Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/mjmolina/plantaris_data

Help your plants to stay healthier with Machine Learning at home.
https://github.com/mjmolina/plantaris_data

circuitpython data-science iot machine-learning machine-learning-algorithms neural-network plants raspberry-pi watering-plants

Last synced: about 1 month ago
JSON representation

Help your plants to stay healthier with Machine Learning at home.

Host: GitHub
URL: https://github.com/mjmolina/plantaris_data
Owner: mjmolina
Created: 2020-08-29T22:46:01.000Z (over 4 years ago)
Default Branch: master
Last Pushed: 2024-06-25T01:35:44.000Z (6 months ago)
Last Synced: 2024-06-25T02:47:33.086Z (6 months ago)
Topics: circuitpython, data-science, iot, machine-learning, machine-learning-algorithms, neural-network, plants, raspberry-pi, watering-plants
Language: Jupyter Notebook
Homepage:
Size: 1.69 MB
Stars: 2
Watchers: 2
Forks: 1
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# plantaris_data
## Category: Data Science Applications Talk

## **Help your plants to stay healthier with Machine Learning at home**

## Talk description
Many studies have also proven that growing indoor house plants, as long as
being a trend, improves health, despite the difficulty to keep them alive. The
fact is that when we grow plants inside our homes, they depend 100% on us and
sometimes it is difficult to know what they need.

In this talk, we will explore how to improve your plants' lives by setting up
a basic plant monitoring system. This might sound complicated, but it is indeed
very simple and useful: thanks to using python and jupyter notebooks. Moreover,
you are going to create a machine learning pipeline from going through the
steps of data labeling, selecting the framework, the model, and you will learn
how to deal with the challenges that one can have in these processes.

Finally, you will see how this project is an excellent way to learn how to deal
with data science challenges, at the same time that you will learn plant
biology and how to implement a real-world machine learning project, and at the
same time help your plant to be happier.

* You can watch the talk [here](https://www.youtube.com/watch?v=S9LbxLDW7ig&t=131s)

## Audience
(1) This talk is beginner friendly. The main idea of this talk is to show with
a practical example how we can implement machine learning at home, at the same
time, how we can store and work with our own data for analysis.

(2) The background knowledge should be basic python knowledge. This proposal of
talk is complementary to a previous personal project called "PLANTARIS"
(https://github.com/mjmolina/plantaris).

## Project structure

```
.
├── boards
│   ├── circuit_moisture.py
│   ├── circuit_watering_simple.py
│   ├── pi_monitor.py
│   └── requirements.txt
│
└── notebooks
├── circuitpython_notebook.ipynb
├── data_analysis_sensors.ipynb
├── data_labeling.ipynb
├── prediction.ipynb
├── requirements.txt
├── temp_hum_processed.csv
└── training.ipynb
```

### boards

This contains the scripts used to monitor the system:

`circuit_watering_simple.py` is an example from the talk of a system,
that is in charge of watering a plant activating a relay that enables a water
pump, according to the moisture sensor values.

### notebooks

Jupyter Notebooks to perform different steps on this experiments:
* `data_labeling.ipynb`, system based on Jupyter Widgets to do an interactive
labeling of all the photos that the system is taking.
* `prediction.ipynb`, ML prediction step, more comments can be found inside.
* `training.ipynb`, ML training step, more comments can be found inside.
* `circuitpython_notebook.ipynb`, configuration to use the CPX directly from
a Notebook.
* `data_analysis_sensors.ipynb`, analysis of all the data gathered by the
system.