notebook.community

Edit and run



In [1]:

    
import numpy as np
import pandas as pd
import utilities as utils
import matplotlib.pyplot as plt
%matplotlib inline



In [2]:

    
data = pd.read_csv("data/food.csv")









    



/Users/Jared/anaconda/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2723: DtypeWarning: Columns (0,3,5,27,36) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)



In [3]:

    
print data.shape
data.head()









    



(65503, 159)






    Out[3]:






  
    
      
      code
      url
      creator
      created_t
      created_datetime
      last_modified_t
      last_modified_datetime
      product_name
      generic_name
      quantity
      ...
      caffeine_100g
      taurine_100g
      ph_100g
      fruits_vegetables_nuts_100g
      collagen_meat_protein_ratio_100g
      cocoa_100g
      chlorophyl_100g
      carbon_footprint_100g
      nutrition_score_fr_100g
      nutrition_score_uk_100g
    
  
  
    
      0
      000000000000012866
      http://world-en.openfoodfacts.org/product/0000...
      date-limite-app
      1447004364
      2015-11-08T17:39:24Z
      1447004364
      2015-11-08T17:39:24Z
      Poêlée à la sarladaise
      NaN
      NaN
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
    
      1
      0000000024600
      http://world-en.openfoodfacts.org/product/0000...
      date-limite-app
      1434530704
      2015-06-17T08:45:04Z
      1434535914
      2015-06-17T10:11:54Z
      Filet de bœuf
      NaN
      2.46 kg
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
    
      2
      0000000036252
      http://world-en.openfoodfacts.org/product/0000...
      tacinte
      1422221701
      2015-01-25T21:35:01Z
      1422221855
      2015-01-25T21:37:35Z
      Lion Peanut x2
      NaN
      NaN
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
    
      3
      0000000039259
      http://world-en.openfoodfacts.org/product/0000...
      tacinte
      1422221773
      2015-01-25T21:36:13Z
      1422221926
      2015-01-25T21:38:46Z
      Twix x2
      NaN
      NaN
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
    
      4
      0000000039529
      http://world-en.openfoodfacts.org/product/0000...
      teolemon
      1420147051
      2015-01-01T21:17:31Z
      1439141740
      2015-08-09T17:35:40Z
      Pack de 2 Twix
      NaN
      NaN
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
  

5 rows × 159 columns



In [4]:

    
usa_data = utils.getByCountry(data, 'United States')
print usa_data.shape









    



(2508, 159)



In [5]:

    
usa_data.describe()









    Out[5]:






  
    
      
      no_nutriments
      additives_n
      ingredients_from_palm_oil_n
      ingredients_from_palm_oil
      ingredients_that_may_be_from_palm_oil_n
      ingredients_that_may_be_from_palm_oil
      nutrition_grade_uk
      energy_100g
      energy_from_fat_100g
      fat_100g
      ...
      caffeine_100g
      taurine_100g
      ph_100g
      fruits_vegetables_nuts_100g
      collagen_meat_protein_ratio_100g
      cocoa_100g
      chlorophyl_100g
      carbon_footprint_100g
      nutrition_score_fr_100g
      nutrition_score_uk_100g
    
  
  
    
      count
      0.0
      1052.000000
      1052.000000
      0.0
      1052.000000
      0.0
      0.0
      1189.000000
      727.000000
      1202.000000
      ...
      4.000000
      0.0
      0.0
      3.000000
      0.0
      1.0
      0.0
      2.000000
      1026.000000
      1026.000000
    
    
      mean
      NaN
      2.180608
      0.000951
      NaN
      0.021863
      NaN
      NaN
      1176.289537
      579.689216
      13.638052
      ...
      0.013477
      NaN
      NaN
      33.333333
      NaN
      60.0
      NaN
      68.500000
      9.060429
      8.935673
    
    
      std
      NaN
      2.779168
      0.030831
      NaN
      0.146306
      NaN
      NaN
      834.188753
      696.134198
      18.230727
      ...
      0.005561
      NaN
      NaN
      31.754265
      NaN
      NaN
      NaN
      79.903066
      9.135097
      9.348419
    
    
      min
      NaN
      0.000000
      0.000000
      NaN
      0.000000
      NaN
      NaN
      0.000000
      0.000000
      0.000000
      ...
      0.007830
      NaN
      NaN
      15.000000
      NaN
      60.0
      NaN
      12.000000
      -10.000000
      -10.000000
    
    
      25%
      NaN
      0.000000
      0.000000
      NaN
      0.000000
      NaN
      NaN
      328.000000
      43.800000
      0.000000
      ...
      0.009143
      NaN
      NaN
      15.000000
      NaN
      60.0
      NaN
      40.250000
      0.000000
      0.000000
    
    
      50%
      NaN
      1.000000
      0.000000
      NaN
      0.000000
      NaN
      NaN
      1290.000000
      300.000000
      6.250000
      ...
      0.013790
      NaN
      NaN
      15.000000
      NaN
      60.0
      NaN
      68.500000
      10.000000
      9.000000
    
    
      75%
      NaN
      3.000000
      0.000000
      NaN
      0.000000
      NaN
      NaN
      1790.000000
      917.000000
      21.400000
      ...
      0.018125
      NaN
      NaN
      42.500000
      NaN
      60.0
      NaN
      96.750000
      16.000000
      17.000000
    
    
      max
      NaN
      17.000000
      1.000000
      NaN
      1.000000
      NaN
      NaN
      3766.000000
      3740.000000
      100.000000
      ...
      0.018500
      NaN
      NaN
      70.000000
      NaN
      60.0
      NaN
      125.000000
      29.000000
      29.000000
    
  

8 rows × 103 columns

What is the most sugary food in the USA?



In [6]:

    
sugar = usa_data.sugars_100g[usa_data.sugars_100g.notnull()]
most_sugar = sugar.sort_values(ascending=False)
usa_data[usa_data.sugars_100g >= most_sugar.iloc[0]]









    Out[6]:






  
    
      
      code
      url
      creator
      created_t
      created_datetime
      last_modified_t
      last_modified_datetime
      product_name
      generic_name
      quantity
      ...
      caffeine_100g
      taurine_100g
      ph_100g
      fruits_vegetables_nuts_100g
      collagen_meat_protein_ratio_100g
      cocoa_100g
      chlorophyl_100g
      carbon_footprint_100g
      nutrition_score_fr_100g
      nutrition_score_uk_100g
    
  
  
    
      47379
      4902124680235
      http://world-en.openfoodfacts.org/product/4902...
      stephane
      1438876475
      2015-08-06T15:54:35Z
      1439069028
      2015-08-08T21:23:48Z
      Super Lemon
      Lemon candy
      2.92 oz (83 g)
      ...
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      14.0
      14.0
    
  

1 rows × 159 columns

Compare countries by average of different nutriments



In [7]:

    
unique_countries = utils.getUniqueCountries(data)



In [8]:

    
sugar_avg = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'sugars_100g')
p = sugar_avg.plot(kind='bar', legend=False, title='Average Sugars_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x102081610>



In [14]:

    
energy_avg = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'energy_100g')
p = energy_avg.plot(kind='bar', legend=False, title='Average Energy_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[14]:





<matplotlib.axes._subplots.AxesSubplot at 0x129e0a0d0>



In [15]:

    
sodium_avg = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'sodium_100g')
p = sodium_avg.plot(kind='bar', legend=False, title='Average Sodium_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[15]:





<matplotlib.axes._subplots.AxesSubplot at 0x12a825c90>



In [16]:

    
fat_100g = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'fat_100g')
p = fat_100g.plot(kind='bar', legend=False, title='Average Fat_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[16]:





<matplotlib.axes._subplots.AxesSubplot at 0x12964f650>



In [17]:

    
proteins_100g = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'proteins_100g')
p = proteins_100g.plot(kind='bar', legend=False, title='Average Proteins_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[17]:





<matplotlib.axes._subplots.AxesSubplot at 0x12ad55450>



In [18]:

    
carbohydrates_100g = utils.compareCountriesByNutrimentAverage(data, unique_countries, 'carbohydrates_100g')
p = carbohydrates_100g.plot(kind='bar', legend=False, title='Average Carbohydrates_100g By Country (w/ Sample Size > 30)')
p.set_xlabel("Country")
p.set_ylabel("Grams")
p









    Out[18]:





<matplotlib.axes._subplots.AxesSubplot at 0x12b29c390>



In [ ]:

	code	url	creator	created_t	created_datetime	last_modified_t	last_modified_datetime	product_name	generic_name	quantity	...	caffeine_100g	taurine_100g	ph_100g	fruits_vegetables_nuts_100g	collagen_meat_protein_ratio_100g	cocoa_100g	chlorophyl_100g	carbon_footprint_100g	nutrition_score_fr_100g	nutrition_score_uk_100g
0	000000000000012866	http://world-en.openfoodfacts.org/product/0000...	date-limite-app	1447004364	2015-11-08T17:39:24Z	1447004364	2015-11-08T17:39:24Z	Poêlée à la sarladaise	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	0000000024600	http://world-en.openfoodfacts.org/product/0000...	date-limite-app	1434530704	2015-06-17T08:45:04Z	1434535914	2015-06-17T10:11:54Z	Filet de bœuf	NaN	2.46 kg	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	0000000036252	http://world-en.openfoodfacts.org/product/0000...	tacinte	1422221701	2015-01-25T21:35:01Z	1422221855	2015-01-25T21:37:35Z	Lion Peanut x2	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	0000000039259	http://world-en.openfoodfacts.org/product/0000...	tacinte	1422221773	2015-01-25T21:36:13Z	1422221926	2015-01-25T21:38:46Z	Twix x2	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	0000000039529	http://world-en.openfoodfacts.org/product/0000...	teolemon	1420147051	2015-01-01T21:17:31Z	1439141740	2015-08-09T17:35:40Z	Pack de 2 Twix	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	no_nutriments	additives_n	ingredients_from_palm_oil_n	ingredients_from_palm_oil	ingredients_that_may_be_from_palm_oil_n	ingredients_that_may_be_from_palm_oil	nutrition_grade_uk	energy_100g	energy_from_fat_100g	fat_100g	...	caffeine_100g	taurine_100g	ph_100g	fruits_vegetables_nuts_100g	collagen_meat_protein_ratio_100g	cocoa_100g	chlorophyl_100g	carbon_footprint_100g	nutrition_score_fr_100g	nutrition_score_uk_100g
count	0.0	1052.000000	1052.000000	0.0	1052.000000	0.0	0.0	1189.000000	727.000000	1202.000000	...	4.000000	0.0	0.0	3.000000	0.0	1.0	0.0	2.000000	1026.000000	1026.000000
mean	NaN	2.180608	0.000951	NaN	0.021863	NaN	NaN	1176.289537	579.689216	13.638052	...	0.013477	NaN	NaN	33.333333	NaN	60.0	NaN	68.500000	9.060429	8.935673
std	NaN	2.779168	0.030831	NaN	0.146306	NaN	NaN	834.188753	696.134198	18.230727	...	0.005561	NaN	NaN	31.754265	NaN	NaN	NaN	79.903066	9.135097	9.348419
min	NaN	0.000000	0.000000	NaN	0.000000	NaN	NaN	0.000000	0.000000	0.000000	...	0.007830	NaN	NaN	15.000000	NaN	60.0	NaN	12.000000	-10.000000	-10.000000
25%	NaN	0.000000	0.000000	NaN	0.000000	NaN	NaN	328.000000	43.800000	0.000000	...	0.009143	NaN	NaN	15.000000	NaN	60.0	NaN	40.250000	0.000000	0.000000
50%	NaN	1.000000	0.000000	NaN	0.000000	NaN	NaN	1290.000000	300.000000	6.250000	...	0.013790	NaN	NaN	15.000000	NaN	60.0	NaN	68.500000	10.000000	9.000000
75%	NaN	3.000000	0.000000	NaN	0.000000	NaN	NaN	1790.000000	917.000000	21.400000	...	0.018125	NaN	NaN	42.500000	NaN	60.0	NaN	96.750000	16.000000	17.000000
max	NaN	17.000000	1.000000	NaN	1.000000	NaN	NaN	3766.000000	3740.000000	100.000000	...	0.018500	NaN	NaN	70.000000	NaN	60.0	NaN	125.000000	29.000000	29.000000