Code Monkey home page Code Monkey logo

breast_cancer_diagnosis's Introduction

breast_cancer_diagnosis

Python Lint

Python implementation to the paper "Evaluation of computationally intelligent techniques for breast cancer diagnosis" published on Neural Computing and Aplications journal (2021).

Install

  • Install pipenv
  • Install dependencies using pipenv: pipenv install --skip-lock (it is important to always use the flag --skip-lock because pipenv has a problem which can take a lot of time to install if not used)
  • To access the virtual environment created, run pipenv shell, now all commands which you run will be performed into virtual enviroment created
  • Activate pre-commit hooks to use black formatter, flake8 lint and Isort references. Run pre-commit install. Now every time you make a commit, black formatter, flake8 and isort will make tests to verify if your code is following the patterns (you can adapt your IDE or text editor to follow this patterns, e.g. vs code)

Dataset

  • Instructions to download the dataset

Training ML models

  • Instructions to execute the training of ML models

Running

  • Inside the virtual environment, execute the test server using python SCRIPT_NAME_HERE

Slides

  • Run: pipenv shell;

  • Than run: jupyter notebook;

  • Open the slide/slide.ipynb;

  • Click on Enter/Exit Live Reveal Slideshow or type Alt-r

  • You can execute the conde on the slides by typing: shift-enter

To read more about the slides read the documentation at: https://rise.readthedocs.io/en/stable/

breast_cancer_diagnosis's People

Contributors

aaneto avatar cleversonahum avatar felipebastosb avatar rodgdutra avatar

Stargazers

 avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

breast_cancer_diagnosis's Issues

Calculate confusion matrix on entire dataset

Paper calculates the confusion matrix over the entire dataset (see section 6.1), I don't think it's correct, but let's implement it as they did since our goal is to reimplement the code. It is important to define the variables TP, FP, TN and FN (vide section 4) since they are used as basis to calculate the metrics defined in 4.1-4.9. Besides the definition of variables, it should show a table with the confusion matrix values.

Create ROC curve

Plot ROC curve as defined in paper section 4.9. It should be similar to figure 18 and 19. Depends on issues #5 and #6 .

ID atribute presence at training set

Paper seems to be using ID attribute in the dataset to train AI agents, but it does not make sense since ID is only a sequence. So we need to check if they really use it or just forgot to inform in their paper, based on our results.

Generate graphs for figures 16 and 17

Use the metric values obtained for each classifier type and generate plots similar to figures 16 and 17. Remember that you should generate an adaptative code that works with many classifiers without require code modifications.

Calculate performance metrics

Calculate performance metrics defined in the paper from sections 4.1-4.8 (does not include the ROC curve). Depends on issue #5 .

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.