python数据分析十八：USDA食品数据库分析(总结，原始数据分享)

分享一下这本书的原始数据数据
# -*- coding: utf-8 -*-
import pandas as pd

from pandas import Series,DataFrame

import numpy as np

'''
分析美国农业部食品数据库
'''
import json

db=json.load(open('C:\\tools\\pydata-book-master\\ch07\\foods-2011-10-03.json'))
print(len(db))

#db的每一条目录都含有某种食品的所有数据字典，nutrients字段是一个字典列表，其中每一个字典对应一种养分
#print(db[1])

#获取数据中字典的key值
#print(db[0].keys())
#dict_keys(['id', 'description', 'tags', 'manufacturer', 'group', 'portions', 'nutrients'])

#获取nutrients下的第一条数据
#print(db[0]['nutrients'][0])
#{'value': 25.18, 'units': 'g', 'description': 'Protein', 'group': 'Composition'}

nutrients=DataFrame(db[0]['nutrients'])
#print(nutrients)

#获取商品的片段，只取出食品的名称，分类，编号，制造商
#设置列名
info_keys=['description','group','id','manufacturer']

info=DataFrame(db,columns=info_keys)

#print(info[:5])

#可以通过value_counts查看食品的分布情况
#print(pd.value_counts(info.group))
# Vegetables and Vegetable Products    812
# Beef Products                        618
# Baked Products                       496
# Breakfast Cereals                    403
# Fast Foods                           365
# Legumes and Legume Products          365
# Lamb, Veal, and Game Products        345
# Sweets                               341
# Pork Products                        328
# Fruits and Fruit Juices              328
# Beverages                            278
# Soups, Sauces, and Gravies           275
# Finfish and Shellfish Products       255
# Baby Foods                           209
# Cereal Grains and Pasta              183
# Ethnic Foods                         165
# Snacks                               162
# Nut and Seed Products                128
# Poultry Products                     116
# Sausages and Luncheon Meats          111
# Dairy and Egg Products               107
# Fats and Oils                         97
# Meals, Entrees, and Sidedishes        57
# Restaurant Foods                      51
# Spices and Herbs                      41

'''
对营养数据进行分析最简单的方法就是，将所有营养数据整合成一张大表 concat
'''
nutrients=[]

for rec in db:
    fnuts=DataFrame(rec['nutrients'])
    #给fnuts表添加一列数据，将每条的id添加到fnuts的id
    fnuts['id']=rec['id']
    nutrients.append(fnuts)

#将所有的表整合到一起
nutrients=pd.concat(nutrients,ignore_index=True)
#print(nutrients)

#查看是否有重复项
#print(nutrients.duplicated().sum())

#删除重复项
nutrients=nutrients.drop_duplicates()
# print(nutrients)


'''
因为大的Dataframe和小的里面中都有gruop和description,这里要重命名   rename

'''
col_mapping={'description':'food','group':'fgroup'}
info=info.rename(columns=col_mapping,copy=False)
#print(info.describe())

col_mapping={'description':'nutrient','group':'nutgroup'}
nutrients=nutrients.rename(columns=col_mapping,copy=False)


'''
做完这些事情后我们就可以把info表和nutrients表合并起来了，merge
'''

ndata=pd.merge(nutrients,info,on='id',how='outer')#以id为连接键，显示nan值，将nutrients和info表结合

#获取其中一条数据
print(ndata.ix[30000])
# nutrient                                       Glycine
# nutgroup                                   Amino Acids
# units                                                g
# value                                             0.04
# id                                                6158
# food            Soup, tomato bisque, canned, condensed
# fgroup                      Soups, Sauces, and Gravies
# manufacturer
# Name: 30000, dtype: object
每天进步一点点
python数据分析十八：USDA食品数据库分析(总结，原始数据分享)

猜你喜欢
