{ "fetched_at": "2026-10-20T10:52:20Z", "source_url": "https://www.kaggle.com/competitions/ece657as21-asg2/data", "pages": [ { "name": "data-description", "content": "# Dataset - DKMA-Covid19-Jan-States \n*Note: this information as the same as the assignment pdf*\n\nThis dataset uses statistics on COVID-19 cases in US states in January of 2021. The original data comes from the following two sources:\n\n- John Hopkins University CSSE COVID-19: \n- US 2020 Census\n\nThe datapoints describe various information about the population and Covid pandemic situation in **50 US States** and over each day of the month of **January 2021**. Each record gives Covid information for that *day* and demographic data for the *whole state* as well. Note the demographic data is duplicated for each state since for all days since it doesn't change that quickly and is based on data from the last census. Also note that the data was combined together from multiple sources and not processed for uniform number formats and was not normalized. As far as we are aware there is no missing data, but there are certainly some states which more extreme values than others, so consideration of outliers is reasonable. All of this will be initial pre-processing you will need to carry out.\n\n### File Descriptions:\n\n- `dkmacovid_train.csv` - main training data with input features and three binary labels.\n\n- `dkmacovid_kaggletest_features.csv` - feature for a test set, with \\\"Id\\\" column for Kaggle competition.\n\n- `dkmacovid_kaggletest_labels.csv` - labels for the kaggle test set\\...oh, you don't get that one :)\n\n### Fields Descriptions: \n\n- **Day**: Date in January 2021 ranging from Jan 2 to Jan 31.\n\n- **State ID**: Arbitrary ID number for each state, based on alphabetical order. Note there are 51 states since the District of Columbia is also included.\n\n- **State**: Name of the US State.\n\n- **Lat**: Latitude for the geographic centre of the state.\n\n- **Long\\_**: Longitude for the geographic centre of the state.\n\n- **Active**: Number of active, tracked COVID-19 cases that day in that state.\n\n- **Incident\\_Rate**: see original data source\n\n- **Total\\_Test\\_Results**: see original data source\n\n- **Case\\_Fatality\\_Ratio**: see original data source\n\n- **Testing\\_Rate**: see original data source\n\n- **Resident Population 2021 Census**: see original data source\n\n- **Population Density 2021 Census**: see original data source\n\n- **Density Rank 2021 Census**: see original data source\n\n- **SexRatio**: see original data source\n\n### Label Description: \n\nEach row of this data dataset represents a particular **day** in January, 2021 in a particular **US State** and has three binary labels which are:\n\n- **`True`** if is the corresponding count went **up** from the previous day.\n\n- **`False`** if is the corresponding count went **down** from the previous day.\n\nThe three binary labels are:\n\n- **Confirmed**: Was there a daily increase in the **confirmed total cases** of COVID-19 in that state on that day?\n\n- **Deaths**: Was there a daily increase in the **number of deaths** from COVID-19 in that state on that day?\n\n- **Recovered**: Was there a daily increase in the number **of people recovered** from COVID-19 in that state on that day?\n\nNote that the labels are fairly **unbalanced**, so there are quite a few more `True` cases than there are `False` cases. **Recovered** is the most balanced, so it should be easier to train. **Deaths** is next and **Confirmed** is the least balanced.\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# Assignment Overview\n\n*Note: this information as the same as the assignment pdf*\n\n**Collaboration:** You may do your work individually or in pairs. You may collaborate with other students in the class on the right tools to use and setting up your programming environment but work on your own solution but be done by members of your group alone. Both members of the pair must sign up for a PairGroup in LEARN *and* in Crowdmark.\n\n**Hand in:** One report per person or pair, via the CROWDMARK website in PDF, or image, format. You will need to divide the PDF up into one file for each `[CM#]` question. These files can be multiple pages. Some \"questions\" in this assignment have no output so no pdf if needed. It is best to start each of `[CM#]` solution on a new page and then drag and drop each onto the relevant question in Crowdmark. You should receive an invite to Crowdmark by email. Overlap and duplicated text between questions is alright, as long as the *entire answer* for each question fully contained within that question's pdf file. Also submit the code/scripts needed to reproduce your work as a python jupyter notebook to the LEARN dropbox.\\\n**Specific objectives:**\n\n- Load the dataset and perform some data cleaning and exploratory plots to understand the dataset.\n\n- Study how to apply some of the methods discussed in class and gain experience on the use of classification algorithms: Naive Bayes, decision tree, random forests, XGBoost.\n\n**Tools:** You can use libraries available in python. You need to mention which libraries you are using, any blogs or papers you used to figure out how to carry out your calculations.\n\n## Kaggle Competition\nYou can use any method from the assignment to produce your answer submission. \nData from five states *Washington, Tennessee, Iowa, Texas, Illinois* has been held out from the `train` set and will be used for testing your trained algorithms on Kaggle and is available on LEARN (or Kaggle) as `dkmacovidkaggletestfeatures.csv`. \n\nIn this part of your report on Crowdmark you must ***enter your group name and url from kaggle***, so we can find your results. You can also report your results from your last submission to kaggle here. (We will see another score using held out data you do not have access to).", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "\nFor your **Team Name** on Kaggle please use the format `GroupX` where `X` is the group number on learn for your dropbox submission.\n\n## Submission Data Format\n\nThe data file you need to submit for evaluation on kaggle has a simple format that follows the Id's used in `dkmacovid_kaggletest_features.csv` and has three binary columns with your algorithm's predicted label. \tThe solution file shown below uses a random assignment to the labels, this serves as the benchmark prediction on kaggle for now. You will need to prepare your own csv file to upload to kaggle as a competition.\n\n| Id | Confirmed | Deaths | Recovered |\n| ---- | --------- | ------ | --------- |\n| 0 | 0 | 0 | 0 |\n| 5 | 0 | 0 | 1 |\n| 10 | 0 | 0 | 1 |\n| 15 | 0 | 0 | 1 |\n| 20 | 0 | 0 | 0 |\n| 25 | 0 | 1 | 1 |\n| 30 | 0 | 0 | 1 |\n| 35 | 1 | 0 | 1 |\n| 40 | 0 | 0 | 1 |\n| 45 | 1 | 0 | 0 |\n| 50 | 0 | 0 | 0 |\n| 55 | 0 | 0 | 1 |\n| 60 | 0 | 1 | 1 |\n| 65 | 0 | 0 | 1 |\n| 70 | 1 | 0 | 1 |\n| 75 | 1 | 0 | 0 |\n| 80 | 0 | 0 | 1 |\n| 85 | 0 | 0 | 1 |\n| 90 | 0 | 0 | 1 |\n| 95 | 0 | 0 | 0 |\n| 100 | 0 | 0 | 1 |\n| 105 | 0 | 0 | 1 |\n| 110 | 0 | 0 | 0 |\n| 115 | 0 | 1 | 1 |\n| 120 | 0 | 1 | 0 |\n| 125 | 0 | 0 | 1 |\n| 130 | 0 | 0 | 0 |\n| 135 | 1 | 0 | 1 |\n| 140 | 1 | 0 | 1 |\n| 145 | 0 | 0 | 1 |\n| 1 | 0 | 0 | 0 |\n| 6 | 1 | 1 | 0 |\n| 11 | 0 | 0 | 0 |\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }