白葡萄酒项目探索研究

                                                               白葡萄酒项目探索研究

代码如下：

import csv

f = open("C:\用户\Shanks\white_wine.csv",'r',encoding="utf-8")

reader = csv.reader(f)

data = []

for row in reader:

    data.append(row)

for i in range(5):

    print(data[i])

f.close()

import csv

f = open("white_wine.csv",'r')

reader = csv.reader(f)

data = []

for row in reader:

    data.append(row)

quality_list = []

for row in data[1:]:

    quality_list.append(int(row[ -1]))

quality_count = set(quality_list)

print("白葡萄酒共有%s种等级, 分别为：%r"

      %(len(quality_count), quality_count))

import csv

f = open("white_wine.csv",'r')

reader = csv.reader(f)

data = []

for row in reader:

    data.append(row)

content_dict = {}

for row in data[1:]:

    quality = int(row[-1])

    if quality not in content_dict.keys():

        content_dict[quality] = [row]

    else:

        content_dict[quality].append(row)

for key in content_dict:

    print('等级为%d， 数量为%d' %(key, len(content_dict[key])))

f.close()

import csv

import numpy as np

import matplotlib.pyplot as plt

f = open("white_wine.csv",'r')

reader = csv.reader(f)

data = []

for row in reader:

    data.append(row)

content_dict = {}

for row in data[1:]:

    quality = int(row[-1])

    if quality not in content_dict.keys():

        content_dict[quality] = [row]

    else:

        content_dict[quality].append(row)

x = []

y = []

for key in content_dict:

    x.append(key)

    y.append(len(content_dict[key]))

plt.bar(x, y)

plt.show()

import csv

f = open("white_wine.csv",'r')

reader = csv.reader(f)

data = []

for row in reader:

    data.append(row)

content_dict = {}

for row in data[1:]:

    quality = int(row[-1])

    if quality not in content_dict.keys():

        content_dict[quality] = [row]

    else:

        content_dict[quality].append(row)

mean_list = []

for key,value in content_dict.items():

    sum = 0

    for row in value:

        sum += float(row[0])

    mean_list.append((key, sum / len(value)))

for item in mean_list:

print(item[0],",", item[1])

结果如下：

白葡萄酒共有7种等级, 分别为：{3, 4, 5, 6, 7, 8, 9}

等级为6， 数量为1539

等级为5， 数量为1020

等级为7， 数量为616

等级为8， 数量为123

等级为4， 数量为115

等级为3， 数量为14

等级为9， 数量为4

6 : 6.812085769980511

5 : 6.907843137254891

7 : 6.755844155844158

8 : 6.708130081300811

4 : 7.052173913043476

3 : 7.535714285714286

9 : 7.5

学习笔记：该数据集的数据形式如下：

首先，我们需要将存储在本地的数据集white_wine.csv读取入内存中。说明：引入csv模块，打开文件将数据保存于列表content中打印content前5行查看白葡萄酒中总共分为几个品质品质quality变量在数据中是一个离散变量，而不是连续的，所以它只会有固定的几个等级。那么我们用Python中自带的集合set来查看白葡萄酒中总共的品质等级

说明：使用集合set查看白葡萄酒总共分为几个品质，并将所有品质等级保存在集合unity_quality中其中，品质等级数据在最后一列按白葡萄酒等级将数据集划分为7个子集，将数据按白葡萄酒等级quality进行切分为7个子集，保存到一个字典中，字典的键为quality具体数值，值为归属于该quality的样本列表

说明：按白葡萄酒等级将数据集划分为7个子集，用字典保存每个子集，字典变量名为content_dict，变量的关键词key为品质，值value为每个品质子集的数据列表。