clean_loc_cui.py

#A function to find the maximun number of features in a single cell
def max_features_in_single_row(train, test, delimiter):
  max_info = 0 
  item_lis = list(train.append(test))
  for i in item_lis:
    if len(i.split("{}".format(delimiter))) > max_info:
      max_info = len(i.split("{}".format(delimiter)))
  print("\n","-"*35)    
  print("Max_Features in One Observation = ", max_info)
  return max_info

clean_loc_cui_2.py

#This function splits a column in to n features where n is the maximum number of features in a single cell
def feature_splitter(feat, name, delimiter, max_info):
  item_lis = list(feat)
  extracted_features = {}
  for i in range(max_info):
    extracted_features['{}_Feature_{}'.format(name, i+1)] = []
  print("-"*35)
  print("Features Dictionary : ", extracted_features)
  #tqdm is a graphics module that helps us see the progress bar
  for i in tqdm(range(len(item_lis))):
    for j in range(max_info):  
      try:
        extracted_features['{}_Feature_{}'.format(name,j+1)].append(item_lis[i].split("{}".format(delimiter))[j].lower().strip())
      except: 
        extracted_features['{}_Feature_{}'.format(name, j+1)].append(np.nan)

  return extracted_features