Context

Pump-it-up project Can you predict which water pumps are faulty? Goal Using data from Taarifa and the Tanzanian Ministry of Water, predict which pumps are functional, which need some repairs, and which don't work at all based on a number of variables about what kind of pump is operating, when it was installed, and how it is managed.

A smart understanding of which waterpoints will fail can improve maintenance operations and ensure that clean, potable water is available to communities across Tanzania.

Taarifa is an open source platform for the crowd sourced reporting and triaging of infrastructure related issues.

This competition is held on DrivenData, it is open until June 28, 2020, 11:59 p.m.

Content

This dataset includes the following files:

• SubmissionFormat.csv (the format in which the submission to the competition on DriveData is possible)
• X_test_raw.csv (predictors for the test set from the competition on DrivenData)
• X_train_raw.csv (predictors for train set from the competition on DrivenData)
• y_train_raw.csv (input labels for train set from the competition on DrivenData)
• train_df_after_EDA.csv (dataframe of the train set (labels and predictors together) after performing an EDA)
• train_df_final.csv (dataframe of the train set (labels and predictors together) after performing data cleaning and preprocessing step)
• X_test_after_EDA.csv (dataframe of the test set (predictors) after performing an EDA)
• X_test_final.csv (dataframe of the test set (predictors) after performing data cleaning and preprocessing step)