Scribd
Upload
10 views

Task 1

Machine learning

Uploaded by

Kashif Alirana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
10 views

Task 1

Machine learning

Uploaded by

Kashif Alirana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Muhammad Kashif Tahir

Predicting House Prices Using MATLAB

Objective:

Build a model to predict house prices based on various features.

1. Introduction
 Objective and Description of the project.
2. Data Generation
 Explanation of synthetic data generation.
 Table of features and their ranges.
3. Data Preparation
 Splitting data into training and testing sets.
 Encoding categorical variables.
 Standardizing numerical features.
4. Model Training
 Training a linear regression model.
5. Model Evaluation
 Making predictions.
 Calculating RMSE.
6. Visualization
 Actual vs Predicted Prices scatter plot.
 Histograms of actual and predicted prices.
 Residuals plot.
 Learning curve.
 Cross-validation RMSE bar plot.

Description:

Use a dataset containing information about houses (e.g., size, number of bedrooms, location) to create a
predictive model that estimates the price of a house.

Key Steps:

1. Data Cleaning and Preprocessing


2. Feature Engineering
3. Model Selection and Training (e.g., Linear Regression)
4. Model Evaluation and Fine-tuning

1. Data Generation

Synthetic data is generated for the following features:

 Size: Size of the house in square feet.


 Bedrooms: Number of bedrooms.
 Bathrooms: Number of bathrooms.
 Floors: Number of floors.
 Age: Age of the house in years.
 Location: Categorical variable with values ('downtown', 'suburb', 'rural').
 Price: Target variable representing the price of the house.

2. Data Preparation

Splitting Data into Training and Testing Sets:

Encoding Categorical Variables:


Standardizing Numerical Features:

3. Model Training
Training a Linear Regression Model:

4. Model Evaluation

Making Predictions:

Calculating Root Mean Squared Error (RMSE):


5. Visualization

Actual vs Predicted Prices:

Histogram of Actual Prices:


Histogram of Predicted Prices:
Residuals Plot:
Learning Curve:

Cross-validation RMSE:
Conclusion:
I developed a linear regression model to predict house prices using synthetic data. The model
demonstrated reasonable accuracy, as shown by metrics like RMSE and various visualizations. Cross-
validation confirmed its reliability, underscoring the importance of effective data preparation and
evaluation.

You might also like