Migrate to uv, ty, and ruff; simplify and fix typing issues

Author: Aaron Meyer

.github/workflows/build.yml

@@ -7,8 +7,10 @@ jobs:
     runs-on: self-hosted
     steps:
     - uses: actions/checkout@v4
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
     - name: Install dependencies
-      run: poetry install
+      run: uv sync
     - name: Build figures
       run: make all -j 12
     - name: Upload files

.github/workflows/pytest.yml

@@ -1,6 +1,3 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
 name: Test
 
 on: [push]
@@ -12,10 +9,18 @@ jobs:
     - uses: actions/checkout@v4
     - name: Setup submodule
       run: git submodule update --init --recursive
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
     - name: Install dependencies
-      run: poetry install
+      run: uv sync
+    - name: Lint with ruff
+      run: uv run ruff check .
+    - name: Check formatting with ruff
+      run: uv run ruff format --check .
+    - name: Type check with ty
+      run: uv run ty check
     - name: Test with pytest
-      run: poetry run pytest --cov=lineage --cov-report=xml --cov-config=.github/workflows/coveragerc
+      run: uv run pytest --cov=lineage --cov-report=xml --cov-config=.github/workflows/coveragerc
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v4
       with:

.gitignore

@@ -4,14 +4,14 @@
 **/.pytest_cache
 **/__pycache__/
 nosetests.xml
-**/.mypy_cache
+**/.ruff_cache
 
 # Notebooks
 **.ipynb
 # Exception to the rule
 !/notebooks/*.ipynb
 
-
+.venv/
 venv/
 profile
 profile.svg
@@ -21,3 +21,5 @@ spell.txt
 .vscode/settings.json
 .vscode
 lineage/data/taxol
+output/
+

README.rst

@@ -29,8 +29,13 @@ This package is supported on *macOS* and *Linux* systems.
 Python dependencies
 ~~~~~~~~~~~~~~~~~~~
 
-``tHMM`` requires ``virtualenv``. All other required packages can then be installed using ``make venv`` to establish a virtual environment. 
-The Python packages that will be installed are listed in pyproject.toml, and can be directly installed using ``poetry install``.
+Dependencies are managed with `uv <https://docs.astral.sh/uv/>`_.
+Install the environment and dependencies by running:
+
+.. code-block:: console
+
+    $ uv sync
+
 
 
 Documentation

docs/conf.py

@@ -10,75 +10,73 @@
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
-from sphinx import addnodes
-import re
 import os
+import re
 import sys
-sys.path.insert(0, os.path.abspath('..'))
+
+from sphinx import addnodes
+
+sys.path.insert(0, os.path.abspath(".."))
 
 
 # -- Project information -----------------------------------------------------
 
-project = 'tHMM'
-copyright = '2022, Farnaz Mohammadi, JC Lagarde, Aaron S Meyer'
-author = 'Farnaz Mohammadi, JC Lagarde, Aaron S Meyer'
+project = "tHMM"
+copyright = "2022, Farnaz Mohammadi, JC Lagarde, Aaron S Meyer"
+author = "Farnaz Mohammadi, JC Lagarde, Aaron S Meyer"
 
 # The full version, including alpha/beta/rc tags
-release = '1.0'
+release = "1.0"
 
 
 # -- General configuration ---------------------------------------------------
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = [
-    'sphinx.ext.autodoc',
-    'autoapi.extension',
-    'sphinx_rtd_theme'
-]
-autodoc_mock_imports = ['bs4', 'requests']
-
-autoapi_dirs = ['../lineage']
+extensions = ["sphinx.ext.autodoc", "autoapi.extension", "sphinx_rtd_theme"]
+autodoc_mock_imports = ["bs4", "requests"]
+
+autoapi_dirs = ["../lineage"]
 autoapi_ignore = ["*/test_*.py", "*/figure*.py"]
-autoapi_type = 'python'
+autoapi_type = "python"
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = 'python'
+language = "python"
 
 # autoapi_generate_api_docs = False
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 
 # -- Options for HTML output -------------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
-autoapi_root = 'technical/api'
+autoapi_root = "technical/api"
 
-autodoc_typehints = 'description'
+autodoc_typehints = "description"
 
 
-event_sig_re = re.compile(r'([a-zA-Z-]+)\s*\((.*)\)')
+event_sig_re = re.compile(r"([a-zA-Z-]+)\s*\((.*)\)")
 
 
 def parse_event(env, sig, signode):
@@ -89,7 +87,7 @@ def parse_event(env, sig, signode):
     name, args = m.groups()
     signode += addnodes.desc_name(name, name)
     plist = addnodes.desc_parameterlist()
-    for arg in args.split(','):
+    for arg in args.split(","):
         arg = arg.strip()
         plist += addnodes.desc_parameter(arg, arg)
     signode += plist
@@ -98,10 +96,9 @@ def parse_event(env, sig, signode):
 
 def setup(app):
     from sphinx.util.docfields import TypedField
-    app.add_object_type('confval', 'confval',
-                        objname='configuration value',
-                        indextemplate='pair: %s; configuration value')
-    fdesc = TypedField('parameter', label='Parameters',
-                       names=['param'], typenames=['type'], can_collapse=True)
-    app.add_object_type('event', 'event', 'pair: %s; event', parse_event,
-                        doc_field_types=[fdesc])
+
+    app.add_object_type(
+        "confval", "confval", objname="configuration value", indextemplate="pair: %s; configuration value"
+    )
+    fdesc = TypedField("parameter", label="Parameters", names=["param"], typenames=["type"], can_collapse=True)
+    app.add_object_type("event", "event", "pair: %s; event", parse_event, doc_field_types=[fdesc])

fit_distribution.py

@@ -1,23 +1,25 @@
-""" Calls the tHMM functions and outputs the parameters needed to generate the Figures. """
+"""Calls the tHMM functions and outputs the parameters needed to generate the Figures."""
 
 import itertools
-from typing import Any, Tuple
+from typing import Any
+
 import numpy as np
 from scipy.optimize import linear_sum_assignment
 from sklearn.metrics import rand_score
-from .tHMM import tHMM
+
 from .BaumWelch import (
-    do_E_step,
     calculate_log_likelihood,
-    do_M_step,
+    do_E_step,
     do_M_E_step,
     do_M_E_step_atonce,
+    do_M_step,
 )
+from .tHMM import tHMM
 
 
 def fit_list(
     tHMMobj_list: list[tHMM], tolerance: float = 1e-6, max_iter: int = 200, rng=None
-) -> Tuple[list[np.ndarray], list[np.ndarray], float]:
+) -> tuple[list[list[np.ndarray]], list[list[list[np.ndarray]]], float]:
     """
     Runs the tHMM function through Baum Welch fitting for a list containing a set of data for different concentrations.
 
@@ -34,10 +36,7 @@ def fit_list(
 
     # Step 0: initialize with random assignments and do an M step
     # when there are no fixed emissions, we need to randomize the start
-    init_gam = [
-        [rng.dirichlet(np.ones(tO.num_states), size=len(lin)) for lin in tO.X]
-        for tO in tHMMobj_list
-    ]
+    init_gam = [[rng.dirichlet(np.ones(tO.num_states), size=len(lin)) for lin in tO.X] for tO in tHMMobj_list]
 
     if len(tHMMobj_list) > 1:  # it means we are fitting several concentrations at once.
         do_M_E_step_atonce(tHMMobj_list, init_gam)
@@ -46,15 +45,15 @@ def fit_list(
 
     # Step 1: first E step
     MSD_list, NF_list, betas_list, gammas_list = map(
-        list, zip(*[do_E_step(tHMM) for tHMM in tHMMobj_list])
+        list, zip(*[do_E_step(tHMM) for tHMM in tHMMobj_list], strict=False)
     )
     old_LL = calculate_log_likelihood(NF_list)
 
     # first stopping condition check
     for _ in range(max_iter):
         do_M_step(tHMMobj_list, MSD_list, betas_list, gammas_list)
         MSD_list, NF_list, betas_list, gammas_list = map(
-            list, zip(*[do_E_step(tHMM) for tHMM in tHMMobj_list])
+            list, zip(*[do_E_step(tHMM) for tHMM in tHMMobj_list], strict=False)
         )
         new_LL = calculate_log_likelihood(NF_list)
         if new_LL - old_LL < tolerance:
@@ -67,7 +66,7 @@ def fit_list(
 
 def Analyze_list(
     pop_list: list, num_states: int, fpi=None, fT=None, rng=None, write_states=False
-) -> Tuple[list[tHMM], float, list[np.ndarray]]:
+) -> tuple[list[tHMM], float, list[list[list[np.ndarray]]]]:
     """This function runs the analyze function for the case when we want to fit multiple conditions at the same time.
     :param pop_list: The list of cell populations to run the analyze function on.
     :param num_states: The number of states that we want to run the model for.
@@ -110,7 +109,7 @@ def run_Analyze_over(
     atonce=False,
     list_of_fpi=None,
     list_of_fT=None,
-) -> list[Tuple[list[tHMM], float, list[np.ndarray]]]:
+) -> list[tuple[list[tHMM], float, list[np.ndarray]]]:
     """
     A function that can be parallelized to speed up figure creation.
 
@@ -180,37 +179,23 @@ def Results(tHMMobj: tHMM, LL: float) -> dict[str, Any]:
 
     true_states_by_lineage = [lin.states for lin in tHMMobj.X]
 
-    results_dict["transition_matrix_similarity"] = np.linalg.norm(
-        tHMMobj.estimate.T - tHMMobj.X[0].T
-    )
+    results_dict["transition_matrix_similarity"] = np.linalg.norm(tHMMobj.estimate.T - tHMMobj.X[0].T)
 
-    results_dict["pi_similarity"] = np.linalg.norm(
-        tHMMobj.X[0].pi - tHMMobj.estimate.pi
-    )
+    results_dict["pi_similarity"] = np.linalg.norm(tHMMobj.X[0].pi - tHMMobj.estimate.pi)
 
     # Get the estimated parameter values
-    results_dict["param_estimates"] = [
-        tHMMobj.estimate.E[x].params for x in range(tHMMobj.num_states)
-    ]
+    results_dict["param_estimates"] = [tHMMobj.estimate.E[x].params for x in range(tHMMobj.num_states)]
 
     # Get the true parameter values
-    results_dict["param_trues"] = [
-        tHMMobj.X[0].E[x].params for x in range(tHMMobj.num_states)
-    ]
+    results_dict["param_trues"] = [tHMMobj.X[0].E[x].params for x in range(tHMMobj.num_states)]
 
     # Get the distance between distributions of two states
-    results_dict["distribution distance 0"] = tHMMobj.estimate.E[0].dist(
-        tHMMobj.X[0].E[0]
-    )
-    results_dict["distribution distance 1"] = tHMMobj.estimate.E[1].dist(
-        tHMMobj.X[0].E[1]
-    )
+    results_dict["distribution distance 0"] = tHMMobj.estimate.E[0].dist(tHMMobj.X[0].E[0])
+    results_dict["distribution distance 1"] = tHMMobj.estimate.E[1].dist(tHMMobj.X[0].E[1])
 
     # 2. Calculate accuracy after switching states
     results_dict["state_counter"] = np.bincount(pred_states[0])
-    results_dict["state_proportions"] = [
-        100.0 * i / len(pred_states[0]) for i in results_dict["state_counter"]
-    ]
+    results_dict["state_proportions"] = [100.0 * i / len(pred_states[0]) for i in results_dict["state_counter"]]
     results_dict["state_proportions_0"] = results_dict["state_proportions"][0]
     results_dict["state_similarity"] = 100.0 * rand_score(
         list(itertools.chain(*true_states_by_lineage)),
@@ -223,7 +208,7 @@ def Results(tHMMobj: tHMM, LL: float) -> dict[str, Any]:
     return results_dict
 
 
-def permute_states(tHMMobj: tHMM, switch_map: np.ndarray) -> Tuple[Any, list]:
+def permute_states(tHMMobj: tHMM, switch_map: np.ndarray) -> tuple[Any, list]:
     """
     This function takes the tHMMobj and the predicted states,
     and finds out whether we need to switch the state identities or not based on the likelihood.
@@ -234,9 +219,7 @@ def permute_states(tHMMobj: tHMM, switch_map: np.ndarray) -> Tuple[Any, list]:
     """
     pred_states = tHMMobj.predict()
 
-    pred_states_switched = [
-        np.array([switch_map[st] for sublist in pred_states for st in sublist])
-    ]
+    pred_states_switched = [np.array([switch_map[st] for sublist in pred_states for st in sublist])]
 
     # Rearrange the values in the transition matrix
     tHMMobj.estimate.T = tHMMobj.estimate.T[switch_map, :]