Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/j0fin/iris-says
A minimalist platform for learning, understanding and realising Iris Flower Classification.:cherry_blossom:
https://github.com/j0fin/iris-says
ai education educational-project educational-tool flask flask-application machine-learning plotly plotly-express pycharm-ide sklearn-library visualization website
Last synced: 2 days ago
JSON representation
A minimalist platform for learning, understanding and realising Iris Flower Classification.:cherry_blossom:
- Host: GitHub
- URL: https://github.com/j0fin/iris-says
- Owner: j0fiN
- License: mit
- Created: 2020-08-14T16:40:34.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-06-09T03:05:40.000Z (over 3 years ago)
- Last Synced: 2024-10-31T17:44:46.595Z (4 months ago)
- Topics: ai, education, educational-project, educational-tool, flask, flask-application, machine-learning, plotly, plotly-express, pycharm-ide, sklearn-library, visualization, website
- Language: HTML
- Homepage:
- Size: 7.95 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Iris says!:cherry_blossom:
### A minimalist platform for learning, understanding and realising Iris Flower Classification.
This is an **educational tool to encourage learning Iris Flower Classification** with inbuilt *graphical visualisations* and *on-spot prediction system*. We have loaded the platform with 7 highly optimized, pretrained models of different algorithms namely,
- Decision Tree Classifier
- Gaussian Naive Bayes
- K-Neighbors Classifier
- Logistic Regression
- Random Forest Classifier
- Support Vector Machine
- Multinomial Naive Bayes.
> The architecture of the model are saved and are reused for **faster prediction.**
### Algorithm :cherry_blossom:
Due to continuous prediction calls, we devised a simple algorithm for **isolated prediction**.
- Each time a user wants to predict with a particular model, the measurands along with the model key is sent to the server.
- The model is searched and when found, loaded as an object file with all the architecture expanded and ready for prediction.
- The expanded object takes in the measurands via the predict function. (The functions are stored within the object's architecture).
- Values are predicted and then return to the DOM.
- Then a javascript function call deletes all the prior data, to avoid unexpected object expansion errors during the process.
## To Get Started:cherry_blossom:
### Production
```bash
git clone https://github.com/j0fiN/Iris-Says.git
cd Iris-Says
pip install -r requirements.txt
python run.py
```
### Testing (algorithm test)
```bash
python -m unittest discover tests
```
## Learn it!:cherry_blossom:
> A full description available about the **dataset and the models.**
## Interact with it!:cherry_blossom:
> Loaded with major graphs which are useful and not very complex to grasp. **Simplicity had been maintained!**
## Realise how it works!:cherry_blossom:
> **With robust, yet flexible configurations**, users can select his own settings and get wonderful predictions.
## Major Reach:cherry_blossom:
This platform is majorily developed for **beginners in Data Analytics/Machine Learning**. Giving a strong foundation in these topics enhances them to move forward faster in this ever-growing field. They will understand how to approach any data and analyze them and then use it to build powerful machine learning models.
The platform can play a major part in **showcasing AI and machine learning for students in high schools and other bootcamps**.
## Higher Optimizations:cherry_blossom:
- The tool can **grow in size** to explore various other famous datasets and the usage of machine learning in each of them and not only iris(A good example would be Boston says!).
- The tool can become a platform for users to **develop their own models on that dataset and upload them**. They can also write content about the database.
- The Graphical visualisations can be **enhanced** using various tools of javascript.
## Tools used to develop the project:cherry_blossom:
- Flask (Python)
- Scikit-Learn (Python)
- Plotly-Express (Python)
- Basic webtools(HTML, CSS, JS(some JQuery too!))
## Contribution:cherry_blossom:
Do contribute if you have ideas, **:star: the repo** if you find it impressive!
> Made with :heart: => **PYTHON**