Dataframe output Key Error

kevin15987

I have a very simple script that does some calculation and creates new columns.

from ayx import Alteryx
import pandas as pd
import numpy as np

df = Alteryx.read("#1")
for i in range(len(df)):
    k = df["WeekNumber"][i]
    while k < 53:
        df[k] = df["Sum_HC"]*((1-df["WeeklyShrinkage"])**(k-df["WeekNumber"][i]))
        k+=1

Alteryx.write(df,1)

When I replace Alteryx.write(df,1) with print(df), it prints perfectly fine, but when I try to write, it gives me the following error

SUCCESS: reading input data "#1"
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   2888             try:
-> 2889                 return self._engine.get_loc(casted_key)
   2890             except KeyError as err:

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: 0

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
<ipython-input-10-33adc0abc4c8> in <module>
     10         k+=1
     11 
---> 12 Alteryx.write(df,1)

c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\ayx\export.py in write(pandas_df, outgoing_connection_number, columns, debug, **kwargs)
     85     When running the workflow in Alteryx, this function will convert a pandas data frame to an Alteryx data stream and pass it out through one of the tool's five output anchors. When called from the Jupyter notebook interactively, it will display a preview of the pandas dataframe. An optional 'columns' argument allows column metadata to specify the field type, length, and name of columns in the output data stream.
     86     """
---> 87     return __CachedData__(debug=debug).write(
     88         pandas_df, outgoing_connection_number, columns=columns, **kwargs
     89     )

c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\ayx\CachedData.py in write(self, pandas_df, outgoing_connection_number, columns, output_filepath)
    426 
    427         for index, colname in enumerate(pandas_df.columns):
--> 428             coltype = str(pandas_df.dtypes[index])
    429             # does the column contain bytearrays? then its probably a blob
    430             # (check only first non-null value in column -- tradeoff for efficiency)

c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\pandas\core\series.py in __getitem__(self, key)
    880 
    881         elif key_is_scalar:
--> 882             return self._get_value(key)
    883 
    884         if (

c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\pandas\core\series.py in _get_value(self, label, takeable)
    989 
    990         # Similar to Index.get_value, but we do not fall back to positional
--> 991         loc = self.index.get_loc(label)
    992         return self.index._get_values_for_loc(self, loc, label)
    993 

c:\users\appdata\local\alteryx\bin\miniconda3\envs\designerbasetools_venv\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
   2889                 return self._engine.get_loc(casted_key)
   2890             except KeyError as err:
-> 2891                 raise KeyError(key) from err
   2892 
   2893         if tolerance is not None:

KeyError: 0

Any ideas? 

philipmannering

Try adding,

df.columns = df.columns.astype(str)

before you write the output. I'm confident that will solve your issue.