从Pyspark列提取时间字段与从Pandas datetime列提取时间字段

from pyspark.sql import SparkSession
from pyspark.sql.functions import to_timestamp, hour, minute, second

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("2022-01-01 10:30:00"), ("2022-01-01 12:45:00")]
df = spark.createDataFrame(data, ["timestamp"])

# 将字符串列转换为时间戳类型
df = df.withColumn("timestamp", to_timestamp(df.timestamp))

# 提取时间字段
df = df.withColumn("hour", hour(df.timestamp))
df = df.withColumn("minute", minute(df.timestamp))
df = df.withColumn("second", second(df.timestamp))

# 显示结果
df.show()

import pandas as pd

# 创建示例数据
data = {"timestamp": ["2022-01-01 10:30:00", "2022-01-01 12:45:00"]}
df = pd.DataFrame(data)

# 将字符串列转换为日期时间类型
df["timestamp"] = pd.to_datetime(df["timestamp"])

# 提取时间字段
df["hour"] = df["timestamp"].dt.hour
df["minute"] = df["timestamp"].dt.minute
df["second"] = df["timestamp"].dt.second

# 显示结果
print(df)