https://github.com/jahanostg/linear-regression_ml-algorithm

Linear Regression Algorithm
https://github.com/jahanostg/linear-regression_ml-algorithm

colab-notebook matplotlib numpy pandas scikit-learn seaborn

Last synced: about 2 months ago
JSON representation

Linear Regression Algorithm

• Host: GitHub
• URL: https://github.com/jahanostg/linear-regression_ml-algorithm
• Owner: jahanOSTG
• Created: 2025-06-18T07:56:13.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-06-18T14:53:45.000Z (about 1 year ago)
• Last Synced: 2025-06-18T15:19:34.779Z (about 1 year ago)
• Topics: colab-notebook, matplotlib, numpy, pandas, scikit-learn, seaborn
• Language: Jupyter Notebook
• Homepage:
• Size: 144 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
#  Linear Regression on Custom Dataset

This repository demonstrates a full linear regression workflow using a dataset.

---

##  Dataset Overview

The dataset (`friend.csv`) contains the following columns:

| Column | Description                               |

|--------|-------------------------------------------|

| ID     | Unique identifier (ignored)               |

| size   | Custom feature (e.g., test score, item size, etc.) |

| Age    | Age of the individual                     |

| prize  | Prize or cost-related value               |

| Number | 🎯 Target variable                         |

---

## ✅ Steps Performed

### 1. Mount Google Drive  

To access the dataset stored in Google Drive.

### 2. Import Libraries  

Used libraries:

- `pandas`

- `numpy`

- `matplotlib`

- `seaborn`

- `scikit-learn`

### 3. Load and Preprocess Data  

- Removed unnecessary columns (`ID`, if not useful).  

- Handled whitespace in column names.  

- One-hot encoding skipped as no categorical columns exist.

### 4. Train-Test Split  

Split the data into training and testing sets using `train_test_split()`.

### 5. Train Model  

Trained a `LinearRegression()` model on the training data.

### 6. Prediction & Evaluation  

- Generated predictions on the test set.  

- Calculated **MAE**, **MSE**, **RMSE**, and **R²** for performance analysis.

  

### 7. Visualization  

-  **Regression Line Plot** to compare actual vs predicted values.  

-  **Residual Plot** to check errors.  

-  **Heatmap** to show correlation between all numeric features.

---

  

  ## About **Linear Regression**

  ### Advantages

  - Simple to implement and efficient to train

  - Overfitting can be reduced by regularization

  - Performs well when the dataset is linearly separable.

  ### Disadvantages

  - Assumes that the data is independent which is rare in real life

  - Prone to noise and overfitting

  - Sensitive to outliers.