Python 从决策树回归器拟合训练数据导致崩溃

试图在一些训练数据上实现决策树回归算法，但调用fit（）时出现错误

    (trainingData, testData) = data.randomSplit([0.7, 0.3])

    vecAssembler = VectorAssembler(inputCols=["_1", "_2", "_3", "_4", "_5", "_6", "_7", "_8", "_9", "_10"], outputCol="features")

    dt = DecisionTreeRegressor(featuresCol="features", labelCol="_11")

    dt_model = dt.fit(trainingData)

生成错误

  File "spark.py", line 100, in <module>
    main()
  File "spark.py", line 87, in main
    dt_model = dt.fit(trainingData)
  File "/opt/spark/python/pyspark/ml/base.py", line 132, in fit
    return self._fit(dataset)
  File "/opt/spark/python/pyspark/ml/wrapper.py", line 295, in _fit
    java_model = self._fit_java(dataset)
  File "/opt/spark/python/pyspark/ml/wrapper.py", line 292, in _fit_java
    return self._java_obj.fit(dataset._jdf)
  File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
  File "/opt/spark/python/pyspark/sql/utils.py", line 79, in deco
    raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.IllegalArgumentException: u'requirement failed: Column features must be of type struct<type:tinyint,size:int,indices:array<int>,values:array<double>> but was actually struct<type:tinyint,size:int,indices:array<int>,values:array<double>>.'

文件“spark.py”，第100行，在
main（）
文件“spark.py”，第87行，主
dt_模型=dt.拟合（训练数据）
文件“/opt/spark/python/pyspark/ml/base.py”，第132行，适合
返回自拟合（数据集）
文件“/opt/spark/python/pyspark/ml/wrapper.py”，第295行，格式为
java\u model=self.\u fit\u java（数据集）
java中的文件“/opt/spark/python/pyspark/ml/wrapper.py”，第292行
返回self.\u java\u obj.fit（dataset.\u jdf）
文件“/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py”，第1257行，in_u调用__
文件“/opt/spark/python/pyspark/sql/utils.py”，第79行，deco格式
引发IllegalArgumentException（s.split（“：”，1）[1]，stackTrace）
pyspark.sql.utils.IllegalArgumentException:u“要求失败：列功能必须是struct类型，但实际上是struct。”

---

但是数据结构完全相同。

您缺少两个步骤。1.变换部分，和2。从转换的数据中选择要素和标签。我假设数据只包含数字数据，即没有分类数据。我将使用

pyspark.ml

编写一个通用的模型训练流程，以帮助您

from pyspark.ml.feature
from pyspark.ml.classification import DecisionTreeClassifier

#date processing part

vecAssembler = VectorAssembler(input_cols=['col_1','col_2',...,'col_10'],outputCol='features')

#you missed these two steps
trans_data = vecAssembler.transform(data)

final_data = trans_data.select('features','col_11') #your label column name is col_11

train_data, test_data = final_data.randomSplit([0.7,0.3])

#ml part

dt = DecisionTreeClassifier(featuresCol='features',labelCol='col_11')

dt_model = dt.fit(train_data)

dt_predictions = dt_model.transform(test_data)

#proceed with the model evaluation part after this