activity-parser 0.9.0__tar.gz

activity_parser-0.9.0/.github/workflows/ci.yml

@@ -0,0 +1,25 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  schedule:
+    - cron: "0 6 1,15 * *"
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+    steps:
+      - uses: actions/checkout@v7
+      - uses: astral-sh/setup-uv@v8.2.0
+        with:
+          enable-cache: true
+          cache-suffix: ${{ matrix.python-version }}
+      - run: uv sync --python ${{ matrix.python-version }}
+      - run: uv run pre-commit run --all-files
+      - run: uv build

activity_parser-0.9.0/.github/workflows/release.yml

@@ -0,0 +1,17 @@
+name: Release
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v7
+      - uses: astral-sh/setup-uv@v8.2.0
+      - run: uv build
+      - uses: pypa/gh-action-pypi-publish@release/v1

activity_parser-0.9.0/.gitignore

@@ -0,0 +1,24 @@
+# Byte-compiled / optimized files
+__pycache__/
+*.py[cod]
+*$py.class
+.DS_Store
+
+# Distribution / packaging
+build/
+dist/
+*.egg-info/
+.eggs/
+
+# Environments
+.venv/
+env/
+
+# Tooling caches
+.pytest_cache/
+.ruff_cache/
+.pyright/
+
+# Editors
+.idea/
+.vscode/

activity_parser-0.9.0/.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+repos:
+  - repo: local
+    hooks:
+      - id: ruff-check
+        name: ruff check
+        entry: uv run ruff check --fix
+        language: system
+        types: [python]
+
+      - id: ruff-format
+        name: ruff format
+        entry: uv run ruff format
+        language: system
+        types: [python]
+
+      - id: pyright
+        name: pyright
+        entry: uv run pyright
+        language: system
+        types: [python]
+        pass_filenames: false
+
+      - id: pytest
+        name: pytest
+        entry: uv run pytest -q
+        language: system
+        pass_filenames: false
+        always_run: true

activity_parser-0.9.0/LICENSE

@@ -0,0 +1,20 @@
+MIT License
+
+Copyright (c) 2023-2026 Tabish Mustufa
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

activity_parser-0.9.0/PKG-INFO

@@ -0,0 +1,97 @@
+Metadata-Version: 2.4
+Name: activity-parser
+Version: 0.9.0
+Summary: Parser for loading FIT, TCX and GPX files into Pandas DataFrames.
+Project-URL: Repository, https://github.com/tabishm52/activity_parser
+Project-URL: Issues, https://github.com/tabishm52/activity_parser/issues
+Author-email: Tabish Mustufa <tabishm@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: fit,fitness,gps,gpx,pandas,parser,tcx
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: GIS
+Requires-Python: >=3.11
+Requires-Dist: fitdecode
+Requires-Dist: lxml
+Requires-Dist: pandas
+Description-Content-Type: text/markdown
+
+# activity-parser
+
+[![CI](https://github.com/tabishm52/activity_parser/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/tabishm52/activity_parser/actions/workflows/ci.yml)
+
+Parser for loading FIT, TCX and GPX activity files into Pandas DataFrames.
+
+Provides a parser object for reading (optionally gzipped) FIT, TCX, and GPX activity files and converting them into Pandas DataFrames.
+During import, column names extracted from activity files are normalized into a canonical set of output column names.
+
+## Installation
+
+```bash
+pip install activity-parser
+```
+
+## Usage
+
+Create a new instance of the `ActivityParser` class to be reused for subsequent parsing of activity files:
+
+```python
+import activity_parser
+parser = activity_parser.ActivityParser()
+```
+
+Parse FIT, TCX and GPX files into normalized DataFrames:
+
+```python
+records, laps, extra = parser.parse('path/to/fit_file.fit')
+records, laps, extra = parser.parse('path/to/gpx_file.gpx')
+records, laps, extra = parser.parse('path/to/tcx_file.tcx')
+```
+
+Regardless of source format, `records` and `laps` use a canonical set of column names (see [Output columns](#output-columns) below), e.g.:
+
+```
+                           distance  speed  cadence  heart_rate
+time
+2026-01-05 08:00:00+00:00      0.00   36.0       80         100
+2026-01-05 08:00:01+00:00      0.01   36.0       81         101
+```
+
+`extra` is not canonicalized like `records` and `laps`: it's a dict of leftover, format-specific metadata passed through with its native field names, and its shape differs by format.
+For FIT, it's keyed by FIT message name (e.g. `session`, `device_info`).
+For TCX/GPX, it's a single dict of the root element's attributes/fields (e.g. `Creator`, `Id`).
+Treat it as raw metadata to inspect per-format rather than something to consume generically.
+
+## Output columns
+
+Units are aligned to FIT's standard units (via `fitdecode.StandardUnitsDataProcessor`), and columns are renamed/converted where needed so the same name means the same unit regardless of source format:
+
+| Column | Unit | FIT | TCX | GPX |
+|---|---|:-:|:-:|:-:|
+| `latitude`, `longitude` | degrees | Yes | Yes | Yes |
+| `altitude` | meters | Yes | Yes | Yes |
+| `distance` | km | Yes | Yes | — |
+| `speed` | km/h | Yes | Yes | (\*) |
+| `cadence` | rpm | Yes | Yes | Yes |
+| `heart_rate` | bpm | Yes | Yes | Yes |
+| `power` | watts | Yes | Yes | Yes |
+| `temperature` | °C | Yes | — | Yes |
+
+Not every column appears in every file: `parse()` only includes columns actually present in the source.
+Two of these gaps are structural (GPX has no field for cumulative distance, in the base spec or in Garmin's `TrackPointExtension`, and TCX has no field for temperature, in the base spec or in Garmin's `ActivityExtension`), so those will never appear regardless of exporter.
+GPX files also have no lap data, so `laps` will always be an empty DataFrame.
+
+(\*) `speed` for GPX is exporter-dependent, not a format limitation: it's defined in Garmin's `TrackPointExtension/v2` schema.
+Any exporter that emits `v2` (or another extension exposing a `speed`-named field) will have it picked up and normalized.
+
+`laps` follows the same convention for shared metrics (`total_distance`, `avg_speed`, `max_speed`, `avg_heart_rate`, `avg_power`, `total_calories`, etc.).
+FIT also exposes FIT-specific fields not available from TCX/GPX (e.g. `fractional_cadence`, `left_right_balance`, `accumulated_power`) under their native FIT names.
+
+## License
+
+MIT

activity_parser-0.9.0/README.md

@@ -0,0 +1,74 @@
+# activity-parser
+
+[![CI](https://github.com/tabishm52/activity_parser/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/tabishm52/activity_parser/actions/workflows/ci.yml)
+
+Parser for loading FIT, TCX and GPX activity files into Pandas DataFrames.
+
+Provides a parser object for reading (optionally gzipped) FIT, TCX, and GPX activity files and converting them into Pandas DataFrames.
+During import, column names extracted from activity files are normalized into a canonical set of output column names.
+
+## Installation
+
+```bash
+pip install activity-parser
+```
+
+## Usage
+
+Create a new instance of the `ActivityParser` class to be reused for subsequent parsing of activity files:
+
+```python
+import activity_parser
+parser = activity_parser.ActivityParser()
+```
+
+Parse FIT, TCX and GPX files into normalized DataFrames:
+
+```python
+records, laps, extra = parser.parse('path/to/fit_file.fit')
+records, laps, extra = parser.parse('path/to/gpx_file.gpx')
+records, laps, extra = parser.parse('path/to/tcx_file.tcx')
+```
+
+Regardless of source format, `records` and `laps` use a canonical set of column names (see [Output columns](#output-columns) below), e.g.:
+
+```
+                           distance  speed  cadence  heart_rate
+time
+2026-01-05 08:00:00+00:00      0.00   36.0       80         100
+2026-01-05 08:00:01+00:00      0.01   36.0       81         101
+```
+
+`extra` is not canonicalized like `records` and `laps`: it's a dict of leftover, format-specific metadata passed through with its native field names, and its shape differs by format.
+For FIT, it's keyed by FIT message name (e.g. `session`, `device_info`).
+For TCX/GPX, it's a single dict of the root element's attributes/fields (e.g. `Creator`, `Id`).
+Treat it as raw metadata to inspect per-format rather than something to consume generically.
+
+## Output columns
+
+Units are aligned to FIT's standard units (via `fitdecode.StandardUnitsDataProcessor`), and columns are renamed/converted where needed so the same name means the same unit regardless of source format:
+
+| Column | Unit | FIT | TCX | GPX |
+|---|---|:-:|:-:|:-:|
+| `latitude`, `longitude` | degrees | Yes | Yes | Yes |
+| `altitude` | meters | Yes | Yes | Yes |
+| `distance` | km | Yes | Yes | — |
+| `speed` | km/h | Yes | Yes | (\*) |
+| `cadence` | rpm | Yes | Yes | Yes |
+| `heart_rate` | bpm | Yes | Yes | Yes |
+| `power` | watts | Yes | Yes | Yes |
+| `temperature` | °C | Yes | — | Yes |
+
+Not every column appears in every file: `parse()` only includes columns actually present in the source.
+Two of these gaps are structural (GPX has no field for cumulative distance, in the base spec or in Garmin's `TrackPointExtension`, and TCX has no field for temperature, in the base spec or in Garmin's `ActivityExtension`), so those will never appear regardless of exporter.
+GPX files also have no lap data, so `laps` will always be an empty DataFrame.
+
+(\*) `speed` for GPX is exporter-dependent, not a format limitation: it's defined in Garmin's `TrackPointExtension/v2` schema.
+Any exporter that emits `v2` (or another extension exposing a `speed`-named field) will have it picked up and normalized.
+
+`laps` follows the same convention for shared metrics (`total_distance`, `avg_speed`, `max_speed`, `avg_heart_rate`, `avg_power`, `total_calories`, etc.).
+FIT also exposes FIT-specific fields not available from TCX/GPX (e.g. `fractional_cadence`, `left_right_balance`, `accumulated_power`) under their native FIT names.
+
+## License
+
+MIT

activity_parser-0.9.0/pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "activity-parser"
+version = "0.9.0"
+description = "Parser for loading FIT, TCX and GPX files into Pandas DataFrames."
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Tabish Mustufa", email = "tabishm@gmail.com" },
+]
+keywords = ["fit", "tcx", "gpx", "gps", "fitness", "pandas", "parser"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Scientific/Engineering :: GIS",
+]
+requires-python = ">=3.11"
+dependencies = [
+    "pandas",
+    "lxml",
+    "fitdecode",
+]
+
+[project.urls]
+Repository = "https://github.com/tabishm52/activity_parser"
+Issues = "https://github.com/tabishm52/activity_parser/issues"
+
+[dependency-groups]
+dev = [
+    "lxml-stubs",
+    "pandas-stubs",
+    "pre-commit",
+    "pyright",
+    "pytest",
+    "ruff",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "W", "F", "I", "PL", "UP"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = ["PLR2004"]

activity_parser-0.9.0/src/activity_parser/__init__.py

@@ -0,0 +1,12 @@
+"""Parser for loading FIT, TCX and GPX files into Pandas DataFrames."""
+
+from .parse_activity import ActivityParser
+from .parse_fit_file import parse_fit
+from .parse_tcx_gpx import parse_gpx, parse_tcx
+
+__all__ = [
+    "ActivityParser",
+    "parse_fit",
+    "parse_gpx",
+    "parse_tcx",
+]

activity_parser-0.9.0/src/activity_parser/parse_activity.py

@@ -0,0 +1,281 @@
+"""Class for parsing FIT, TCX and GPX files into Pandas DataFrames."""
+
+from collections.abc import Mapping, Sequence
+from os import PathLike
+from pathlib import Path
+from typing import IO, Any
+
+import pandas as pd
+
+from .parse_fit_file import parse_fit
+from .parse_tcx_gpx import parse_gpx, parse_tcx
+
+
+def select_and_rename_cols(
+    df: pd.DataFrame,
+    selector: Sequence[str],
+    mapper: Mapping[str, str],
+) -> pd.DataFrame:
+    """Select and rename columns from a DataFrame."""
+    cols = [col for col in selector if col in df.columns]
+    return df.loc[:, cols].rename(columns=mapper)
+
+
+def normalize_extension(ext: str) -> str:
+    """Normalize an extension string to one of: fit, tcx, gpx."""
+    normalized = ext.lower().lstrip(".")
+    if normalized == "gz":
+        raise ValueError("Ambiguous extension: .gz without base extension.")
+    return normalized
+
+
+def infer_extension(file: str | PathLike[str]) -> str:
+    """Infer normalized extension from a path-like input."""
+    p = Path(file)
+    ext = p.suffix
+    if ext.lower() == ".gz":
+        ext = Path(p.stem).suffix
+    return normalize_extension(ext)
+
+
+class ActivityParser:
+    """Parser for FIT, GPX and TCX files.
+
+    Each instance of this class is a parser object that can be used to import FIT, GPX
+    and TCX files into DataFrames. During parsing, the column names in the resulting
+    DataFrames are normalized to a standard set of names to allow for more
+    interchangeable use of DataFrames from the different activity file types.
+    """
+
+    def __init__(self, strict_xml: bool = False) -> None:
+        """Initialize parser settings, selectors, and mappers.
+
+        Args:
+            strict_xml: If True, TCX/GPX XML parsing fails on malformed input.
+                If False, parser recovery is enabled.
+        """
+        self.strict_xml = strict_xml
+
+        # 'Selectors' specify the list and order of columns to be copied from each
+        # DataFrame (records and laps for each file type), and 'mappers' translate the
+        # imported column names into canonical names
+
+        self.fit_records_selector = [
+            "position_lat",
+            "position_long",
+            "altitude",
+            "distance",
+            "speed",
+            "cadence",
+            "fractional_cadence",
+            "heart_rate",
+            "power",
+            "left_right_balance",
+            "accumulated_power",
+            "temperature",
+        ]
+
+        self.tcx_records_selector = [
+            "LatitudeDegrees",
+            "LongitudeDegrees",
+            "AltitudeMeters",
+            "DistanceKm",
+            "Speed",
+            "Cadence",
+            "HeartRateBpm",
+            "Watts",
+        ]
+
+        self.gpx_records_selector = [
+            "lat",
+            "lon",
+            "ele",
+            "speed",
+            "cad",
+            "hr",
+            "power",
+            "atemp",
+        ]
+
+        self.fit_records_mapper = {
+            "position_lat": "latitude",
+            "position_long": "longitude",
+            "altitude": "altitude",
+            "distance": "distance",
+            "speed": "speed",
+            "cadence": "cadence",
+            "fractional_cadence": "fractional_cadence",
+            "heart_rate": "heart_rate",
+            "power": "power",
+            "left_right_balance": "left_right_balance",
+            "accumulated_power": "accumulated_power",
+            "temperature": "temperature",
+        }
+
+        self.tcx_records_mapper = {
+            "LatitudeDegrees": "latitude",
+            "LongitudeDegrees": "longitude",
+            "AltitudeMeters": "altitude",
+            "DistanceKm": "distance",
+            "Speed": "speed",
+            "Cadence": "cadence",
+            "HeartRateBpm": "heart_rate",
+            "Watts": "power",
+        }
+
+        self.gpx_records_mapper = {
+            "lat": "latitude",
+            "lon": "longitude",
+            "ele": "altitude",
+            "speed": "speed",
+            "cad": "cadence",
+            "hr": "heart_rate",
+            "power": "power",
+            "atemp": "temperature",
+        }
+
+        self.fit_laps_selector = [
+            "event",
+            "event_type",
+            "lap_trigger",
+            "start_time",
+            "total_elapsed_time",
+            "total_timer_time",
+            "start_position_lat",
+            "start_position_long",
+            "end_position_lat",
+            "end_position_long",
+            "total_distance",
+            "total_ascent",
+            "total_descent",
+            "avg_vam",
+            "avg_speed",
+            "max_speed",
+            "avg_cadence",
+            "max_cadence",
+            "avg_fractional_cadence",
+            "max_fractional_cadence",
+            "total_strokes",
+            "avg_heart_rate",
+            "max_heart_rate",
+            "time_in_hr_zone",
+            "avg_power",
+            "max_power",
+            "normalized_power",
+            "left_right_balance",
+            "time_in_power_zone",
+            "total_work",
+            "avg_temperature",
+            "max_temperature",
+            "total_calories",
+            "total_fat_calories",
+            "sport",
+            "sub_sport",
+        ]
+
+        self.tcx_laps_selector = [
+            "TriggerMethod",
+            "StartTime",
+            "TotalTimeSeconds",
+            "DistanceKm",
+            "AvgSpeed",
+            "MaximumSpeed",
+            "Cadence",
+            "MaxBikeCadence",
+            "AverageHeartRateBpm",
+            "MaximumHeartRateBpm",
+            "AvgWatts",
+            "MaxWatts",
+            "Calories",
+        ]
+
+        # Just use the FIT names for lap data as canonical
+        self.fit_laps_mapper = {}
+
+        self.tcx_laps_mapper = {
+            "TriggerMethod": "lap_trigger",
+            "StartTime": "start_time",
+            "TotalTimeSeconds": "total_elapsed_time",
+            "DistanceKm": "total_distance",
+            "AvgSpeed": "avg_speed",
+            "MaximumSpeed": "max_speed",
+            "Cadence": "avg_cadence",
+            "MaxBikeCadence": "max_cadence",
+            "AverageHeartRateBpm": "avg_heart_rate",
+            "MaximumHeartRateBpm": "max_heart_rate",
+            "AvgWatts": "avg_power",
+            "MaxWatts": "max_power",
+            "Calories": "total_calories",
+        }
+
+    def parse(
+        self,
+        file: str | PathLike[str] | IO[bytes],
+        ext: str | None = None,
+    ) -> tuple[pd.DataFrame, pd.DataFrame, dict[str, Any]]:
+        """Loads a FIT, TCX or GPX activity into Pandas DataFrames.
+
+        During import, column names in ``records`` and ``laps`` are normalized into a
+        canonical set of names. Note this function does not guarantee that all canonical
+        columns appear in the output, it only renames the columns that are present in
+        the activity file.
+
+        Args:
+            file: Binary file-like or path-like object. A path-like argument ending in
+                ``.gz`` will be unzipped before processing.
+            ext: File type, case-insensitive: ``fit``, ``tcx``, or ``gpx``. Required for
+                a file-like ``file``; optional for a path-like ``file`` (inferred from
+                the name).
+
+        Returns:
+            Tuple containing records, laps, and selected extra metadata.
+        """
+        if ext is not None:
+            ext_normalized = normalize_extension(ext)
+        elif isinstance(file, (str, PathLike)):
+            ext_normalized = infer_extension(file)
+        else:
+            raise ValueError("ext must be provided when file is a file-like object.")
+
+        if ext_normalized == "fit":
+            records, laps, extra = parse_fit(file)
+            records = select_and_rename_cols(
+                records,
+                self.fit_records_selector,
+                self.fit_records_mapper,
+            )
+            records.rename_axis("time", inplace=True)
+            laps = select_and_rename_cols(
+                laps,
+                self.fit_laps_selector,
+                self.fit_laps_mapper,
+            )
+
+        elif ext_normalized == "tcx":
+            records, laps, extra = parse_tcx(file, strict_xml=self.strict_xml)
+            records = select_and_rename_cols(
+                records,
+                self.tcx_records_selector,
+                self.tcx_records_mapper,
+            )
+            records.rename_axis("time", inplace=True)
+            laps = select_and_rename_cols(
+                laps,
+                self.tcx_laps_selector,
+                self.tcx_laps_mapper,
+            )
+
+        elif ext_normalized == "gpx":
+            records, laps, extra = parse_gpx(file, strict_xml=self.strict_xml)
+            records = select_and_rename_cols(
+                records,
+                self.gpx_records_selector,
+                self.gpx_records_mapper,
+            )
+            records.rename_axis("time", inplace=True)
+            # Note GPX files have no lap information
+
+        else:
+            raise ValueError(f"File type not supported: {ext_normalized}")
+
+        return records, laps, extra