Question

我在使用基于树的基于python的算法时遇到问题：这是我的火车功能：

# The function to execute the training.
def train():
    print('Starting the training.')
    try:

        # Take the set of files and read them all into a single pandas dataframe
        input_files = [ os.path.join(training_path, file) for file in os.listdir(training_path) ]
        if len(input_files) == 0:
            raise ValueError(('There are no files in {}.\n' +
                              'This usually indicates that the channel ({}) was incorrectly specified,\n' +
                              'the data specification in S3 was incorrectly specified or the role specified\n' +
                              'does not have permission to access the data.').format(training_path, channel_name))
        raw_data = [ pd.read_csv(file, header=0) for file in input_files ]
        train_data = pd.concat(raw_data)

        # labels are in the first column
        train_y = train_data.ix[:,0]
        train_X = train_data.ix[:,1:]

        # Now use scikit-learn's decision tree classifier to train the model.
        clf = tree.DecisionTreeClassifier(max_leaf_nodes=50)
        clf = clf.fit(train_X, train_y)

        # save the model
        with open(os.path.join(model_path, 'tree-model.pkl'), 'wb') as out:
            pickle.dump(clf, out, protocol=0)
        print('Training complete.')
    except Exception as e:
        # Write out an error file. This will be returned as the failureReason in the
        # DescribeTrainingJob result.
        trc = traceback.format_exc()
        with open(os.path.join(output_path, 'failure'), 'w') as s:
            s.write('Exception during training: ' + str(e) + '\n' + trc)
        # Printing this causes the exception to be in the training job logs, as well.
        print('Exception during training: ' + str(e) + '\n' + trc, file=sys.stderr)
        # A non-zero exit code causes the training job to be marked as Failed.
        sys.exit(255)

if __name__ == '__main__':
    train()

    # A zero exit code causes the job to be marked a Succeeded.
    sys.exit(0)

我使用此数据集进行了训练：

    setosa  5.1     3.5     1.4     0.2
0   setosa  4.9     3.0     1.4     0.2
1   setosa  4.7     3.2     1.3     0.2
2   setosa  4.6     3.1     1.5     0.2
3   setosa  5.0     3.6     1.4     0.2
4   setosa  5.4     3.9     1.7     0.4
5   setosa  4.6     3.4     1.4     0.3

但是当我尝试使用测试数据预测价值时：

import itertools

a = [20*i for i in range(3)]
b = [10+i for i in range(10)]
indices = [i+j for i,j in itertools.product(a,b)]

test_data=shape.iloc[indices[:-1]]
test_X=test_data.iloc[:,1:]
test_y=test_data.iloc[:,0]

test_X.values

array([[4.8, 3.4, 1.6, 0.2],
       [4.8, 3. , 1.4, 0.1],
       [4.3, 3. , 1.1, 0.1],
       [5.8, 4. , 1.2, 0.2],
       [5.7, 4.4, 1.5, 0.4],
       [5.4, 3.9, 1.3, 0.4],
       [5.1, 3.5, 1.4, 0.3],
       [5.7, 3.8, 1.7, 0.3],
       [5.1, 3.8, 1.5, 0.3],
       [5.4, 3.4, 1.7, 0.2],
       [5.4, 3.4, 1.5, 0.4],
       [5.2, 4.1, 1.5, 0.1],
       [5.5, 4.2, 1.4, 0.2],
       [4.9, 3.1, 1.5, 0.2],
       [5. , 3.2, 1.2, 0.2],
       [5.5, 3.5, 1.3, 0.2],
       [4.9, 3.6, 1.4, 0.1],
       [4.4, 3. , 1.3, 0.2],
       [5.1, 3.4, 1.5, 0.2],
       [5. , 3.5, 1.3, 0.3],
       [6.4, 3.2, 4.5, 1.5],
       [6.9, 3.1, 4.9, 1.5],
       [5.5, 2.3, 4. , 1.3],
       [6.5, 2.8, 4.6, 1.5],
       [5.7, 2.8, 4.5, 1.3],
       [6.3, 3.3, 4.7, 1.6],
       [4.9, 2.4, 3.3, 1. ],
       [6.6, 2.9, 4.6, 1.3],
       [5.2, 2.7, 3.9, 1.4]])

我收到此错误消息：

ValueError: Number of features of the model must match the input. Model n_features is 4 and input n_features is 3

很奇怪，我在测试和培训数据中看到有4种特征，我不知道为什么它只能识别3种

能帮我解决这个问题吗？

谢谢

模型的特征数量必须与输入匹配。模型n_features为4，输入n_features为3

0 个答案: