7 yes 0 moderate False False False False False True False False True False False True False False False\n", "4 60 no none -1.446316 0.649743 212.8 yes 5 moderate False False False False True False False False True False False False False False True" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Identify categorical features from the dataset file to be referenced.\n", "categorical_features = ['age_group', 'smoking_history', 'diet', 'exercise_frequency']\n", "\n", "# Apply one-hot encoding to convert the text categories into dummy numerical categories (specifically true or false)\n", "df_encoded = pd.get_dummies(df, columns=categorical_features, drop_first=True)\n", "\n", "# Print the results to ensure the categorical features have been converted to variables such as true or false correctly.\n", "df_encoded.head()\n" ] }, { "cell_type": "markdown", "id": "3b6926b7-31d0-4558-9695-c16570087104", "metadata": {}, "source": [ "# Divide and randomise the dataset into training" ] }, { "cell_type": "code", "execution_count": 9, "id": "a5174be9-c40b-457e-afd5-1ec97c70ed0a", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "((693, 23), (148, 23), (149, 23))" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "# Remove rows with missing target labels (specifically, the 'cancer_risk' label, as it has missing data) \n", "df_encoded = df_encoded.dropna(subset=['cancer_risk'])\n", "\n", "#Import the splitting model from the scikit-learn model.\n", "from sklearn.model_selection import train_test_split\n", "\n", "# Separate features and target\n", "X = df_encoded.drop('cancer_risk', axis=1)\n", "y = df_encoded['cancer_risk']\n", "\n", "# First split: 70% training, 30% temp\n", "X_train, X_temp, y_train, y_temp = train_test_split(\n", " X, y, test_size=0.30, random_state=42, stratify=y\n", ")\n", "\n", "# Second split: 15% validation, 15% test\n", "X_val, X_test, y_val, y_test = train_test_split(\n", " X_temp, y_temp, test_size=0.50, random_state=42, stratify=y_temp\n", ")\n", "\n", "# Print the results of said sizes to ensure it is working correctly.\n", "X_train.shape, X_val.shape, X_test.shape\n" ] }, { "cell_type": "markdown", "id": "b4c21ba9-b730-4150-8b38-dfb5b00f87c1", "metadata": {}, "source": [ "# Select the most important features in the training dataset that may influence cancer risk, dropping 2 unnecessary features." ] }, { "cell_type": "code", "execution_count": 10, "id": "c94e2161-e95d-4a84-864d-bc1388bd4d48", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(693, 21)" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Drop two unnecessary features/columns that aren't relevant to cancer risk evaluation and wouldn't affect if someone would be likely to have cancer.\n", "X_train = X_train.drop(['travelled_overseas', 'number_of_children'], axis=1)\n", "X_val = X_val.drop(['travelled_overseas', 'number_of_children'], axis=1)\n", "X_test = X_test.drop(['travelled_overseas', 'number_of_children'], axis=1)\n", "\n", "# Print the results to allow the user to determine the changes have worked\n", "X_train.shape\n" ] }, { "cell_type": "markdown", "id": "49174e92-2e15-461a-844f-ffa90c0d7c99", "metadata": {}, "source": [ "# Part 3: Train and evaluate ML model - Task 1: Train ML model 1" ] }, { "cell_type": "code", "execution_count": 11, "id": "b95cb28a-5312-4f55-8485-61c4e95e782e", "metadata": {}, "outputs": [], "source": [ "# Select an appropriate initial model size by setting the number of layers and neurons.\n", "\n", "\n", "from sklearn.neural_network import MLPClassifier\n", "\n", "mlp_model_1 = MLPClassifier(\n", " hidden_layer_sizes=(64, 32),\n", " activation='relu',\n", " solver='adam',\n", " max_iter=300,\n", " random_state=42\n", ")\n" ] }, { "cell_type": "code", "execution_count": 13, "id": "9a44bcdd-8605-4e21-9a7a-1a3296f46909", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "age int64\n", "family_history str\n", "alcohol_consumption str\n", "bmi float64\n", "blood_pressure float64\n", "cholesterol_level float64\n", "age_group_15-24 bool\n", "age_group_25-34 bool\n", "age_group_35-44 bool\n", "age_group_45-54 bool\n", "age_group_55-64 bool\n", "age_group_65-74 bool\n", "age_group_75-84 bool\n", "age_group_85+ bool\n", "smoking_history_former bool\n", "smoking_history_never bool\n", "diet_good bool\n", "diet_poor bool\n", "exercise_frequency_low bool\n", "exercise_frequency_moderate bool\n", "exercise_frequency_none bool\n", "dtype: object" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# BUG FIXING: List any non numerical rows\n", "X_train.dtypes" ] }, { "cell_type": "code", "execution_count": 14, "id": "f16e2e40-e065-44ca-b944-e9a2921d89db", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/tmp/ipykernel_82/146862157.py:2: Pandas4Warning: For backward compatibility, 'str' dtypes are included by select_dtypes when 'object' dtype is specified. This behavior is deprecated and will be removed in a future version. Explicitly pass 'str' to `include` to select them, or to `exclude` to remove them and silence this warning.\n", "See https://pandas.pydata.org/docs/user_guide/migration-3-strings.html#string-migration-select-dtypes for details on how to write code that works with pandas 2 and 3.\n", " X_train.select_dtypes(include=['object']).head()\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
family_historyalcohol_consumption
494yesnone
379yeshigh
220yesnone
732yeshigh
869nolow
\n", "
" ], "text/plain": [ " family_history alcohol_consumption\n", "494 yes none\n", "379 yes high\n", "220 yes none\n", "732 yes high\n", "869 no low" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# BUG FIXING: Check if the text value exists\n", "X_train.select_dtypes(include=['object']).head()" ] }, { "cell_type": "code", "execution_count": 18, "id": "f62a9503-664a-43d9-9afa-0029695acce8", "metadata": {}, "outputs": [], "source": [ "# BUG FIXING - Rayyan Hodges\n", "\n", "# Force all non-numeric columns to be one-hot encoded\n", "X_train = pd.get_dummies(X_train)\n", "X_val = pd.get_dummies(X_val)\n", "X_test = pd.get_dummies(X_test)\n", "\n", "# Align columns so they match exactly\n", "X_train, X_val = X_train.align(X_val, join=\"left\", axis=1, fill_value=0)\n", "X_train, X_test = X_train.align(X_test, join=\"left\", axis=1, fill_value=0)\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "cfcddd52-1a78-4c07-8f5d-036682a8cad6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "MLPClassifier(hidden_layer_sizes=(64, 32), max_iter=300, random_state=42)" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Train model 1 on generated data\n", "mlp_model_1.fit(X_train, y_train)" ] }, { "cell_type": "markdown", "id": "600e90f1-fc12-4300-ab60-76b4656bf5d8", "metadata": {}, "source": [ "# Run the validation data through the ML model." ] }, { "cell_type": "code", "execution_count": 22, "id": "4d08a5ac-93cf-4da5-a266-7052ea31ac6a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['low', 'high', 'high', 'moderate', 'low', 'high', 'high', 'high',\n", " 'low', 'low'], dtype='