AzureML Web服务错误

Question

我尝试使用Python脚本在AzureML中实现随机林分类器。它在实验中运行良好但我在测试Web服务时遇到错误。

# The script MUST contain a function named azureml_main
# which is the entry point for this module.

# imports up here can be used to 
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix

# The entry point function can contain up to two input arguments:
#   Param<dataframe1>: a pandas.DataFrame
#   Param<dataframe2>: a pandas.DataFrame
def azureml_main(dataframe1 = None, dataframe2 = None):

    label_x = dataframe1[['NSP']]
    del dataframe1['NSP']

    label_y = dataframe2[['NSP']]
    del dataframe2['NSP']
    trained_model = random_forest_classifier(dataframe1, label_x)
    # print ("Trained model :: ", trained_model)
    predictions = trained_model.predict(dataframe2)


    # print ("Train Accuracy :: ", accuracy_score(label_x, trained_model.predict(dataframe1)))
    print ("Test Accuracy  :: ", accuracy_score(label_y, predictions))
    # print (" Confusion matrix ", confusion_matrix(dataframe2, predictions))
    cm = confusion_matrix(label_y, predictions)
    TP = cm[0][0]
    FP = cm[0][1]
    FN = cm[1][0]
    TN = cm[1][1]
    print("True Positive: ", TP, "False Positive: ", FP, "True Negative: ", TN, "False Negative: ",FN)
    # If a zip file is connected to the third input port is connected,
    # it is unzipped under ".\Script Bundle". This directory is added
    # to sys.path. Therefore, if your zip file contains a Python file
    # mymodule.py you can import it using:
    # import mymodule

    # Return value must be of a sequence of pandas.DataFrame
    return pd.DataFrame(predictions)

def random_forest_classifier(features, target):
    """
    To train the random forest classifier with features and target data
    :param features:
    :param target:
    :return: trained random forest classifier
    """
    clf = RandomForestClassifier()
    clf.fit(features, target)
    return clf

当我通过输入值测试Web服务时，它会显示此错误。

  

85：错误0085：脚本评估期间发生以下错误，请查看输出日志以获取更多信息：---------- Python解释器启动错误消息-------- - 执行函数时捕获异常：Traceback（最近一次调用最后一次）：文件＆＃34; \ server \ InvokePy.py＆＃34;，第120行，在executeScript outframe = mod.azureml_main（* inframes）文件＆＃34; \ temp-6305281036382248739.py＆＃34;，第52行，在azureml_main文件＆＃34; C：\ pyhome \ lib \ site-packages \ sklearn \ ensemble \ forest.py＆＃34;，第498行，预测proba = self .predict_proba（X）文件＆＃34; C：\ pyhome \ lib \ site-packages \ sklearn \ ensemble \ forest.py＆＃34;，第537行，在predict_proba中X = self._validate_X_predict（X）文件＆＃34; C：\ pyhome \ lib \ site-packages \ sklearn \ ensemble \ forest.py＆＃34;，第319行，在_validate_X_predict中返回self.estimators_ [0] ._ validate_X_predict（X，check_input = True）文件＆＃34; C： \ pyhome \ lib \ site-packages \ sklearn \ tree \ tree.py＆＃34;，第365行，在_validate_X_predict中X = check_array（X，dtype = DTYPE，acce pt_sparse =＆＃34; csr＆＃34;）文件＆＃34; C：\ pyhome \ lib \ site-packages \ sklearn \ utils \ validation.py＆＃34;，第407行，在check_array上下文中））ValueError：Found array 0个样本（形状=（0,21）），最小值为1。 ----------来自Python解释器的错误消息结束----------，错误代码：ModuleExecutionError，Http状态代码：400，时间戳：星期四，2017年12月7日15:24： 18 GMT

谁能告诉我错误在哪里？