Nirmal Nirmal - 6 months ago 29
Python Question

TypeError: got an unexpected keyword argument

The seemingly simple code below throws the following error:

Traceback (most recent call last):
File "/home/nirmal/process.py", line 165, in <module>
'time_diff': f.last(adf['time_diff']).over(window_device_rows)
TypeError: __call__() got an unexpected keyword argument 'this_campaign'


Code:



# Function to flag network timeouts
def flag_network_timeout(**kwargs):
if kwargs['this_network'] != kwargs['last_network'] \
or kwargs['this_campaign'] != kwargs['last_campaign'] \
or kwargs['this_adgroup'] != kwargs['last_adgroup'] \
or kwargs['this_creative'] != kwargs['last_creative'] \
or kwargs['time_diff'] > network_timeout:
return 1
else:
return 0
flag_network_timeout = f.udf(flag_network_timeout, IntegerType())

# Column spec to go over the device events and flag network resets
network_timeout_flag = flag_network_timeout(**{
'last_network': f.first(adf['network']).over(window_device_rows),
'last_campaign': f.first(adf['campaign']).over(window_device_rows),
'last_adgroup': f.first(adf['adgroup']).over(window_device_rows),
'last_creative': f.first(adf['creative']).over(window_device_rows),
'this_network': f.last(adf['network']).over(window_device_rows),
'this_campaign': f.last(adf['campaign']).over(window_device_rows),
'this_adgroup': f.last(adf['adgroup']).over(window_device_rows),
'this_creative': f.last(adf['creative']).over(window_device_rows),
'time_diff': f.last(adf['time_diff']).over(window_device_rows)
})

# Update dataframe with the new columns
adf = adf.select('*', network_timeout_flag.alias('network_timeout'))


What am I doing wrong please? Thank you.

Answer

You get an exception because UserDefinedFunction.__call__ supports only varargs and not keyword args.

def __call__(self, *cols):
    sc = SparkContext._active_spark_context
    jc = self._judf.apply(_to_seq(sc, cols, _to_java_column))
    return Column(jc)

At much more basic level UDF can receive only Column arguments, which will be expanded to their corresponding value on runtime, and not standard Python objects.

Personally I wouldn't use **kwargs for this at all, but ignoring that you can achieve what you want by composing SQL expressions:

def flag_network_timeout_(**kwargs):

    cond = (
        (kwargs['this_network'] != kwargs['last_network']) |
        (kwargs['this_campaign'] != kwargs['last_campaign']) |
        (kwargs['this_adgroup'] != kwargs['last_adgroup']) |
        (kwargs['this_creative'] != kwargs['last_creative']) |
        (kwargs['time_diff'] > network_timeout))

    return f.when(cond, 1).otherwise(0)
Comments