python数据分析之Pandas实践练习

!/usr/bin/env python

-- coding:utf-8 --

"""
    项目名称：全球食品数据分析
    项目参考：https://www.kaggle.com/bhouwens/d/openfoodfacts/world-food-facts/how-much-sugar-do-we-eat/discussion
"""

import zipfile
import os
import pandas as pd
import matplotlib.pyplot as plt



#得到zip文件中的第一个文件名
def get_dataset_filename(zip_filepath):
    with zipfile.ZipFile(zip_filepath) as zf:
        return  zf.namelist()[0]

def unzip(zip_filepath,dest_path):
    with zipfile.ZipFile(zip_filepath) as zf:
        zf.extractall(path=dest_path)


def run_main():
    # 数据采集路径
    dataset_path = "../data"
    #zip文件名
    zip_filename = "open-food-facts.zip"
    # zip文件路径
    zip_filepath = os.path.join(dataset_path,zip_filename)
    dataset_filename = get_dataset_filename(zip_filepath);
    dataset_filepath = os.path.join(dataset_path, dataset_filename)

    print("解压zip....",end="")
    #unzip(zip_filepath,dataset_path)
    print("解压完成！")


    #读取这两列countries_en additives_n数据
    data = pd.read_csv(dataset_filepath,usecols=['countries_en','additives_n'])

    #1、数据清理
    #去除缺失数据
    data = data.dropna()

    #将国家名称统一转化为小写 或者大写，便于groupby
    data['countries_en'] = data['countries_en'].str.lower()

    #2、数据分组统计
    #country_additives = data['additives_n'].groupby()
    country_additives = data.groupby('countries_en').sum()
    # print(type(country_additives))
    # print(country_additives.index)
    # print(country_additives.values)
    #3、经过观察发现'countries_en'中的数值不是单独的国家名称，有的是多个国家名称用逗号隔开，如 Albania,Belgium,France,Germany,Italy,Netherlands,Spain,正确的统计应该是将这些值拆开成多个行记录，然后进行分组统计
    #循环索引
    for country_index in country_additives.index:
        #拆分索引
        if len(country_index.split(',')) > 1:
            for ct in  country_index.split(','):
                #获取行索引对应的值，value 是 Dataframe对象
                value = country_additives.loc[[country_index]]
                #重命名行索引名称
                value.rename(index={country_index:ct},  inplace=True)
                #把value添加到country_additives中
                country_additives=country_additives.append(value)
            #把拆分后的对象都添加到country_additives中后，删除country_index行
            country_additives.drop([country_index],inplace=True)

    #4、再次groupby
    country_data =country_additives.groupby('countries_en').sum()
    #5、排序
    result = country_data.sort_values(by='additives_n',ascending=False)

    #6、pandas 可视化 top10
    result.iloc[:10].plot.bar()
    plt.show()

    #5、保存处理结果
    result.to_csv("./country_additives.csv")



if __name__ == '__main__':
    run_main()