# Medical Sound Classification Challenge — Data

来源：https://www.kaggle.com/competitions/airs-ai-in-respiratory-sounds/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset contains three type of data for each individual. The data is identified using candidateID assigned to each person. The sounds can be mapped using this candidateID. The sound and embedding files are present in the directory of given candidateID

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sounds/{candidateID}** - the directory corresponding to the person having the candidateID. Each directory contains four different files.
   *   **cough.wav** - recording of cough sound containing at least 3 cough bouts, where maximium length of recording is 15 secs.
   *   **vowel.wav** - recording of chanting of vowel O sound where maximum length of recording is 6 secs.
   *   **emb_cough.json** - list of embeddings of size 512 of first four cough bouts in cough.wav
   *   **emb_vowel.json** - list of embeddings of size 512 of vowel sound containing only one embedding of sound from 2 sec to 4 sec interval in vowel.wav

## Columns

*   `candidateID` - Mapping of the person to sound recordings, embeddings, disease and other physiological/demographical information provided in the table.
*   `age` - Age of the person. It is an *integer* number in between 18 and 80
*   `gender` - Gender of the person. A *Boolean* output
*   `tbContactHistory` - Any neighboring or co-living family/friend/co-worker had TB or not. A *boolean* output
*   `wheezingHistory` - History of wheezing or not. A *Boolean* output
*   `phlegmCough` - the person produce phlegm with cough or not. A *Boolean* output
*   `familyAsthmaHistory` - Any history of Asthma in the family or not. A *Boolean* output.
*   `feverHistory` - history of fever/weight loss >3kg/decreased appetite in last one month from the time of recording. a  *Boolean* output.
*   `coldPresent` - cold present at the time of recording or not. A *Boolean* output
*   `packYears` - Number of cigarette packs smoked by the person in his entire lifetime. *Integer* number between 0 to 800
*   `disease` - label of disease of the person. It includes **three labels**, two if diseased classes and one of healthy individuals. *Integer* value denoting one class and this is our **target** variable.

The participant of this competition is free to use any or all files provided in the data to predict the label of the disease.