使用 VotingClassifier 在 sklearn2pmml 中保存模型时出错

Question

我是编程新手，在 pmml 中保存模型时遇到了一些问题。我有一个数据库，我需要选择属性，然后使用多数票，最后保存在 pmml 中。即使是多数投票部分也有效，但是当我使用 sklearn2pmml 将模型保存在最后一行时，它会出错。

from pandas import read_csv
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from mlxtend.classifier import EnsembleVoteClassifier
from sklearn.metrics import accuracy_score
from sklearn2pmml import make_pmml_pipeline
from sklearn2pmml import sklearn2pmml
from sklearn.compose import ColumnTransformer, make_column_transformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn2pmml.pipeline import PMMLPipeline
from sklearn.ensemble import VotingClassifier
import joblib

url = 'D:/treinamento.CSV'
df = read_csv(url, header=None)
data = df.values

url_test = 'D:/TESTE.CSV'
df_test = read_csv(url_test, header=None)
data_test = df_test.values
   
X = data[:, :-1]
y = data_test[:, -1]

X_train = data[:, :-1]
X_test = data_test[:, :-1]
y_train = data[:, -1]
y_test = y
#features selection
features1 = [2, 5, 7]
features2 = [0, 1, 4, 5, 7]
features3 = [0, 1, 4, 5, 6]
features4 = [1, 4]
numeric_transformer = Pipeline(steps=[('scaler', StandardScaler())])
preprocessor1 = ColumnTransformer(transformers=[('numerical', numeric_transformer, features1)])
preprocessor2 = ColumnTransformer(transformers=[('numerical', numeric_transformer, features2)])
preprocessor3 = ColumnTransformer(transformers=[('numerical', numeric_transformer, features3)])
preprocessor4 = ColumnTransformer(transformers=[('numerical', numeric_transformer, features4)])

pipe1 = PMMLPipeline(steps=[('preprocessor', preprocessor1),('classifier', DecisionTreeClassifier(min_samples_split = 2))])
pipe2 = PMMLPipeline(steps=[('preprocessor', preprocessor2),('classifier', DecisionTreeClassifier(min_samples_split = 2))])
pipe3 = PMMLPipeline(steps=[('preprocessor', preprocessor3),('classifier', DecisionTreeClassifier(min_samples_split = 2))])
pipe4 = PMMLPipeline(steps=[('preprocessor', preprocessor4),('classifier', DecisionTreeClassifier(min_samples_split = 2))])



eclf = VotingClassifier(estimators=[('pipe1', PMMLPipeline(steps=[('preprocessor', preprocessor1),('classifier', DecisionTreeClassifier(min_samples_split = 2))])),
                                    ('pipe2', PMMLPipeline(steps=[('preprocessor', preprocessor2),('classifier', DecisionTreeClassifier(min_samples_split = 2))])),
                                    ('pipe3', PMMLPipeline(steps=[('preprocessor', preprocessor3),('classifier', DecisionTreeClassifier(min_samples_split = 2))])),
                                    ('pipe4', PMMLPipeline(steps=[('preprocessor', preprocessor4),('classifier', DecisionTreeClassifier(min_samples_split = 2))]))], voting='hard', weights=[1,1,1,1])

eclf.fit(X_train, y_train)
yhat = eclf.predict(X_test)
accuracy = accuracy_score(y_test, yhat)
print('Accuracy: %.3f' % (accuracy * 100))

sklearn2pmml(eclf, "D:/Mestrado/ARTIGO DRC/dados_pos_revisao/cross validation - dados reavaliados/4 revisao/5 FOLDS/1 FOLD/eclf.pmml", with_repr = True)

代码错误

65 sklearn2pmml(eclf, "D:/mest/eclf.pmml", with_repr = True)

~\anaconda3\lib\site-packages\sklearn2pmml\__init__.py in sklearn2pmml(pipeline, pmml, user_classpath, with_repr, debug, java_encoding)
    222                 print("{0}: {1}".format(java_version[0], java_version[1]))
    223         if not isinstance(pipeline, PMMLPipeline):
--> 224                 raise TypeError("The pipeline object is not an instance of " + PMMLPipeline.__name__ + ". Use the 'sklearn2pmml.make_pmml_pipeline(obj)' utility function to translate a regular Scikit-Learn estimator or pipeline to a PMML pipeline")
    225         estimator = pipeline._final_estimator
    226         cmd = ["java", "-cp", os.pathsep.join(_classpath(user_classpath)), "org.jpmml.sklearn.Main"]

TypeError: The pipeline object is not an instance of PMMLPipeline. Use the 'sklearn2pmml.make_pmml_pipeline(obj)' utility function to translate a regular Scikit-Learn estimator or pipeline to a PMML pipeline

Answer 1

管道对象不是 PMMLPipeline 的实例

您是否阅读过 SkLearn2PMML 错误信息？可能不会，因为它清楚地说明了问题所在！

您在完全错误的地方使用了PMMLPipeline 类。它只能用作VotingClassifier 估计器的最顶层包装器。

请像这样重新组织您的代码：

pipeline = PMMLPipeline([
  ("classifier", VotingClassifier([
    ("pipe1", Pipeline(...)),
    ("pipe2", Pipeline(...)),
    ("pipe3", Pipeline(...))
  ]))
])
sklearn2pmml(pipeline, "pipeline.pmml")