csv文件的读写

Let's import our datafile mpg.csv, which contains fuel economy data for 234 cars.

• mpg : miles per gallon
• class : car classification
• cty : city mpg
• cyl : # of cylinders
• displ : engine displacement in liters
• drv : f = front-wheel drive, r = rear wheel drive, 4 = 4wd
• fl : fuel (e = ethanol E85, d = diesel, r = regular, p = premium, c = CNG)
• hwy : highway mpg
• manufacturer : automobile manufacturer
• model : model of car
• trans : type of transmission
• year : model year

import csv

%precision 2

with open('mpg.csv') as csvfile:
    mpg = list(csv.DictReader(csvfile))
    
mpg[:3] # The first three dictionaries in our list.

[OrderedDict([('', '1'),
              ('manufacturer', 'audi'),
              ('model', 'a4'),
              ('displ', '1.8'),
              ('year', '1999'),
              ('cyl', '4'),
              ('trans', 'auto(l5)'),
              ('drv', 'f'),
              ('cty', '18'),
              ('hwy', '29'),
              ('fl', 'p'),
              ('class', 'compact')]),
 OrderedDict([('', '2'),
              ('manufacturer', 'audi'),
              ('model', 'a4'),
              ('displ', '1.8'),
              ('year', '1999'),
              ('cyl', '4'),
              ('trans', 'manual(m5)'),
              ('drv', 'f'),
              ('cty', '21'),
              ('hwy', '29'),
              ('fl', 'p'),
              ('class', 'compact')]),
 OrderedDict([('', '3'),
              ('manufacturer', 'audi'),
              ('model', 'a4'),
              ('displ', '2'),
              ('year', '2008'),
              ('cyl', '4'),
              ('trans', 'manual(m6)'),
              ('drv', 'f'),
              ('cty', '20'),
              ('hwy', '31'),
              ('fl', 'p'),
              ('class', 'compact')])]

len(mpg)

234

%得到列的名字
1 mpg[0].keys()

odict_keys(['', 'manufacturer', 'model', 'displ', 'year', 'cyl', 'trans', 'drv', 'cty', 'hwy', 'fl', 'class'])

%这是如何找到所有汽车的平均燃料经济关系。字典中的所有值都是字符串，所以我们需要转换成浮点数。
1 sum(float(d['cty']) for d in mpg) / len(mpg)

16.86

sum(float(d['hwy']) for d in mpg) / len(mpg)

23.44

%使用set去掉重复的项
1 cylinders = set(d['cyl'] for d in mpg)
cylinders

{'4', '5', '6', '8'}

%通过cylinder的数量划分组别，并计算每个组别的平均值
 1 CtyMpgByCyl = []

for c in cylinders: # iterate over all the cylinder levels
    summpg = 0
    cyltypecount = 0
    for d in mpg: # iterate over all dictionaries
        if d['cyl'] == c: # if the cylinder level type matches,
            summpg += float(d['cty']) # add the cty mpg
            cyltypecount += 1 # increment the count
    CtyMpgByCyl.append((c, summpg / cyltypecount)) # append the tuple ('cylinder', 'avg mpg')

CtyMpgByCyl.sort(key=lambda x: x[0])
CtyMpgByCyl

[('4', 21.01), ('5', 20.50), ('6', 16.22), ('8', 12.57)]