Python - 如何计算列表中的特定部分

Question

我是 python 的新手，我正在努力如何在 python 中添加 cvs 文件的某些部分。 我不允许使用“导入 cvs” 我正在从https://vincentarelbundock.github.io/Rdatasets/datasets.html导入 TipJoke CVS 文件

这是迄今为止我唯一有效的代码，我完全不知道从哪里开始。

if __name__ == '__main__':
from pprint import pprint
from string import punctuation
f = open("TipJoke.csv", "r")
tipList = []
for line in f:
    #deletes the quotes
    line = line.replace('"', '')
    tipList.append(line)
pprint(tipList[])

输出：

 [',Card,Tip,Ad,Joke,None\n',
 '1,None,1,0,0,1\n',
 '2,Joke,1,0,1,0\n',
 '3,Ad,0,1,0,0\n',
 '4,None,0,0,0,1\n',
 '5,None,1,0,0,1\n',
 '6,None,0,0,0,1\n',
 '7,Ad,0,1,0,0\n',
 '8,Ad,0,1,0,0\n',
 '9,None,0,0,0,1\n',
 '10,None,0,0,0,1\n',
 '11,None,1,0,0,1\n',
 '12,Ad,0,1,0,0\n',
 '13,None,0,0,0,1\n',
 '14,Ad,1,1,0,0\n',
 '15,Joke,1,0,1,0\n',
 '16,Joke,0,0,1,0\n',
 '17,Joke,1,0,1,0\n',
 '18,None,0,0,0,1\n',
 '19,Joke,0,0,1,0\n',
 '20,None,0,0,0,1\n',
 '21,Ad,1,1,0,0\n',
 '22,Ad,1,1,0,0\n',
 '23,Ad,0,1,0,0\n',
 '24,Joke,0,0,1,0\n',
 '25,Joke,1,0,1,0\n',
 '26,Joke,0,0,1,0\n',
 '27,None,1,0,0,1\n',
 '28,Joke,1,0,1,0\n',
 '29,Joke,1,0,1,0\n',
 '30,None,1,0,0,1\n',
 '31,Joke,0,0,1,0\n',
 '32,None,1,0,0,1\n',
 '33,Joke,1,0,1,0\n',
 '34,Ad,0,1,0,0\n',
 '35,Joke,0,0,1,0\n',
 '36,Ad,1,1,0,0\n',
 '37,Joke,0,0,1,0\n',
 '38,Ad,0,1,0,0\n',
 '39,Joke,0,0,1,0\n',
 '40,Joke,0,0,1,0\n',
 '41,Joke,1,0,1,0\n',
 '42,None,0,0,0,1\n',
 '43,None,0,0,0,1\n',
 '44,Ad,0,1,0,0\n',
 '45,None,0,0,0,1\n',
 '46,None,0,0,0,1\n',
 '47,Ad,0,1,0,0\n',
 '48,Joke,0,0,1,0\n',
 '49,Joke,1,0,1,0\n',
 '50,None,1,0,0,1\n',
 '51,None,0,0,0,1\n',
 '52,Joke,1,0,1,0\n',
 '53,Joke,1,0,1,0\n',
 '54,Joke,0,0,1,0\n',
 '55,None,1,0,0,1\n',
 '56,Ad,0,1,0,0\n',
 '57,Joke,0,0,1,0\n',
 '58,None,0,0,0,1\n',
 '59,Ad,0,1,0,0\n',
 '60,Joke,1,0,1,0\n',
 '61,Ad,0,1,0,0\n',
 '62,None,1,0,0,1\n',
 '63,Joke,0,0,1,0\n',
 '64,Ad,0,1,0,0\n',
 '65,Joke,0,0,1,0\n',
 '66,Ad,0,1,0,0\n',
 '67,Ad,0,1,0,0\n',
 '68,Ad,0,1,0,0\n',
 '69,None,0,0,0,1\n',
 '70,Joke,1,0,1,0\n',
 '71,None,1,0,0,1\n',
 '72,None,0,0,0,1\n',
 '73,None,0,0,0,1\n',
 '74,Joke,0,0,1,0\n',
 '75,Ad,1,1,0,0\n',
 '76,Ad,0,1,0,0\n',
 '77,Ad,1,1,0,0\n',
 '78,Joke,0,0,1,0\n',
 '79,Joke,0,0,1,0\n',
 '80,Ad,1,1,0,0\n',
 '81,Ad,0,1,0,0\n',
 '82,None,0,0,0,1\n',
 '83,Ad,0,1,0,0\n',
 '84,Joke,0,0,1,0\n',
 '85,Joke,0,0,1,0\n',
 '86,Ad,1,1,0,0\n',
 '87,None,1,0,0,1\n',
 '88,Joke,1,0,1,0\n',
 '89,Ad,0,1,0,0\n',
 '90,None,0,0,0,1\n',
 '91,None,0,0,0,1\n',
 '92,Joke,0,0,1,0\n',
 '93,Joke,0,0,1,0\n',
 '94,Ad,0,1,0,0\n',
 '95,Ad,0,1,0,0\n',
 '96,Ad,0,1,0,0\n',
 '97,Joke,1,0,1,0\n',
 '98,None,0,0,0,1\n',
 '99,None,0,0,0,1\n',
 '100,None,1,0,0,1\n',
 '101,Joke,0,0,1,0\n',
 '102,Joke,0,0,1,0\n',
 '103,Ad,1,1,0,0\n',
 '104,Ad,0,1,0,0\n',
 '105,Ad,0,1,0,0\n',
 '106,Ad,1,1,0,0\n',
 '107,Ad,0,1,0,0\n',
 '108,None,0,0,0,1\n',
 '109,Ad,0,1,0,0\n',
 '110,Joke,1,0,1,0\n',
 '111,None,0,0,0,1\n',
 '112,Ad,0,1,0,0\n',
 '113,Ad,0,1,0,0\n',
 '114,None,0,0,0,1\n',
 '115,Ad,0,1,0,0\n',
 '116,None,0,0,0,1\n',
 '117,None,0,0,0,1\n',
 '118,Ad,0,1,0,0\n',
 '119,None,1,0,0,1\n',
 '120,Ad,1,1,0,0\n',
 '121,Ad,0,1,0,0\n',
 '122,Ad,1,1,0,0\n',
 '123,None,0,0,0,1\n',
 '124,None,0,0,0,1\n',
 '125,Joke,1,0,1,0\n',
 '126,Joke,1,0,1,0\n',
 '127,Ad,0,1,0,0\n',
 '128,Joke,0,0,1,0\n',
 '129,Joke,0,0,1,0\n',
 '130,Ad,0,1,0,0\n',
 '131,None,0,0,0,1\n',
 '132,None,0,0,0,1\n',
 '133,None,0,0,0,1\n',
 '134,Joke,1,0,1,0\n',
 '135,Ad,0,1,0,0\n',
 '136,None,0,0,0,1\n',
 '137,Joke,0,0,1,0\n',
 '138,Ad,0,1,0,0\n',
 '139,Ad,0,1,0,0\n',
 '140,None,0,0,0,1\n',
 '141,Joke,0,0,1,0\n',
 '142,None,0,0,0,1\n',
 '143,Ad,0,1,0,0\n',
 '144,None,1,0,0,1\n',
 '145,Joke,0,0,1,0\n',
 '146,Ad,0,1,0,0\n',
 '147,Ad,0,1,0,0\n',
 '148,Ad,0,1,0,0\n',
 '149,Joke,1,0,1,0\n',
 '150,Ad,1,1,0,0\n',
 '151,Joke,1,0,1,0\n',
 '152,None,0,0,0,1\n',
 '153,Ad,0,1,0,0\n',
 '154,None,0,0,0,1\n',
 '155,None,0,0,0,1\n',
 '156,Ad,0,1,0,0\n',
 '157,Ad,0,1,0,0\n',
 '158,Joke,0,0,1,0\n',
 '159,None,0,0,0,1\n',
 '160,Joke,1,0,1,0\n',
 '161,None,1,0,0,1\n',
 '162,Ad,1,1,0,0\n',
 '163,Joke,0,0,1,0\n',
 '164,Joke,0,0,1,0\n',
 '165,Ad,0,1,0,0\n',
 '166,Joke,1,0,1,0\n',
 '167,Joke,1,0,1,0\n',
 '168,Ad,0,1,0,0\n',
 '169,Joke,1,0,1,0\n',
 '170,Joke,0,0,1,0\n',
 '171,Ad,0,1,0,0\n',
 '172,Joke,0,0,1,0\n',
 '173,Joke,0,0,1,0\n',
 '174,Ad,0,1,0,0\n',
 '175,None,0,0,0,1\n',
 '176,Joke,1,0,1,0\n',
 '177,Ad,0,1,0,0\n',
 '178,Joke,0,0,1,0\n',
 '179,Joke,0,0,1,0\n',
 '180,None,0,0,0,1\n',
 '181,None,0,0,0,1\n',
 '182,Ad,0,1,0,0\n',
 '183,None,0,0,0,1\n',
 '184,None,0,0,0,1\n',
 '185,None,0,0,0,1\n',
 '186,None,0,0,0,1\n',
 '187,Ad,0,1,0,0\n',
 '188,None,1,0,0,1\n',
 '189,Ad,0,1,0,0\n',
 '190,Ad,0,1,0,0\n',
 '191,Ad,0,1,0,0\n',
 '192,Joke,1,0,1,0\n',
 '193,Joke,0,0,1,0\n',
 '194,Ad,0,1,0,0\n',
 '195,None,0,0,0,1\n',
 '196,Joke,1,0,1,0\n',
 '197,Joke,0,0,1,0\n',
 '198,Joke,1,0,1,0\n',
 '199,Ad,0,1,0,0\n',
 '200,None,0,0,0,1\n',
 '201,Joke,1,0,1,0\n',
 '202,Joke,0,0,1,0\n',
 '203,Joke,0,0,1,0\n',
 '204,Ad,0,1,0,0\n',
 '205,None,0,0,0,1\n',
 '206,Ad,0,1,0,0\n',
 '207,Ad,0,1,0,0\n',
 '208,Joke,0,0,1,0\n',
 '209,Ad,0,1,0,0\n',
 '210,Joke,0,0,1,0\n',
 '211,None,0,0,0,1\n']

我目前正在尝试查找指定卡片类型的条目总数和为指定卡片类型提供的小费百分比，精度为两位小数。 提示栏是卡片类型（无、广告、笑话）后面的 0 或 1。

Answer 1

这有效

from pprint import pprint
from string import punctuation

counts = {"Joke": 0, "Ad": 0, "None": 0}
with open("TipJoke.csv", "r") as f:
    for line in f:
        line_clean = line.replace('"', "").replace("\n", "").split(",")
        try:
            counts[line_clean[1]] += int(line_clean[2])
        except:
            pass


print(counts)

Answer 2

如果你被允许使用 pandas 库，那么

将熊猫导入为 pd

df = pd.read_csv("TipJoke.csv")

df 是一个 Pandas 数据框对象，您可以根据需要在其中执行多个过滤任务。

例如，如果你想获取笑话的数据，你可以这样过滤：

print(df[df["Card"] == "Joke"])

不过，我只是为您提供方向，而不是您问题的全部逻辑。