Python / Spark将多个变量转换为双精度类型的列

import pandas as pd

# 创建包含多个变量的列表
variables = [1, 2, 3, 4, 5]

# 创建数据框
df = pd.DataFrame({'variables': variables})

# 将列转换为双精度类型
df['variables'] = df['variables'].astype(float)

# 打印转换后的数据框
print(df)

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

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

# 创建包含多个变量的DataFrame
variables = [(1,), (2,), (3,), (4,), (5,)]
df = spark.createDataFrame(variables, ['variables'])

# 将列转换为双精度类型
df = df.withColumn('variables', col('variables').cast('double'))

# 打印转换后的DataFrame
df.show()