# Business Analytics Summer20 Classification — Data

来源：https://www.kaggle.com/competitions/business-analytics-summer20-classification/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

### Data Overview

The data was already pre-processed. Here's some brief overview of some of the attributes, the rest can be explored on your own.

**'courier_id', 'wave_index', 'tracking_id', 'date', 'group', 'id',:**

These are the demographic information of the order and its courier. The column names are somewhat self-explanatory.

**'courier_wave_start_lng', 'courier_wave_start_lat':**

These are the starting longitude and latitude of that wave of a certain courier

**'level', 'speed', 'max_load':**

These are the courier information: the level of the courier, the speed of the courier and the max load of the courier

**'weather_grade':**

This is the weather condition of the order

**'aoi_id':**

The id of the Area of Interest (i.e. the delivery destination)

**'shop_id':**

The id of the shop
      
**'source_type', 'source_tracking_id', 'source_lng', 'source_lat':**

The information of the courier's previous action.

**'target_lng', 'target_lat':**

Geographical information of the target

**'grid_distance':**

The shortest traversable distance to the target provided by the GPS

**'hour':**

The hour in the day

**'urgency'**

Identifies how urgent the order is

**'action_type'**

The target variable in classification. This is masked from the test set

**'expected_use_time':**

The target variable in regression. This is also masked from the test set

NOT ALL VARIABLES ARE NECESSARILY NEEDED

You should use your own judgement as to what to use for your model.