[SOLVED] New Assignment 3 2025

New Assignment 32025

Part 1 Select an appropriate model to train the dataset and make predictions (3 Points)

The UCI Adult dataset-sometimes called the Census Income dataset-is a classic resource in machine learning for demonstrating classification tasks, particularly binary classification.

Dataset Description

·Number of Instances:Around 48,842 rows(depending on whether duplicates/missing rows are handled).

·Number  of  Attributes:14  features(plus the  target)

·Feature    Types:

■ Numeric(e.g.,age,hours-per-week,capital-gain).

■ Categorical   (e.g.,workclass,marital-status,occupation,sex).

·Target    Column:

■ Labeled as income,with possible values >50K or<=50K.

·Common  practice  is to convert this to  binary(1 for>50K,O for<=50K).

Feature List

·age(numeric)

·workclass        (categorical:Private,Self-emp,Government,etc.)

·fnlwgt(numeric:“final weight,”representing how many people in the US population each record represents)

·education (categorical:Bachelors,HS-grad,etc.)

·education_num (numeric:1-16,encoded  years  of  education)

·marital_status(categorical)

·occupation (categorical)

·relationship(categorical:Husband,Wife,Not-in-family,etc.)

·race (categorical)

·sex(categorical:Male/Female)

·capital_gain(numeric)

·capital_loss(numeric)

·hours_per_week (numeric)

·native_country(categorical)

·income          (target:>50K/<=50K)

Task Overview

Data   Acquisition   &Understanding(Code   provided)

·Download  the  dataset (e.g.,adult.data  from  the   UCI  Repository  or  Kaggle).

·Familiarize  yourself  with  the   14  features  and  the  target  column  (>50K/<=50K).

Data  Cleaning

·Import  the  dataset into  a  DataFrame  (Code  provided)

·Identify  and  handle  missing  values  (often  represented  by”?”).Decide  whether  to  drop  or  impute  those  rows( 0.25 points). Feature   Engineering   &Encoding

·Convert   the   target   (income)to   a   binary   numeric:1   if>50K,0 if<=50K(0.25 points).

·Encode      categorical      columns appropriately(e.g.,workclass,education,marital_status):(0.5   points)

■ One-hot  encoding(dummy  variables)or  label  encoding.

·Consider dropping  high-cardinality  or  rarely  occurring  categories,or  grouping  them.

Data  Splitting:Split  into  train  and  test  sets(0.5   points)

Model  Training:Select   a suitable model and appropriate columns to  train  the  model.(0.5   points)

Evaluation:( 0.5 points)

·Generate  predictions  on  the  test set  and  compute  classification  metrics:

■   Accuracy

■      Precision,Recall,F1-score

■  Confusion  matrix  Prediction:Make  an  imaginary  person,use  the  model  to  predict  whether  the  person’s  income  will  be  above  50K(0.5 points).