Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/akshay-rajan/expertsystem
A User Interface for Data Preprocessing, Building and Testing Machine Learning Models.
https://github.com/akshay-rajan/expertsystem
bootstrap d3js django javascript jquery machine-learning numpy pandas plotly sklearn
Last synced: 2 days ago
JSON representation
A User Interface for Data Preprocessing, Building and Testing Machine Learning Models.
- Host: GitHub
- URL: https://github.com/akshay-rajan/expertsystem
- Owner: akshay-rajan
- Created: 2024-08-11T14:16:28.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-12-09T16:44:11.000Z (30 days ago)
- Last Synced: 2024-12-09T17:44:24.397Z (29 days ago)
- Topics: bootstrap, d3js, django, javascript, jquery, machine-learning, numpy, pandas, plotly, sklearn
- Language: HTML
- Homepage: https://expertsyst.me
- Size: 15.1 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Expert System
Expert System is a platform that allows users to do preprocessing, build, train, and test Machine Learning models without any programming languages. Designed to make Machine Learning accessible to everyone, this project provides an interface to handle the entire Machine Learning workflow.
## Key Features
- **Data Upload:** Easily upload datasets for processing and analysis, or choose from one of the sample datasets available.
- **Preprocessing:** Perform
- Encoding
- Scaling
- Handling Missing Values
- **Algorithm Selection:** Choose from:
Classification
KNN,
Naive Bayes,
Logistic Regression,
SVM,
Decision Tree,
Random Forest
Regression
Linear Regression,
Lasso Regression,
Ridge Regression,
Decision Tree,
Random Forest,
Clustering
K-Means,
Hierarchical Clustering
- **Customization:** Select features, target variables, and fine-tune hyperparameters.
- **Model Building:** Train models using selected configurations.
- **Predictions:** Generate predictions using the trained model.
- **Evaluation Metrics:**
- Accuracy, Precision, Recall, F1 Score (for classification)
- MAE, MSE, RMSE, R-Squared (for regression)
- Inertia, Silhouette Score (for clustering)
- **Visualization:** Generate visualizations like heatmaps, scatters, cluster plots and dendrograms.
- **Sample Code:** View sample Python code for the training process.
- **Model Download:** Export trained models as `.pkl` files for reuse.
- **Learn**: Learn about Data Science and Machine Learning concepts using the notes available.
Expert System is especially aimed at students who want to explore Machine Learning concepts without the complexities of coding.
### [Screenshots](./SCREENSHOTS.md)
## Workflow
```mermaid
flowchart LR
A(Start) --> B(Preprocessing)
B --> D(Modelling)
D --> E[Select Algorithm]
E --> F[Pick Features, Target, Hyperparameters]
F --> G(Training)
G --> H[Evaluation Metrics]
H --> I[Prediction using the model]
I --> J[View Code]
J --> K[Download the Model]
K --> Z(End)
```
## Technologies Used
## Usage
1. Clone the project:
```
git clone https://github.com/akshay-rajan/expertsystem.git
```
2. Navigate to the project directory:
```
cd expertsystem
```
3. Create a virutal environment:
```bash
python -m venv myenv
```
4. Activate the virtual environment:
- **Linux / MacOS**
```bash
source myenv/bin/activate
```
- **Windows**
```bash
.\myenv\Scripts\activate
```
5. Install the requirements:
```bash
pip install -r requirements.txt
```
6. Run database migrations:
```bash
python manage.py migrate
```
7. Start the Django server:
```bash
python manage.py runserver
```
The application will be accessible at at http://127.0.0.1:8000/ .
---
> **Akshay R**,
>**Deepu Joseph**,
>*Masters in Computer Applications*,
>*College of Enginnering, Trivandrum*
>(*2023-25*)