downsampler 0.1.0__tar.gz → 0.3.0__tar.gz

downsampler-0.3.0/PKG-INFO

@@ -0,0 +1,335 @@
+Metadata-Version: 2.4
+Name: downsampler
+Version: 0.3.0
+Summary: Timeseries DataFrame downsampling with LTTB, aggregation methods, gap handling, and fidelity testing
+Author-email: Eelco Doornbos <eelco.doornbos@knmi.nl>
+License-Expression: MIT
+Project-URL: Homepage, https://gitlab.com/KNMI-OSS/spaceweather/libs/downsampler
+Project-URL: Repository, https://gitlab.com/KNMI-OSS/spaceweather/libs/downsampler
+Keywords: timeseries,downsampling,lttb,pandas,visualization
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=2.0
+Requires-Dist: pandas>=1.3
+Requires-Dist: lttbc>=0.3
+Requires-Dist: scipy>=1.7
+Requires-Dist: requests>=2.32.5
+Dynamic: license-file
+
+# downsampler
+
+[![PyPI](https://img.shields.io/pypi/v/downsampler)](https://pypi.org/project/downsampler/)
+[![Python](https://img.shields.io/pypi/pyversions/downsampler)](https://pypi.org/project/downsampler/)
+[![License](https://img.shields.io/pypi/l/downsampler)](https://opensource.org/licenses/MIT)
+
+A Python package for time series DataFrame downsampling with LTTB, M4, multiple aggregation methods, gap handling, and fidelity testing.
+
+## Features
+
+- **Multiple downsampling methods**:
+  - LTTB (visual fidelity)
+  - M4 (guaranteed extrema preservation)
+  - Traditional aggregations (mean, median, min, max)
+- **Gap-aware processing**: Automatically detects and handles gaps in time series
+- **Edge handling**: Flag, discard, or keep edge points
+- **Multi-aggregate output**: Generate min/mean/max columns in a single call
+- **Range-based downsampling**: Fetch data from external sources with automatic edge buffering
+- **Multi-resolution pyramid**: Generate downsampled versions at multiple cadences in one call
+- **Fidelity testing**: Compare methods and measure visual accuracy
+
+## Installation
+
+```bash
+pip install downsampler
+```
+
+> **Note (Linux + Python 3.11):** the `lttbc` dependency's prebuilt cp311
+> Linux wheel was compiled against NumPy 1.x and fails to import under
+> NumPy 2 (`numpy.core.multiarray failed to import`). Force a source build:
+> `pip install --no-binary lttbc downsampler`. Other Python versions and
+> macOS have no prebuilt wheel and build from source automatically. With
+> uv, this repo's `[tool.uv] no-binary-package` setting handles it.
+
+## Quick Start
+
+### Basic Downsampling
+
+```python
+import pandas as pd
+from downsampler import downsample_dataframe
+
+# Create sample data
+df = pd.DataFrame(
+    {'temperature': range(1000)},
+    index=pd.date_range('2024-01-01', periods=1000, freq='1s')
+)
+
+# Downsample to 1-minute cadence (default: mean)
+result = downsample_dataframe(df, target_cadence='PT1M')
+```
+
+### Using Different Methods
+
+```python
+from downsampler import downsample_dataframe, DownsampleConfig, AggregationMethod
+
+# Mean (default)
+result = downsample_dataframe(df, '10min')
+
+# Maximum
+result = downsample_dataframe(df, '10min', method='max')
+
+# LTTB for visual fidelity
+config = DownsampleConfig(
+    method=AggregationMethod.LTTB,
+    lttb_target_column='temperature'
+)
+result = downsample_dataframe(df, '10min', config=config)
+
+# M4 for guaranteed extrema preservation
+result = downsample_dataframe(df, '10min', method='m4')
+
+# M4 with collinearity filtering (reduces output size)
+result = downsample_dataframe(df, '10min', method='m4', m4_collinearity_threshold=0.01)
+```
+
+### Multi-Aggregate Downsampling
+
+Create min/mean/max columns for visualization with error bands:
+
+```python
+from downsampler import downsample_dataframe_multi_aggregate
+
+result = downsample_dataframe_multi_aggregate(
+    df,
+    target_cadence='1min',
+    variables=['temperature', 'pressure'],
+    aggregations=['min', 'mean', 'max']
+)
+# Result has columns: temperature_min, temperature_mean, temperature_max, etc.
+```
+
+### Multi-Resolution Pyramid
+
+Generate downsampled versions at multiple cadences for storage:
+
+```python
+from downsampler import downsample_dataframe_resolutions
+
+results = downsample_dataframe_resolutions(
+    df,
+    cadences=['1min', '5min', '15min', '1h'],
+)
+# Returns {Timedelta('0 days 00:01:00'): DataFrame, ...}
+
+for cadence, result_df in results.items():
+    print(f"{cadence}: {len(result_df)} points")
+```
+
+### M4 Downsampling (Extrema Preservation)
+
+M4 guarantees exact preservation of minimum and maximum values, making it ideal for monitoring dashboards and alerting systems:
+
+```python
+from downsampler import downsample_dataframe
+
+# Basic M4 - preserves exact min/max
+result = downsample_dataframe(df, '1min', method='m4')
+
+# Verify extrema preservation
+assert df['temperature'].min() == result['temperature'].min()
+assert df['temperature'].max() == result['temperature'].max()
+
+# M4 with deduplication (default, removes consecutive duplicates)
+result = downsample_dataframe(df, '1min', method='m4', m4_deduplicate=True)
+
+# M4 with collinearity filtering (reduces size on smooth data)
+result = downsample_dataframe(df, '1min', method='m4', m4_collinearity_threshold=0.01)
+```
+
+**M4 Features:**
+- Selects up to 4 points per bucket: first, last, min, max
+- **Guaranteed** exact extrema preservation (no approximation)
+- Variable output size (typically 2-4x reduction vs 10x for traditional methods)
+- Deduplication: removes consecutive duplicates (20-50% reduction)
+- Collinearity filtering: removes min/max points near first-last line (0-75% reduction)
+- Superior peak detection compared to LTTB
+
+**When to use M4:**
+- Monitoring dashboards where missing a spike could be critical
+- Alerting systems that need exact threshold crossings
+- Pre-computing multiple cadences with controllable size/fidelity trade-offs
+- Multi-variable sensor data where each variable's extrema matter
+
+### Handling Gaps
+
+```python
+from downsampler import DownsampleConfig
+
+config = DownsampleConfig(
+    gap_threshold='5min'  # Gaps > 5 min trigger segmentation
+)
+result = downsample_dataframe(df, '1min', config=config)
+```
+
+### Range-Based Downsampling
+
+For data that needs to be fetched from an external source:
+
+```python
+from downsampler import downsample_range
+
+def fetch_from_api(start, end):
+    # Your data fetching logic here
+    return pd.DataFrame(...)
+
+# Single fetch with automatic edge buffering
+result = downsample_range(
+    fetcher=fetch_from_api,
+    output_start=pd.Timestamp('2024-01-01'),
+    output_end=pd.Timestamp('2024-01-02'),
+    target_cadence='1H'
+)
+
+# Batched mode for large ranges
+result = downsample_range(
+    fetcher=fetch_from_api,
+    output_start=pd.Timestamp('2024-01-01'),
+    output_end=pd.Timestamp('2024-02-01'),
+    target_cadence='1H',
+    batch_size='P1D'  # Process one day at a time
+)
+```
+
+### Fidelity Comparison
+
+Compare different methods to find the best one for your data:
+
+```python
+from downsampler.fidelity import FidelityComparison, summary_table
+
+comp = FidelityComparison(original_df, 'signal')
+results = comp.compare('10s', store_downsampled=True)
+
+print(summary_table(results))
+# See examples/fidelity_comparison.py (marimo notebook) for interactive visualization
+```
+
+## Configuration Options
+
+### DownsampleConfig
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `method` | AggregationMethod | MEAN | Downsampling method |
+| `lttb_target_column` | str | None | Column to optimize for LTTB |
+| `m4_deduplicate` | bool | True | For M4: remove consecutive duplicates |
+| `m4_collinearity_threshold` | float | None | For M4: filter collinear points (0.0-1.0) |
+| `include_columns` | list[str] | [] | Columns to include (empty = all) |
+| `exclude_columns` | list[str] | [] | Columns to exclude |
+| `gap_threshold` | str/Timedelta | "auto" | Min duration for gaps |
+| `edge_handling` | EdgeHandling | KEEP | How to handle edges |
+| `edge_window` | int | 2 | Points at each edge |
+| `min_points_per_segment` | int | 1 | Min points per segment; smaller segments are dropped |
+| `min_completeness` | float | 0.9 | Min fraction of expected points per bucket |
+| `source_cadence` | str/Timedelta | None | Source data cadence (estimated if None) |
+
+### Aggregation Methods
+
+- `MEAN`: Arithmetic mean (best for general use)
+- `MEDIAN`: Median (robust to outliers)
+- `MIN`: Minimum value (preserves lows)
+- `MAX`: Maximum value (preserves highs)
+- `LTTB`: Largest Triangle Three Buckets (best visual fidelity)
+- `M4`: Min-Max-First-Last (guaranteed extrema preservation, best for monitoring/alerting)
+
+### Edge Handling
+
+- `KEEP`: Keep edge points as-is (default)
+- `FLAG`: Add `_is_edge` column
+- `DISCARD`: Remove edge points
+
+## Examples
+
+See the `examples/` directory for complete examples:
+
+- `basic_downsampling.py`: Core downsampling features
+- `multi_aggregate.py`: Creating min/mean/max columns
+- `range_downsample.py`: Range-based downsampling with automatic edge buffering
+- `fidelity_comparison.py`: Interactive fidelity comparison (marimo notebook)
+
+### Running the fidelity comparison notebook
+
+**Option 1 — Project install via uv** (best for development):
+
+```bash
+uv run --extra dev marimo edit examples/fidelity_comparison.py
+```
+
+**Option 2 — Marimo sandbox** (self-contained, uses inline PEP 723 metadata):
+
+```bash
+marimo edit --sandbox examples/fidelity_comparison.py
+```
+
+## API Reference
+
+### DataFrame-Mode Functions
+
+```python
+downsample_dataframe(df, target_cadence, config=None, **kwargs) -> DataFrame
+downsample_dataframe_multi_aggregate(df, target_cadence, variables, aggregations, ...) -> DataFrame
+downsample_dataframe_resolutions(df, cadences, config=None, **kwargs) -> dict[Timedelta, DataFrame]
+```
+
+### Range-Mode Functions
+
+```python
+downsample_range(fetcher, output_start, output_end, target_cadence, config=None, batch_size=None, ...) -> DataFrame
+downsample_range_multi_aggregate(fetcher, output_start, output_end, target_cadence, variables, ...) -> DataFrame
+downsample_range_resolutions(fetcher, output_start, output_end, cadences, config=None, ...) -> dict[Timedelta, DataFrame]
+```
+
+### Low-Level Functions
+
+```python
+downsample_lttb(df, target_column, target_cadence, ...) -> DataFrame
+downsample_m4(df, target_cadence, deduplicate=True, collinearity_threshold=None, ...) -> DataFrame
+downsample_mean(df, target_cadence, ...) -> DataFrame
+downsample_median(df, target_cadence, ...) -> DataFrame
+downsample_min(df, target_cadence, ...) -> DataFrame
+downsample_max(df, target_cadence, ...) -> DataFrame
+```
+
+### Gap Functions
+
+```python
+find_gap_indices(df, timedelta_max_gap) -> Series
+groupby_gaps(df, timedelta_max_gap) -> DataFrameGroupBy
+split_at_gaps(df, timedelta_max_gap) -> list[DataFrame]
+mark_gaps_in_dataframe(df, nominal_timedelta, ...) -> DataFrame
+```
+
+### Fidelity Functions
+
+```python
+compute_metrics(original, downsampled, column) -> FidelityMetrics
+FidelityComparison(original_df, column).compare(cadences, methods, ...) -> list[ComparisonResult]
+summary_table(results) -> DataFrame
+```
+
+## License
+
+MIT License - see LICENSE file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit issues and pull requests.

downsampler-0.3.0/README.md

@@ -0,0 +1,309 @@
+# downsampler
+
+[![PyPI](https://img.shields.io/pypi/v/downsampler)](https://pypi.org/project/downsampler/)
+[![Python](https://img.shields.io/pypi/pyversions/downsampler)](https://pypi.org/project/downsampler/)
+[![License](https://img.shields.io/pypi/l/downsampler)](https://opensource.org/licenses/MIT)
+
+A Python package for time series DataFrame downsampling with LTTB, M4, multiple aggregation methods, gap handling, and fidelity testing.
+
+## Features
+
+- **Multiple downsampling methods**:
+  - LTTB (visual fidelity)
+  - M4 (guaranteed extrema preservation)
+  - Traditional aggregations (mean, median, min, max)
+- **Gap-aware processing**: Automatically detects and handles gaps in time series
+- **Edge handling**: Flag, discard, or keep edge points
+- **Multi-aggregate output**: Generate min/mean/max columns in a single call
+- **Range-based downsampling**: Fetch data from external sources with automatic edge buffering
+- **Multi-resolution pyramid**: Generate downsampled versions at multiple cadences in one call
+- **Fidelity testing**: Compare methods and measure visual accuracy
+
+## Installation
+
+```bash
+pip install downsampler
+```
+
+> **Note (Linux + Python 3.11):** the `lttbc` dependency's prebuilt cp311
+> Linux wheel was compiled against NumPy 1.x and fails to import under
+> NumPy 2 (`numpy.core.multiarray failed to import`). Force a source build:
+> `pip install --no-binary lttbc downsampler`. Other Python versions and
+> macOS have no prebuilt wheel and build from source automatically. With
+> uv, this repo's `[tool.uv] no-binary-package` setting handles it.
+
+## Quick Start
+
+### Basic Downsampling
+
+```python
+import pandas as pd
+from downsampler import downsample_dataframe
+
+# Create sample data
+df = pd.DataFrame(
+    {'temperature': range(1000)},
+    index=pd.date_range('2024-01-01', periods=1000, freq='1s')
+)
+
+# Downsample to 1-minute cadence (default: mean)
+result = downsample_dataframe(df, target_cadence='PT1M')
+```
+
+### Using Different Methods
+
+```python
+from downsampler import downsample_dataframe, DownsampleConfig, AggregationMethod
+
+# Mean (default)
+result = downsample_dataframe(df, '10min')
+
+# Maximum
+result = downsample_dataframe(df, '10min', method='max')
+
+# LTTB for visual fidelity
+config = DownsampleConfig(
+    method=AggregationMethod.LTTB,
+    lttb_target_column='temperature'
+)
+result = downsample_dataframe(df, '10min', config=config)
+
+# M4 for guaranteed extrema preservation
+result = downsample_dataframe(df, '10min', method='m4')
+
+# M4 with collinearity filtering (reduces output size)
+result = downsample_dataframe(df, '10min', method='m4', m4_collinearity_threshold=0.01)
+```
+
+### Multi-Aggregate Downsampling
+
+Create min/mean/max columns for visualization with error bands:
+
+```python
+from downsampler import downsample_dataframe_multi_aggregate
+
+result = downsample_dataframe_multi_aggregate(
+    df,
+    target_cadence='1min',
+    variables=['temperature', 'pressure'],
+    aggregations=['min', 'mean', 'max']
+)
+# Result has columns: temperature_min, temperature_mean, temperature_max, etc.
+```
+
+### Multi-Resolution Pyramid
+
+Generate downsampled versions at multiple cadences for storage:
+
+```python
+from downsampler import downsample_dataframe_resolutions
+
+results = downsample_dataframe_resolutions(
+    df,
+    cadences=['1min', '5min', '15min', '1h'],
+)
+# Returns {Timedelta('0 days 00:01:00'): DataFrame, ...}
+
+for cadence, result_df in results.items():
+    print(f"{cadence}: {len(result_df)} points")
+```
+
+### M4 Downsampling (Extrema Preservation)
+
+M4 guarantees exact preservation of minimum and maximum values, making it ideal for monitoring dashboards and alerting systems:
+
+```python
+from downsampler import downsample_dataframe
+
+# Basic M4 - preserves exact min/max
+result = downsample_dataframe(df, '1min', method='m4')
+
+# Verify extrema preservation
+assert df['temperature'].min() == result['temperature'].min()
+assert df['temperature'].max() == result['temperature'].max()
+
+# M4 with deduplication (default, removes consecutive duplicates)
+result = downsample_dataframe(df, '1min', method='m4', m4_deduplicate=True)
+
+# M4 with collinearity filtering (reduces size on smooth data)
+result = downsample_dataframe(df, '1min', method='m4', m4_collinearity_threshold=0.01)
+```
+
+**M4 Features:**
+- Selects up to 4 points per bucket: first, last, min, max
+- **Guaranteed** exact extrema preservation (no approximation)
+- Variable output size (typically 2-4x reduction vs 10x for traditional methods)
+- Deduplication: removes consecutive duplicates (20-50% reduction)
+- Collinearity filtering: removes min/max points near first-last line (0-75% reduction)
+- Superior peak detection compared to LTTB
+
+**When to use M4:**
+- Monitoring dashboards where missing a spike could be critical
+- Alerting systems that need exact threshold crossings
+- Pre-computing multiple cadences with controllable size/fidelity trade-offs
+- Multi-variable sensor data where each variable's extrema matter
+
+### Handling Gaps
+
+```python
+from downsampler import DownsampleConfig
+
+config = DownsampleConfig(
+    gap_threshold='5min'  # Gaps > 5 min trigger segmentation
+)
+result = downsample_dataframe(df, '1min', config=config)
+```
+
+### Range-Based Downsampling
+
+For data that needs to be fetched from an external source:
+
+```python
+from downsampler import downsample_range
+
+def fetch_from_api(start, end):
+    # Your data fetching logic here
+    return pd.DataFrame(...)
+
+# Single fetch with automatic edge buffering
+result = downsample_range(
+    fetcher=fetch_from_api,
+    output_start=pd.Timestamp('2024-01-01'),
+    output_end=pd.Timestamp('2024-01-02'),
+    target_cadence='1H'
+)
+
+# Batched mode for large ranges
+result = downsample_range(
+    fetcher=fetch_from_api,
+    output_start=pd.Timestamp('2024-01-01'),
+    output_end=pd.Timestamp('2024-02-01'),
+    target_cadence='1H',
+    batch_size='P1D'  # Process one day at a time
+)
+```
+
+### Fidelity Comparison
+
+Compare different methods to find the best one for your data:
+
+```python
+from downsampler.fidelity import FidelityComparison, summary_table
+
+comp = FidelityComparison(original_df, 'signal')
+results = comp.compare('10s', store_downsampled=True)
+
+print(summary_table(results))
+# See examples/fidelity_comparison.py (marimo notebook) for interactive visualization
+```
+
+## Configuration Options
+
+### DownsampleConfig
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `method` | AggregationMethod | MEAN | Downsampling method |
+| `lttb_target_column` | str | None | Column to optimize for LTTB |
+| `m4_deduplicate` | bool | True | For M4: remove consecutive duplicates |
+| `m4_collinearity_threshold` | float | None | For M4: filter collinear points (0.0-1.0) |
+| `include_columns` | list[str] | [] | Columns to include (empty = all) |
+| `exclude_columns` | list[str] | [] | Columns to exclude |
+| `gap_threshold` | str/Timedelta | "auto" | Min duration for gaps |
+| `edge_handling` | EdgeHandling | KEEP | How to handle edges |
+| `edge_window` | int | 2 | Points at each edge |
+| `min_points_per_segment` | int | 1 | Min points per segment; smaller segments are dropped |
+| `min_completeness` | float | 0.9 | Min fraction of expected points per bucket |
+| `source_cadence` | str/Timedelta | None | Source data cadence (estimated if None) |
+
+### Aggregation Methods
+
+- `MEAN`: Arithmetic mean (best for general use)
+- `MEDIAN`: Median (robust to outliers)
+- `MIN`: Minimum value (preserves lows)
+- `MAX`: Maximum value (preserves highs)
+- `LTTB`: Largest Triangle Three Buckets (best visual fidelity)
+- `M4`: Min-Max-First-Last (guaranteed extrema preservation, best for monitoring/alerting)
+
+### Edge Handling
+
+- `KEEP`: Keep edge points as-is (default)
+- `FLAG`: Add `_is_edge` column
+- `DISCARD`: Remove edge points
+
+## Examples
+
+See the `examples/` directory for complete examples:
+
+- `basic_downsampling.py`: Core downsampling features
+- `multi_aggregate.py`: Creating min/mean/max columns
+- `range_downsample.py`: Range-based downsampling with automatic edge buffering
+- `fidelity_comparison.py`: Interactive fidelity comparison (marimo notebook)
+
+### Running the fidelity comparison notebook
+
+**Option 1 — Project install via uv** (best for development):
+
+```bash
+uv run --extra dev marimo edit examples/fidelity_comparison.py
+```
+
+**Option 2 — Marimo sandbox** (self-contained, uses inline PEP 723 metadata):
+
+```bash
+marimo edit --sandbox examples/fidelity_comparison.py
+```
+
+## API Reference
+
+### DataFrame-Mode Functions
+
+```python
+downsample_dataframe(df, target_cadence, config=None, **kwargs) -> DataFrame
+downsample_dataframe_multi_aggregate(df, target_cadence, variables, aggregations, ...) -> DataFrame
+downsample_dataframe_resolutions(df, cadences, config=None, **kwargs) -> dict[Timedelta, DataFrame]
+```
+
+### Range-Mode Functions
+
+```python
+downsample_range(fetcher, output_start, output_end, target_cadence, config=None, batch_size=None, ...) -> DataFrame
+downsample_range_multi_aggregate(fetcher, output_start, output_end, target_cadence, variables, ...) -> DataFrame
+downsample_range_resolutions(fetcher, output_start, output_end, cadences, config=None, ...) -> dict[Timedelta, DataFrame]
+```
+
+### Low-Level Functions
+
+```python
+downsample_lttb(df, target_column, target_cadence, ...) -> DataFrame
+downsample_m4(df, target_cadence, deduplicate=True, collinearity_threshold=None, ...) -> DataFrame
+downsample_mean(df, target_cadence, ...) -> DataFrame
+downsample_median(df, target_cadence, ...) -> DataFrame
+downsample_min(df, target_cadence, ...) -> DataFrame
+downsample_max(df, target_cadence, ...) -> DataFrame
+```
+
+### Gap Functions
+
+```python
+find_gap_indices(df, timedelta_max_gap) -> Series
+groupby_gaps(df, timedelta_max_gap) -> DataFrameGroupBy
+split_at_gaps(df, timedelta_max_gap) -> list[DataFrame]
+mark_gaps_in_dataframe(df, nominal_timedelta, ...) -> DataFrame
+```
+
+### Fidelity Functions
+
+```python
+compute_metrics(original, downsampled, column) -> FidelityMetrics
+FidelityComparison(original_df, column).compare(cadences, methods, ...) -> list[ComparisonResult]
+summary_table(results) -> DataFrame
+```
+
+## License
+
+MIT License - see LICENSE file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit issues and pull requests.

{downsampler-0.1.0 → downsampler-0.3.0}/pyproject.toml

@@ -4,11 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "downsampler"
-version = "0.1.0"
+version = "0.3.0"
 description = "Timeseries DataFrame downsampling with LTTB, aggregation methods, gap handling, and fidelity testing"
 readme = "README.md"
-license = {text = "MIT"}
-requires-python = ">=3.10"
+license = "MIT"
+requires-python = ">=3.11"
 authors = [
     {name = "Eelco Doornbos", email = "eelco.doornbos@knmi.nl"}
 ]
@@ -16,28 +16,36 @@ keywords = ["timeseries", "downsampling", "lttb", "pandas", "visualization"]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering",
 ]
 dependencies = [
-    "numpy>=1.20",
+    "numpy>=2.0",
     "pandas>=1.3",
-    "lttb>=0.3",
+    "lttbc>=0.3",
     "scipy>=1.7",
+    "requests>=2.32.5",
 ]
 
-[project.optional-dependencies]
-viz = ["matplotlib>=3.5", "altair>=5.0"]
+[dependency-groups]
 test = ["pytest>=7.0", "pytest-cov>=4.0"]
-dev = ["downsampler[viz,test]"]
+dev = [{include-group = "test"}, "marimo"]
 
 [project.urls]
-Homepage = "https://gitlab.com/KNMI-OSS/spaceweather/downsampler"
-Repository = "https://gitlab.com/KNMI-OSS/spaceweather/downsampler"
+Homepage = "https://gitlab.com/KNMI-OSS/spaceweather/libs/downsampler"
+Repository = "https://gitlab.com/KNMI-OSS/spaceweather/libs/downsampler"
+
+[tool.uv]
+# lttbc's prebuilt cp311 Linux wheel was compiled against NumPy 1.x and
+# crashes on import under NumPy 2 ("numpy.core.multiarray failed to
+# import"). Building from source compiles it against the installed NumPy.
+# Other Python versions ship no Linux wheel and always build from source.
+# Same workaround as in spaceweather-data-pipelines; drop when lttbc
+# publishes NumPy-2 wheels.
+no-binary-package = ["lttbc"]
 
 [tool.setuptools.packages.find]
 where = ["src"]