当我尝试将我的Pipeline提交到评分系统时，我会收到下面的ValueError。我不确定我应该从哪里删除12500行数据。
ValueError: blocks[0,:] has incompatible row dimensions. Got blocks[0,2].shape[0] == 13892, expected 1544.我的任务是构建一个模型，将疗养院的业务特征与它们的第一周期调查结果以及第一周期与第二周期调查之间的时间相结合，以预测第二周期的总分数。
这是我用来完成上述任务的代码。
# 创建一个自定义转换器来计算调查1与调查2时间之间的差值class TimedeltaTransformer(BaseEstimator, TransformerMixin): def __init__(self, t1_col, t2_col): self.t1_col = t1_col self.t2_col = t2_col def fit(self, X, y=None): if not isinstance(X, pd.DataFrame): X = pd.DataFrame(X) self.col_1 = X[self.t1_col].apply(pd.to_datetime) self.col_2 = X[self.t2_col].apply(pd.to_datetime) return self def transform(self, X): difference_list = [] difference = self.col_1 - self.col_2 for obj in difference: difference_list.append(obj.total_seconds()) return np.array(difference_list).reshape(-1,1)# 创建TimedeltaTransformer对象cycle_1_date = 'CYCLE_1_SURVEY_DATE'cycle_2_date = 'CYCLE_2_SURVEY_DATE'time_feature = TimedeltaTransformer(cycle_1_date, cycle_2_date)# 使用自定义列选择转换器来提取cycle_1_featurescycle_1_cols = ['CYCLE_1_DEFS', 'CYCLE_1_NFROMDEFS', 'CYCLE_1_NFROMCOMP', 'CYCLE_1_DEFS_SCORE', 'CYCLE_1_NUMREVIS', 'CYCLE_1_REVISIT_SCORE', 'CYCLE_1_TOTAL_SCORE']cycle_1_features = Pipeline([ ('cst2', ColumnSelectTransformer(cycle_1_cols)), ])# 创建我的survey_model Pipeline对象# Pipeline对象是一个两步过程，首先是一个特征联合转换# 并结合业务特征、cycle_1特征以及时间特征；然后将转换后的特征拟合到# RandomForestRegressorsurvey_model = Pipeline([ ('features', FeatureUnion([ ('business', business_features), ('survey', cycle_1_features), ('time', time_feature), ])), ('forest', RandomForestRegressor()),])# 拟合我的pipeline不会产生错误survey_model.fit(data, cycle_2_score.astype(int))# 调用predict函数并将其传递给评分系统会引发ValueErrorgrader.score.ml__survey_model(survey_model.predict)拟合后的pipeline看起来像这样
Pipeline(memory=None, steps=[('features', FeatureUnion(n_jobs=None, transformer_list=[('business', FeatureUnion(n_jobs=None, transformer_list=[('simple', Pipeline(memory=None, steps=[('cst', ColumnSelectTransformer(columns=['BEDCERT', 'RESTOT', 'INHOSP', 'CCRC_FACIL', 'SFF', 'CHOW_LAST_12MOS', 'SPRINKLER_STATUS', 'EXP_TOTAL', 'ADJ_TOTAL'])), ('imputer', SimpleImpute... transformer_weights=None, verbose=False)), ('forest', RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=None, verbose=0, warm_start=False))], verbose=False)一些额外背景：我正在构建这个模型，以便将其predict方法传递到一个自定义的评分系统中用于一个项目。评分系统将一个字典列表传递给我的估计器的predict或predict_proba方法，而不是一个DataFrame。这意味着模型必须能够处理这两种数据类型。因此，我需要提供一个自定义的ColumnSelectTransformer来代替scikit-learn自己的ColumnTransformer。
下面是与业务特征和ColumnSelectTransformer相关的额外代码
# 自定义转换器，用于从数据框中选择列并返回数组class ColumnSelectTransformer(BaseEstimator, TransformerMixin): def __init__(self, columns): self.columns = columns def fit(self, X, y=None): return self def transform(self, X): if not isinstance(X, pd.DataFrame): X = pd.DataFrame(X) return X[self.columns].valuessimple_features = Pipeline([ ('cst', ColumnSelectTransformer(simple_cols)), ('imputer', SimpleImputer(strategy='mean')),])owner_onehot = Pipeline([ ('cst', ColumnSelectTransformer(['OWNERSHIP'])), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder()),])cert_onehot = Pipeline([ ('cst', ColumnSelectTransformer(['CERTIFICATION'])), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder()),])categorical_features = FeatureUnion([ ('owner_onehot', owner_onehot), ('cert_onehot', cert_onehot),])business_features = FeatureUnion([ ('simple', simple_features), ('categorical', categorical_features)])最后，这是完整的错误信息
---------------------------------------------------------------------------ValueError Traceback (most recent call last)<ipython-input-165-790ca6139493> in <module>()----> 1 grader.score.ml__survey_model(survey_model.predict)/opt/conda/lib/python3.7/site-packages/static_grader/grader.py in func(*args, **kw) 92 def __getattr__(self, method): 93 def func(*args, **kw):---> 94 return self(method, *args, **kw) 95 return func 96 /opt/conda/lib/python3.7/site-packages/static_grader/grader.py in __call__(self, question_name, func) 88 return 89 test_cases = json.loads(resp.text)---> 90 test_cases_grading(question_name, func, test_cases) 91 92 def __getattr__(self, method):/opt/conda/lib/python3.7/site-packages/static_grader/grader.py in test_cases_grading(question_name, func, test_cases) 40 for test_case in test_cases: 41 if inspect.isroutine(func):---> 42 sub_res = func(*test_case['args'], **test_case['kwargs']) 43 elif not test_case['args'] and not test_case['kwargs']: 44 sub_res = func/opt/conda/lib/python3.7/site-packages/sklearn/utils/metaestimators.py in <lambda>(*args, **kwargs) 114 115 # lambda, but not partial, allows help() to work with update_wrapper--> 116 out = lambda *args, **kwargs: self.fn(obj, *args, **kwargs) 117 # update the docstring of the returned function 118 update_wrapper(out, self.fn)/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in predict(self, X, **predict_params) 419 Xt = X 420 for _, name, transform in self._iter(with_final=False):--> 421 Xt = transform.transform(Xt) 422 return self.steps[-1][-1].predict(Xt, **predict_params) 423 /opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in transform(self, X) 963 return np.zeros((X.shape[0], 0)) 964 if any(sparse.issparse(f) for f in Xs):--> 965 Xs = sparse.hstack(Xs).tocsr() 966 else: 967 Xs = np.hstack(Xs)/opt/conda/lib/python3.7/site-packages/scipy/sparse/construct.py in hstack(blocks, format, dtype) 463 464 """--> 465 return bmat([blocks], format=format, dtype=dtype) 466 467 /opt/conda/lib/python3.7/site-packages/scipy/sparse/construct.py in bmat(blocks, format, dtype) 584 exp=brow_lengths[i], 585 got=A.shape[0]))--> 586 raise ValueError(msg) 587 588 if bcol_lengths[j] == 0:ValueError: blocks[0,:] has incompatible row dimensions. Got blocks[0,2].shape[0] == 13892, expected 1544.回答：
修复我的TimedeltaTransformer有帮助。
class TimedeltaTransformer(BaseEstimator, TransformerMixin): def __init__(self, t1_col, t2_col): self.t1_col = t1_col self.t2_col = t2_col def fit(self, X, y=None): return self def transform(self, X): if not isinstance(X, pd.DataFrame): X = pd.DataFrame(X) timedelta_series = (pd.to_datetime(X[self.t1_col]) - pd.to_datetime(X[self.t2_col])) array_list = [] for x in timedelta_series: array_list.append(x.total_seconds()) return np.array(array_list).reshape(-1,1)