{ "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": [ "
| \n", " | age | \n", "age_group | \n", "
|---|---|---|
| 0 | \n", "51 | \n", "45-54 | \n", "
| 1 | \n", "92 | \n", "85+ | \n", "
| 2 | \n", "14 | \n", "0-14 | \n", "
| 3 | \n", "71 | \n", "65-74 | \n", "
| 4 | \n", "60 | \n", "55-64 | \n", "
| \n", " | bmi | \n", "blood_pressure | \n", "
|---|---|---|
| count | \n", "1.000000e+03 | \n", "1.000000e+03 | \n", "
| mean | \n", "-4.618528e-17 | \n", "-3.552714e-17 | \n", "
| std | \n", "1.000500e+00 | \n", "1.000500e+00 | \n", "
| min | \n", "-1.684915e+00 | \n", "-1.703831e+00 | \n", "
| 25% | \n", "-8.885765e-01 | \n", "-8.621512e-01 | \n", "
| 50% | \n", "3.871853e-03 | \n", "-1.077505e-02 | \n", "
| 75% | \n", "8.860227e-01 | \n", "8.687217e-01 | \n", "
| max | \n", "1.733849e+00 | \n", "1.775369e+00 | \n", "
| \n", " | age | \n", "family_history | \n", "alcohol_consumption | \n", "bmi | \n", "blood_pressure | \n", "cholesterol_level | \n", "travelled_overseas | \n", "number_of_children | \n", "cancer_risk | \n", "age_group_15-24 | \n", "age_group_25-34 | \n", "age_group_35-44 | \n", "age_group_45-54 | \n", "age_group_55-64 | \n", "age_group_65-74 | \n", "age_group_75-84 | \n", "age_group_85+ | \n", "smoking_history_former | \n", "smoking_history_never | \n", "diet_good | \n", "diet_poor | \n", "exercise_frequency_low | \n", "exercise_frequency_moderate | \n", "exercise_frequency_none | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "51 | \n", "no | \n", "low | \n", "0.484421 | \n", "1.631857 | \n", "226.4 | \n", "no | \n", "5 | \n", "moderate | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "True | \n", "False | \n", "False | \n", "True | \n", "
| 1 | \n", "92 | \n", "no | \n", "moderate | \n", "-1.492695 | \n", "1.399135 | \n", "170.9 | \n", "yes | \n", "2 | \n", "low | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "True | \n", "False | \n", "True | \n", "False | \n", "False | \n", "False | \n", "
| 2 | \n", "14 | \n", "no | \n", "none | \n", "0.525611 | \n", "0.569092 | \n", "279.9 | \n", "yes | \n", "4 | \n", "high | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "
| 3 | \n", "71 | \n", "yes | \n", "low | \n", "1.665199 | \n", "-0.101925 | \n", "280.7 | \n", "yes | \n", "0 | \n", "moderate | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "False | \n", "
| 4 | \n", "60 | \n", "no | \n", "none | \n", "-1.451505 | \n", "0.650544 | \n", "212.8 | \n", "yes | \n", "5 | \n", "moderate | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "False | \n", "True | \n", "False | \n", "False | \n", "False | \n", "False | \n", "False | \n", "True | \n", "
| \n", " | family_history | \n", "alcohol_consumption | \n", "
|---|---|---|
| 494 | \n", "yes | \n", "none | \n", "
| 379 | \n", "yes | \n", "high | \n", "
| 220 | \n", "yes | \n", "none | \n", "
| 732 | \n", "yes | \n", "high | \n", "
| 869 | \n", "no | \n", "low | \n", "
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.
MLPClassifier(hidden_layer_sizes=(128, 64), max_iter=500, random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.