Skip to main content

Tools to analyse climate data for machine learning and event analysis

Project description

climpy

logo

Climpy is working to help climate researchers to analyse climate data, write in formats ready to be used with machine learning models and analyse the accuracy of model predictions

https://github.com/climai/climpy/actions/workflows/python-app.yml/badge.svg

The package is divided into three parts

  • Transform: The transform module transforms by applying different conditions on your dataset. The class diagram below will detail on the application of the module.
---
Transform
---

classDiagram

Hazard <|-- Criterion

class Condition{
    args
    returns_event
    func()
}

class Criterion{
    sequence
    apply_conditions()
    valid_conditions(sequence) bool
}

class Hazard{

    event_locations
    n_events
    apply_conditions()
    valid_conditions()
    get_event(n) Event
    all_events() EventList
}

class DataArray{
    xr.DataArray variables
    xr.DataArray functions()
}

class LinkDataHazard{
    on_events()
    get_values()
}

class Event{
    data
    location
    start_time
    end_time
    
    r
    tau

    set_intensity()
}

class EventList{
    event_list
}

DataArray -- LinkDataHazard
LinkDataHazard -- Hazard
Hazard *-- EventList
EventList *--Event
Condition .. Criterion
Condition .. Hazard
  • ml_data: The ml_data module creates/writes data to be used conveniently for different kinds of machine learning models. The class diagram below will detail on the application of the module.
---
Data ML
---
classDiagram


List *-- DataArray

class X{
    values
    meta
}

class Y{
    values
    meta
}

class MLData{
    X
    Y
    tvt_split()
}


class DataArray{
    xr.DataArray variables
    xr.DataArray functions()
}

class Split
  • Metrics: The metrics module can be applied to observed and simulated variables. This would include exhaustive set of different metrics that can be used on climate related data

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

climpy-0.0.3-py3-none-any.whl (10.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page