Skip to content

Commit

Permalink
Merge branch 'main' into dev/siqi
Browse files Browse the repository at this point in the history
  • Loading branch information
clara-sq committed Jan 16, 2025
2 parents fe63314 + b0aed08 commit b46d557
Show file tree
Hide file tree
Showing 4 changed files with 195 additions and 12 deletions.
27 changes: 21 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@

Geochemistry π is an **open-sourced highly automated machine learning Python framework** dedicating to build up MLOps level 1 software product for data-driven geochemistry discovery on tabular data.

**Our goal**: one data-mining run in 5 minutes, ten data-mining runs in 10 minutes.

Core capabilities are:

+ **Continous Training**
Expand Down Expand Up @@ -63,6 +65,20 @@ Eos Website: https://eos.org/editor-highlights/machine-learning-for-geochemists

![Geochemistry pi news](https://github.com/ZJUEarthData/geochemistrypi/assets/47497750/bdd33a31-824a-492e-adcf-e660da4eaf1d)

## Video Demo

Have an overview of how our software can accelerate your data-mining experiment.

- Geochemistry π v0.7.0 Introduction Video [[Bilibili]](https://www.bilibili.com/video/BV1TorTYVEgn/?vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=6IVaO_gq22A)

- Geochemistry π v0.7.0 for Regression Demo [[Bilibili]](https://www.bilibili.com/video/BV1VormYvEt8/?spm_id_from=333.1387.homepage.video_card.click&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=eTJ-IV1n4QM)

- Geochemistry π v0.7.0 for Classification Demo [[Bilibili]](https://www.bilibili.com/video/BV1ZDrSYjEBv/?spm_id_from=333.1387.homepage.video_card.click&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=c_eDI2gVTr0)

- MLflow UI user guide - Geochemistry π v0.5.0 [[Bilibili]](https://b23.tv/CW5Rjmo) | [[YouTube]](https://www.youtube.com/watch?v=Yu1nzNeLfRY)

- Geochemistry π - Download and Run the Beta Version [[Bilibili]](https://www.bilibili.com/video/BV1UM4y1Q7Ju/?spm_id_from=333.999.0.0&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=EeVaJ3H7_AU&list=PLy8hNsI55lvh1UHjhVhqNUj3xPdV9sEiM&index=9)

## Quick Installation

Our software is well tested on **macOS** and **Windows** system with **Python 3.9**. Other systems and Python version are not guranteed.
Expand Down Expand Up @@ -123,6 +139,7 @@ Check the updated version of our software:
geochemistrypi --version
```


## Data Preparation

In order to utilize the functions provided by our software, your own data set should satisfy:
Expand Down Expand Up @@ -172,6 +189,10 @@ Once the software starts, there are two folders `geopi_output` and `geopi_tracki

`geopi_output`: It is a regular folder aligning with MLflow's storage structure, which users can operate.

From v0.7.0 onwards, there is one new command with the option `--desktop` to read the training data and application from the folder `geopi_input` on desktop.

`geopi_input`: It is used to put the datasets you want our software to process.

### Case 1: Run with built-in data set for model training and model inference

On command line:
Expand Down Expand Up @@ -275,12 +296,6 @@ On Jupyter Notebook / Google Colab:

+ Copy the URL shown on the console into any browser to open the MLflow web interface. The URL is normally like this http://127.0.0.1:5000. Search MLflow online to see more operations and usages.

For more details: Please refer to:

- Geochemistry π - Download and Run the Beta Version [[Bilibili]](https://www.bilibili.com/video/BV1UM4y1Q7Ju/?spm_id_from=333.999.0.0&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=EeVaJ3H7_AU&list=PLy8hNsI55lvh1UHjhVhqNUj3xPdV9sEiM&index=9)

- MLflow UI user guide - Geochemistry π v0.5.0 [[Bilibili]](https://b23.tv/CW5Rjmo) | [[YouTube]](https://www.youtube.com/watch?v=Yu1nzNeLfRY)


## Roadmap

Expand Down
56 changes: 56 additions & 0 deletions docs/source/For Developer/Project packaging process.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
# Project packaging process

## Table of Contents

- [1. Download the original code file from the project's [Github address]([Jin-sjh/Geochemistrypi: an open-sourced highly automated machine learning Python framework for data-driven geochemistry discovery](https://github.com/Jin-sjh/Geochemistrypi))](#1)
- [2. Open the folder in WinRAR](#2)
- [3. Select `Command'`-> `Add file to compressed file`](#3)
- [4. Create a compressed file in self-extracting format](#4)
- [5. Check `Advanced` -> `Self-extracting file option`](#5)
- [6. In the General TAB, set the path to the decompression](#6)
- [7. Set the shortcut options in the Advanced TAB](#7)
- [8. In the Text and ICONS TAB, set the exe's title, window text, and icon](#8)

---

## 1. Download the original code file from the project's [Github address]([Jin-sjh/Geochemistrypi: an open-sourced highly automated machine learning Python framework for data-driven geochemistry discovery](https://github.com/Jin-sjh/Geochemistrypi))<a id="1"></a>

![o51scq3a n42](https://github.com/user-attachments/assets/dccaad75-6548-4264-9cf8-8d57c51b969c)

After downloading, decompress the package to your desktop.

![xst5fmw4 csv](https://github.com/user-attachments/assets/67b71efd-7339-4246-9208-b726385f682c)

## 2. Open the folder in WinRAR<a id="2"></a>

![ynsiziqk 4fl](https://github.com/user-attachments/assets/5762acc2-504b-4667-898d-da9f455b5eeb)

## 3. Select `Command` -> `Add file to compressed file`<a id="3"></a>

![zbdsdpau jql](https://github.com/user-attachments/assets/56122bb7-003e-468c-9f62-6c0d254e20a3)

## 4. Create a compressed file in self-extracting format<a id="4"></a>

![ze3f3nfr p0a](https://github.com/user-attachments/assets/a4f53646-4eb3-4ebb-86eb-86189ef5eff0)

Select Create a self-extracting compressed file in Compression Options.

## 5. Check `Advanced` -> `Self-extracting file option`<a id="5"></a>

![image](https://github.com/user-attachments/assets/a922a0ab-1d10-4ad8-a242-d2615a3b1103)

## 6. In the General TAB, set the path to the decompression<a id="6"></a>

![d4blwqro o1e](https://github.com/user-attachments/assets/79e17f42-8d06-4cf7-aee9-a890c6a7fc80)

## 7. Set the shortcut options in the Advanced TAB<a id="7"></a>

![image](https://github.com/user-attachments/assets/ca9cd19b-2cbf-4b52-bafe-7d25960e4ed8)

## 8. In the Text and ICONS TAB, set the exe's title, window text, and icon<a id="8"></a>

![image](https://github.com/user-attachments/assets/033c2cf2-5ee5-45b1-be9f-cdf09b090765)

Corresponding part:

![image](https://github.com/user-attachments/assets/5bf0d112-480f-4dfd-aac3-4f5f1c7abbd7)
97 changes: 97 additions & 0 deletions docs/source/For User/EXE Installation and Operation Guide.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,97 @@
# EXE Installation and Operation Guide

## Table of Contents

- [1. EXE Installation Framework](#section1)
- [1.1 Check whether anaconda is installed](#subsection1-1)
- [1.2 Create Virtual Environment](#subsection1-2)
- [1.3 Check for Software Updates](#subsection1-3)
- [1.4 Launch the Project](#subsection1-4)
- [2. User Operation Steps](#section2)
- [2.1 Double-click to Launch EXE File](#subsection2-1)
- [2.2 Select Installation Location](#subsection2-2)
- [2.3 Run Desktop Project Icon](#subsection2-3)
- [2.4 Detect Project Updates](#subsection2-4)
- [2.5 Place Spreadsheet Files](#subsection2-5)
- [2.6 Enter 'y' to Continue](#subsection2-6)

---

## 1 EXE Installation Framework <a id="section1"></a>

### 1.1 Check whether anaconda is installed <a id="subsection1-1"></a>

![image](https://github.com/user-attachments/assets/643140d8-a47f-4f95-9e24-c0f55a07497e)

Anaconda Distribution is a free distribution of Python/R for scientific computing, which makes it easy to manage Python runtime environments. The installation program will first check whether Anaconda is installed on your computer. If not installed, the program will download and install it from the official website; if installed, it will proceed to the next step.

![image](https://github.com/user-attachments/assets/d51797f2-a806-4554-a31d-6d03b9c73822)

### 1.2 Create Virtual Environment <a id="subsection1-2"></a>

The installation program will run Anaconda, automatically install dependent libraries, and create the virtual environment required for the project.

![image](https://github.com/user-attachments/assets/5d21402c-3275-4c97-b998-562854a77851)

**Note:**

- At this stage. Only option `1` can be used for installation

![image](https://github.com/user-attachments/assets/090f1a5a-c8fd-4f19-8333-06c24675e6b7)

### 1.3 Check for software updates <a id="subsection1-3"></a>

When the software runs, it will automatically detect whether the current code is the latest version. If it is not the latest version, it will prompt the user to update.

![image](https://github.com/user-attachments/assets/3cb3577f-f17f-4148-b646-645684db4845)

### 1.4 Launch the Project <a id="subsection1-4"></a>

After the project is launched, two folders will be automatically created on the desktop: one for placing spreadsheet data to be processed, and the other for saving the results of the project.



---

## 2. User Operation Steps <a id="section2"></a>

### 2.1 Double-click to Launch EXE File <a id="subsection2-1"></a>

![image](https://github.com/user-attachments/assets/f7efc376-3487-4738-b7a3-44d504c5d5e2)

After downloading the installation program from the specified location, double-click the file to start it.

**Note:**

- The installation program may be incorrectly identified as a virus by Windows and deleted. If this happens, please turn off real-time protection in the Windows Security Center and install again.

### 2.2 Select Installation Location <a id="subsection2-2"></a>

![image](https://github.com/user-attachments/assets/5bf0d112-480f-4dfd-aac3-4f5f1c7abbd7)

- The installation program defaults to `C:\Program Files (x86)\geochemistrypi`.
- If the computer system prohibits external software operations in the specified path, you can choose to adjust the installation location to another place, such as `C:\Users\Dell\Desktop`.

### 2.3 Run Desktop Project Icon <a id="subsection2-3"></a>

![image](https://github.com/user-attachments/assets/11103ecf-71ba-494b-8108-6d1881f6360a)

After installation, shortcuts will be created on the desktop and in the `All Apps` menu bar of the `Win` key. Clicking either shortcut will start the program.

### 2.4 Detect Project Updates <a id="subsection2-4"></a>

After the program starts, it will automatically detect whether it is the latest version. If there is an update, it will automatically download and install the latest version.

![image](https://github.com/user-attachments/assets/3cb3577f-f17f-4148-b646-645684db4845)

### 2.5 Place Spreadsheet Files <a id="subsection2-5"></a>

After the program starts, two folders will be automatically created on the desktop. Users can place the spreadsheet data files to be processed in `geopi_data_input`, and the results of the project processing will be stored in `geopi_data_output`.

![image](https://github.com/user-attachments/assets/e6f3e414-dd72-443a-8d2a-a40d89070b72)

### 2.6 Enter 'y' to Continue <a id="subsection2-6"></a>

After placing the files, confirmation is required. Enter 'y' to proceed to the operation interface.

![image](https://github.com/user-attachments/assets/7bfb1436-aab2-47cb-8d10-91ec30121f60)
27 changes: 21 additions & 6 deletions docs/source/Home/Introduction.md
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@

Geochemistry π is an **open-sourced highly automated machine learning Python framework** dedicating to build up MLOps level 1 software product for data-driven geochemistry discovery on tabular data.

**Our goal**: one data-mining run in 5 minutes, ten data-mining runs in 10 minutes.

Core capabilities are:

+ **Continous Training**
Expand Down Expand Up @@ -65,6 +67,20 @@ Eos Website: https://eos.org/editor-highlights/machine-learning-for-geochemists

![Geochemistry pi news](https://github.com/ZJUEarthData/geochemistrypi/assets/47497750/bdd33a31-824a-492e-adcf-e660da4eaf1d)

## Video Demo

Have an overview of how our software can accelerate your data-mining experiment.

- Geochemistry π v0.7.0 Introduction Video [[Bilibili]](https://www.bilibili.com/video/BV1TorTYVEgn/?vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=6IVaO_gq22A)

- Geochemistry π v0.7.0 for Regression Demo [[Bilibili]](https://www.bilibili.com/video/BV1VormYvEt8/?spm_id_from=333.1387.homepage.video_card.click&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=eTJ-IV1n4QM)

- Geochemistry π v0.7.0 for Classification Demo [[Bilibili]](https://www.bilibili.com/video/BV1ZDrSYjEBv/?spm_id_from=333.1387.homepage.video_card.click&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=c_eDI2gVTr0)

- MLflow UI user guide - Geochemistry π v0.5.0 [[Bilibili]](https://b23.tv/CW5Rjmo) | [[YouTube]](https://www.youtube.com/watch?v=Yu1nzNeLfRY)

- Geochemistry π - Download and Run the Beta Version [[Bilibili]](https://www.bilibili.com/video/BV1UM4y1Q7Ju/?spm_id_from=333.999.0.0&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=EeVaJ3H7_AU&list=PLy8hNsI55lvh1UHjhVhqNUj3xPdV9sEiM&index=9)

## Quick Installation

Our software is well tested on **macOS** and **Windows** system with **Python 3.9**. Other systems and Python version are not guranteed.
Expand Down Expand Up @@ -125,6 +141,7 @@ Check the updated version of our software:
geochemistrypi --version
```


## Data Preparation

In order to utilize the functions provided by our software, your own data set should satisfy:
Expand Down Expand Up @@ -174,6 +191,10 @@ Once the software starts, there are two folders `geopi_output` and `geopi_tracki

`geopi_output`: It is a regular folder aligning with MLflow's storage structure, which users can operate.

From v0.7.0 onwards, there is one new command with the option `--desktop` to read the training data and application from the folder `geopi_input` on desktop.

`geopi_input`: It is used to put the datasets you want our software to process.

### Case 1: Run with built-in data set for model training and model inference

On command line:
Expand Down Expand Up @@ -277,12 +298,6 @@ On Jupyter Notebook / Google Colab:

+ Copy the URL shown on the console into any browser to open the MLflow web interface. The URL is normally like this http://127.0.0.1:5000. Search MLflow online to see more operations and usages.

For more details: Please refer to:

- Geochemistry π - Download and Run the Beta Version [[Bilibili]](https://www.bilibili.com/video/BV1UM4y1Q7Ju/?spm_id_from=333.999.0.0&vd_source=27944ab3b73a78970c1a52a5dcbb9140) | [[YouTube]](https://www.youtube.com/watch?v=EeVaJ3H7_AU&list=PLy8hNsI55lvh1UHjhVhqNUj3xPdV9sEiM&index=9)

- MLflow UI user guide - Geochemistry π v0.5.0 [[Bilibili]](https://b23.tv/CW5Rjmo) | [[YouTube]](https://www.youtube.com/watch?v=Yu1nzNeLfRY)


## Roadmap

Expand Down

0 comments on commit b46d557

Please sign in to comment.