Weird Error

[lauragustafson]

from fhub_core import Feature
from fhub_transformers.missing import LagImputer
from sklearn.preprocessing import Imputer, StandardScaler, MinMaxScaler
from fhub_transformers import NamedFramer, SimpleFunctionTransformer
feature = Feature(input=input, transformer=transformer)

input = 'precipitation_amt_mm'
transformer = [
    LagImputer(groupby_kwargs={'level': 'city'}),
    Imputer(),
    SimpleFunctionTransformer(
        lambda ser: ser if ser > 0 else ser
    ),
]
mapper = feature.as_dataframe_mapper()
mapper.fit(X_df, y_df)
mapper.transform(X_df)

gives error:

AttributeError                            Traceback (most recent call last)
<ipython-input-83-0de258be511f> in <module>()
----> 1 mapper.transform(X_df)

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/sklearn_pandas/dataframe_mapper.py in transform(self, X)
    277             if transformers is not None:
    278                 with add_column_names_to_exception(columns):
--> 279                     Xt = transformers.transform(Xt)
    280             extracted.append(_handle_feature(Xt))
    281 

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/fhub_core/feature.py in wrapped(X, y, **kwargs)
     48                     return func(convert(X), y=convert(y), **kwargs)
     49                 else:
---> 50                     return func(convert(X), **kwargs)
     51             except catch as e:
     52                 formatted_exc = indent(traceback.format_exc(), n=8)

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/fhub_core/feature.py in transform(self, X, **transform_kwargs)
     22     def transform(self, X, **transform_kwargs):
     23         _transform = make_robust_to_tabular_types(super().transform)
---> 24         return _transform(X, **transform_kwargs)
     25 
     26 

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/fhub_core/feature.py in wrapped(X, y, **kwargs)
     48                     return func(convert(X), y=convert(y), **kwargs)
     49                 else:
---> 50                     return func(convert(X), **kwargs)
     51             except catch as e:
     52                 formatted_exc = indent(traceback.format_exc(), n=8)

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/sklearn/pipeline.py in _transform(self, X)
    424         for name, transform in self.steps:
    425             if transform is not None:
--> 426                 Xt = transform.transform(Xt)
    427         return Xt
    428 

~/miniconda3/envs/dengue_preiction/lib/python3.6/site-packages/fhub_transformers/base.py in transform(self, X, **transform_kwargs)
     36     def transform(self, X, **transform_kwargs):
     37         if self.groupby_kwargs:
---> 38             call = X.sort_index().groupby(**self.groupby_kwargs).apply
     39         else:
     40             call = X.sort_index().pipe

AttributeError: precipitation_amt_mm: 'numpy.ndarray' object has no attribute 'sort_index'

Not sure if this is just me using this incorrectly.

[micahjsmith]

The input to each component in the transformer pipeline is a tabular type (pd.DataFrame, pd.Series, np.array, etc.). So in lambda ser, the parameter ser is the entire series, whereas it looks like you want to apply a lambda to every row. So this syntax wouldn't work.

You could use

def f(ser):
    ser.apply(lambda row: row if row > 0 else row)

and pass f to SimpleFunctionTransformer.

Regardless of whether your transformation has any meaning, see above xref about debugging output