%pip install datasets polars

Collecting datasets
  Downloading datasets-2.14.5-py3-none-any.whl (519 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 519.6/519.6 kB 4.8 MB/s eta 0:00:00
Requirement already satisfied: polars in /usr/local/lib/python3.10/dist-packages (0.17.3)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.23.5)
Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)
Collecting dill<0.3.8,>=0.3.0 (from datasets)
  Downloading dill-0.3.7-py3-none-any.whl (115 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 115.3/115.3 kB 11.5 MB/s eta 0:00:00
Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)
Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)
Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.1)
Collecting xxhash (from datasets)
  Downloading xxhash-3.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 194.1/194.1 kB 19.2 MB/s eta 0:00:00
Collecting multiprocess (from datasets)
  Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 134.8/134.8 kB 13.6 MB/s eta 0:00:00
Requirement already satisfied: fsspec[http]<2023.9.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)
Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.8.5)
Collecting huggingface-hub<1.0.0,>=0.14.0 (from datasets)
  Downloading huggingface_hub-0.17.1-py3-none-any.whl (294 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 294.8/294.8 kB 26.8 MB/s eta 0:00:00
Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.1)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)
Requirement already satisfied: typing_extensions>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from polars) (4.5.0)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)
Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (3.2.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)
Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)
Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.2)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.0)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.14.0->datasets) (3.12.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.4)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2023.7.22)
Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.3.post1)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)
Installing collected packages: xxhash, dill, multiprocess, huggingface-hub, datasets
Successfully installed datasets-2.14.5 dill-0.3.7 huggingface-hub-0.17.1 multiprocess-0.70.15 xxhash-3.3.0

from datasets import load_dataset
import polars as pl

ds = load_dataset("argilla/databricks-dolly-15k-curated-en")

ds['train'][0]

{'id': '0',
 'category': 'closed_qa',
 'original-instruction': 'When did Virgin Australia start operating?',
 'original-context': "Virgin Australia, the trading name of Virgin Australia Airlines Pty Ltd, is an Australian-based airline. It is the largest airline by fleet size to use the Virgin brand. It commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route.[3] It suddenly found itself as a major airline in Australia's domestic market after the collapse of Ansett Australia in September 2001. The airline has since grown to directly serve 32 cities in Australia, from hubs in Brisbane, Melbourne and Sydney.[4]",
 'original-response': 'Virgin Australia commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route.',
 'new-instruction': {'user_id': [None],
  'value': ['When did Virgin Australia start operating?'],
  'status': ['submitted']},
 'new-context': {'user_id': [None],
  'value': ["Virgin Australia, the trading name of Virgin Australia Airlines Pty Ltd, is an Australian-based airline. It is the largest airline by fleet size to use the Virgin brand. It commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route. It suddenly found itself as a major airline in Australia's domestic market after the collapse of Ansett Australia in September 2001. The airline has since grown to directly serve 32 cities in Australia, from hubs in Brisbane, Melbourne and Sydney."],
  'status': ['submitted']},
 'new-response': {'user_id': [None],
  'value': ['Virgin Australia commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route.'],
  'status': ['submitted']},
 'external_id': None}
df = pl.from_arrow(ds['train'].data.table)

grouped = df.groupby('category').agg(pl.col('original-instruction').str.lengths().alias('length').mean())
grouped
shape: (8, 2)
category length
str f64
"creative_writi… 89.729958
"brainstorming" 60.71267
"information_ex… 74.921958
"classification… 123.231273
"open_qa" 45.715868
"closed_qa" 73.166758
"general_qa" 74.157919
"summarization" 56.284244 
grouped = grouped.sort('length')

import matplotlib.pyplot as plt
import matplotlib

matplotlib.style.use('fivethirtyeight')
categories = grouped['category']
lengths = grouped['length']


plt.figure(figsize=(10, 6))
plt.bar(categories, lengths)
plt.xticks(rotation=45, ha='right')
plt.ylabel('Mean Length')
plt.title('original-instruction length for each category')
plt.tight_layout()
plt.savefig('groupby-fig.png')
plt.show()

<Figure size 640x480 with 0 Axes>