通过在pyspark - sql中将字符串列转换为整型来获取非空值的计数

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

# 创建SparkSession
spark = SparkSession.builder.appName("String to Integer Conversion").getOrCreate()

# 读取数据
data = [("John", "25"), ("Alice", "30"), ("Bob", ""), ("Tom", "35")]
df = spark.createDataFrame(data, ["Name", "Age"])

# 将字符串列转换为整型，并过滤出非空值
filtered_df = df.filter(col("Age").cast("integer").isNotNull())

# 获取非空值的计数
count = filtered_df.count()

# 打印结果
print("非空值的计数：", count)

# 关闭SparkSession
spark.stop()