anotherdev/testing-datasets

---
license:
- other
pretty_name: >-
testing datasets in a sandbox
this is not a real dataset it is sandbox for testing
size_categories:
- 0<n<1k
tags:
- other
# supported task_categories
# text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, conversational, feature-extraction, text-generation, text2text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-retrieval, time-series-forecasting, text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, other
task_categories:
- other
# supported task_ids
# acceptability-classification, entity-linking-classification, fact-checking, intent-classification, language-identification, multi-class-classification, multi-label-classification, multi-input-text-classification, natural-language-inference, semantic-similarity-classification, sentiment-classification, topic-classification, semantic-similarity-scoring, sentiment-scoring, sentiment-analysis, hate-speech-detection, text-scoring, named-entity-recognition, part-of-speech, parsing, lemmatization, word-sense-disambiguation, coreference-resolution, extractive-qa, open-domain-qa, closed-domain-qa, news-articles-summarization, news-articles-headline-generation, dialogue-generation, dialogue-modeling, language-modeling, text-simplification, explanation-generation, abstractive-qa, open-domain-abstractive-qa, closed-domain-qa, open-book-qa, closed-book-qa, slot-filling, masked-language-modeling, keyword-spotting, speaker-identification, audio-intent-classification, audio-emotion-recognition, audio-language-identification, multi-label-image-classification, multi-class-image-classification, face-detection, vehicle-detection, instance-segmentation, semantic-segmentation, panoptic-segmentation, image-captioning, image-inpainting, image-colorization, super-resolution, grasping, task-planning, tabular-multi-class-classification, tabular-multi-label-classification, tabular-single-column-regression, rdf-to-text, multiple-choice-qa, multiple-choice-coreference-resolution, document-retrieval, utterance-retrieval, entity-linking-retrieval, fact-checking-retrieval, univariate-time-series-forecasting, multivariate-time-series-forecasting, visual-question-answering, document-question-answering
task_ids:
- parsing
dataset_info:
- config_name: audio_class
features:
- name: file_path
dtype: string
- name: audio_path
dtype: string
- name: lang
dtype: string
- name: dbytes_len
dtype: int64
- name: dbytes
dtype: binary
splits:
- name: audio_class
# download_size: 1
# dataset_size: 1
- config_name: audio_base
features:
- name: file_path
dtype: string
- name: audio_path
dtype: string
- name: lang
dtype: string
- name: dbytes_len
dtype: int64
- name: dbytes
dtype: binary
splits:
- name: audio_base
# download_size: 1
# dataset_size: 1
- config_name: audio_import
features:
- name: file_path
dtype: string
- name: audio_path
dtype: string
- name: lang
dtype: string
- name: dbytes_len
dtype: int64
- name: dbytes
dtype: binary
splits:
- name: audio_import
# download_size: 1
# dataset_size: 1
- config_name: audio_function
features:
- name: file_path
dtype: string
- name: audio_path
dtype: string
- name: lang
dtype: string
- name: dbytes_len
dtype: int64
- name: dbytes
dtype: binary
splits:
- name: audio_function
# download_size: 1
# dataset_size: 1
- config_name: image_base
features:
- name: filename
dtype: string
- name: repo
dtype: string
- name: path
dtype: string
- name: dbytes
dtype: binary
- name: dbytes_len
dtype: int64
- name: dbytes_mb
dtype: string
- name: type
dtype: string
splits:
- name: image_base
# download_size: 1
# dataset_size: 1
- config_name: image_import
features:
- name: filename
dtype: string
- name: repo
dtype: string
- name: path
dtype: string
- name: dbytes
dtype: binary
- name: dbytes_len
dtype: int64
- name: dbytes_mb
dtype: string
- name: type
dtype: string
splits:
- name: image_import
# download_size: 1
# dataset_size: 1
- config_name: image_function
features:
- name: filename
dtype: string
- name: repo
dtype: string
- name: path
dtype: string
- name: dbytes
dtype: binary
- name: dbytes_len
dtype: int64
- name: dbytes_mb
dtype: string
- name: type
dtype: string
splits:
- name: image_function
# download_size: 1
# dataset_size: 1
- config_name: image_class
features:
- name: filename
dtype: string
- name: repo
dtype: string
- name: path
dtype: string
- name: dbytes
dtype: binary
- name: dbytes_len
dtype: int64
- name: dbytes_mb
dtype: string
- name: type
dtype: string
splits:
- name: image_class
# download_size: 1
# dataset_size: 1
- config_name: text_instruct
# features:
#- name: filename
# dtype: string
#- name: repo
# dtype: string
#- name: path
# dtype: string
#- name: dbytes
# dtype: binary
#- name: dbytes_len
# dtype: int64
#- name: dbytes_mb
# dtype: string
#- name: type
# dtype: string
splits:
- name: text_instruct
# download_size: 1
# dataset_size: 1
- config_name: text_python
splits:
- name: text_python_ai_research
- name: text_python_many_repos
# download_size: 1
# dataset_size: 1
configs:
- config_name: audio_class
data_files:
- split: audio_class
path: files/audio/test-audio-class.parquet
- config_name: audio_base
data_files:
- split: audio_base
path: files/audio/test-audio-base.parquet
- config_name: audio_import
data_files:
- split: audio_import
path: files/audio/test-audio-import.parquet
- config_name: audio_function
data_files:
- split: audio_function
path: files/audio/test-audio-function.parquet
- config_name: image_base
data_files:
- split: image_base
path: files/image/test-image-base.parquet
- config_name: image_import
data_files:
- split: image_import
path: files/image/test-image-import.parquet
- config_name: image-function
data_files:
- split: image_function
path: files/image/test-image-function.parquet
- config_name: image-class
data_files:
- split: image_class
path: files/image/test-image-class.parquet
- config_name: text_instruct
data_files:
- split: text_instruct
path: files/instruct/test-text-instruct.parquet
- config_name: text_python
data_files:
- split: text_python_ai_research
path: files/text/test-text-python-ai-research.parquet
- split: text_python_many_repos
path: files/text/test-text-python-many-repos.parquet
---

# Testing Datasets

### How to use the dataset

```python
from datasets import load_dataset

# load audio
print("loading audio")
ds_audio = load_dataset("anotherdev/testing-datasets", data_dir="files/audio")
print(ds_audio)

# load image
print("loading images")
ds_image = load_dataset("anotherdev/testing-datasets", data_dir="files/image")
print(ds_image)

# load text
print("loading text")
ds_text = load_dataset("anotherdev/testing-datasets", data_dir="files/text")
print(ds_text)

# load instruct
print("loading instruct")
ds_instr = load_dataset("anotherdev/testing-datasets", data_dir="files/instruct")
print(ds_instr)
```

原始信息汇总

数据集概述

基本信息

• 名称: testing datasets in a sandbox
• 描述: 这不是一个真实的数据集，它是用于测试的沙盒环境。
• 大小类别: 0<n<1k
• 标签: other
• 任务类别: other
• 任务ID: parsing

配置信息

音频配置

• config_name: audio_class

  • 特征:
    • file_path: string
    • audio_path: string
    • lang: string
    • dbytes_len: int64
    • dbytes: binary
  • 分割: audio_class
  • 数据文件:
    • split: audio_class
    • path: files/audio/test-audio-class.parquet

• config_name: audio_base

  • 特征:
    • file_path: string
    • audio_path: string
    • lang: string
    • dbytes_len: int64
    • dbytes: binary
  • 分割: audio_base
  • 数据文件:
    • split: audio_base
    • path: files/audio/test-audio-base.parquet

• config_name: audio_import

  • 特征:
    • file_path: string
    • audio_path: string
    • lang: string
    • dbytes_len: int64
    • dbytes: binary
  • 分割: audio_import
  • 数据文件:
    • split: audio_import
    • path: files/audio/test-audio-import.parquet

• config_name: audio_function

  • 特征:
    • file_path: string
    • audio_path: string
    • lang: string
    • dbytes_len: int64
    • dbytes: binary
  • 分割: audio_function
  • 数据文件:
    • split: audio_function
    • path: files/audio/test-audio-function.parquet

图像配置

• config_name: image_base

  • 特征:
    • filename: string
    • repo: string
    • path: string
    • dbytes: binary
    • dbytes_len: int64
    • dbytes_mb: string
    • type: string
  • 分割: image_base
  • 数据文件:
    • split: image_base
    • path: files/image/test-image-base.parquet

• config_name: image_import

  • 特征:
    • filename: string
    • repo: string
    • path: string
    • dbytes: binary
    • dbytes_len: int64
    • dbytes_mb: string
    • type: string
  • 分割: image_import
  • 数据文件:
    • split: image_import
    • path: files/image/test-image-import.parquet

• config_name: image_function

  • 特征:
    • filename: string
    • repo: string
    • path: string
    • dbytes: binary
    • dbytes_len: int64
    • dbytes_mb: string
    • type: string
  • 分割: image_function
  • 数据文件:
    • split: image_function
    • path: files/image/test-image-function.parquet

• config_name: image_class

  • 特征:
    • filename: string
    • repo: string
    • path: string
    • dbytes: binary
    • dbytes_len: int64
    • dbytes_mb: string
    • type: string
  • 分割: image_class
  • 数据文件:
    • split: image_class
    • path: files/image/test-image-class.parquet

文本配置

• config_name: text_instruct

  • 分割: text_instruct
  • 数据文件:
    • split: text_instruct
    • path: files/instruct/test-text-instruct.parquet

• config_name: text_python

  • 分割:
    • text_python_ai_research
    • text_python_many_repos
  • 数据文件:
    • split: text_python_ai_research
    • path: files/text/test-text-python-ai-research.parquet
    • split: text_python_many_repos
    • path: files/text/test-text-python-many-repos.parquet