Raman Spectroscopy Analysis Application
Getting Started
Getting Started
System Requirements
Minimum Requirements
Recommended Requirements
Installation Options
1. Source Installation (Recommended for Developers)
2. Portable Executable (Windows Only)
3. Installer (Windows Only)
Quick Start Tutorial
Step 1: Launch the Application
Step 2: Create Your First Project
Step 3: Import Data
Step 4: Preprocess Your Data
Step 5: Analyze Your Data
Step 6: Machine Learning (Optional)
Next Steps
Getting Help
Documentation Resources
Community Support
Video Tutorials (Coming Soon)
Feedback
Installation Guide
Prerequisites
Python Version
System Dependencies
Installation Methods
Method 1: From Source
Step 1: Clone the Repository
Step 2: Create Virtual Environment
Step 3: Verify Installation
Step 4: Run the Application
Updating from Source
Method 2: Portable Executable (Windows Only)
Step 1: Download
Step 2: Extract
Step 3: Run
Features
Limitations
Method 3: Installer (Windows Only)
Step 1: Download
Step 2: Run Installer
Step 3: Launch
Features
Uninstallation
Post-Installation
Verify Installation
Optional: Install Development Tools
Configure Application Settings
Troubleshooting Installation
Common Issues
Python Version Mismatch
Module Not Found Errors
Permission Denied (Linux/macOS)
UV Installation Fails
Windows Executable Blocked
Getting Help
Next Steps
Advanced Installation
Installing Specific Versions
Installing with Optional Dependencies
Building from Source (Advanced)
Quick Start
Prerequisites
Tutorial: Analyzing Blood Plasma Samples
Step 1: Launch and Create Project (2 minutes)
Step 2: Import Data (3 minutes)
Step 3: Preprocess Data (5 minutes)
Step 4: Exploratory Analysis with PCA (3 minutes)
Step 5: Statistical Testing (2 minutes)
Optional: Machine Learning Classification
Step 6: Train ML Model (Optional, +10 minutes)
Next Steps
Learn More About Methods
Advanced Workflows
Best Practices
Common Issues
Data Import Problems
Preprocessing Errors
Analysis Issues
Getting Help
Feedback
User Guide
User Guide
Guide Structure
1.
Interface Overview
2.
Data Import and Management
3.
Preprocessing Pipeline
4.
Analysis Methods
5.
Machine Learning
6.
Best Practices
Quick Navigation
By Task
By Research Goal
Typical Workflows
Workflow 1: Quality Control and Exploratory Analysis
Workflow 2: Classification Model Development
Workflow 3: Spectral Unmixing
Common Questions
When Should I Use Each Analysis Method?
What Preprocessing Should I Use?
How Do I Ensure Valid Results?
Getting Help
Documentation Resources
Community Support
Video Tutorials (Coming Soon)
Contributing to This Guide
Interface Overview
Table of Contents
Main Window Layout
Window Structure
Key Components
Navigation System
Tab-Based Navigation
Home Page
Data Package Page
Preprocess Page
Exploratory Analysis Page
Modeling & Classification Page
Workspace Page
Common UI Elements
Panels and Widgets
Data Selector Panel
Parameter Panel
Results Panel
Toast Notifications
Dialog Windows
Multi-Group Selection Dialog
External Evaluation Dialog
Customization
Theme Selection
Language Selection
Layout Customization
Split-View Mode
Compact Mode
Font Settings
Panel Visibility
Default Directories
Workflow Integration
Typical User Workflow
Context Preservation
Accessibility Features
High Contrast Mode
Screen Reader Support
Keyboard-Only Navigation
Tips and Best Practices
Performance Optimization
Multi-Monitor Setup
Quick Actions
Troubleshooting UI Issues
Interface Not Responding
Missing Panels
Font Rendering Issues
Theme Not Applying
See Also
Data Import Guide
Table of Contents
Supported File Formats
Primary Formats
CSV Files (Recommended)
TXT Files (Text Format)
ASC/ASCII Files
PKL Files
Future Import Support (Planned)
Import Workflow
Step 1: Navigate to Data Package Page
Step 2: Select Files for Import
Step 3: Data Validation
Step 4: Preview and Confirm
Step 5: Confirmation
Data Organization
Project Structure
Creating Data Packages
Metadata Management
Group Management
Creating Sample Groups
Assigning Samples to Groups
Multi-Group Assignment
Data Validation
Automatic Checks
1. Wavenumber Consistency
2. Missing Values
3. Outlier Detection
4. Duplicate Spectra
Manual Validation Tools
Spectrum Viewer
Batch Validation
Advanced Features
Wavenumber Calibration
Data Merging
Data Splitting
Export Data
Batch Import
Best Practices
File Organization
Naming Conventions
Quality Control
Troubleshooting
Import Fails
Wavenumber Mismatch
Memory Issues
Missing Groups
See Also
Preprocessing Guide
Table of Contents
Overview
Why Preprocess?
Preprocessing Philosophy
Pipeline Builder Interface
Main Layout
Components
Method Categories
1. Baseline Correction
AsLS (Asymmetric Least Squares)
AirPLS (Adaptive Iteratively Reweighted Penalized Least Squares)
Polynomial Baseline
FABC (Fully Automatic Baseline Correction)
2. Smoothing and Denoising
Savitzky-Golay Filter
Gaussian Smoothing
Moving Average
Median Filter
3. Normalization
Vector Normalization (L2 Norm)
Min-Max Normalization
Area Normalization
SNV (Standard Normal Variate)
MSC (Multiplicative Scatter Correction)
4. Derivatives
First Derivative (Savitzky-Golay)
Second Derivative
5. Advanced Methods
Convolutional Denoising Autoencoder (CDAE)
Wavelet Transform
Peak Ratio Feature Engineering
Building a Pipeline
Step-by-Step Guide
Step 1: Start with Raw Data
Step 2: Add Baseline Correction
Step 3: Add Smoothing (Optional)
Step 4: Add Normalization
Step 5: Validate Pipeline
Step 6: Save and Apply
Common Pipelines
1. Standard Pipeline (General Purpose)
2. Minimal Pipeline (Low Noise Data)
3. Aggressive Denoising (High Noise Data)
4. Derivative-Based Pipeline
5. Chemometric Pipeline (Quantitative Analysis)
6. Deep Learning Preprocessing
Advanced Tips
Parameter Optimization
Method Order Guidelines
Computational Efficiency
Validation Strategy
Troubleshooting
Problem: Peaks Disappear After Preprocessing
Problem: Baseline Still Present
Problem: Spectra Look Too Smooth
Problem: Pipeline Slow to Apply
Problem: Inconsistent Results
See Also
Analysis Guide
Table of Contents
Overview
Analysis Workflow
Exploratory Analysis Page Interface
Exploratory Analysis
Principal Component Analysis (PCA)
Running PCA
Results
Interpretation Tips
UMAP (Uniform Manifold Approximation and Projection)
Running UMAP
UMAP vs PCA
t-SNE (t-Distributed Stochastic Neighbor Embedding)
Clustering Analysis
Hierarchical Clustering
K-Means Clustering
Statistical Analysis
Pairwise Group Comparisons
t-Test (Parametric)
Mann-Whitney U Test (Non-Parametric)
Multi-Group Comparisons
ANOVA (Analysis of Variance)
Correlation Analysis
Pearson Correlation
Spearman Correlation
Band Ratio Analysis
Visualization Methods
Interactive Heatmap
Waterfall Plot
Overlaid Spectra
Peak Scatter Plot
Correlation Matrix
Results Interpretation
Statistical Significance
Effect Size
Biological Interpretation
Export and Reporting
Export Options
Creating Reports
Publication-Ready Figures
Troubleshooting
No Group Separation in PCA
Statistical Tests Show No Significance
Analysis Takes Too Long
See Also
Machine Learning Guide
Table of Contents
Overview
Modeling & Classification Page
When to Use ML
ML Workflow
Complete Workflow
Step-by-Step Guide
Step 1: Prepare Data
Step 2: Split Data
Step 3: Select Training Data
Step 4: Choose Algorithm
Step 5: Configure Validation
Step 6: Set Hyperparameters
Step 7: Train Model
Step 8: Evaluate on Test Set
Algorithm Selection
Support Vector Machine (SVM)
Random Forest (RF)
XGBoost (Extreme Gradient Boosting)
Logistic Regression (LR)
Algorithm Comparison
Training and Validation
Validation Strategies
GroupKFold (Recommended)
Stratified K-Fold
Leave-One-Patient-Out (LOPOCV)
Hold-out Test Set
Hyperparameter Optimization
Grid Search
Random Search
Bayesian Optimization
Preventing Overfitting
Model Evaluation
Classification Metrics
Accuracy
Precision, Recall, F1-Score
ROC Curve and AUC
Confusion Matrix
Multi-Class Metrics
Regression Metrics
MAE (Mean Absolute Error)
RMSE (Root Mean Squared Error)
R² (Coefficient of Determination)
Model Interpretation
Feature Importance
Random Forest Feature Importance
SHAP Values (SHapley Additive exPlanations)
Permutation Importance
Model Transparency
Model Export and Deployment
Saving Trained Models
Loading Models for Prediction
Model Deployment Checklist
Troubleshooting
Poor Performance (Accuracy <70%)
Overfitting (Train >> Test)
Class Imbalance
Data Leakage
See Also
Best Practices
Table of Contents
Data Quality
Sample Preparation
Data Acquisition
Sample Size Determination
Data Organization
Preprocessing Strategy
Choosing Methods
Validation
Documentation
Statistical Analysis
Test Selection
Multiple Testing Correction
Effect Sizes
Machine Learning
Data Splitting
Cross-Validation Strategy
Feature Selection
Model Selection
Validation Requirements
Reproducibility
Code and Environment
Documentation
Publication and Reporting
Figures
Tables
Methods Section
Results Section
Discussion
Ethical Considerations
Checklists
Before Analysis
Before Preprocessing
Before Statistical Analysis
Before Machine Learning
Before Publication
Common Pitfalls to Avoid
❌ Data Leakage
❌ Spectrum-Level Splitting
❌ Peeking at Test Set
❌ Multiple Testing Without Correction
❌ Cherry-Picking Results
❌ Overfitting
❌ Missing Documentation
Resources
Recommended Reading
Software Citations
See Also
Analysis Methods
Analysis Methods Reference
Purpose of This Reference
Method Categories
Preprocessing Methods
Exploratory Analysis
Statistical Methods
Machine Learning
Quick Method Selector
By Research Question
By Data Characteristics
Method Selection Flowchart
Preprocessing Guidelines
Recommended Pipeline for Raman Data
Validation Best Practices
Critical Rules
Parameter Selection Guides
Parameter Tables
Visual Parameter Guides
Decision Trees
Interpretation Guides
Example Results
What to Report
Common Misinterpretations
Citations and References
Using This Documentation in Publications
Bibliography
Contributing Method Documentation
Support
Preprocessing Methods Reference
Table of Contents
Baseline Correction
AsLS (Asymmetric Least Squares)
AirPLS (Adaptive Iteratively Reweighted Penalized Least Squares)
Polynomial Baseline
Whittaker Smoothing
FABC (Fully Automatic Baseline Correction)
Butterworth High-Pass Filter
Smoothing and Denoising
Savitzky-Golay Filter
Gaussian Smoothing
Moving Average
Median Filter
Kernel Denoising
Normalization
Vector Normalization (L2 Norm)
Min-Max Normalization
Area Normalization
Standard Normal Variate (SNV)
Multiplicative Scatter Correction (MSC)
Quantile Normalization
Probabilistic Quotient Normalization (PQN)
Rank Transformation
Derivatives
First Derivative (Savitzky-Golay)
Second Derivative
Feature Engineering
Peak Ratio
Wavelet Transform
Advanced Methods
Convolutional Denoising Autoencoder (CDAE)
Background Subtraction
Calibration
Method Selection Guide
Decision Matrix
Common Pipelines
Parameter Constraints
Automatic Validation
Best Practices
General Guidelines
Method-Specific Tips
Troubleshooting
Common Issues
References
See Also
Exploratory Analysis Methods
Table of Contents
Principal Component Analysis (PCA)
Theory
Parameters
Usage Example
Output Components
Interpretation
Scores Plot
Loadings Plot
Explained Variance
Common Use Cases
1. Group Visualization
2. Outlier Detection
3. Feature Selection
4. Dimensionality Reduction for ML
Troubleshooting
Assumptions
When to Use
Advanced Options
Whitening
Incremental PCA
Reference
MCR-ALS
UMAP (Uniform Manifold Approximation and Projection)
Theory
Parameters
Usage Example
PCA vs UMAP Comparison
Interpretation
Troubleshooting
When to Use
Reference
t-SNE (t-Distributed Stochastic Neighbor Embedding)
Theory
Parameters
Usage Example
Interpretation
UMAP vs t-SNE
Troubleshooting
When to Use
Reference
Hierarchical Clustering
Theory
Parameters
Usage Example
Dendrogram Interpretation
Visualization
Choosing Number of Clusters
Troubleshooting
When to Use
Reference
K-Means Clustering
Theory
Parameters
Usage Example
Choosing Number of Clusters (K)
Method 1: Elbow Method
Method 2: Silhouette Score
Method 3: Gap Statistic
Cluster Validation
Silhouette Analysis
Troubleshooting
Assumptions and Limitations
When to Use
Reference
DBSCAN (Density-Based Spatial Clustering)
Theory
Parameters
Usage Example
Advantages
Disadvantages
Troubleshooting
When to Use
Reference
Method Comparison
Quick Reference Table
Decision Tree
Typical Workflow
Validation Metrics
Silhouette Score
Davies-Bouldin Index
Calinski-Harabasz Index
Best Practices
General Guidelines
Reproducibility
See Also
Statistical Analysis Methods
Table of Contents
T-Tests
Types of T-Tests
1. Independent Samples T-Test
2. Paired Samples T-Test
3. One-Sample T-Test
Interpretation
Troubleshooting
When to Use
Mann-Whitney U Test
Theory
Assumptions
Usage Example
Interpretation
When to Use
ANOVA (Analysis of Variance)
One-Way ANOVA
Usage Example
Application Parameters
Grouped Mode vs Simple Mode
Post-Hoc Tests (Optional)
Checking Assumptions
Welch’s ANOVA
Interpretation
When to Use
Pairwise Statistical Tests
Available Tests
1. Independent T-Test (t_test)
2. Mann-Whitney U Test (mann_whitney)
3. Wilcoxon Signed-Rank Test (wilcoxon)
Usage in Application
Interpretation
Best Practices
Correlation Analysis
Pearson Correlation
Usage Example
Spearman Correlation
Kendall’s Tau
Partial Correlation
Correlation Matrix
Troubleshooting
Multiple Testing Correction
Methods
1. Bonferroni Correction
2. Holm-Bonferroni Method
3. False Discovery Rate (FDR) - Benjamini-Hochberg
4. Permutation Testing
Comparison Table
Decision Guide
Effect Size Measures
Cohen’s d
Eta-Squared (η²)
Omega-Squared (ω²)
Reporting Effect Sizes
Band Ratio Analysis
Theory
Calculation
Integration Methods
Statistical Testing
Best Practices
Best Practices
General Workflow
Reporting Checklist
Common Mistakes to Avoid
See Also
Machine Learning Methods
Table of Contents
Support Vector Machines (SVM)
Theory
Kernel Functions
1. Linear Kernel
2. RBF (Radial Basis Function) Kernel
3. Polynomial Kernel
Hyperparameters
C (Regularization Parameter)
Gamma (γ) - RBF Kernel Only
Usage Example
Hyperparameter Optimization
Interpretation
Troubleshooting
When to Use
Class Imbalance
Reference
Random Forest
Theory
Hyperparameters
n_estimators
max_depth
min_samples_split
min_samples_leaf
max_features
Usage Example
Hyperparameter Optimization
Feature Importance
SHAP Values
Out-of-Bag (OOB) Score
Advantages
Limitations
When to Use
Reference
XGBoost
Theory
Hyperparameters
n_estimators
learning_rate (eta)
max_depth
subsample
colsample_bytree
gamma (min_split_loss)
lambda (reg_lambda) - L2 Regularization
alpha (reg_alpha) - L1 Regularization
Usage Example
Hyperparameter Optimization
Feature Importance
Learning Curves
Advantages
Limitations
When to Use
Reference
Logistic Regression
Theory
Hyperparameters
C (Inverse Regularization)
penalty
solver
max_iter
Usage Example
Hyperparameter Optimization
Interpretation
Advantages
Limitations
When to Use
Reference
Multi-Layer Perceptron (MLP)
Theory
Hyperparameters
hidden_layer_sizes
activation
alpha
learning_rate_init
max_iter
early_stopping
Usage Example
Hyperparameter Optimization
Learning Curves
Advantages
Limitations
When to Use
Reference
Model Evaluation
Classification Metrics
Accuracy
Precision
Recall (Sensitivity)
F1-Score
ROC-AUC
Confusion Matrix
Classification Report
Cross-Validation
K-Fold Cross-Validation
Stratified K-Fold
Group K-Fold (Patient-Level)
See Also
API Documentation
API Documentation
Documentation Organization
Core Modules
Pages
Components
Functions
Widgets
Quick Reference
Key Classes
Application Core
Data Management
Preprocessing
Analysis
Machine Learning
Common Patterns
Adding a New Preprocessing Method
Adding a New Analysis Method
Creating Custom Widgets
Development Setup
Prerequisites
Running Tests
Building Documentation
Code Style
Architecture Overview
Module Dependencies
Data Flow
Signal/Slot Connections
Extension Points
Plugin System (Planned)
Integration APIs
REST API (Planned)
Command Line Interface (Planned)
Contributing
API Versioning
Deprecation Policy
Support
License
Core Application API
Table of Contents
Application Entry Points
main.py
MainApplication Class
dev_runner.py
DevRunner Class
Configuration System
configs/configs.py
AppConfig Class
configs/user_settings.py
UserSettings Class
Localization
Locale System
Translation Files
LocaleManager Class
Utilities
utils.py
File I/O Functions
Data Validation
Progress Tracking
Splash Screen
splash_screen.py
SplashScreen Class
Error Handling
Custom Exceptions
DataError
PreprocessingError
ModelError
Error Logging
Threading and Async Operations
WorkerThread Class
Performance Utilities
Caching
Profiling
Testing Utilities
Mock Data Generation
Best Practices
Configuration Management
Error Handling
Threading
See Also
Pages API
Table of Contents
Page Architecture
BasePage Class
Home Page
pages/home_page.py
HomePage Class
Data Package Page
pages/data_package_page.py
DataPackagePage Class
Preprocessing Page
pages/preprocess_page.py
PreprocessPage Class
Exploratory Analysis Page
pages/exploratory_analysis_page.py
AnalysisPage Class
Modeling & Classification Page
pages/machine_learning_page.py
MachineLearningPage Class
Workspace Page
pages/workspace_page.py
WorkspacePage Class
Best Practices
Data Flow Between Pages
Error Handling in Pages
Progress Reporting
See Also
Components API
Table of Contents
Component Architecture
Component Hierarchy
App Tabs
components/app_tabs.py
AppTabs Class
Page Registry
components/page_registry.py
PageRegistry Class
Toast Notifications
components/toast.py
Toast Class
Spectrum Viewer
components/widgets/matplotlib_widget.py
SpectrumViewer Class
Data Table
components/widgets/views_widget.py
DataTable Class
Parameter Panel
components/widgets/parameter_widgets.py
ParameterPanel Class
Pipeline Builder
components/widgets/component_selector_panel.py
PipelineBuilder Class
Results Panel
components/widgets/results_panel.py
ResultsPanel Class
Multi-Group Dialog
components/widgets/multi_group_dialog.py
MultiGroupDialog Class
External Evaluation Dialog
components/widgets/external_evaluation_dialog.py
ExternalEvaluationDialog Class
Component Communication
Signal-Slot Patterns
Event Bus Pattern
Best Practices
Component Reusability
State Management
Error Handling in Components
See Also
Functions API
Table of Contents
Data Loading Functions
functions/data_loader.py
load_spectra_from_csv()
save_spectra_to_csv()
load_raman_peaks()
Preprocessing Functions
Baseline Correction
apply_asls()
apply_airpls()
apply_polynomial_baseline()
apply_whittaker_baseline()
apply_fabc()
apply_butterworth_filter()
Smoothing
apply_savgol()
apply_gaussian_filter()
apply_moving_average()
apply_median_filter()
apply_kernel_denoise()
Normalization
apply_vector_norm()
apply_minmax_norm()
apply_area_norm()
apply_snv()
apply_msc()
apply_quantile_norm()
apply_pqn()
apply_rank_transform()
Derivatives
apply_first_derivative()
apply_second_derivative()
Advanced Processing
apply_cdae()
apply_background_subtraction()
apply_wavelength_calibration()
apply_peak_ratio()
apply_wavelet_transform()
Analysis Functions
Dimensionality Reduction
apply_pca()
apply_umap()
apply_tsne()
Clustering
apply_kmeans()
apply_hierarchical_clustering()
apply_dbscan()
Statistical Tests
apply_ttest()
apply_mannwhitneyu()
apply_anova()
apply_kruskal()
apply_correlation()
apply_multiple_testing_correction()
Machine Learning Functions
Model Training
train_svm()
train_random_forest()
train_xgboost()
train_logistic_regression()
train_mlp()
Model Evaluation
evaluate_model()
plot_confusion_matrix()
plot_roc_curve()
plot_learning_curve()
Feature Importance
get_feature_importance()
plot_feature_importance()
calculate_permutation_importance()
Utility Functions
functions/utils.py
validate_spectra_data()
generate_mock_spectra()
calculate_snr()
find_peaks()
integrate_region()
resample_spectrum()
split_train_test()
export_pipeline()
load_pipeline()
Pipeline Execution
execute_preprocessing_pipeline()
Best Practices
Function Usage
Error Handling
Pipeline Design
Performance Optimization
See Also
Widgets API
Table of Contents
Widget Architecture
Base Widget Principles
Common Widget Pattern
Enhanced Parameter Widgets
components/widgets/enhanced_parameter_widgets.py
FloatParameterWidget
IntParameterWidget
BoolParameterWidget
ChoiceParameterWidget
StringParameterWidget
RangeParameterWidget
Constrained Parameter Widgets
components/widgets/constrained_parameter_widgets.py
ConstrainedFloatWidget
AutoValidatingComboBox
Icons and Resources
components/widgets/icons.py
get_icon()
get_themed_icon()
IconButton
Matplotlib Widget
components/widgets/matplotlib_widget.py
MatplotlibWidget
InteractivePlot
Component Selector Panel
components/widgets/component_selector_panel.py
ComponentSelectorPanel
Results Panel Details
components/widgets/results_panel.py
ResultsPanel
Views Widget
components/widgets/views_widget.py
SpectrumTableView
Grouping Widgets
components/widgets/grouping/
GroupManager
Custom Dialogs
Parameter Editor Dialog
Method Selection Dialog
Widget Styling
Theme Support
Widget-Specific Styling
Best Practices
Widget Design
Signal Management
State Management
Performance
See Also
Development
Development Guide
📚 Guide Contents
Architecture
Contributing Guide
Build System
Testing Guide
🚀 Quick Start for Developers
Prerequisites
Setup Development Environment
Running the Application
📂 Project Structure
🛠️ Development Tools
Code Quality
Testing
Documentation
Build Tools
🔧 Common Development Tasks
Adding a New Preprocessing Method
Adding a New Page
Adding a New Widget
Updating Translations
📖 Coding Standards
Python Style
Documentation
Example
🤝 Getting Help
📝 License
🔗 See Also
Architecture
What to read first
Contributing Guide
Minimal contribution workflow (current)
Build System
Recommended approach
Testing Guide
Smoke tests (current)
Additional Resources
Changelog
[Unreleased]
Documentation
[1.0.0-alpha] - 2026-01-24
Added
Core Features
Preprocessing (40+ Methods)
Analysis Methods
Machine Learning
Build System
Fixed
January 2026
October 2025
Changed
Security
[0.1.0] - 2025-10-01
Added
Release Notes
Version 1.0.0-alpha
Migration Guides
From v0.1.0 to v1.0.0-alpha
Contributors
Core Development
Supervision
Acknowledgments
License
Citation
Support
Troubleshooting Guide
Quick Diagnostic Steps
Installation Issues
Python Version Error
Module Not Found
UV Installation Fails
Permission Denied (Linux/macOS)
Windows SmartScreen Blocks Executable
Application Launch Issues
Application Doesn’t Start
Application Crashes on Startup
Black/Blank Window
Data Import Issues
File Not Recognized
Dimension Mismatch Error
Data Looks Wrong After Import
Preprocessing Issues
Preview Shows All Zeros
Baseline Correction Not Working
Smoothing Removes Peaks
Normalization Produces Strange Results
Pipeline Fails to Execute
Analysis Issues
PCA Shows No Group Separation
Statistical Tests Show No Significant Differences
Analysis Takes Forever
Plots Don’t Appear
Machine Learning Issues
Model Training Fails
100% Training Accuracy, Poor Test Accuracy
Groups Imbalanced (90% vs 10%)
SHAP Values Take Forever
Can’t Export Trained Model
Performance Issues
Application Runs Slowly
High RAM Usage
Disk Space Issues
UI Issues
Text Too Small/Large
Japanese Text Shows as Boxes (□□□)
Buttons Not Responding
Getting More Help
Collect Diagnostic Information
Where to Get Help
Emergency: Application Completely Broken
Contributing to This Guide
Frequently Asked Questions (FAQ)
General Questions
What is this application for?
Who developed this software?
Is this software free?
Can I use this for clinical diagnosis?
What platforms are supported?
Installation Questions
Do I need Python installed?
Why is the executable so large (375 MB)?
How do I update to a new version?
Can I install on a computer without internet?
Data Questions
What file formats are supported?
What data structure is required?
My data has x-axis in nm, not cm⁻¹. What should I do?
Can I import multiple files at once?
How do I handle replicates?
Preprocessing Questions
What preprocessing should I use?
What is the difference between AsLS and AirPLS?
Should I normalize before or after baseline correction?
Can I save my preprocessing pipeline?
My preview shows all zeros after preprocessing. What’s wrong?
Analysis Questions
PCA shows no group separation. What should I do?
How many principal components should I use?
What is “multiple testing correction” and do I need it?
Machine Learning Questions
What algorithm should I choose?
How much data do I need?
My model has 100% accuracy. Is that good?
Export and Results Questions
How do I export results?
Can I get publication-quality figures?
How do I cite this software?
Language and Localization Questions
Can I use the interface in Japanese?
Some text is still in English after changing language. Why?
Still Have Questions?
Documentation
Community
Contributing
Glossary
A
B
C
D
E
F
G
H
I
K
L
M
N
O
P
Q
R
S
T
U
V
W
X
Japanese Terms / 日本語用語
Abbreviations
Contributing
References
Table of Contents
Raman Spectroscopy
Fundamentals
Medical Applications
Preprocessing Methods
Baseline Correction
Smoothing and Denoising
Normalization
Feature Engineering
Machine Learning
Dimensionality Reduction
Classification
Interpretability
Validation
Software Libraries
Core Dependencies
Specialized Libraries
Medical Applications
Blood Plasma Analysis
Pre-disease (未病) Detection
Standards and Guidelines
Best Practices
Quality Control
Related Resources
Online Resources
Educational Materials
Software Citation
Contributing
Raman Spectroscopy Analysis Application
Index
Index