Merge pull request #83 from emotional-cities/package-structure

glopesdev · web-flow · commit 87ceb531a78a · 2025-02-13T10:40:05.000Z
Update build system to use uv
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -0,0 +1,32 @@
+# Builds the python environment; linter and formatting via ruff
+
+name: build
+on:
+  push:
+    branches: ['*']
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  build_run_tests:
+    name: Python ${{ matrix.python-version }} on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python-version: [3.9, 3.11]
+      fail-fast: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+      - name: Install dependencies
+        run: pip install -e .[dev]
+
+      - name: ruff
+        run: ruff check .
diff --git a/.gitignore b/.gitignore
@@ -1,8 +1,18 @@
-.vscode
-
-# Python temp files
-__pycache__
-*.pyc
-*.egg-info
-dist
-.idea/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+
+# Distribution / packaging
+dist/
+_version.py
+*.egg-info/
+*.egg
+
+# IDE
+.vscode/*
+
+# Test
+.coverage
+
+# Environment
+.venv/
+uv.lock
diff --git a/LICENSE b/LICENSE
@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2022 NeuroGEARS Ltd
+Copyright (c) 2022-2025 NeuroGEARS Ltd
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
diff --git a/README.md b/README.md
@@ -1,21 +1,27 @@
 # pluma-analysis
 
+![build](https://github.com/emotional-cities/pluma-analysis/actions/workflows/build.yml/badge.svg?branch=main)
+
 A low-level interface to data collected with the [pluma](https://github.com/emotional-cities/pluma) urban data acquisition system. Data used in the notebooks has been made publicly available in Amazon Simple Storage Service (S3) buckets.
 
 More information about sample data sharing can be found in the [eMOTIONAL Cities data-share repository](https://github.com/emotional-cities/data-share).
 
-## Compatible Environments
+## Set-up Instructions
+
+We recommend [uv](https://docs.astral.sh/uv/) for python version, environment, and package dependency management. However, any other tool compatible with the `pyproject.toml` standard should work.
+
+### Install from PyPI
 
-[Visual Studio Code](https://code.visualstudio.com/): All notebooks have been tested in Visual Studio Code on a Windows platform. Tests in other platforms and environments are forthcoming and will be added here.
+```
+uv pip install pluma-analysis
+```
 
-## How to build
+### Install from source
 
-1. Open project folder in VS Code
-2. Install [miniconda](https://docs.conda.io/en/latest/miniconda.html) (Python 3.9)
-3. Install [Python Extension for VS Code](https://marketplace.visualstudio.com/items?itemName=ms-python.python)
-4. Create environment from VS Code:
-  - `Ctrl+Shift+P` > `Create Environment`
-  - Select `.conda` environment
-5. Make sure correct environment is selected in the notebook
+```
+git clone https://github.com/emotional-cities/pluma-analysis.git
+cd pluma-analysis
+uv sync --all-extras
+```
 
-The current notebook requires Python 3.9+ to run successfully. The file `environment.yml` contains the list of minimal package dependencies required.
+This package was developed for the eMOTIONAL CITIES Project, which received funding from European Union’s Horizon 2020 research and innovation programme, under the grant agreement No 945307. The eMOTIONAL CITIES Project is a consortium of 12 partners co-coordinated by IGOT and FMUL, taking place between 2021 and 2025. More information at https://emotionalcities-h2020.eu/
diff --git a/pluma/export/streams.py b/pluma/export/streams.py
@@ -44,8 +44,7 @@ def export_stream_to_csv(
             resampling_function_kws=resampling_function_kws,
         )
     else:
-        raise NotImplementedError(f"Export of stream type\
-                                  {type(stream)} is not yet supported.")
+        raise NotImplementedError(f"Export of stream type {type(stream)} is not yet supported.")
 
 
 def export_uniform_table_stream(
diff --git a/pluma/io/eeg.py b/pluma/io/eeg.py
@@ -28,7 +28,7 @@ def get_eeg_file(root: Union[str, ComplexPath] = "", if_multiple_load_index: int
         ret = None
     elif len(expected_files) > 1:
         warnings.warn(
-            f"Multiple *.nedf files found in {root}. " f"Loading {expected_files[if_multiple_load_index]}."
+            f"Multiple *.nedf files found in {root}. Loading {expected_files[if_multiple_load_index]}."
         )
         ret = expected_files[if_multiple_load_index]
     else:
diff --git a/pluma/io/harp.py b/pluma/io/harp.py
@@ -84,12 +84,10 @@ def read_harp_bin(file: Union[str, ComplexPath], time_offset: float = 0) -> pd.D
         with path.open("rb") as stream:
             data = np.frombuffer(stream.read(), dtype=np.uint8)
     except FileNotFoundError:
-        warnings.warn(f"Harp stream file\
-            {path} could not be found.")
+        warnings.warn(f"Harp stream file {path} could not be found.")
         return pd.DataFrame()
     except FileExistsError:
-        warnings.warn(f"Harp stream file\
-            {path} could not be found.")
+        warnings.warn(f"Harp stream file {path} could not be found.")
         return pd.DataFrame()
     if len(data) == 0:
         return None
diff --git a/pluma/io/microphone.py b/pluma/io/microphone.py
@@ -32,9 +32,7 @@ def load_microphone(
             micdata = np.frombuffer(stream.read(), dtype=dtype)
             micdata = micdata.reshape((-1, channels))
     except FileNotFoundError:
-        warnings.warn(f"Microphone stream file\
-            {path} could not be found.")
+        warnings.warn(f"Microphone stream file {path} could not be found.")
     except FileExistsError:
-        warnings.warn(f"Microphone stream file\
-            {path} could not be found.")
+        warnings.warn(f"Microphone stream file {path} could not be found.")
     return micdata
diff --git a/pluma/io/ubx.py b/pluma/io/ubx.py
@@ -62,12 +62,10 @@ def read_ubx_file(path: Union[str, ComplexPath]) -> pd.DataFrame:
         with path.open("rb") as fstream:
             out = read(fstream)
     except FileNotFoundError:
-        warnings.warn(f"UBX file\
-            {path} could not be found.")
+        warnings.warn(f"UBX file {path} could not be found.")
         return pd.DataFrame()
     except FileExistsError:
-        warnings.warn(f"UBX file\
-            {path} could not be found.")
+        warnings.warn(f"UBX file {path} could not be found.")
         return pd.DataFrame()
 
     df = pd.DataFrame({"Message": out})
diff --git a/pluma/io/zeromq.py b/pluma/io/zeromq.py
@@ -25,10 +25,8 @@ def load_zeromq(
 
             data_frames.append(pd.DataFrame(np.fromfile(path.path, dtype=np.dtype(dtypes[i]))))
     except FileNotFoundError:
-        warnings.warn(f"Stream file\
-                {path} could not be found.")
+        warnings.warn(f"Stream file {path} could not be found.")
     except FileExistsError:
-        warnings.warn(f"Stream file\
-                {path} could not be found.")
+        warnings.warn(f"Stream file {path} could not be found.")
 
     return pd.concat(data_frames, axis=1)
diff --git a/pluma/preprocessing/ecg.py b/pluma/preprocessing/ecg.py
@@ -20,7 +20,7 @@ def heartrate_from_ecg(
     Args:
         ecg_data (Stream or DataFrame): ECG input data
         sample_rate (float, optional): ECG sampling rate (Hz). Defaults to 50.
-        skip_slice (int, optional): How to slice the incoming raw array. Fs corresponds to the sampling rate post-slicing. Defaults to 4.
+        skip_slice (int, optional): How to slice the incoming raw array. Fs corresponds to the sampling rate post-slicing. Defaults to 20.
         bpmmax (float, optional): Maximum theoretical heartrate. Defaults to 200.0.
         highpass_cutoff (float, optional): Cutoff frequency of the high-pass filter (Hz). Defaults to 5.
         segment_width (int, optional): Segment window size (in seconds) over which to compute heartrate. Defaults to 5.
@@ -37,7 +37,7 @@ def heartrate_from_ecg(
     if invert:
         ecg = ecg * (-1.0)
 
-    # sensor acquires at 50hz but saves at 1khz
+    # sensor acquires at 50hz but is sampled at 1khz
     ecg = ecg.Value0[::skip_slice].astype(np.float64)
 
     # high-pass filter seems to give consistently less rejected peaks than notch
diff --git a/pluma/schema/__init__.py b/pluma/schema/__init__.py
@@ -129,8 +129,7 @@ def _iter_schema_streams(schema: Union[DotMap, Stream, None] = None):
                 for _nested in Dataset._iter_schema_streams(_stream):
                     yield _nested
         else:
-            raise TypeError(f"Invalid type was found. Must be of \
-                            {Union[DotMap, Stream]}")
+            raise TypeError(f"Invalid type was found. Must be of {Union[DotMap, Stream]}")
 
     def reload_streams(self, force_load: bool = False) -> None:
         """Recursively loads, from disk , all available streams in the streams' schema
diff --git a/pluma/stream/csv.py b/pluma/stream/csv.py
@@ -31,11 +31,9 @@ def load(self):
         try:
             self.data = pd.read_csv(path.path)
         except FileNotFoundError:
-            warnings.warn(f"Glia stream file\
-                        {path} could not be found.")
+            warnings.warn(f"Glia stream file {path} could not be found.")
         except FileExistsError:
-            warnings.warn(f"Glia stream file\
-                        {path} could not be found.")
+            warnings.warn(f"Glia stream file {path} could not be found.")
 
     def resample(self):
         pass
diff --git a/pluma/stream/georeference.py b/pluma/stream/georeference.py
@@ -102,8 +102,7 @@ def _validate_build_spacetime_from_dataframe(self, df: pd.DataFrame) -> bool:
         got = [x for x in df.columns]
 
         if not (all(elem in got for elem in expected)):
-            raise KeyError(f"Not compatible. Expected {expected}\
-                , and got {got}")
+            raise KeyError(f"Not compatible. Expected {expected} , and got {got}")
         else:
             return True
 
diff --git a/pluma/stream/siconversion.py b/pluma/stream/siconversion.py
@@ -19,9 +19,10 @@ def validate_si_meta(self, data: pd.DataFrame) -> bool:
             raise AssertionError("No conversion units are set.")
 
         if not (n_handles == n_units == n_col):
-            raise AssertionError(f"Number of SI conversion handles (={n_handles}),\
-        units' labels (={n_units}),\
-            and DataFrame columns (={n_col}) must be the same")
+            raise AssertionError(
+                f"Number of SI conversion handles (={n_handles}), units' labels (={n_units}),\
+                  and DataFrame columns (={n_col}) must be the same"
+            )
 
     def convert_to_si(self, df: pd.DataFrame) -> pd.DataFrame:
         if self.is_si:
diff --git a/pluma/sync/ubx2harp.py b/pluma/sync/ubx2harp.py
@@ -140,9 +140,7 @@ def get_clockcalibration_lookup(
 ) -> SyncLookup:
     # Get the TIM_TM2 Message that timestamps the incoming TTL
     if not (ubx_stream.has_event(_UBX_MSGIDS.TIM_TM2)):
-        raise KeyError(f"UbxStream does not contain \
-            {_UBX_MSGIDS.TIM_TM2.value}\
-                event. Try to load it?")
+        raise KeyError(f"UbxStream does not contain {_UBX_MSGIDS.TIM_TM2.value} event. Try to load it?")
 
     tim_tm2 = ubx_stream.data.TIM_TM2.copy()  # TTL
     tim_tm2.insert(
diff --git a/pyproject.toml b/pyproject.toml
@@ -47,16 +47,14 @@ classifiers = [
 
 [project.optional-dependencies]
 dev = [
-    "setuptools_scm",
     "ruff",
 ]
 
+[tool.ruff]
+line-length = 110
+
 [build-system]
-requires = [
-    "setuptools>=45",
-    "wheel",
-    "setuptools_scm[toml]>=6.2",
-]
+requires = ["setuptools>=64", "setuptools-scm>=8"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
@@ -66,6 +64,4 @@ include-package-data = true
 include = ["pluma*"]
 
 [tool.setuptools_scm]
-
-[tool.ruff]
-line-length = 110
+version_file = "pluma/_version.py"

Original file line number	Diff line number	Diff line change
`@@ -44,8 +44,7 @@ def export_stream_to_csv(`
`44`	`44`	`resampling_function_kws=resampling_function_kws,`
`45`	`45`	`)`
`46`	`46`	`else:`
`47`		`- raise NotImplementedError(f"Export of stream type\`
`48`		`- {type(stream)} is not yet supported.")`
	`47`	`+ raise NotImplementedError(f"Export of stream type {type(stream)} is not yet supported.")`
`49`	`48`
`50`	`49`
`51`	`50`	`def export_uniform_table_stream(`
Original file line number	Diff line number	Diff line change
`@@ -28,7 +28,7 @@ def get_eeg_file(root: Union[str, ComplexPath] = "", if_multiple_load_index: int`
`28`	`28`	`ret = None`
`29`	`29`	`elif len(expected_files) > 1:`
`30`	`30`	`warnings.warn(`
`31`		`- f"Multiple *.nedf files found in {root}. " f"Loading {expected_files[if_multiple_load_index]}."`
	`31`	`+ f"Multiple *.nedf files found in {root}. Loading {expected_files[if_multiple_load_index]}."`
`32`	`32`	`)`
`33`	`33`	`ret = expected_files[if_multiple_load_index]`
`34`	`34`	`else:`