Merge pull request #83 from AartGoossens/feature/tcx_metadata

Finishes metadata loading for read_tcx()

.github/workflows/test.yml

@@ -8,7 +8,7 @@ jobs:
     strategy:
       max-parallel: 4
       matrix:
-        python-version: [3.6, 3.7, 3.8, 3.9]
+        python-version: [3.6, 3.7, 3.8, 3.9, '3.10.0-alpha.7']
     steps:
     - uses: actions/checkout@master
     - name: Set up Python ${{ matrix.python-version }}

docker/Dockerfile.jupyter

@@ -2,7 +2,15 @@ FROM python
 
 RUN pip install jupyter
 
+RUN mkdir /build
+WORKDIR /build
+COPY pyproject.toml poetry.lock README.md ./
+RUN mkdir /sweat
+COPY sweat ./sweat
+
+RUN pip install .
+
 RUN mkdir /src/
-WORKDIR /src/
+WORKDIR /src/docs/docs
 
-CMD pip install . && cd docs/docs/ && jupyter notebook --ip=0.0.0.0  --port=8888 --allow-root --NotebookApp.token='' --NotebookApp.password=''
+CMD jupyter notebook --ip=0.0.0.0  --port=8888 --allow-root --NotebookApp.token='' --NotebookApp.password=''

docker/Dockerfile.test

@@ -7,12 +7,14 @@ ENV PYTHONUNBUFFERED=1
 RUN apt update
 RUN apt install -y software-properties-common
 RUN add-apt-repository -y ppa:deadsnakes/ppa
+RUN apt update
 RUN apt install -y \
     curl \
     python3.6-dev \
     python3.7-dev \
     python3.8-dev \
     python3.9-dev \
+    python3.10-dev \
     python3-pip
 RUN pip3 install --upgrade pip
 

docker/docker-compose.docs.yml

@@ -22,6 +22,8 @@ services:
     build:
       context: ..
       dockerfile: docker/Dockerfile.jupyter
+    environment:
+      - PYTHONPATH=/src:${PYTHONPATH}
     ports:
       - "8889:8888"
     volumes:

docs/docs/changelog.md

@@ -15,6 +15,11 @@ Types of changes:
 - `Fixed` for any bug fixes.
 - `Security` in case of vulnerabilities.
 
+## [Unreleased] - {yyyy-mm-dd}
+### Added
+- Adds testing for Python 3.10
+- `read_tcx()` now supports a metadata=True kwarg that will return device data.
+
 ## [0.20.3] - 2021-04-20
 ### Fixed
 - `sweat.read_fit()` now supports integer column names.

docs/docs/features/data_loading.md

@@ -164,6 +164,20 @@ example_tcx = sweat.examples(path="3173437224.tcx")
 data = sweat.read_tcx(example_tcx.path)
 ```
 
+### Metadata
+The `read_tcx()` function accepts a `metadata=True` parameter.
+When set to `True` (default is `False`) a dictionairy is returned, with the dataframe in the "data" key, and in the key "device" a `Device` object that has the attributes `name`, `product_id`, `serial_number`, `sensors` and `metadata`:
+
+```python
+import sweat
+
+
+data = sweat.read_tcx("path_to.tcx", metadata=True)
+
+data["device"]
+-> Device(name='Garmin Edge 1000', product_id='1836', serial_number='3907354759', metadata={'creator_xml': ...}, sensors=[])
+```
+
 ## Strava
 The `sweat.read_strava()` function can be used to pull data from Strava.
 Sweat assumes you already have an API access token. Read more about that [here](http://developers.strava.com/docs/authentication/).

pyproject.toml

@@ -36,7 +36,7 @@ openpyxl = "^3.0.7"
 legacy_tox_ini = """
 [tox]
 isolated_build = true
-envlist = py36,py37,py38,py39
+envlist = py36,py37,py38,py39,py3.10
 
 [testenv]
 whitelist_externals = poetry

sweat/io/fit.py

@@ -18,7 +18,11 @@
 
 def process_location_columns(df, columns=None):
     if columns is None:
-        columns = [c for c in df.columns if isinstance(c, str) and (c.endswith("_lat") or c.endswith("_long"))]
+        columns = [
+            c
+            for c in df.columns
+            if isinstance(c, str) and (c.endswith("_lat") or c.endswith("_long"))
+        ]
     else:
         columns = [c for c in columns if c in df.columns]
 

sweat/io/tcx.py

@@ -110,17 +110,16 @@ def read_tcx(
         if metadata:
             creator = activity.find("default:Creator", NAMESPACES)
             device_name = xml_find_value_or_none(creator, "default:Name", NAMESPACES)
-            device_unit_id = xml_find_value_or_none(
-                creator, "default:UnitId", NAMESPACES
-            )
-            device_product_id = xml_find_value_or_none(
-                creator, "default:ProductId", NAMESPACES
+            unit_id = xml_find_value_or_none(creator, "default:UnitId", NAMESPACES)
+            product_id = xml_find_value_or_none(
+                creator, "default:ProductID", NAMESPACES
             )
 
             device = Device(
                 name=device_name,
-                serial_number=device_unit_id,
-                metadata={},
+                product_id=product_id,
+                serial_number=unit_id,
+                metadata={"creator_xml": creator},
             )
 
     tcx_df = pd.DataFrame(records)

sweat/io/utils.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import List
 
 import pandas as pd
@@ -50,15 +50,17 @@ def create_empty_dataframe():
 
 
 @dataclass
-class BaseDevice:
+class Sensor:
     name: str
-    serial_number: str
-    metadata: dict
+    product_id: str = None
+    serial_number: str = None
+    metadata: dict = field(default_factory=dict)
 
 
-class Sensor(BaseDevice):
-    pass
-
-
-class Device(BaseDevice):
-    sensors: List[Sensor]
+@dataclass
+class Device:
+    name: str
+    product_id: str = None
+    serial_number: str = None
+    metadata: dict = field(default_factory=dict)
+    sensors: List[Sensor] = field(default_factory=list)

tests/io/test_tcx.py

@@ -27,10 +27,8 @@ def test_read_tcx(example):
     assert activity["session"].max() == example.sessions - 1
 
 
-@pytest.mark.parametrize(
-    "example", [(i) for i in sweat.examples(file_type=FileTypeEnum.tcx)]
-)
-def test_read_tcx_metadata(example):
+def test_read_tcx_metadata():
+    example = sweat.examples(path="activity_4078723797.tcx")
     activity = tcx.read_tcx(example.path, metadata=True)
 
     assert isinstance(activity, dict)
@@ -46,3 +44,10 @@ def test_read_tcx_metadata(example):
 
     assert "session" in data.columns
     assert data["session"].max() == example.sessions - 1
+
+    device = activity["device"]
+    assert device.name == "Garmin Edge 1000"
+    assert device.product_id is not None
+    assert device.serial_number is not None
+    assert device.sensors == []
+    assert "creator_xml" in device.metadata