Skip to content

In this project, we will use causal inference to extract useful features that can be used in diagnosis prediction modeling.

Notifications You must be signed in to change notification settings

skevin-dev/Causal_inference-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Causal_inference-

Table of content

Project_Overview

Breast Cancer Screening Breast cancer, the most common invasive cancer in females, is the second leading cause of cancer death in women, after lung cancer.   One in every 38 women will develop breast cancer during their lifetime (2.6 percent ). The likelihood of long-term survival for a person with breast cancer increases with early detection and precise diagnosis.  In this project, we will use causal inference to extract useful features that can be used in diagnosis prediction modeling. 

installation

git clone https://github.com/skevin-dev/Causal_inference-
jupyter notebook 
pip install -r requirements.txt

data

Data can be found here

Target variables

  * Diagnosis(Malignant / benign)

Independent variables

  * the circumference (mean of distances from the center to points on the perimeter)
  * the concavity (severity of concave portions of the contour)
  * points that are concave (number of concave portions of the contour)
  * fractal dimension of symmetry (“coastline approximation” — 1)
  * the texture (standard deviation of gray-scale values)
  * Perimeter\s area
  * suppleness (local variation in radius lengths)
  * compactness (area2 / perimeter2 — 1.0)

Notebooks

All the analysis and examples of implementation can be here in the form of .ipynb file

Scripts

All the modules for the analysis can be found here

Author

👤 Shyaka Kevin

About

In this project, we will use causal inference to extract useful features that can be used in diagnosis prediction modeling.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published