# DSC Bi-Weekly Challenge #1 – NYC Real Estate Price — Data

来源：https://www.kaggle.com/competitions/dsc-nyc-real-estate/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset contains transaction records across the five boroughs. Note: This data is provided in its raw form. Participants must handle missing values (often marked as "-" or "0"), identify extreme outliers, and encode high-cardinality categorical variables.

## Files

*   **training.csv** - the training set
*   **testing.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format

1. Identification & Location

   - Property_ID: (Synthetic) A unique identifier created for the competition to track predictions.
   - BOROUGH: Digit code for the borough (1: Manhattan, 2: Bronx, 3: Brooklyn, 4: Queens, 5: Staten Island).
   - NEIGHBORHOOD: Common name of the neighborhood.
   - ADDRESS / ZIP CODE: Specific physical location of the property.
   - BLOCK & LOT: Tax identifiers used by the NYC Department of Finance.
   - APARTMENT NUMBER: Provided for specific residential units.

2. Property Characteristics

   - BUILDING CLASS CATEGORY: Broad property categories (e.g., "01 ONE FAMILY DWELLINGS").
   - TAX CLASS (Present & Time of Sale): Property tax categories (Classes 1, 2, 3, or 4).
   - BUILDING CLASS (Present & Time of Sale): Specific codes (e.g., A1, R4) describing the structure’s use.
   - YEAR BUILT: The year the structure was constructed (contains anomalies like year 0).
   - RESIDENTIAL / COMMERCIAL / TOTAL UNITS: The count of individual units within the building.
   - LAND SQUARE FEET: The total area of the tax lot.
   - GROSS SQUARE FEET: The total area of all floors in the building.

3. Transaction Details

   - SALE PRICE: The total price paid. (Used to derive targets in training; omitted in testing).
   - SALE DATE: The date of the transaction.