Introduction about semanticClimate tools

The #semanticClimate tools provides an innovative approach to manage climate data efficiently. This page provides an overview of these tools and their practical applications in semantifying the climate reports and data.

Requirements for Installing Tools with pip :

• Python : Ensure that Python is installed on your system. Download python from here and select the option Add Python to Path while installing.

• pip : pip is the package installer for Python. Verify that pip is installed by running: pip --version

amilib

Release Category: Beta

Developed By: Peter Murray-Rust

amilib has tools for finding, cleaning, converting, searching, republishing legacy documents (PDF, PNG, etc.).

It is a Python library designed for document processing, and dictionary creation.

We can create dictionaries using amilib from existing set of words. The library simplifies data extraction and manipulation, offering a user-friendly interface for processing data formats like HTML and XML. It ensures that complex operations like term marking and dictionary building can be performed with minimal coding effort.

• Installation - Use pip to install the tool/package. Use this code pip install amilib to install latest amilib version.

Check the successful installation with command : amilib --help. You should see a help message come up.

• Code Repository - github

• Tutorials (Jupyter Notebook/ Colab Notebook)

  • Creating Wikimedia enhanced dictionary with amilib from wordlist

  • Creating JQuery Datatables from the retrieved articles

CLICK HERE for more tutorials

amiclimate

Release Category: Alpha

Developed By: Peter Murray-Rust

amiclimate is a NLP and semantic software and material for managing climate knowledge.

It is a Python code for accessing and transforming key climate documents. A refactoring of the (bloated) pyamihtml repository and has the functionality for downloading and parsing

1. IPCC reports
2. IPCC glossary
3. UNFCCC reports (COP, etc.)

This repository will NOT have the complete IPCC or UNFCCC corpus , but will have small exemplars.

• Code Repository - github

• README file for amiclimate : amiclimate/README.md

pyamiimage

Release Category: Alpha

Developed By: Peter Murray-Rust

pyamiimage is a set of tools to extract semantic information from scientific diagrams.

The output of pyamiimage is an image with annotations of substrate, products and enzymes.

• Installation - Use the code pip install pyamiimage to install pyamiimage

• Code Repository - github

• README file of pyamiimage : pyamiimage/README.md

pygetpapers

Release Category: Production

Developed By: Ayush Garg

pygetpapers is a tool to assist text miners. It makes requests to open access scientific text repositories, analyses the hits, and systematically downloads the articles without further interaction.

It has been developed by Ayush Garg under the guidance of the OpenVirus community and Peter Murray Rust and Rik Smith-Unna funded by ContentMine.

It comes with the packages pygetpapers and download tools which provide various functions to download, process and save research papers and their metadata.

We use pygetpapers for querying current and past scholarly literature in bulk.

• Installation - Use the code pip install pygetpapers to install pygetpapers

Check the successful installation with command : pygetpapers --help. You should see a help message come up.

• Code Repository - github

• README file of pygetpapers : pygetpapers/README.md

• Tutorials (Jupyter Notebook/ Colab Notebook and video demo)

  • descriptive demo of the literature search with pygetpapers

  • literature search: Google colab notebook

  • Creating JQuery Datatables from the retrieved articles

docanalysis

Release Category: Production

Developed By: Shweata N. Hegde

docanalysis is a command-line tool that processes document collections (CProjects) and performs text analysis.

It can:

1. Divide documents into sections
2. Perform text mining and natural language processing (NLP)
3. Generate dictionaries of terms

It uses custom code along with Python tools like NLTK, and it can use spaCy or scispaCy for extracting and annotating entities. The tool creates summary data and word lists as output.

• Installation - Use the code pip install docanalysis to install docanalysis

Check the successful installation with command : docanalysis --help. You should see a help message come up.

• Code Repository - github

• README file of docanalysis : docanalysis/README.md

• Tutorials (Jupyter Notebook/ Colab Notebook)

  • google colab notebook

  • Search for specific terms using dictionaries

← Back