使用pyspark从每个行的数组中获取不同的计数

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

spark = SparkSession.builder.appName("ArrayCount").getOrCreate()

data = [("A", [1, 2, 3]),
        ("B", [2, 3, 4]),
        ("C", [3, 4, 5])]
df = spark.createDataFrame(data, ["id", "array_col"])

df_exploded = df.select("id", explode("array_col").alias("value"))

result = df_exploded.groupBy("id").agg(countDistinct("value").alias("distinct_count"))

result.show()

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

spark = SparkSession.builder.appName("ArrayCount").getOrCreate()

data = [("A", [1, 2, 3]),
        ("B", [2, 3, 4]),
        ("C", [3, 4, 5])]
df = spark.createDataFrame(data, ["id", "array_col"])

df_exploded = df.select("id", explode("array_col").alias("value"))

result = df_exploded.groupBy("id").agg(countDistinct("value").alias("distinct_count"))

result.show()