# Additional_Datathon'23 — Data

来源：https://www.kaggle.com/competitions/additionaldatathon23/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set


## About Dataset
The given dataset contains few contaminations of the water resources from various states of India. 
<br>

## Columns
 <p>
* STATION CODE - The id of the station where the data is collected <br>
* LOCATIONS - Place <br>
* STATE - State to which the location belongs <br>
* TEMP - Temperature of water at the time of measuring 
* DO - Dissolved Oxygen in water <br>
* PH - Acid-base level in water <br>
* CONDUCTIVITY - Salinity of water <br>
* BOD - Biochemical oxygen on demand <br>
* NITRATE - Nitrate and nitrite contamination <br>
* FECAL - livestock fecal matter presence <br>
* Row_Id - index of the observation <br>
</p>

## Literature
The parameters given in the dataset are actual Laboratory test scores of the water sample. However, these values of each parameter has to be converted to index values in accordance with standard metric given by World Health Organization. The range for conversion is given below. Derive a suitability percentage accordingly. 
\``
```
DO
X>6, value=100
5 to 6, value=80
4 to 5, value=60
3 to 4, value=40
Otherwise, value=0

PH
7 to 8.5, value=100
8.5 to 8.6 or 6.8 to 6.9, value=80
8.6 to 8.8 or 6.7 to 6.8, value=60
8.8 to 9 or 6.5 to 6.7, value=40
Otherwise, value=0

CONDUCTIVITY
0 to 75, value=100
75 to 150, value=80
150 to 225, value=60
225 to 400, value=40
Otherwise, value=0

BOD
0 to 3, value=100
3 to 6, value=80
6 to 80, value=60
80 to 125, value=40
Otherwise, value=0

NITRATE
0 to 20, value=100
20 to 50, value=80
50 to 100, value=60
100 to 200, value=40
Otherwise, value=0

FECAL
0 to 5, value=100
5 to 50, value=80
50 to 500, value=60
500 to 10000, value=40
Otherwise, value=0

Suitability% = 28.1%(DO)+ 16.5% (PH)+ 28.1%(CONDUCTIVITY)+ 23.4%(BOD)+ 2.8%(NITRATE)+0.9%(FECAL)
```