Tutorials

Step-by-step guides to master trend_classifier.

Learning Path

These tutorials build on each other. We recommend following them in order:

#	Tutorial	Duration	What You'll Learn
1	Quick Start	5 min	Basic usage, first segmentation
2	Segment Analysis	10 min	Segment properties, DataFrame export
3	Visualization	10 min	All plotting methods
4	Configuration	15 min	Parameters, presets, tuning
5	Classification	10 min	Categorize trends
6	Optimization	20 min	Optuna hyperparameter tuning
7	Detector Comparison	15 min	Compare algorithms

Prerequisites

Before starting, ensure you have:

pip install trend-classifier[all]
pip install yfinance  # For sample data

Interactive Notebooks

All tutorials are Jupyter notebooks. You can:

1. Read online - View rendered versions in this documentation
2. Run locally - Clone the repo and run in Jupyter
3. Open in Colab - Click the Colab badge in each notebook

git clone https://github.com/izikeros/trend_classifier.git
cd trend_classifier
jupyter lab notebooks/

Quick Reference

Common Patterns

Basic segmentation:

seg = Segmenter(df=df, column="Close", n=40)
seg.calculate_segments()
seg.plot_segments()

Export results:

df = seg.segments.to_dataframe()

Use different detector:

seg = Segmenter(df=df, detector="pelt", detector_params={"penalty": 5})

Key Classes

• Segmenter - Main entry point
• Segment - Single trend segment
• SegmentList - Collection with DataFrame export
• Config - Configuration presets