rapidtide 3.0.11__tar.gz → 3.1.1__tar.gz

{rapidtide-3.0.11 → rapidtide-3.1.1}/CHANGELOG.md

@@ -1,5 +1,26 @@
 # Release history
 
+## Version 3.1.1 (11/17/25)
+* (rapidtide, retroregress) Correctly output relevant maps when doing CVR processing.  Closes https://github.com/bbfrederick/rapidtide/issues/226.  Thank you to https://github.com/beccaclements99 for finding this!
+* (rapiditde) Fixed a crashing bug when using PCA to estimate the initial sLFO regressor.
+* (happy) Made tensorflow an optional install because of more tf weirdness.  If tensorflow is not present, default to using the pytorch deep learning filter.  If tensorflow is present, enable the ``--usetensorflow`` option.
+* (package) Added support for python 3.14 (if you use 3.14, you cannot currently install tensorflow, so happy will use the pytorch deep learning filter).
+* (package) Lots of type hint refinements.
+* (package) Fixed lots of typos and minor bugs.
+
+## Version 3.1 (11/8/25)
+* (happy) Moved to a pytorch implementation of the deep learning filter, as tensorflow seems to be barely maintained these days.  The pytorch filter is now the default, and performance seems indistinguishable.  I'll keep the tensorflow version around until it becomes (more) cumbersome to do so.  Use ``--usetensorflow`` to get the old filter.
+* (happy) Added "pulsatility" map output - the percentage pulsatile cardiac variation around the mean in each voxel.
+* (happy) Made pass labelling consistent for output files.
+* (happy) Switched nifti file output to use maplist (jsons have description fields now).
+* (rapidtide) Output some timecourse statistics before and after sLFO regression.
+* (atlasaverage) Fixed label output when extracting data from 3D files.
+* (package) Added type hints to all core routines (thanks Claude!).  Everything works, but I'll probably be finetuning the type hints for a while to make them more specific (and I'll be resolving sloppy type handling that I'm now aware of due to mypy).
+* (package) Added docstrings to all core routines (thanks script I wrote that calls qwen3-coder locally so I don't run out of Claude tokens!).
+* (package) Added support for python 3.13 (now that tensorflow is FINALLY available for 3.13).
+* (package) Dropped support for python 3.9 (it doesn't support modern type hint formats).
+* (package) More dependabot PRs.
+
 ## Version 3.0.11 (8/27/25)
 * (Docker) Fixed a critical bug in building the container.
 * (happy) Added the ability to specify an overall processing mask.

rapidtide-3.1.1/CLAUDE.md

@@ -0,0 +1,191 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+Rapidtide is a Python package for modeling, characterizing, visualizing, and removing time-varying physiological blood signals from fMRI and fNIRS datasets. The package has two primary workhorses:
+
+- **rapidtide**: Characterizes bulk blood flow through time delay analysis on functional imaging data, finding time-lagged correlations between voxelwise time series in the low-frequency oscillation (LFO) band
+- **happy**: Extracts and analyzes cardiac signals from fMRI data using hypersampling techniques, even when TR is too long to properly sample cardiac waveforms
+
+## Architecture
+
+### Code Organization
+
+```
+rapidtide/
+├── scripts/          # Command-line entry points (~65 utilities)
+├── workflows/        # Main processing pipelines (rapidtide, happy, and various utilities)
+├── tests/            # Pytest test suite (~44 test files)
+├── candidatetests/   # Work-in-progress tests (not run in CI)
+├── data/             # Reference data, models, and examples
+└── [modules]         # Core processing modules (see below)
+```
+
+### Key Modules
+
+- **io.py**: NIFTI/text file I/O operations
+- **filter.py**: Signal filtering and preprocessing
+- **correlate.py**: Cross-correlation and time-lag analysis
+- **fit.py**: Peak fitting and parameter estimation
+- **resample.py**: Time series resampling utilities
+- **stats.py**: Statistical analysis functions
+- **multiproc.py**: Parallel processing infrastructure
+- **happy_supportfuncs.py**: Cardiac signal processing for happy workflow
+- **dlfilter.py / dlfiltertorch.py**: Deep learning filters for signal cleaning
+- **RapidtideDataset.py**: Dataset class for tidepool GUI
+- **OrthoImageItem.py**: Orthogonal image display for tidepool GUI
+
+### Script/Workflow Architecture
+
+All command-line tools follow a consistent pattern:
+1. `rapidtide/scripts/<name>.py` - Minimal entry point that imports from workflows
+2. `rapidtide/workflows/<name>.py` - Main processing logic
+3. `rapidtide/workflows/<name>_parser.py` - Argument parsing (for complex tools)
+
+Entry points are registered in `pyproject.toml` under `[project.scripts]`.
+
+### Main Workflows
+
+**rapidtide workflow** (`rapidtide/workflows/rapidtide.py`):
+- Performs voxel-wise time delay analysis on fMRI data
+- Generates multiple 3D NIFTI maps (lag time, correlation values, masks, etc.)
+- Outputs text files with significance thresholds and processing parameters
+
+**happy workflow** (`rapidtide/workflows/happy.py`):
+- Extracts cardiac waveforms from fMRI using slice-selective averaging
+- Cleans estimates using deep learning filters
+- Constructs cardiac pulsation maps over a single cardiac cycle
+
+## Development Commands
+
+### Setup and Installation
+
+```bash
+# Install package in development mode with all dependencies
+pip install -e .[tests,doc]
+
+# Or for all optional dependencies
+pip install -e .[all]
+```
+
+### Testing
+
+```bash
+# Run full test suite
+pytest rapidtide/tests/
+
+# Run specific test file
+pytest rapidtide/tests/test_filter.py
+
+# Run with coverage
+pytest --cov=rapidtide rapidtide/tests/
+
+# Run specific test function
+pytest rapidtide/tests/test_filter.py::test_function_name -v
+```
+
+Note: Tests are run in CI via CircleCI for Python 3.9, 3.10, 3.11, and 3.12.
+
+### Code Formatting
+
+```bash
+# Format code with black (line length: 99)
+black rapidtide/
+
+# Check specific file
+black --check rapidtide/filter.py
+```
+
+Black configuration in `pyproject.toml`:
+- Line length: 99
+- Target: Python 3.9+
+- Excludes: versioneer files, candidatetests, disabledtests, data/examples
+
+### Building and Distribution
+
+```bash
+# Build package
+python -m build
+
+# Install locally
+pip install .
+
+# Build Docker container
+./builddocker.sh
+
+# Test Docker container
+./testdocker.sh
+```
+
+### Running Main Tools
+
+```bash
+# Run rapidtide analysis
+rapidtide <input_4d_nifti> <output_root> [options]
+
+# Run happy analysis
+happy <input_4d_nifti> <output_root> [options]
+
+# View results in GUI
+tidepool  # Then select a lag time map file
+
+# Quick timecourse visualization
+showtc <textfile>
+
+# Cross-correlation between two timecourses
+showxcorrx <file1> <file2>
+```
+
+## Important Constraints
+
+### Python Version
+- **Minimum**: Python 3.9
+- **Maximum**: Python 3.12 (tensorflow limitation)
+- Uses modern Python features (f-strings, type hints)
+
+### Data Formats
+- Input: 4D NIFTI files for fMRI data
+- Output: 3D NIFTI maps, text files with timecourses/parameters
+- Timecourses: Whitespace-separated text files
+
+### FSL Dependency
+Some tools (rapidtide2std, happy2std) require a working FSL installation for registration to MNI152 space.
+
+## Key Design Patterns
+
+### Versioning
+Uses versioneer for automatic version management from git tags:
+- Version set in `rapidtide/_version.py` (auto-generated)
+- Tag prefix: `v` (e.g., v2.9.0)
+
+### Testing Philosophy
+- Main tests in `rapidtide/tests/` are run in CI
+- Experimental/incomplete tests in `rapidtide/candidatetests/`
+- Many tests use synthetic data and compare against reference outputs
+- Full workflow tests: `test_fullrunrapidtide_v*.py`, `test_fullrunhappy_v*.py`
+
+### Multiprocessing
+Many operations support parallel processing:
+- Uses `rapidtide/multiproc.py` and `rapidtide/genericmultiproc.py`
+- Configurable number of worker processes
+- Shared memory for efficiency
+
+## Special Notes
+
+- The codebase uses extensive command-line argument parsing with validation in `workflows/parser_funcs.py`
+- Deep learning models for signal filtering are in `rapidtide/data/models/`
+- The package includes a GUI tool (tidepool) built with PyQt6 for visualizing results
+- Reference data and example datasets are in `rapidtide/data/`
+- Documentation is built with Sphinx and hosted on ReadTheDocs
+
+## Style Conventions
+
+See the contributing guide at http://rapidtide.readthedocs.io/en/latest/contributing.html for full style guidelines.
+
+Key points:
+- Use Black formatter with 99-character line length
+- Follow NumPy docstring format
+- Keep changes focused on specific issues/features
+- Work on feature branches, not main

{rapidtide-3.0.11/rapidtide.egg-info → rapidtide-3.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rapidtide
-Version: 3.0.11
+Version: 3.1.1
 Summary: Tools for performing correlation analysis on fMRI data.
 Author: Taylor Salo, Daniel M. Drucker, Ph.D., Jeffrey N Stout, Yaroslav O. Halchenko, Derek Monroe
 Author-email: "Blaise deB. Frederick" <blaise.frederick@gmail.com>
@@ -16,32 +16,34 @@ Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Image Recognition
 Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.9
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: numpy
-Requires-Dist: scipy<=1.15.3
+Requires-Dist: scipy
 Requires-Dist: pandas
 Requires-Dist: pyarrow
 Requires-Dist: scikit-image
 Requires-Dist: scikit-learn
 Requires-Dist: nibabel
 Requires-Dist: nilearn
-Requires-Dist: matplotlib>=3.3.0
-Requires-Dist: pyqtgraph>=0.13.4
+Requires-Dist: matplotlib
+Requires-Dist: pyqtgraph
 Requires-Dist: pyqt6-sip
 Requires-Dist: pyqt6
 Requires-Dist: requests
 Requires-Dist: statsmodels
 Requires-Dist: pywavelets
-Requires-Dist: tensorflow>=2.18.0
-Requires-Dist: tf-keras>=2.18.0
+Requires-Dist: torch
 Requires-Dist: tqdm
 Requires-Dist: versioneer
+Provides-Extra: tf
+Requires-Dist: tensorflow>=2.18.0; extra == "tf"
+Requires-Dist: tf-keras>=2.18.0; extra == "tf"
 Provides-Extra: test
 Requires-Dist: codecov; extra == "test"
 Requires-Dist: coverage; extra == "test"

{rapidtide-3.0.11 → rapidtide-3.1.1}/pyproject.toml

@@ -14,30 +14,29 @@ classifiers = [
     'Intended Audience :: Science/Research',
     'Topic :: Scientific/Engineering :: Image Recognition',
     'License :: OSI Approved :: Apache Software License',
-    'Programming Language :: Python :: 3.9',
     'Programming Language :: Python :: 3.10',
     'Programming Language :: Python :: 3.11',
     'Programming Language :: Python :: 3.12',
+    'Programming Language :: Python :: 3.13',
 ]
-requires-python = '>=3.9'
+requires-python = '>=3.10'
 dependencies = [
   'numpy',
-  'scipy<=1.15.3',
+  'scipy',
   'pandas',
   'pyarrow',
   'scikit-image',
   'scikit-learn',
   'nibabel',
   'nilearn',
-  'matplotlib >= 3.3.0',
-  'pyqtgraph >= 0.13.4',
+  'matplotlib',
+  'pyqtgraph',
   'pyqt6-sip',
   'pyqt6',
   'requests',
   'statsmodels',
   'pywavelets',
-  'tensorflow >= 2.18.0',
-  'tf-keras >= 2.18.0',
+  'torch',
   'tqdm',
   'versioneer',
 ]
@@ -59,6 +58,10 @@ authors = [
 'Changelog' = 'https://github.com/bbfrederick/rapidtide/blob/main/CHANGELOG.md'
 
 [project.optional-dependencies]
+tf = [
+  'tensorflow >= 2.18.0',
+  'tf-keras >= 2.18.0',
+]
 test = [
   'codecov',
   'coverage',
@@ -82,6 +85,7 @@ doc = [
 adjustoffset = 'rapidtide.scripts.adjustoffset:entrypoint'
 aligntcs = 'rapidtide.scripts.aligntcs:entrypoint'
 applydlfilter = 'rapidtide.scripts.applydlfilter:entrypoint'
+applyppgproc = 'rapidtide.scripts.applyppgproc:entrypoint'
 atlasaverage = 'rapidtide.scripts.atlasaverage:entrypoint'
 atlastool = 'rapidtide.scripts.atlastool:entrypoint'
 calcicc = 'rapidtide.scripts.calcicc:entrypoint'
@@ -165,7 +169,7 @@ all = ['rapidtide[doc,test]']
 
 [tool.black]
 line-length = 99
-target-version = ['py39']
+target-version = ['py310']
 include = '\.pyi?$'
 exclude = '''
 (