multi-modal-automl 0.0.1

A Python project

Brain-AutoML

An open-source Python framework for systematic review based on PRISMA : systematic-reviewpy

Chaudhari, C., Purswani, G. (2023). Stock Market Prediction Techniques Using Artificial Intelligence: A Systematic Review. In: Kumar, S., Sharma, H., Balachandran, K., Kim, J.H., Bansal, J.C. (eds) Third Congress on Intelligent Systems. CIS 2022. Lecture Notes in Networks and Systems, vol 608. Springer, Singapore. https://doi.org/10.1007/978-981-19-9225-4_17

• Introduction
• Features
• Installation
• Contribution
• Future Improvements

Introduction

The main objective of the Python framework is to automate systematic reviews to save reviewers time without creating constraints that might affect the review quality. The other objective is to create an open-source and highly customisable framework with options to use or improve any parts of the framework. python framework supports each step in the systematic review workflow and suggests using checklists provided by Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA).

Authors

The packages systematic-reviewpy and browser-automationpy are part of Research paper An open-source Python framework for systematic review based on PRISMA created by Chandravesh chaudhari, Doctoral candidate at CHRIST (Deemed to be University), Bangalore, India under supervision of Dr. Geetanjali purswani.

Features

• supported file types: ris, json, and pandas IO
• supports the complete workflow for systematic reviews.
• supports to combine multiple databases citations.
• supports searching words with boolean conditions and filter based on counts.
• browser automation using browser-automationpy
• validation of downloaded articles.
• contains natural language processing techniques such as stemming and lemmatisation for text mining.
• sorting selected research papers based on database.
• generating literature review excel or csv file.
• automatically generates analysis tables and graphs.
• automatically generates workflow diagram.
• generate the ASReview supported file for Active-learning Screening

Significance

• Saves time
• Automate monotonous tasks
• Never makes mistakes
• Provides replicable results

Installation

This project is available at PyPI. For help in installation check instructions

python3 -m pip install systematic-reviewpy  

Dependencies

Required

• rispy - A Python 3.6+ reader/writer of RIS reference files.
• pandas - A Python package that provides fast, flexible, and expressive data structures designed to make working with "relational" or "labeled" data both easy and intuitive.

Optional

• browser-automationpy
• pdftotext - Simple PDF text extraction
• PyMuPDF - PyMuPDF (current version 1.19.2) - A Python binding with support for MuPDF, a lightweight PDF, XPS, and E-book viewer, renderer, and toolkit.

Important links

• Documentation
• Quick tour
• Project maintainer (feel free to contact)
• Future Improvements
• License

Contribution

all kinds of contributions are appreciated.

• Improving readability of documentation
• Feature Request
• Reporting bugs
• Contribute code
• Asking questions in discussions

Future Improvements

• Web based GUI