问将原始文本数据格式化为使用熊猫的列

EN

master_dict = {'<35':'Age','>35':'Age','M':'Gender','F':'Gender','White':'BehaviorA','Black':'BehaviorA',
               'Red':'BehaviorA','Big':'BehaviorB','Small':'BehaviorB','Medium':'BehaviorC'}
               
file_data = '''\
Index,Properties
ItemA,F,Red,Small,Medium,<35
ItemB,>35,Black,Big,M'''

#initialize the pandas dataframe dictionary
data_dict = {}

#iterate through each row in the file
for i, line in enumerate(file_data.split('\n')):
    #ignore header row (i == 0)
    if i == 0:continue

    #remove \n and leading spaces. split on comma
    prop = line.strip().split(',')

    #initialize dict for each item
    d = {}
    for ix, p in enumerate(prop):
        #capture index values (ItemA, ItemB)
        if ix == 0: key = p;continue

        #for all others, get the column header and value
        #column header is mapped to the value in the master dictionary; use that
        else: d[master_dict[p]]=p

    #create a row with the index value
    data_dict[key] = d

#once all the rows have been added to the data dictionary, its ready for us to create a dataframe
import pandas as pd
#create a dataframe with the data dictionary. transpose will ensure keys are set as index
df = pd.DataFrame(data_dict).T

print (df)

      Gender BehaviorA BehaviorB BehaviorC  Age
ItemA      F       Red     Small    Medium  <35
ItemB      M     Black       Big       NaN  >35