DS-1000 is a code generation benchmark with a thousand data science questions spanning seven Python libraries that (1) reflects diverse, realistic, and practical use cases, (2) has a reliable metric, (3) defends against memorization by perturbing questions.
dnanper/basemodel-qwen2-7B-eval-ds1000 dataset hosted on Hugging Face and contributed by the HF Datasets community
This data set combines vegetation datasets from three mapping project areas in the Sacramento Valley and riparian areas of the San Joaquin Valley to facilitate regional planning, conservation, and enhancement of biological resources by state and local agencies, project partners and regional stakeholders. This dataset meets the National Vegetation Classfication Standared and California Vegetation Classification and Mapping Standards. Vegetation is mapped to the Alliance level with a 1-acre minimum mapping unit. Polygons are also attributed with total bird's-eye cover of trees, shrubs and herbs. Detailed reports on the classification and mapping standards can be downloaded (see summary for links).
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Catalog of datasets published by the Municipality of Milan, on the portal http://dati.comune.milano.it (according to the DCAT-AP_IT standard) in tabular format.
Die nationalen Verkehrsmodelle basieren auf den Strukturdaten 2010. Dieser Datensatz enthält einige Modelle für 2040. Weitere Modelle sind für 2040 sowie für 2010, 2020 und 2030 in den anderen Datensätzen des Projekts verfügbar. Für einen Überblick über den Aufbau des Datensatzes können Sie sich das Dokument ansehen: (Read me first) Projektbeschreibung Verkehrsmodellierung im UVEK D/F/I.
Les modèles nationaux des transports sont effectués sur la base des données structurelles de 2010. Ce jeu de données contient certains modèles pour 2040. D’autres modèles sont disponibles pour 2040, ainsi que pour 2010, 2020 et 2030 dans les autres jeux de données du projet. Pour une vue d'ensemble de la structure des données, vous pouvez consulter le document: (Read me first) Projektbeschreibung Verkehrsmodellierung im UVEK D/F/I.
National transport models are based on structural data from 2010. This dataset contains some models for 2040. Other models are available for 2040, as well as for 2010, 2020 and 2030 in the other datasets of the project. For an overview of the data structure, you can consult the document: (Read me first) Projektbeschreibung Verkehrsmodellierung im UVEK D/F/I.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
DS-1000 is a code generation benchmark with a thousand data science questions spanning seven Python libraries that (1) reflects diverse, realistic, and practical use cases, (2) has a reliable metric, (3) defends against memorization by perturbing questions.