filter-stations

Documentation

You can find the documentation for the project by following this link
https://filter-stations.readthedocs.io/en/latest/

Getting Started

All methods require an API key and secret, which can be obtained by contacting dsail-info@dkut.ac.ke.

AuthManager: The new secure gateway. Log in once with your credentials to automatically unlock access to all downstream data loaders
RainLoader: class is used to get our DSAIL unified weather dataset from HuggingFace (See the documentation for more information on this)
MediumForecaster: Connects to the Google Weather API to pull 1-to-10 day forecasts (both hourly and daily)
SeasonalForecaster: Connects to Open-Meteo API to pull seasonal forecasts.
The RetrieveData class is used to retrieve data from the TAHMO API endpoints.
The Kieni class is used to get weather data for stations 100km around Kieni from the central point.with water level data.

Example

from filter_stations import AuthManager, MediumForecaster, RetrieveData, SeasonalForecaster

# 1. Authenticate once securely
auth = AuthManager(email="your_email@domain.com", password="your_password")

# 2. Initialize any tool you need seamlessly
weather = MediumForecaster(auth_session=auth)
tahmo = RetrieveData(auth_session=auth)
seasonal = SeasonalForecaster(auth_session=auth)

# 3. Pull your Medium Range weather forecast data 
nyeri_forecast = weather.get_weather_api_forecast(lat=-0.41, lon=36.95, days=7)

# Seasonal Forecasting Example

# 4. See what is available
print(seasonal.list_all_models())

# 5. Pull 6 months of ECMWF AIFS and Standard IFS data simultaneously
data = seasonal.get_forecast(
    lat=-0.41,
    lon=36.95,
    models=["ecmwf_seasonal_ensemble_mean_seamless"], 
    forecast_months=6,
    daily=['temperature_2m_max',
            'temperature_2m_mean',
            'temperature_2m_min',
            'precipitation_sum',
            'rain_sum',
            'pressure_msl_min',
            'pressure_msl_mean',
            'relative_humidity_2m_min',
            'relative_humidity_2m_mean',
            'relative_humidity_2m_max',
            'dew_point_2m_max',
            'dew_point_2m_mean',
            'dew_point_2m_min',
            'surface_pressure_min',
            'surface_pressure_mean',
            'surface_pressure_max',
            'cloud_cover_min',
            'cloud_cover_mean',
            'cloud_cover_max' ]
)

# 6. View the AIFS DataFrame (first model in the list)
aifs_df = data[0]["daily_df"]
print(aifs_df)

seasonal.list_api_variables()

To get started on the module test it out on Google Colab

For earlier versions <= v0.6.2 use the link below for documentation

https://filter-stations.netlify.app/

Citations

If you use this package in your research, please cite it using the following BibTeX entry:

@misc{filter-stations,
  author = {Austin Kaburia},
  title = {filter-stations},
  year = {2024},
  publisher = {Python Package Index},
  journal = {PyPI},
  howpublished = {\url{https://pypi.org/project/filter-stations/}},
}

Metadata

Release files for filter-stations 0.8.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for filter-stations 0.8.3
File	Size	Uploaded
filter_stations-0.8.3.tar.gz	40.8 MB	Mar 27, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for filter-stations 0.8.3
File	Interpreter	ABI	Platform	Reset
filter_stations-0.8.3-py3-none-any.whl 28.0 MB Mar 27, 2026	Python 3	none	any	Details

Total release size: 68.8 MB

Release files / filter_stations-0.8.3.tar.gz

Download URL	filter_stations-0.8.3.tar.gz
Size	40.8 MB
Tags	Source
SHA-256 checksum How to use checksums	`918b537750b3d8e7ec3d3a5924848fc9ee6bafa9e0b3b3989b0c31cf528fc562`
BLAKE2b-256 checksum How to use checksums	`4297907ec537d82d30940653018e15bcf3c0232feeb837307f93f57db5e963ea`
Upload date	Mar 27, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.3`

Release files / filter_stations-0.8.3-py3-none-any.whl

Download URL	filter_stations-0.8.3-py3-none-any.whl
Size	28.0 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`5d7be30902596255b1f27d1fb2c8ffd126b8e65fd303078ac5f3e1e3ad84846d`
BLAKE2b-256 checksum How to use checksums	`9d73ea236bd4bcf04ea878409ec0a2bbdda4ef355bd7ddf2c762f8275bf29851`
Upload date	Mar 27, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.14.3`