如何使用pyspark读取Excel文件？

pip install pyspark pandas

from pyspark.sql import SparkSession
import pandas as pd

spark = SparkSession.builder \
    .appName("Read Excel with PySpark") \
    .getOrCreate()

excel_data = pd.read_excel("path/to/excel_file.xlsx")
df = spark.createDataFrame(excel_data)

# 示例：筛选出年龄大于30的数据
filtered_data = df.filter(df.age > 30)

filtered_data.show()

from pyspark.sql import SparkSession
import pandas as pd

# 创建SparkSession
spark = SparkSession.builder \
    .appName("Read Excel with PySpark") \
    .getOrCreate()

# 读取Excel文件
excel_data = pd.read_excel("path/to/excel_file.xlsx")
df = spark.createDataFrame(excel_data)

# 处理Excel数据
filtered_data = df.filter(df.age > 30)

# 显示结果
filtered_data.show()