Using **kwargs for multiple file upload

March 14, 2022

I have written a code as follows that takes in different inputs in the __init__ of the class and functions that come afterwards use the key arguments for a certain process (I have brought an example here but the original code has more functions and more files to process).

import os
from config import data_directory #directory where the datasets are located
import pandas as pd

class Analysis(object):
    def __init__(self, **kwargs):
        self.data1 = kwargs.get('data1')
        self.data2 = kwargs.get('data1')
    def analysis1(self):
        print(self.data1['col1'],
              self.data2['col1'])
    def analysis2(self):
        print(self.data2['col3'])

def analyzing():
    tobeanalyzed = Analysis()
    tobeanalyzed.analysis1()
    tobeanalyzed.analysis2()

return tobeanalyzed

if __name__ == '__main__':
    analyzing(data1 =pd.read_csv(os.path.join(data_directory , 'file1.csv'), na_filter = False), 
       data2 = pd.read_csv(os.path.join(data_directory , 'file2.csv'), na_filter = False))

I guess there is something wrong with the way I have defined the data1 and data2 but do not know how to correct it.

Error:

TypeError: analyzing() got an unexpected keyword argument 'data1'

>Solution :

You need to allow **kwargs on the analyzing function as well and pass them on to the Analysis constructor:

import os
from config import data_directory #directory where the datasets are located
import pandas as pd

class Analysis(object):
    def __init__(self, **kwargs):
        self.data1 = kwargs.get('data1')
        self.data2 = kwargs.get('data1')
    def analysis1(self):
        print(self.data1['col1'],
              self.data2['col1'])
    def analysis2(self):
        print(self.data2['col3'])

def analyzing(**kwargs):
    tobeanalyzed = Analysis(**kwargs)
    tobeanalyzed.analysis1()
    tobeanalyzed.analysis2()

    return tobeanalyzed

if __name__ == '__main__':
    analyzing(data1 =pd.read_csv(os.path.join(data_directory , 'file1.csv'), na_filter = False), 
       data2 = pd.read_csv(os.path.join(data_directory , 'file2.csv'), na_filter = False))