Error with the 'feature' column when creating a databunch

[vrodriguezf]

Hi,

I found a weird error when creating the databunch following the steps of the first notebook:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2656             try:
-> 2657                 return self._engine.get_loc(key)
   2658             except KeyError:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'feature'

During handling of the above exception, another exception occurred:

KeyError                                  Traceback (most recent call last)
4 frames
<ipython-input-45-c74cce7b4c94> in <module>()
      3 target_colname = 'target' # *
      4 valid_pct = 0.2 # *
----> 5 db = (TimeSeriesList.from_df(df = df, path = '.', cols=df.columns.values[3:], feat='feature')
      6       .split_by_rand_pct(valid_pct= valid_pct, seed=seed)
      7       .label_from_df(cols=target_colname, label_cls=CategoryList)

/content/timeseriesAI/fastai_timeseries/exp/nb_TSBasicData.py in from_df(cls, df, path, cols, feat, processor, **kwargs)
    204         assert inputs.isna().sum().sum(
    205         ) == 0, f"You have NaN values in column(s) {cols} of your dataframe, please fix it."
--> 206         inputs = df2array(inputs, feat)
    207         res = cls(
    208             items=inputs,

/content/timeseriesAI/fastai_timeseries/exp/nb_TSBasicData.py in df2array(df, feat)
    297     if feat is None:
    298         return df.values[:, None]
--> 299     for i, ch in enumerate(df[feat].unique()):
    300         data_i = df[df[feat] == ch].values[:, None]
    301         if i == 0: data = data_i

/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py in __getitem__(self, key)
   2925             if self.columns.nlevels > 1:
   2926                 return self._getitem_multilevel(key)
-> 2927             indexer = self.columns.get_loc(key)
   2928             if is_integer(indexer):
   2929                 indexer = [indexer]

/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2657                 return self._engine.get_loc(key)
   2658             except KeyError:
-> 2659                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   2660         indexer = self.get_indexer([key], method=method, tolerance=tolerance)
   2661         if indexer.ndim > 1 or indexer.size > 1:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'feature'

Best!

[vrodriguezf]

Hi,

The error is caused because I was not including the feature column into the values of the cols parameter. Fixed now.