Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/carlos1971salud/predicci-n-del-dengue

https://github.com/carlos1971salud/predicci-n-del-dengue

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Carlos1971Salud
  • Language: Jupyter Notebook
  • Default Branch: master
  • Size: 1.47 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 11 months ago · Last pushed 11 months ago
Metadata Files
Readme

README.txt 

Introduction:
DengAI is a machine learning project with the goal of predicting the spread of Dengue fever across the globe. Specifically, the aim of the project is to predict the next pandemic of the disease before it occurs in San Juan, Puerto Rico or Iquitos, Peru. Dengue fever is primarily transmitted through mosquitos carrying the disease, and it is therefore highly dependent on climate and vegetation factors.

Setup:
Language used : Python 
Put the *.ipynb inside your anaconda workspace and open this file.

Data set: [Dengue Data](https://github.com/dhwanikaneria/DenguePrediction/tree/master/Data)

Feature Engineering:
It is the process to make Algorithms of Machine Learning efficient by introducing new features to the dataset or transforming our features.
From observing the dataset, we found that cases recorded for a given week are not the result of that week but of the previous week. The most likely reason for this is that the incubation period is 4-7 days. Therefore the infection in the given week is directly related to previous week.
To apply this on the dataset, we shifted data by one week. We experimented with shifting data by 1 week, 2 weeks, and 3 weeks to get an idea regarding how the data pattern is effected by time period.


Model Training and Validation:
We are using below Performance metrics.
Mean Absolute Error: MAE measures the average magnitude of the errors in a set of predictions, without considering their direction.

Owner

  • Login: Carlos1971Salud
  • Kind: user

GitHub Events

Total
  • Create event: 2
Last Year
  • Create event: 2