>>> from datasets import load_dataset
>>> dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")

>>> dataset["label"][:10]
[1, 0, 1, 0, 1, 1, 0, 1, 0, 0]
>>> sorted_dataset = dataset.sort("label")
>>> sorted_dataset["label"][:10]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
>>> sorted_dataset["label"][-10:]
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1]

>>> shuffled_dataset = sorted_dataset.shuffle(seed=42)
>>> shuffled_dataset["label"][:10]
[1, 1, 1, 0, 1, 1, 1, 1, 1, 0]

>>> iterable_dataset = dataset.to_iterable_dataset(num_shards=128)
>>> shuffled_iterable_dataset = iterable_dataset.shuffle(seed=42, buffer_size=1000)

>>> small_dataset = dataset.select([0, 10, 20, 30, 40, 50])
>>> len(small_dataset)
6

>>> start_with_ar = dataset.filter(lambda example: example["sentence1"].startswith("Ar"))
>>> len(start_with_ar)
6
>>> start_with_ar["sentence1"]
['Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A {@html "$4.56 , having earlier set a record high of A$"} 4.57 .',
'Arison said Mann may have been one of the pioneers of the world music movement and he had a deep love of Brazilian music .',
'Arts helped coach the youth on an eighth-grade football team at Lombardi Middle School in Green Bay .',
'Around 9 : 00 a.m. EDT ( 1300 GMT ) , the euro was at $ 1.1566 against the dollar , up 0.07 percent on the day .',
"Arguing that the case was an isolated example , Canada has threatened a trade backlash if Tokyo 's ban is not justified on scientific grounds .",
'Artists are worried the plan would harm those who need help most - performers who have a difficult time lining up shows .'
]

>>> even_dataset = dataset.filter(lambda example, idx: idx % 2 == 0, with_indices=True)
>>> len(even_dataset)
1834
>>> len(dataset) / 2
1834.0

>>> dataset.train_test_split(test_size=0.1)
{'train': Dataset(schema: {'sentence1': 'string', 'sentence2': 'string', 'label': 'int64', 'idx': 'int32'}, num_rows: 3301),
'test': Dataset(schema: {'sentence1': 'string', 'sentence2': 'string', 'label': 'int64', 'idx': 'int32'}, num_rows: 367)}
>>> 0.1 * len(dataset)
366.8

>>> from datasets import load_dataset
>>> dataset = load_dataset("stanfordnlp/imdb", split="train")
>>> print(dataset)
Dataset({
    features: ['text', 'label'],
    num_rows: 25000
})

>>> dataset.shard(num_shards=4, index=0)
Dataset({
    features: ['text', 'label'],
    num_rows: 6250
})
>>> print(25000/4)
6250.0

>>> dataset
Dataset({
    features: ['sentence1', 'sentence2', 'label', 'idx'],
    num_rows: 3668
})
>>> dataset = dataset.rename_column("sentence1", "sentenceA")
>>> dataset = dataset.rename_column("sentence2", "sentenceB")
>>> dataset
Dataset({
    features: ['sentenceA', 'sentenceB', 'label', 'idx'],
    num_rows: 3668
})

>>> dataset = dataset.remove_columns("label")
>>> dataset
Dataset({
    features: ['sentence1', 'sentence2', 'idx'],
    num_rows: 3668
})
>>> dataset = dataset.remove_columns(["sentence1", "sentence2"])
>>> dataset
Dataset({
    features: ['idx'],
    num_rows: 3668
})

>>> dataset
Dataset({
    features: ['sentence1', 'sentence2', 'label', 'idx'],
    num_rows: 3668
})
>>> dataset = dataset.select_columns(['sentence1', 'sentence2', 'idx'])
>>> dataset
Dataset({
    features: ['sentence1', 'sentence2', 'idx'],
    num_rows: 3668
})
>>> dataset = dataset.select_columns('idx')
>>> dataset
Dataset({
    features: ['idx'],
    num_rows: 3668
})

>>> dataset.features
{'sentence1': Value('string'),
'sentence2': Value('string'),
'label': ClassLabel(names=['not_equivalent', 'equivalent']),
'idx': Value('int32')}

>>> from datasets import ClassLabel, Value
>>> new_features = dataset.features.copy()
>>> new_features["label"] = ClassLabel(names=["negative", "positive"])
>>> new_features["idx"] = Value("int64")
>>> dataset = dataset.cast(new_features)
>>> dataset.features
{'sentence1': Value('string'),
'sentence2': Value('string'),
'label': ClassLabel(names=['negative', 'positive']),
'idx': Value('int64')}

>>> dataset.features
{'audio': Audio(sampling_rate=44100, mono=True)}

>>> dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
>>> dataset.features
{'audio': Audio(sampling_rate=16000, mono=True)}

>>> from datasets import load_dataset
>>> dataset = load_dataset("rajpurkar/squad", split="train")
>>> dataset.features
{'id': Value('string'),
 'title': Value('string'),
 'context': Value('string'),
 'question': Value('string'),
 'answers': {'text': List(Value('string')),
  'answer_start': List(Value('int32'))}}

>>> flat_dataset = dataset.flatten()
>>> flat_dataset
Dataset({
    features: ['id', 'title', 'context', 'question', 'answers.text', 'answers.answer_start'],
 num_rows: 87599
})

>>> def add_prefix(example):
...     example["sentence1"] = 'My sentence: ' + example["sentence1"]
...     return example

>>> updated_dataset = small_dataset.map(add_prefix)
>>> updated_dataset["sentence1"][:5]
['My sentence: Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
"My sentence: Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .",
'My sentence: They had published an advertisement on the Internet on June 10 , offering the cargo for sale , he added .',
'My sentence: Around 0335 GMT , Tab shares were up 19 cents , or 4.4 % , at A {@html "$4.56 , having earlier set a record high of A$"} 4.57 .',
]

>>> updated_dataset = dataset.map(lambda example: {"new_sentence": example["sentence1"]}, remove_columns=["sentence1"])
>>> updated_dataset.column_names
['sentence2', 'label', 'idx', 'new_sentence']

>>> updated_dataset = dataset.map(lambda example, idx: {"sentence2": f"{idx}: " + example["sentence2"]}, with_indices=True)
>>> updated_dataset["sentence2"][:5]
['0: Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .',
 "1: Yucaipa bought Dominick 's in 1995 for {@html "$693 million and sold it to Safeway for$"} 1.8 billion in 1998 .",
 "2: On June 10 , the ship 's owners had published an advertisement on the Internet , offering the explosives for sale .",
 '3: Tab shares jumped 20 cents , or 4.6 % , to set a record closing high at A $ 4.57 .',
 '4: PG & E Corp. shares jumped {@html "$1.63 or 8 percent to$"} 21.03 on the New York Stock Exchange on Friday .'
]

>>> updated_dataset = dataset.map(lambda example, idx: {"sentence2": f"{idx}: " + example["sentence2"]}, with_indices=True, num_proc=4)

>>> import torch
>>> from multiprocess import set_start_method
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> from datasets import load_dataset
>>>
>>> # Get an example dataset
>>> dataset = load_dataset("fka/awesome-chatgpt-prompts", split="train")
>>>
>>> # Get an example model and its tokenizer
>>> model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-0.5B-Chat").eval()
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B-Chat")
>>>
>>> def gpu_computation(batch, rank):
...     # Move the model on the right GPU if it's not there already
...     device = f"cuda:{(rank or 0) % torch.cuda.device_count()}"
...     model.to(device)
...
...     # Your big GPU call goes here, for example:
...     chats = [[
...         {"role": "system", "content": "You are a helpful assistant."},
...         {"role": "user", "content": prompt}
...     ] for prompt in batch["prompt"]]
...     texts = [tokenizer.apply_chat_template(
...         chat,
...         tokenize=False,
...         add_generation_prompt=True
...     ) for chat in chats]
...     model_inputs = tokenizer(texts, padding=True, return_tensors="pt").to(device)
...     with torch.no_grad():
...         outputs = model.generate(**model_inputs, max_new_tokens=512)
...     batch["output"] = tokenizer.batch_decode(outputs, skip_special_tokens=True)
...     return batch
>>>
>>> if __name__ == "__main__":
...     set_start_method("spawn")
...     updated_dataset = dataset.map(
...         gpu_computation,
...         batched=True,
...         batch_size=16,
...         with_rank=True,
...         num_proc=torch.cuda.device_count(),  # one process per GPU
...     )

RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method.

>>> def chunk_examples(examples):
...     chunks = []
...     for sentence in examples["sentence1"]:
...         chunks += [sentence[i:i + 50] for i in range(0, len(sentence), 50)]
...     return {"chunks": chunks}

>>> chunked_dataset = dataset.map(chunk_examples, batched=True, remove_columns=dataset.column_names)
>>> chunked_dataset[:10]
{'chunks': ['Amrozi accused his brother , whom he called " the ',
            'witness " , of deliberately distorting his evidenc',
            'e .',
            "Yucaipa owned Dominick 's before selling the chain",
            ' to Safeway in 1998 for $ 2.5 billion .',
            'They had published an advertisement on the Interne',
            't on June 10 , offering the cargo for sale , he ad',
            'ded .',
            'Around 0335 GMT , Tab shares were up 19 cents , or',
            ' 4.4 % , at A $ 4.56 , having earlier set a record']}

>>> dataset
Dataset({
 features: ['sentence1', 'sentence2', 'label', 'idx'],
 num_rows: 3668
})
>>> chunked_dataset
Dataset({
    features: ['chunks'],
    num_rows: 10470
})

>>> from random import randint
>>> from transformers import pipeline

>>> fillmask = pipeline("fill-mask", model="roberta-base")
>>> mask_token = fillmask.tokenizer.mask_token
>>> smaller_dataset = dataset.filter(lambda e, i: i<100, with_indices=True)

>>> def augment_data(examples):
...     outputs = []
...     for sentence in examples["sentence1"]:
...         words = sentence.split(' ')
...         K = randint(1, len(words)-1)
...         masked_sentence = " ".join(words[:K]  + [mask_token] + words[K+1:])
...         predictions = fillmask(masked_sentence)
...         augmented_sequences = [predictions[i]["sequence"] for i in range(3)]
...         outputs += [sentence] + augmented_sequences
...
...     return {"data": outputs}

>>> augmented_dataset = smaller_dataset.map(augment_data, batched=True, remove_columns=dataset.column_names, batch_size=8)
>>> augmented_dataset[:9]["data"]
['Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
 'Amrozi accused his brother, whom he called " the witness ", of deliberately withholding his evidence.',
 'Amrozi accused his brother, whom he called " the witness ", of deliberately suppressing his evidence.',
 'Amrozi accused his brother, whom he called " the witness ", of deliberately destroying his evidence.',
 "Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion .",
 'Yucaipa owned Dominick Stores before selling the chain to Safeway in 1998 for $ 2.5 billion.',
 "Yucaipa owned Dominick's before selling the chain to Safeway in 1998 for $ 2.5 billion.",
 'Yucaipa owned Dominick Pizza before selling the chain to Safeway in 1998 for $ 2.5 billion.'
]

>>> import aiohttp
>>> import asyncio
>>> from huggingface_hub import get_token
>>> sem = asyncio.Semaphore(20)  # max number of simultaneous queries
>>> async def query_model(model, prompt):
...     api_url = f"https://huggingface.co/proxy/api-inference.huggingface.co/models/{model}/v1/chat/completions"
...     headers = {"Authorization": f"Bearer {get_token()}", "Content-Type": "application/json"}
...     json = {"messages": [{"role": "user", "content": prompt}], "max_tokens": 20, "seed": 42}
...     async with sem, aiohttp.ClientSession() as session, session.post(api_url, headers=headers, json=json) as response:
...         output = await response.json()
...         return {"Output": output["choices"][0]["message"]["content"]}

>>> from datasets import load_dataset
>>> ds = load_dataset("Maxwell-Jia/AIME_2024", split="train")
>>> model = "microsoft/Phi-3-mini-4k-instruct"
>>> prompt = 'What is this text mainly about ? Here is the text:\n\n```\n{Problem}\n```\n\nReply using one or two words max, e.g. "The main topic is Linear Algebra".'
>>> async def get_topic(example):
...     return await query_model(model, prompt.format(Problem=example['Problem']))
>>> ds = ds.map(get_topic)
>>> ds[0]
{'ID': '2024-II-4',
 'Problem': 'Let {@html "$x,y$"} and {@html "$z$"} be positive real numbers that...',
 'Solution': 'Denote $\\log_2(x) = a$, $\\log_2(y) = b$, and...,
 'Answer': 33,
 'Output': 'The main topic is Logarithms.'}

>>> from datasets import load_dataset

# load all the splits
>>> dataset = load_dataset('nyu-mll/glue', 'mrpc')
>>> encoded_dataset = dataset.map(lambda examples: tokenizer(examples["sentence1"]), batched=True)
>>> encoded_dataset["train"][0]
{'sentence1': 'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
'sentence2': 'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .',
'label': 1,
'idx': 0,
'input_ids': [  101,  7277,  2180,  5303,  4806,  1117,  1711,   117,  2292, 1119,  1270,   107,  1103,  7737,   107,   117,  1104,  9938, 4267, 12223, 21811,  1117,  2554,   119,   102],
'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
}

>>> from datasets import Dataset
>>> import torch.distributed

>>> dataset1 = Dataset.from_dict({"a": [0, 1, 2]})

>>> if training_args.local_rank > 0:
...     print("Waiting for main process to perform the mapping")
...     torch.distributed.barrier()

>>> dataset2 = dataset1.map(lambda x: {"a": x["a"] + 1})

>>> if training_args.local_rank == 0:
...     print("Loading results from main process")
...     torch.distributed.barrier()

>>> from datasets import load_dataset
>>> dataset = load_dataset("cornell-movie-review-data/rotten_tomatoes", split="train")
>>> batched_dataset = dataset.batch(batch_size=4)
>>> batched_dataset[0]
{'text': ['the rock is destined to be the 21st century\'s new " conan " and that he\'s going to make a splash even greater than arnold schwarzenegger , jean-claud van damme or steven segal .',
        'the gorgeously elaborate continuation of " the lord of the rings " trilogy is so huge that a column of words cannot adequately describe co-writer/director peter jackson\'s expanded vision of j . r . r . tolkien\'s middle-earth .',
        'effective but too-tepid biopic',
        'if you sometimes like to go to the movies to have fun , wasabi is a good place to start .'],
'label': [1, 1, 1, 1]}

>>> from datasets import concatenate_datasets, load_dataset

>>> stories = load_dataset("ajibawa-2023/General-Stories-Collection", split="train")
>>> stories = stories.select_columns(["text"])  # only keep the 'text' column
>>> wiki = load_dataset("wikimedia/wikipedia", "20231101.en", split="train")
>>> wiki = wiki.select_columns(["text"])  # only keep the 'text' column

>>> assert stories.features.type == wiki.features.type
>>> bert_dataset = concatenate_datasets([stories, wiki])

>>> from datasets import Dataset
>>> stories_ids = Dataset.from_dict({"ids": list(range(len(stories)))})
>>> stories_with_ids = concatenate_datasets([stories, stories_ids], axis=1)

>>> from datasets import Dataset, interleave_datasets
>>> seed = 42
>>> probabilities = [0.3, 0.5, 0.2]
>>> d1 = Dataset.from_dict({"a": [0, 1, 2]})
>>> d2 = Dataset.from_dict({"a": [10, 11, 12, 13]})
>>> d3 = Dataset.from_dict({"a": [20, 21, 22]})
>>> dataset = interleave_datasets([d1, d2, d3], probabilities=probabilities, seed=seed)
>>> dataset["a"]
[10, 11, 20, 12, 0, 21, 13]

>>> d1 = Dataset.from_dict({"a": [0, 1, 2]})
>>> d2 = Dataset.from_dict({"a": [10, 11, 12, 13]})
>>> d3 = Dataset.from_dict({"a": [20, 21, 22]})
>>> dataset = interleave_datasets([d1, d2, d3], stopping_strategy="all_exhausted")
>>> dataset["a"]
[0, 10, 20, 1, 11, 21, 2, 12, 22, 0, 13, 20]

>>> dataset = dataset.with_format(type="torch")

>>> dataset.set_format(type="torch")

>>> dataset.format
{'type': 'torch', 'format_kwargs': {}, 'columns': [...], 'output_all_columns': False}
>>> dataset = dataset.with_format(None)
>>> dataset.format
{'type': None, 'format_kwargs': {}, 'columns': [...], 'output_all_columns': False}

>>> ds = Dataset.from_dict({"text": ["foo", "bar"], "tokens": [[0, 1, 2], [3, 4, 5]]})
>>> ds = ds.with_format("torch")
>>> ds[0]
{'text': 'foo', 'tokens': tensor([0, 1, 2])}
>>> ds[:2]
{'text': ['foo', 'bar'],
 'tokens': tensor([[0, 1, 2],
         [3, 4, 5]])}

>>> ds = Dataset.from_dict({"text": ["foo", "bar"], "label": [0, 1]})
>>> ds = ds.with_format("pandas")
>>> ds[:2]
  text  label
0  foo      0
1  bar      1

>>> ds = ds.map(lambda df: df.assign(upper_text=df.text.str.upper()), batched=True)
>>> ds[:2]
  text  label upper_text
0  foo      0        FOO
1  bar      1        BAR

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
>>> def encode(batch):
...     return tokenizer(batch["sentence1"], batch["sentence2"], padding="longest", truncation=True, max_length=512, return_tensors="pt")
>>> dataset = dataset.with_transform(encode)
>>> dataset.format
{'type': 'custom', 'format_kwargs': {'transform': <function __main__.encode(batch)>}, 'columns': ['idx', 'label', 'sentence1', 'sentence2'], 'output_all_columns': False}

>>> import numpy as np
>>> from pydub import AudioSegment

>>> audio_dataset_amr = Dataset.from_dict({"audio": ["audio_samples/audio.amr"]})

>>> def decode_audio_with_pydub(batch, sampling_rate=16_000):
...     def pydub_decode_file(audio_path):
...         sound = AudioSegment.from_file(audio_path)
...         if sound.frame_rate != sampling_rate:
...             sound = sound.set_frame_rate(sampling_rate)
...         channel_sounds = sound.split_to_mono()
...         samples = [s.get_array_of_samples() for s in channel_sounds]
...         fp_arr = np.array(samples).T.astype(np.float32)
...         fp_arr /= np.iinfo(samples[0].typecode).max
...         return fp_arr
...
...     batch["audio"] = [pydub_decode_file(audio_path) for audio_path in batch["audio"]]
...     return batch

>>> audio_dataset_amr.set_transform(decode_audio_with_pydub)

encoded_dataset.push_to_hub("username/my_dataset")

dataset.push_to_hub("username/my_dataset", num_proc=8)

from datasets import load_dataset
reloaded_dataset = load_dataset("username/my_dataset", streaming=True)

>>> encoded_dataset.save_to_disk("path/of/my/dataset/directory")
>>> # later
>>> from datasets import load_from_disk
>>> reloaded_dataset = load_from_disk("path/of/my/dataset/directory")

>>> encoded_dataset.to_csv("path/of/my/dataset.csv")

>>> encoded_dataset.to_csv("hf://datasets/username/dataset_name/path/of/my/dataset.csv")
>>> encoded_dataset.to_csv("hf://buckets/username/raw_data_bucket/path/of/my/dataset.csv")