# DPhi Kaggle Challenge — Data

来源：https://www.kaggle.com/competitions/dphi-amsterdam-airbnb-data/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## About the Data
The code competition data set can be found below. There are 3 different data sets available:

- **airbnb_listing_train.csv:** this data set can be used to build and test your model. It contains all the variables including the variable that has to be predicted i.e. **price**. This dataset contains 12901 observations/records divided into 16 columns (including the target column - **'price'**)
- **airbnb_listing_validate.csv:** this data set should be used to create the submissions. The data set contains all the variables that are also in the train data set except for the **'price'**.
- **sample_submission.csv:** this is an example of what your submissions should look like. Note that there are no automatic checks performed on your uploaded file so make sure that your submission file matches this file perfectly. Also, note that the order in which observations are presented in the validation set must be preserved when delivering predictions.

The data sets have not been cleaned since this is an important step in creating a predictive model. Note also that there are many opportunities to engineer your own features. It is allowed to merge your data with other online data as long as you can make sure that your model also works on the validation data. Note also that the data sets are large so be aware of overfitting your models.

## Feature Description
- **id:** The id of each lodge/home/listing
- **name:** The name/description of the lodge/home
- **host_id:** The id of the host
- **host_name:** Name of the host
- **neighbourhood:** Name of the neighbourhood place
- **neighbourhood_group:** Group in the neighbourhood
- **latitude:** Latitude of the location
- **longitude:** Longitude of the location
- **room_type:** Type of the room that consumer booked, for example, private room or an entire home, etc.
- **minimum_nights:** The minimum number of nights customer will stay
- **number_of_reviews:** Number of reviews given to the lodge/home
- **last_review:** The date of the last review given to the lodge/home
- **reviews_per_month:** Average reviews per month
- **calculated_host_listings_count:** The count of the listing that each host has
- **availability_365:** The number of days (out of 365 days) for which lodge/home is available 
- **price:** Price for the lodging/homestays in USD - the target variable

## Acknowledgement
This dataset is downloaded from Airbnb Inside.
[http://insideairbnb.com/get-the-data.html](http://insideairbnb.com/get-the-data.html)