# Dataset - DKMA-Covid19-Jan-States 
*Note: this information as the same as the assignment pdf*

This dataset uses statistics on COVID-19 cases in US states in January of 2021. The original data comes from the following two sources:

-   John Hopkins University CSSE COVID-19:   <https://github.com/CSSEGISandData/COVID-19/tree/master/csse_covid_19_data>
-   US 2020 Census

The 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.

### File Descriptions:

-   `dkmacovid_train.csv` - main training data with input features and three binary labels.

-   `dkmacovid_kaggletest_features.csv` - feature for a test set, with \"Id\" column for Kaggle competition.

-   `dkmacovid_kaggletest_labels.csv` - labels for the kaggle test set\...oh, you don't get that one :)

### Fields Descriptions: 

-   **Day**: Date in January 2021 ranging from Jan 2 to Jan 31.

-   **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.

-   **State**: Name of the US State.

-   **Lat**: Latitude for the geographic centre of the state.

-   **Long\_**: Longitude for the geographic centre of the state.

-   **Active**: Number of active, tracked COVID-19 cases that day in that state.

-   **Incident\_Rate**: see original data source

-   **Total\_Test\_Results**: see original data source

-   **Case\_Fatality\_Ratio**: see original data source

-   **Testing\_Rate**: see original data source

-   **Resident Population 2021 Census**: see original data source

-   **Population Density 2021 Census**: see original data source

-   **Density Rank 2021 Census**: see original data source

-   **SexRatio**: see original data source

### Label Description: 

Each row of this data dataset represents a particular **day** in January, 2021 in a particular **US State** and has three binary labels which are:

-   **`True`** if is the corresponding count went **up** from the previous day.

-   **`False`** if is the corresponding count went **down** from the previous day.

The three binary labels are:

-   **Confirmed**: Was there a daily increase in the **confirmed total cases** of COVID-19 in that state on that day?

-   **Deaths**: Was there a daily increase in the **number of deaths** from COVID-19 in that state on that day?

-   **Recovered**: Was there a daily increase in the number **of people recovered** from COVID-19 in that state on that day?

Note 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.