使用Spark UDF从spark数据帧中提取有符号浮点值的整数/小数部分

from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import FloatType, IntegerType

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

data = [(3.14,), (-2.5,), (7.8,), (-4.2,)]
df = spark.createDataFrame(data, ["value"])
df.show()

+-----+
|value|
+-----+
| 3.14|
| -2.5|
|  7.8|
| -4.2|
+-----+

def extract_decimal(value):
    return int(value) if value >= 0 else int(value) - 1

extract_decimal_udf = udf(extract_decimal, IntegerType())

df = df.withColumn("integer_part", extract_decimal_udf(df["value"]))
df.show()

+-----+------------+
|value|integer_part|
+-----+------------+
| 3.14|           3|
| -2.5|          -2|
|  7.8|           7|
| -4.2|          -5|
+-----+------------+