Python数据处理

数据清洗：标准化和脚本化

｜

167

"""

missing_count = 0

for

response

in

zipped_data:

for

question, answer

in

response:

if

not

answer:

missing_count += 1

return

missing_count

def

find_duplicate_data(zipped_data):

"""

Returns a list of unique elements and a number of duplicates found when given

a UNICEF zipped_data list. This function assumes that the first three rows of

data are structured to have the house, cluster, and line number of the

interview and uses these values to create a unique key that should not be

repeated.

"""

set_of_keys = set([

'%s-%s-%s' % (row[0][1], row[1][1], row[2][1])

for

row

in

zipped_data])

#TODO: this will throw ...