{ "fetched_at": "2026-10-19T17:47:01Z", "source_url": "https://www.kaggle.com/competitions/ds28-water-pump-challenge/data", "pages": [ { "name": "data-description", "content": "## File Descriptions\n- `train_features.csv`: the training set features\n- `train_labels.csv`: the training set labels\n- `test_features.csv`: the test set features\n- `sample_submission.csv`: a sample submission file in the correct format\n\n## Features\nYour goal is to predict the operating condition of a waterpoint for each record in the dataset. You are provided the following set of information about the waterpoint:\n\n- `amount_tsh`: Total static head (amount water available to waterpoint)\n- `date_recorded`: The date the row was entered\n- `funder`: Who funded the well\n- `gps_height`: Altitude of the well\n- `installer`: Organization that installed the well\n- `longitude`: GPS coordinate\n- `latitude`: GPS coordinate\n- `wpt_name`: Name of the waterpoint if there is one\n- `num_private`:\n- `basin`: Geographic water basin\n- `subvillage`: Geographic location\n- `region`: Geographic location\n- `region_code`: Geographic location (coded)\n- `district_code`: Geographic location (coded)\n- `lga`: Geographic location\n- `ward`: Geographic location\n- `population`: Population around the well\n- `public_meeting`: True/False\n- `recorded_by`: Group entering this row of data\n- `scheme_management`: Who operates the waterpoint\n- `scheme_name`: Who operates the waterpoint\n- `permit`: If the waterpoint is permitted\n- `construction_year`: Year the waterpoint was constructed\n- `extraction_type`: The kind of extraction the waterpoint uses\n- `extraction_type_group`: The kind of extraction the waterpoint uses\n- `extraction_type_class`: The kind of extraction the waterpoint uses\n- `management`: How the waterpoint is managed\n- `management_group`: How the waterpoint is managed\n- `payment`: What the water costs\n- `payment_type`: What the water costs\n- `water_quality`: The quality of the water\n- `quality_group`: The quality of the water\n- `quantity`: The quantity of water\n- `quantity_group`: The quantity of water\n- `source`: The source of the water\n- `source_type`: The source of the water\n- `source_class`: The source of the water\n- `waterpoint_type`: The kind of waterpoint\n- `waterpoint_type_group`: The kind of waterpoint\n\n## Labels\nThere are three possible values:\n\n- `functional`: the waterpoint is operational and there are no repairs needed\n- `functional needs repair`: the waterpoint is operational, but needs repairs\n- `non functional`: the waterpoint is not operational", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "## Can you predict which water pumps are faulty?\n\nUsing data from Taarifa and the Tanzanian Ministry of Water, can you predict which pumps are functional, which need some repairs, and which don't work at all? Predict one of these three classes 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 water pumps will fail can improve maintenance operations and ensure that clean, potable water is available to communities across Tanzania.\n\nThis predictive modeling challenge comes from [DrivenData](https://www.drivendata.org/competitions/7/pump-it-up-data-mining-the-water-table/), an organization that helps non-profits by hosting data science competitions for social impact. The competition has open licensing: \"The data is available for use outside of DrivenData.\" We are reusing the data on Kaggle's InClass platform so we can run a weeklong challenge just for your Lambda School Data Science cohort.\n\nThe data comes from the Taarifa waterpoints dashboard, which aggregates data from the Tanzania Ministry of Water. In their own words:\n\n> Taarifa is an open-source platform for the crowd sourced reporting and triaging of infrastructure related issues. Think of it as a bug tracker for the real world which helps to engage citizens with their local government. We are currently working on an Innovation Project in Tanzania, with various partners.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:

\n
\n

The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:

\n

\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]

\n

The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.

\n

Submission Format

\n

For every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).

\n

The file should contain a header and have the following format:

\n
AuthorId,DuplicateAuthorIds
1,1
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }