Welcome to Geochemistry π

Home

• Introduction
  • Video Demo
  • Quick Installation
    • 1. Download via Terminal
    • 2. Download via EXE
  • Quick Update
  • Data Preparation
  • Running Example
    • Case 1: Run with built-in data set for model training and model inference
    • Case 2: Run with your own data set on desktop for model training and model inference
    • Case 3: Run with your own data set without model inference
    • Case 4: Implement model inference on application data
    • Case 5: Activate MLflow web interface
  • Roadmap
    • First Phase
    • Second Phase
  • Geochemistry π Mind Map
  • Team Info
  • Join Us :)
  • In-house Materials
  • In-house Videos
  • Contributors
• Change Log
  • [Unreleased]
  • [0.7.0] - 2025-01-27
    • Added
    • Changed
  • [0.6.1] - 2024-07-05
    • Added
    • Changed
    • Fixed
  • [0.6.0] - 2024-06-02
    • Added
    • Changed
    • Fixed
  • [0.5.0] - 2024-01-14
    • Added
    • Changed
  • [0.4.0] - 2023-12-15
    • Added
    • Changed
  • [0.3.0] - 2023-08-11
    • Added
  • [0.2.1] - 2023-05-01
    • Fixed
  • [0.2.0] - 2023-04-19
    • Added
  • [0.1.0] - 2023-02-01
    • Added

For User

• User Guide
  • 1. Installation
    • 1.1 Check Environment
    • 1.2 Quick Install
    • 1.3 Advanced Install
  • 2. Example
  • 3. Data Format
  • 4. Use
    • 4.1 Selection algorithm
    • 4.2 World Map Projection for A Specific Element Option
    • 4.3 Do you want to continue to project a new element in the World Map
    • 4.4 Select the data range you want to process
    • 4.5 Strategy for Missing Values
    • 4.6 Hypothesis Testing on Imputation Method
    • 4.7 Feature Engineering
    • 4.8 Do you want to continue to construct a new feature
    • 4.9 Mode Options
    • 4.10 Data Split - X Set and Y Set
    • 4.11 Feature Scaling on X Set
    • 4.12 Data Split - Train Set and Test Set
    • 4.13 Model Selection
  • 5. Bug Report
  • 6. How to use pickle and joblib
  • 7. Advice
• Installation Manual
  • Contents
    • 1. Preparation
    • 2. Download Geochemistry π in Virtual Environment
    • 3. Solutions and Suggestions for Installation Failure
• Model Example
  • Data Preprocessing
    • Data Schema
    • Loading Data
    • World Map Projection
    • Statistical Summary
    • Missing Value
    • Feature Engineering
  • Classification
    • Table of Contents
    • 1. Train-Test Data Preparation
    • 2. Missing Value Processing
    • 3. Data Processing
    • 4. Model Selection
  • Regression
    • 1. Introduction to Regression
    • 2. Introduction to Regression function of Geochemistry π
    • 3. Model Selection
  • Clustering
    • Table of Contents
    • Data Preparation
    • Model Selection
    • Data Results
  • Decomposition
    • Table of Contents
    • 1. T-distributed Stochastic Neighbor Embedding (T-SNE)
    • 2. Preparation
    • 3. NAN value process
    • 4. Feature engineering
    • 5. Model Selection
    • 6. T-SNE
  • Anomaly Detection
    • Table of Contents
    • 1. Train-Test Data Preparation
    • 2. Missing Value Processing
    • 3. Data Processing
    • 4. Model Selection
    • 5.Hyper-Parameters Specification
    • 6.Results
  • Network Analysis
• Contact Us
  • Bug Report
  • Bug Template
  • Join Us
  • Q&A
• Docs Link
  • 1. Geochemistry π Project Introduction
  • 2. Code Download Link
  • 3. Installing and Model Running Video
  • 4. Installing and Model Running Docs
  • 5. Users Feedback Doc

For Developer

• Developer Guide
  • 1. Installation
    • 1.1 Check Environment
    • 1.2 Quick Install
    • 1.3 Advanced Install
  • 2. Example
  • 3. Data Format
  • 4. Use
    • 4.1 Selection algorithm
    • 4.2 World Map Projection for A Specific Element Option
    • 4.3 Do you want to continue to project a new element in the World Map
    • 4.4 Select the data range you want to process
    • 4.5 Strategy for Missing Values
    • 4.6 Hypothesis Testing on Imputation Method
    • 4.7 Feature Engineering
    • 4.8 Do you want to continue to construct a new feature
    • 4.9 Mode Options
    • 4.10 Data Split - X Set and Y Set
    • 4.11 Feature Scaling on X Set
    • 4.12 Data Split - Train Set and Test Set
    • 4.13 Model Selection
  • 5. Bug Report
  • 6. Advice
• Contributing
  • Code of Contuct
    • 1. Naming Conventions
    • 2. Space Usage
    • 3. Variable Type Hint
    • 4. TODO or FIXME Comments
    • 5. Docstring
    • 6. Test Module
    • 7. Git Commit Message
  • Contributors
    • Leader:
    • Technical Group:
    • Product Group:
    • Former Contributors:
• Deployment
  • Local Deployment
  • Docker Deployment
• Complete Pull Request
• Add New Model To Framework
  • Table of Contents
  • 1. Framework - Design Pattern and Hierarchical Pipeline Architecture
  • 2. Understand Machine Learning Algorithm
  • 3. Construct Model Workflow Class
    • 3.1 Add Basic Elements
    • 3.2 Add Manual Hyperparameter Tuning Functionality
    • 3.3 Add Automated Hyperparameter Tuning (AutoML) Functionality
    • 3.4 Add Application Function to Model Workflow Class
  • 4. Instantiate Model Workflow Class
    • 4.1 Find File
    • 4.2 Import Module
    • 4.3 Define activate Method
    • 4.4 Create Model Workflow Object
    • 4.5 Invoke Other Methods in Scikit-learn API Style
    • 4.6 Add model_name to MODE_MODELS or NON_AUTOML_MODELS
  • 5. Test Model Workflow Class
  • 6. Completed Pull Request
  • 7. Precautions
• Docs Link
  • 1. Project’s Share Docs
  • 2. Technical Video (in Bilibili app)
  • 3. Leanring Materials in Nutstore
    • Folders Introduction
    • Improtant Files in Nutstore
  • 4. Member Notice

Indices and tables

• Index

• Module Index

• Search Page