pyspark中从JSON到Dataframe的数组

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, explode

spark = SparkSession.builder.getOrCreate()

json_data = spark.read.json('path/to/json_file.json')

[
    {
        "name": "Alice",
        "age": 25,
        "languages": ["Python", "Java", "Scala"]
    },
    {
        "name": "Bob",
        "age": 30,
        "languages": ["C++", "Go", "Rust"]
    }
]

df = json_data.select(
    col("name"),
    col("age"),
    explode("languages").alias("language")
)

df.show()

+-----+---+--------+
| name|age|language|
+-----+---+--------+
|Alice| 25|  Python|
|Alice| 25|    Java|
|Alice| 25|   Scala|
|  Bob| 30|     C++|
|  Bob| 30|      Go|
|  Bob| 30|    Rust|
+-----+---+--------+