Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def parseFile(fileName):
- with open(fileName, 'r') as f:
- lines=[line.split(',') for line in f.readlines()]
- dico={}
- for w, word in enumerate(lines[0]):
- if word[-1]=='\n': word=word[:-1]
- if word[0]=='\xef': word=word[3:]
- if 'Id' in word: word='Id'
- dico[word]=list(set([line[w] for line in lines[1:]])) # set acts like <uniq>
- return dico
- trainDico = parseFile('./challenge_data/train.csv')
- testDico = parseFile('./challenge_data/test.csv')
- #### OR
- import pandas as pd
- df_train = pd.read_csv('./challenge_data/train.csv')
- df_test = pd.read_csv('./challenge_data/test.csv')
Add Comment
Please, Sign In to add comment