# Foot Traffic in Wuerzburg — Data

来源：https://www.kaggle.com/competitions/foot-traffic-wue/data

采集时间：2026-10-19T19:35:43Z

In this competition, you will predict hourly pedestrian counts for three streets in the city center of Wuerzburg, Germany. Each hourly pedestrian count refers to the following full hour, i.e., an entry for 8 a.m. refers to the time period 8:00-8:59 a.m. 
The data covers the period from April 2, 2019, to September 29, 2024. The start of the measurements in the three streets under consideration took place at different times:
- **Schoenbornstrasse**: April 2, 2019
- **Spiegelstrasse**: September 7, 2022
- **Kaiserstrasse**:  September 29, 2022

The test.csv dataset encompasses both the validation data for the public ranking as well as the test data for the private (and ultimately deciding) ranking. The test data is given by the last week of the data and the validation data by the second last week. 
*Note*: The validation data will be made available to all participants one month before the end of the competition to help improve the forecasts for the test data.

There are three target variables: `n_pedestrians`, `n_pedestrians_towards`, `n_pedestrians_away`. 

The variable `n_pedestrians` is the total number of pedestrians that the counter has measured in the last hour in the street in question. The additional variables `n_pedestrians_towards` and `n_pedestrians_away` describe how many of these pedestrians moved towards the city center and how many moved away from the city center. Predictions about these two additional variables allow us to model the flow of pedestrians within the city center.

Each row of both the training and test data has a unique `id`, which is the combination of the considered street, the date, and the hour of the day.

## Files

**train.csv** 
The training data encompasses the timeframe from April 2, 2019, until September 15, 2024. It contains the following data:
- Time-related features such as the date, hour, and weekday.
- Information about the weather during the last hour.
- Information about incidents like construction sites.
- Information about the measurement type. On some occasions, the pedestrian counts were modelled instead of being directly measured.
- The three target variables `n_pedestrians`, `n_pedestrians_towards`, `n_pedestrians_away`.


**test.csv**
The test.csv file encompasses the timeframe from September 16, 2019, until September 29, 2024. The first week of test.csv constitutes the validation data for the public leaderboard and the second week is the test data for the private leaderboard. It contains the following data:
- Time-related features such as the date, hour, and weekday.
- Information about the weather during the last hour.
- Information about incidents like construction sites.
- Information about the measurement type.

*Note*: Whole columns regarding incidents and the measurement type are provided for the validation and test data, it should be noted that no incidents or measurement errors occurred during this timeframe. 

**sample_submission.csv** 
A sample submission file in the correct format: Each submission must contain a prediction for the three target variables `n_pedestrians`, `n_pedestrians_towards`, `n_pedestrians_away` for every `id` given in the test data.

**counterGeoLocations.json**
In this JSON-file you will find exact coordinates for the position of each pedestrian counters of the three streets.