Implementation:Online ml River Datasets Bikes

Knowledge Sources	Online_ml_River
Domains	Online_Learning, Datasets, Regression
Last Updated	2026-02-08 16:00 GMT

Overview

Concrete dataset for regression provided by the River library.

Description

Bike sharing station information from the city of Toulouse. The goal is to predict the number of bikes in 5 different bike stations from the city of Toulouse.

This dataset contains 182,470 samples with 8 features for regression tasks.

Usage

This dataset is useful for:

• Time series forecasting and prediction tasks
• Bike sharing demand prediction
• Urban transportation analysis
• Real-world regression problems with temporal patterns

Code Reference

Source Location

• Repository: Online_ml_River
• File: river/datasets/bikes.py

Signature

class Bikes(base.RemoteDataset):
    def __init__(self):
        super().__init__(
            url="https://maxhalford.github.io/files/datasets/toulouse_bikes.zip",
            size=13_125_015,
            n_samples=182_470,
            n_features=8,
            task=base.REG,
            filename="toulouse_bikes.csv",
        )

    def _iter(self):
        return stream.iter_csv(
            self.path,
            target="bikes",
            converters={
                "clouds": int,
                "humidity": int,
                "pressure": float,
                "temperature": float,
                "wind": float,
                "bikes": int,
            },
            parse_dates={"moment": "%Y-%m-%d %H:%M:%S"},
        )

Import

from river import datasets
dataset = datasets.Bikes()

I/O Contract

Inputs

Name	Type	Required	Description
(none)	—	—	No parameters needed

Outputs

Name	Type	Description
iter()	tuple(dict, int)	Yields (features_dict, target) pairs where features include weather conditions and target is bike count

Dataset Properties

Property	Value
Number of samples	182,470
Number of features	8
Task	Regression
Format	CSV
Size	13,125,015 bytes

Features

The dataset includes the following features:

• clouds: Cloud coverage (integer)
• humidity: Humidity level (integer)
• pressure: Atmospheric pressure (float)
• temperature: Temperature (float)
• wind: Wind speed (float)
• moment: Timestamp (datetime)
• bikes: Number of bikes available (target variable)

Usage Examples

from river import datasets

dataset = datasets.Bikes()
for x, y in dataset:
    print(x, y)
    break

References

• A short introduction and conclusion to the OpenBikes 2016 Challenge

Related Pages

• Environment:Online_ml_River_Python_Runtime_Environment