给我一份基于spark对二手车价格进行可视化与预测的完整代码

好的，以下是基于 Spark 的二手车价格可视化与预测的完整代码，供你参考：

# 导入必要的库
from pyspark import SparkConf, SparkContext
from pyspark.sql import SparkSession, functions as F
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.regression import GBTRegressor
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder

# 创建 SparkSession
conf = SparkConf().setAppName("二手车价格预测").setMaster("local[*]")
sc = SparkContext(conf=conf)
spark = SparkSession.builder.config(conf=conf).getOrCreate()

# 读取数据
df = spark.read.csv("path/to/dataset.csv", header=True, inferSchema=True)

# 数据清洗
df = df.select("brand", "model", "year", "mileage", "price")
df = df.filter("brand is not null and model is not null and year is not null and mileage is not null and price is not null")
df = df.filter("year >= 2000 and year <= 2021")
df = df.filter("mileage >= 0 and mileage <= 300000")
df = df.filter("price >= 0 and price <= 1000000")

# 特征工程
assembler = VectorAssembler(inputCols=["year", "mileage"], outputCol="features")
data = assembler.transform(df).select("brand", "model", "features", "price")

# 划分训练集和测试集
train_data, test_data = data.randomSplit([0.7, 0.3], seed=123)

# 定义模型
gbt = GBTRegressor(featuresCol="features", labelCol="price")

# 定义参数网