python
import pyspark
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.regression import LinearRegression
spark = pyspark.sql.SparkSession.builder.getOrCreate()
df = spark.read.csv('data.csv', header=True, inferSchema=True)
assembler = VectorAssembler(inputCols=['feature1', 'feature2'], outputCol='features')
df = assembler.transform(df)
train_df, test_df = df.randomSplit([0.7, 0.3])
lr = LinearRegression(featuresCol='features', labelCol='label')
model = lr.fit(train_df)
predictions = model.transform(test_df)
evaluator = RegressionEvaluator(labelCol='label', predictionCol='prediction')
rmse = evaluator.evaluate(predictions, {evaluator.metricName: 'rmse'})
r2 = evaluator.evaluate(predictions, {evaluator.metricName: 'r2'})
print("RMSE:", rmse)
print("R2 Score:", r2)
