将Pandas最佳拟合函数转换为pyspark

import pandas as pd
from pyspark.sql import SparkSession
from pyspark.ml.regression import LinearRegression
from pyspark.ml.feature import VectorAssembler

spark = SparkSession.builder.getOrCreate()

# 假设有一个名为df的Pandas DataFrame，包含特征列'x'和目标列'y'
# 将Pandas DataFrame转换为Spark DataFrame
spark_df = spark.createDataFrame(df)

# 创建特征向量列
assembler = VectorAssembler(inputCols=['x'], outputCol='features')
spark_df = assembler.transform(spark_df)

# 创建线性回归模型对象
lr = LinearRegression(featuresCol='features', labelCol='y')

# 拟合数据
model = lr.fit(spark_df)

# 获取系数
coefficients = model.coefficients

# 获取截距
intercept = model.intercept