# Drinking Water Quality Prediction — Data

来源：https://www.kaggle.com/competitions/drinking-water-quality/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Overview
The data has been split into two groups:

* **Training set (train.csv)**
* **Test set (test.csv)**

**The training set** should be used to build your machine learning models. The training set includes both the features and the result variable (`compliance_2021`).

If you succeed in building a good machine learning model, then you have created a model that enables to predict the quality of the next test based on the metrics of previous tests.

**The test set** should be used to see how well your model performs on unseen data. The test set doesn’t include the result variable. It is your job to predict it using the model you built on the training data!

We also include **sample_submission.csv** - an example of what the submission file should look like (the predictions in the sample file are picked randomly).

# Features
The features include various numeric metrics (e.g. color, smell, ph-level, coli-type bacteria) from previous water tests that are used by the inspectors to define whether the quality is compliant with the regulation. For each water station, you have information about the test results of the years 2019 and 2020. The corresponding year number is added at the end of each variable name.  In addition, you have the information about the compliance of the station in 2019 (`compliance_2019`) and 2020 (`compliance_2020`). The result variable is `compliance_2021`.

NB: There are many missing values (not all of the variables are always tested in each station). Choose your own approach of how to deal with them.