pyspark 中的交叉验证
在pyspark中调用交叉验证的方式来建模。
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.evaluation import BinaryClassificationEvaluator
from pyspark.ml.tuning import CrossValidator
from pysparl.ml.feature import VectorAssembler
from pyspark.ml.tuning import ParamGridBuilder
df = spark.read_csv('./******/table.csv',header=True,inferSchema = True)#数据集导入
df.show(6)
#数据集展示A
+---+-----+---------------+---------------+----+-----+------+------+------+----+----+----+----+-----+-----+-----+
|Age| BMI|Fasting glucose|Fasting insulin| FSH| LH|LH/FSH| PRL| E2| T| P| TC| TG|HDL-c|LDL-c|class|
+---+-----+---------------+---------------+----+-----+------+------+------+----+----+----+----+-----+-----+-----+
| 25|20.87| 4.69| 11.47|4.94| 6.76| 1.37|558.28|312.38|1.25|1.28|3.84|0.42| 2.46| 1.26| 1.0|
| 27|22.82| 4.4|