pip install pyspark_huggingface

hf auth login

>>> import pyspark_huggingface
huggingface datasource enabled for pyspark 3.x.x (backport from pyspark 4)

>>> import pyspark_huggingface
>>> from pyspark.sql import SparkSession
>>> spark = SparkSession.builder.appName("demo").getOrCreate()
>>> df = spark.read.format("huggingface").load("stanfordnlp/imdb")

>>> import pyspark_huggingface
>>> from pyspark.sql import SparkSession
>>> spark = SparkSession.builder.appName("demo").getOrCreate()
>>> df = spark.read.format("huggingface").option("config", "7M").load("BAAI/Infinity-Instruct")
>>> df.show()
+---+----------------------------+-----+----------+--------------------+        
| id|               conversations|label|langdetect|              source|
+---+----------------------------+-----+----------+--------------------+
|  0|        [{human, def exti...|     |        en|      code_exercises|
|  1|        [{human, See the ...|     |        en|                flan|
|  2|        [{human, This is ...|     |        en|                flan|
|  3|        [{human, If you d...|     |        en|                flan|
|  4|        [{human, In a Uni...|     |        en|                flan|
|  5|        [{human, Read the...|     |        en|                flan|
|  6|        [{human, You are ...|     |        en|          code_bagel|
|  7|        [{human, I want y...|     |        en|          Subjective|
|  8|        [{human, Given th...|     |        en|                flan|
|  9|[{human, 因果联系原则是法...|     |     zh-cn|          Subjective|
| 10|        [{human, Provide ...|     |        en|self-oss-instruct...|
| 11|        [{human, The univ...|     |        en|                flan|
| 12|        [{human, Q: I am ...|     |        en|                flan|
| 13|        [{human, What is ...|     |        en|      OpenHermes-2.5|
| 14|        [{human, In react...|     |        en|                flan|
| 15|        [{human, Write Py...|     |        en|      code_exercises|
| 16|        [{human, Find the...|     |        en|            MetaMath|
| 17|        [{human, Three of...|     |        en|            MetaMath|
| 18|        [{human, Chandra ...|     |        en|            MetaMath|
| 19|[{human, 用经济学知识分析...|     |     zh-cn|          Subjective|
+---+----------------------------+-----+----------+--------------------+

>>> df_langdetect_only = (
...     spark.read.format("huggingface")
...     .option("config", "7M")
...     .option("columns", '["langdetect"]')
...     .load("BAAI/Infinity-Instruct")
... )
>>> df_langdetect_only.groupBy("langdetect").count().show()
+----------+-------+                                                            
|langdetect|  count|
+----------+-------+
|        en|6697793|
|     zh-cn| 751313|
+----------+-------+

>>> df_chinese_only = (
...     spark.read.format("huggingface")
...     .option("config", "7M")
...     .option("filters", '[("langdetect", "=", "zh-cn")]')
...     .load("BAAI/Infinity-Instruct")
... )
>>> df_chinese_only.show()
+---+----------------------------+-----+----------+----------+                  
| id|               conversations|label|langdetect|    source|
+---+----------------------------+-----+----------+----------+
|  9|[{human, 因果联系原则是法...|     |     zh-cn|Subjective|
| 19|[{human, 用经济学知识分析...|     |     zh-cn|Subjective|
| 38| [{human, 某个考试共有A、...|     |     zh-cn|Subjective|
| 39|[{human, 撰写一篇关于斐波...|     |     zh-cn|Subjective|
| 57|[{human, 总结世界历史上的...|     |     zh-cn|Subjective|
| 61|[{human, 生成一则广告词。...|     |     zh-cn|Subjective|
| 66|[{human, 描述一个有效的团...|     |     zh-cn|Subjective|
| 94|[{human, 如果比利和蒂芙尼...|     |     zh-cn|Subjective|
|102|[{human, 生成一句英文名言...|     |     zh-cn|Subjective|
|106|[{human, 写一封感谢信，感...|     |     zh-cn|Subjective|
|118| [{human, 生成一个故事。}...|     |     zh-cn|Subjective|
|174|[{human, 高胆固醇水平的后...|     |     zh-cn|Subjective|
|180|[{human, 基于以下角色信息...|     |     zh-cn|Subjective|
|192|[{human, 请写一篇文章，概...|     |     zh-cn|Subjective|
|221|[{human, 以诗歌形式表达对...|     |     zh-cn|Subjective|
|228|[{human, 根据给定的指令，...|     |     zh-cn|Subjective|
|236|[{human, 打开一个新的生成...|     |     zh-cn|Subjective|
|260|[{human, 生成一个有关未来...|     |     zh-cn|Subjective|
|268|[{human, 如果有一定数量的...|     |     zh-cn|Subjective|
|273| [{human, 题目：小明有5个...|     |     zh-cn|Subjective|
+---+----------------------------+-----+----------+----------+

>>> import pyspark_huggingface
>>> from pyspark.sql import SparkSession
>>> spark = SparkSession.builder.appName("demo").getOrCreate()
>>> df = (
...     spark.read.format("huggingface")
...     .option("config", "7M")
...     .option("columns", '["source"]')
...     .load("BAAI/Infinity-Instruct")
... )
>>> spark.sql("SELECT source, count(*) AS total FROM {df} GROUP BY source ORDER BY total DESC", df=df).show()
+--------------------+-------+
|              source|  total|
+--------------------+-------+
|                flan|2435840|
|          Subjective|1342427|
|      OpenHermes-2.5| 855478|
|            MetaMath| 690138|
|      code_exercises| 590958|
|Orca-math-word-pr...| 398168|
|          code_bagel| 386649|
|        MathInstruct| 329254|
|python-code-datas...|  88632|
|instructional_cod...|  82920|
|        CodeFeedback|  79513|
|self-oss-instruct...|  50467|
|Evol-Instruct-Cod...|  43354|
|CodeExercise-Pyth...|  27159|
|code_instructions...|  23130|
|  Code-Instruct-700k|  10860|
|Glaive-code-assis...|   9281|
|python_code_instr...|   2581|
|Python-Code-23k-S...|   2297|
+--------------------+-------+

>>> import pyspark_huggingface
>>> df.write.format("huggingface").save("username/dataset_name")

>>> df_chinese_only.write.format("huggingface").mode("overwrite").save("username/Infinity-Instruct-Chinese-Only")

>>> df = spark.read.format("huggingface").option("data_dir", "data").load("buckets/username/my-bucket")
>>> # OR with a glob pattern
>>> # df = spark.read.format("huggingface").option("data_files", "data/*.parquet").load("buckets/username/my-bucket")
>>> df.write.format("huggingface").option("data_dir", "new-data").save("buckets/username/my-bucket")