如何使用where子句从一个pyspark dataframe获取值

from pyspark.sql import SparkSession

# 初始化Spark会话
spark = SparkSession.builder.appName("example").getOrCreate()

# 创建示例DataFrame
data = [("Alice", 34), ("Bob", 45), ("Cathy", 29)]
columns = ["Name", "Age"]
df = spark.createDataFrame(data, columns)

# 显示原始DataFrame
df.show()

+-----+---+
| Name|Age|
+-----+---+
|Alice| 34|
|  Bob| 45|
|Cathy| 29|
+-----+---+

# 过滤年龄大于30的员工
filtered_df = df.where(df.Age > 30)
filtered_df.show()

+-----+---+
| Name|Age|
+-----+---+
|Alice| 34|
|  Bob| 45|
+-----+---+

# 过滤年龄在30到40之间的员工
filtered_df = df.where((df.Age > 30) & (df.Age < 40))
filtered_df.show()

+-----+---+
| Name|Age|
+-----+---+
|Alice| 34|
+-----+---+

# 错误的示例
# df.where(df.Age > "30")  # 错误：Age列是整数类型，不能与字符串比较

# 正确的示例
df.where(df.Age > 30)  # 正确：使用整数进行比较