Develop Reference

ValueError: could not convert string to float: '4223-BKEOR'

directory = "path/to/directory"
filename = "C:\\Users\\home\\Desktop\\Python Projects\\TelcomCustomer-Churn_2.csv"
full_path = os.path.join(directory, filename)
def load_csv(path='C:\\Users\\home\\Desktop\\Python Projects\\TelcomCustomer-Churn_2.csv'):
df = pd.read_csv('C:\\Users\\home\\Desktop\\Python Projects\\TelcomCustomer-Churn_2.csv')
return df
def preprocess_data(df):
df['TotalCharges'] = df['TotalCharges'].replace(" ", 0).astype('float')
​
# Identify numeric and categorical columns
numeric_cols = df.select_dtypes(include='number').columns.tolist()
categorical_cols = df.select_dtypes(include='object').columns.tolist()
​
# Fill in missing numeric values with the mean of the column
for col in numeric_cols:
df[col].fillna(df[col].mean(), inplace=True)
​
# Fill in missing categorical values with the mode of the column
for col in categorical_cols:
df[col].fillna(df[col].mode()[0], inplace=True)
​
# Drop duplicates
df.drop_duplicates(inplace=True)
​
# One-hot encode categorical features
X_cat = pd.get_dummies(df, columns=categorical_cols)
​
X = X_cat.drop(columns='Churn_Yes', axis=1)
y = X_cat['Churn_Yes']
return X, y
def Split_data(X, y):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
return X_train_scaled, X_test_scaled, y_train, y_test
)
print(Split_data(X, y))
the error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_592\3782283586.py in <module>
----> 1 print(Split_data(X, y))
~\AppData\Local\Temp\ipykernel_592\18160545.py in Split_data(X, y)
5 # Scale the features
6 scaler = StandardScaler()
----> 7 X_train_scaled = scaler.fit_transform(X_train)
8 X_test_scaled = scaler.transform(X_test)
9 return X_train_scaled, X_test_scaled, y_train, y_test
~\anaconda3\lib\site-packages\sklearn\base.py in fit_transform(self, X, y, **fit_params)
850 if y is None:
851 # fit method of arity 1 (unsupervised transformation)
--> 852 return self.fit(X, **fit_params).transform(X)
853 else:
854 # fit method of arity 2 (supervised transformation)
~\anaconda3\lib\site-packages\sklearn\preprocessing\_data.py in fit(self, X, y, sample_weight)
804 # Reset internal state before fitting
805 self._reset()
--> 806 return self.partial_fit(X, y, sample_weight)
807
808 def partial_fit(self, X, y=None, sample_weight=None):
~\anaconda3\lib\site-packages\sklearn\preprocessing\_data.py in partial_fit(self, X, y, sample_weight)
839 """
840 first_call = not hasattr(self, "n_samples_seen_")
--> 841 X = self._validate_data(
842 X,
843 accept_sparse=("csr", "csc"),
~\anaconda3\lib\site-packages\sklearn\base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
564 raise ValueError("Validation should be done on X, y or both.")
565 elif not no_val_X and no_val_y:
--> 566 X = check_array(X, **check_params)
567 out = X
568 elif no_val_X and not no_val_y:
~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
744 array = array.astype(dtype, casting="unsafe", copy=False)
745 else:
--> 746 array = np.asarray(array, order=order, dtype=dtype)
747 except ComplexWarning as complex_warning:
748 raise ValueError(
~\anaconda3\lib\site-packages\pandas\core\generic.py in __array__(self, dtype)
2062
2063 def __array__(self, dtype: npt.DTypeLike | None = None) -> np.ndarray:
-> 2064 return np.asarray(self._values, dtype=dtype)
2065
2066 def __array_wrap__(
ValueError: could not convert string to float: '4223-BKEOR'
I did not understand where i have done the mistake in the above code

The error happend because one of the data in your X_train contains non numeric value.
Try the below and see if it works:
numeric_cols = X_train.select_dtypes(include='number').columns.tolist()
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train[numeric_cols])
X_test_scaled = scaler.transform(X_test[numeric_cols])

It happens beacause,your dataset may contains some of the column as object type, as python by default allocated memory in heap. So check the datatypes of column in dataframe by dataset_Name.dtypes and make sure to typecast it into float64.

i want to establish a pipe line to pubg data on kaggle to procces it but when i implement a pipe line this error get to me

i want to establish a pipe line to pubg data on kaggle to procces it but when i implement a pipe line this error get to me:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
/tmp/ipykernel_35/3879657662.py in <module>
8 ])
9
---> 10 pubg_num_tr = num_pipeline.fit_transform(pubg_num)
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
424 """
425 fit_params_steps = self._check_fit_params(**fit_params)
--> 426 Xt = self._fit(X, y, **fit_params_steps)
427
428 last_step = self._final_estimator
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
353 message_clsname="Pipeline",
354 message=self._log_message(step_idx),
--> 355 **fit_params_steps[name],
356 )
357 # Replace the transformer of the step with the fitted
/opt/conda/lib/python3.7/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
347
348 def __call__(self, *args, **kwargs):
--> 349 return self.func(*args, **kwargs)
350
351 def call_and_shelve(self, *args, **kwargs):
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
891 with _print_elapsed_time(message_clsname, message):
892 if hasattr(transformer, "fit_transform"):
--> 893 res = transformer.fit_transform(X, y, **fit_params)
894 else:
895 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.7/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
845 if y is None:
846 # fit method of arity 1 (unsupervised transformation)
--> 847 return self.fit(X, **fit_params).transform(X)
848 else:
849 # fit method of arity 2 (supervised transformation)
/tmp/ipykernel_35/2077244363.py in transform(self, X)
13 total_distance = X[:, walkDistance_ix] + X[:, rideDistance_ix]+X[:, swimDistance_ix]
14 if self.add_total_distance_per_seconda:
---> 15 add_total_distance_per_seconda = X[:, total_distance] / X[:, matchDuration_ix]
16 return np.c_[X, walk_distance_per_seconda, total_distance,
17 add_total_distance_per_seconda]
IndexError: arrays used as indices must be of integer (or boolean) type
my pipeline code is:
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
num_pipeline = Pipeline([
('imputer', SimpleImputer(strategy="median")),
('attribs_adder', CombinedAttributesAdder()),
('std_scaler', StandardScaler())
])
pubg_num_tr = num_pipeline.fit_transform(pubg_num)
i implemented an attribute adder and it worked properly but when i turn on the pipline it fails, i need a solution without the need to converse a float to integers because it harms data.

ValueError when using ColumnTransformer() in an Sklearn Pipeline - Using custom class of Spacy for GloveVectorizer

I've got a dataset with multiple text columns and a target column. I'm trying to use a Cusom Class of Spacy to use Glove embeddings for my text column, and also trying to do it with a Pipeline. But I'm getting a ValueError. Following is my code:
data_features = df.copy()[["title", "description"]]
train_data, test_data, train_target, test_target = train_test_split(data_features, df['target'], test_size = 0.1)
I created this custom class to use glove embeddings. I got the code from this tutorial.
class SpacyVectorTransformer(BaseEstimator, TransformerMixin):
def __init__(self, nlp):
self.nlp = nlp
self.dim = 300
def fit(self, X, y):
return self
def transform(self, X):
return [self.nlp(text).vector for text in X]
Loading the nlp model:
nlp = spacy.load("en_core_web_sm")
This is the column transformer that I'm trying to use in my pipeline:
col_preprocessor = ColumnTransformer(
[
('title_glove', SpacyVectorTransformer(nlp), 'title'),
('description_glove', SpacyVectorTransformer(nlp), 'description'),
],
remainder='drop',
n_jobs=1
)
Here is my pipeline:
pipeline_glove = Pipeline([
('col_preprocessor', col_preprocessor),
('classifier', LogisticRegression())
])
When I run the fit method, I get the error that follows:
pipeline_glove.fit(train_data, train_target)
Error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-219-8543ea744205> in <module>
----> 1 pipeline_glove.fit(train_data, train_target)
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
328 """
329 fit_params_steps = self._check_fit_params(**fit_params)
--> 330 Xt = self._fit(X, y, **fit_params_steps)
331 with _print_elapsed_time('Pipeline',
332 self._log_message(len(self.steps) - 1)):
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
294 message_clsname='Pipeline',
295 message=self._log_message(step_idx),
--> 296 **fit_params_steps[name])
297 # Replace the transformer of the step with the fitted
298 # transformer. This is necessary when loading the transformer
/opt/conda/lib/python3.7/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
353
354 def __call__(self, *args, **kwargs):
--> 355 return self.func(*args, **kwargs)
356
357 def call_and_shelve(self, *args, **kwargs):
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
738 with _print_elapsed_time(message_clsname, message):
739 if hasattr(transformer, 'fit_transform'):
--> 740 res = transformer.fit_transform(X, y, **fit_params)
741 else:
742 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.7/site-packages/sklearn/compose/_column_transformer.py in fit_transform(self, X, y)
549
550 self._update_fitted_transformers(transformers)
--> 551 self._validate_output(Xs)
552
553 return self._hstack(list(Xs))
/opt/conda/lib/python3.7/site-packages/sklearn/compose/_column_transformer.py in _validate_output(self, result)
410 raise ValueError(
411 "The output of the '{0}' transformer should be 2D (scipy "
--> 412 "matrix, array, or pandas DataFrame).".format(name))
413
414 def _validate_features(self, n_features, feature_names):
ValueError: The output of the 'title_glove' transformer should be 2D (scipy matrix, array, or pandas DataFrame).

the error message tells you, what you need to fix.
ValueError: The output of the 'title_glove' transformer should be 2D
(scipy matrix, array, or pandas DataFrame).
But what you are returning with your current transformer (SpacyVectorTransformer) is a list. You can fix it, by turning the list into a pandas DataFrame for instance like this:
import pandas as pd
class SpacyVectorTransformer(BaseEstimator, TransformerMixin):
def __init__(self, nlp):
self.nlp = nlp
self.dim = 300
def fit(self, X, y):
return self
def transform(self, X):
return pd.DataFrame([self.nlp(text).vector for text in X])
Next time, please also provide a minimal, reproducible example. In your provided code, there are no imports as well as no DataFrame called "df".

Unable to fit() a Scikit-Learn pipeline without being returned a ValueError

I need your help!
I've been getting a ValueError below when trying to fit my Pipeline.
ValueError: blocks[0,:] has incompatible row dimensions. Got blocks[0,2].shape[0] == 1, expected 13892.
I've been tasked to build a model that combines the business_features of nursing homes with their cycle 1 survey results, as well as the time between the cycle 1 and cycle 2 survey to predict the cycle 2 total score.
This is my code that I'm using to accomplish the task above.
# Creating a custom transformer to calculate the difference between survey
# 1 & survey 2 times
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):
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 = self.col_1 - self.col_2
return difference.values
# Creating TimedeltaTransformer object
cycle_1_date = 'CYCLE_1_SURVEY_DATE'
cycle_2_date = 'CYCLE_2_SURVEY_DATE'
time_feature = TimedeltaTransformer(cycle_1_date, cycle_2_date)
# Using a custom column selecter transformer to extract cycle_1_features
cycle_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)),
])
# Creating my survey_model Pipeline object
# Pipeline object is a 2 step process, first a feature union transforming
# and combining the business features, cycle_1 features as well as time
# feature; followed by fitting the transformed features into a
# RandomForestRegressor
survey_model = Pipeline([
('features', FeatureUnion([
('business', business_features),
('survey', cycle_1_features),
('time', time_feature),
])),
('forest', RandomForestRegressor()),
])
# Trying to fit my Pipeline throws the ValueError described above
survey_model.fit(data, cycle_2_score.astype(int))
Some additional context: I'm building this model to have its predict_proba method passed into a custom grader for a project. The grader passes a list of dictionaries to the predict or predict_proba method of my estimator, not a DataFrame. This means that the model must work with both data types. For this reason, I need to provide a custom ColumnSelectTransformer to use instead scikit-learn's own ColumnTransformer.
Below is additional code related to the business features and ColumnSelectTransformer
# Custom transformer to select columns from a dataframe and returns the
# dataframe as an array
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].values
simple_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)
])
Finally, below is the full error raised
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-218-046724d81b69> in <module>()
----> 1 survey_model.fit(data, cycle_2_score.astype(int))
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
350 This estimator
351 """
--> 352 Xt, fit_params = self._fit(X, y, **fit_params)
353 with _print_elapsed_time('Pipeline',
354 self._log_message(len(self.steps) - 1)):
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
315 message_clsname='Pipeline',
316 message=self._log_message(step_idx),
--> 317 **fit_params_steps[name])
318 # Replace the transformer of the step with the fitted
319 # transformer. This is necessary when loading the transformer
/opt/conda/lib/python3.7/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
353
354 def __call__(self, *args, **kwargs):
--> 355 return self.func(*args, **kwargs)
356
357 def call_and_shelve(self, *args, **kwargs):
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
714 with _print_elapsed_time(message_clsname, message):
715 if hasattr(transformer, 'fit_transform'):
--> 716 res = transformer.fit_transform(X, y, **fit_params)
717 else:
718 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
919
920 if any(sparse.issparse(f) for f in Xs):
--> 921 Xs = sparse.hstack(Xs).tocsr()
922 else:
923 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] == 1, expected 13892.
Further, the data and metadata can be gotten here
%%bash
mkdir data
wget http://dataincubator-wqu.s3.amazonaws.com/mldata/providers-train.csv -nc -P ./ml-data
wget http://dataincubator-wqu.s3.amazonaws.com/mldata/providers-metadata.csv -nc -P ./ml-data

Changing my TimeDeltaConverter seems to have helped.
Firstly by changing it to be a series of ints and then reshaping it to be reshape(-1,1).
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)

Raising ValueError (extra rows) when submitting pipeline.predict into grader

I've been getting a ValueError below when trying to submit my Pipeline into a grader. And I'm not sure where I'm supposed to shave off 12500 rows of data.
ValueError: blocks[0,:] has incompatible row dimensions. Got blocks[0,2].shape[0] == 13892, expected 1544.
I've been tasked to build a model that combines the business_features of nursing homes with their cycle 1 survey results, as well as the time between the cycle 1 and cycle 2 survey to predict the cycle 2 total score.
This is my code that I'm using to accomplish the task above.
# Creating a custom transformer to calculate the difference between survey
# 1 & survey 2 times
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)
# Creating TimedeltaTransformer object
cycle_1_date = 'CYCLE_1_SURVEY_DATE'
cycle_2_date = 'CYCLE_2_SURVEY_DATE'
time_feature = TimedeltaTransformer(cycle_1_date, cycle_2_date)
# Using a custom column selecter transformer to extract cycle_1_features
cycle_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)),
])
# Creating my survey_model Pipeline object
# Pipeline object is a 2 step process, first a feature union transforming
# and combining the business features, cycle_1 features as well as time
# feature; followed by fitting the transformed features into a
# RandomForestRegressor
survey_model = Pipeline([
('features', FeatureUnion([
('business', business_features),
('survey', cycle_1_features),
('time', time_feature),
])),
('forest', RandomForestRegressor()),
])
# Fitting my pipeline produces no error
survey_model.fit(data, cycle_2_score.astype(int))
# Calling the predict function and passing it into the grader raises a ValueError
grader.score.ml__survey_model(survey_model.predict)
The fitted pipeline looks like this
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)
Some additional context: I'm building this model to have its predict method passed into a custom grader for a project. The grader passes a list of dictionaries to the predict or predict_proba method of my estimator, not a DataFrame. This means that the model must work with both data types. For this reason, I need to provide a custom ColumnSelectTransformer to use instead scikit-learn's own ColumnTransformer.
Below is additional code related to the business features and ColumnSelectTransformer
# Custom transformer to select columns from a dataframe and returns the
# dataframe as an array
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].values
simple_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)
])
Finally, below is the full error raised
---------------------------------------------------------------------------
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.

Fixing my TimeDeltaTransformer helped.
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)