Processing the open food databse to extract a dataset to use for the visualization.
In [1]:
import pandas as pd
import numpy as np
import re
from scipy import sparse as sparse
# SK-learn libraries for feature extraction from text.
from sklearn.feature_extraction.text import *
data_dir = "/Users/seddont/Dropbox/Tom/MIDS/W209_work/Tom_project/"
code_dir = "/Users/seddont/Dropbox/Tom/MIDS/W209_work/w209finalproject/"
Working from the full database, because the usda_imports_filtered.csv file in the shared drive does not have brand information, which might be useful for displaying.
In [2]:
# Get sample of the full database to understand what columns we want
smp = pd.read_csv(data_dir+"en.openfoodfacts.org.products.csv", sep = "\t", nrows = 100)
In [3]:
for c in smp.columns:
print(c)
code
url
creator
created_t
created_datetime
last_modified_t
last_modified_datetime
product_name
generic_name
quantity
packaging
packaging_tags
brands
brands_tags
categories
categories_tags
categories_en
origins
origins_tags
manufacturing_places
manufacturing_places_tags
labels
labels_tags
labels_en
emb_codes
emb_codes_tags
first_packaging_code_geo
cities
cities_tags
purchase_places
stores
countries
countries_tags
countries_en
ingredients_text
allergens
allergens_en
traces
traces_tags
traces_en
serving_size
no_nutriments
additives_n
additives
additives_tags
additives_en
ingredients_from_palm_oil_n
ingredients_from_palm_oil
ingredients_from_palm_oil_tags
ingredients_that_may_be_from_palm_oil_n
ingredients_that_may_be_from_palm_oil
ingredients_that_may_be_from_palm_oil_tags
nutrition_grade_uk
nutrition_grade_fr
pnns_groups_1
pnns_groups_2
states
states_tags
states_en
main_category
main_category_en
image_url
image_small_url
energy_100g
energy-from-fat_100g
fat_100g
saturated-fat_100g
-butyric-acid_100g
-caproic-acid_100g
-caprylic-acid_100g
-capric-acid_100g
-lauric-acid_100g
-myristic-acid_100g
-palmitic-acid_100g
-stearic-acid_100g
-arachidic-acid_100g
-behenic-acid_100g
-lignoceric-acid_100g
-cerotic-acid_100g
-montanic-acid_100g
-melissic-acid_100g
monounsaturated-fat_100g
polyunsaturated-fat_100g
omega-3-fat_100g
-alpha-linolenic-acid_100g
-eicosapentaenoic-acid_100g
-docosahexaenoic-acid_100g
omega-6-fat_100g
-linoleic-acid_100g
-arachidonic-acid_100g
-gamma-linolenic-acid_100g
-dihomo-gamma-linolenic-acid_100g
omega-9-fat_100g
-oleic-acid_100g
-elaidic-acid_100g
-gondoic-acid_100g
-mead-acid_100g
-erucic-acid_100g
-nervonic-acid_100g
trans-fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
-sucrose_100g
-glucose_100g
-fructose_100g
-lactose_100g
-maltose_100g
-maltodextrins_100g
starch_100g
polyols_100g
fiber_100g
proteins_100g
casein_100g
serum-proteins_100g
nucleotides_100g
salt_100g
sodium_100g
alcohol_100g
vitamin-a_100g
beta-carotene_100g
vitamin-d_100g
vitamin-e_100g
vitamin-k_100g
vitamin-c_100g
vitamin-b1_100g
vitamin-b2_100g
vitamin-pp_100g
vitamin-b6_100g
vitamin-b9_100g
folates_100g
vitamin-b12_100g
biotin_100g
pantothenic-acid_100g
silica_100g
bicarbonate_100g
potassium_100g
chloride_100g
calcium_100g
phosphorus_100g
iron_100g
magnesium_100g
zinc_100g
copper_100g
manganese_100g
fluoride_100g
selenium_100g
chromium_100g
molybdenum_100g
iodine_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
glycemic-index_100g
water-hardness_100g
In [4]:
# Specify what columns we need for the visualization. For speed purposes going to
# remove any we don't really need
wanted_cols = ['code', 'creator', 'product_name', 'brands', 'brands_tags', 'serving_size',
'serving_size', 'energy_100g', 'fat_100g', 'cholesterol_100g',
'carbohydrates_100g', 'sugars_100g', 'fiber_100g', 'proteins_100g', 'sodium_100g']
# Create a list of columns to drop to check it worked ok
drop_cols = [c for c in smp.columns if c not in wanted_cols]
print(drop_cols)
['url', 'created_t', 'created_datetime', 'last_modified_t', 'last_modified_datetime', 'generic_name', 'quantity', 'packaging', 'packaging_tags', 'categories', 'categories_tags', 'categories_en', 'origins', 'origins_tags', 'manufacturing_places', 'manufacturing_places_tags', 'labels', 'labels_tags', 'labels_en', 'emb_codes', 'emb_codes_tags', 'first_packaging_code_geo', 'cities', 'cities_tags', 'purchase_places', 'stores', 'countries', 'countries_tags', 'countries_en', 'ingredients_text', 'allergens', 'allergens_en', 'traces', 'traces_tags', 'traces_en', 'no_nutriments', 'additives_n', 'additives', 'additives_tags', 'additives_en', 'ingredients_from_palm_oil_n', 'ingredients_from_palm_oil', 'ingredients_from_palm_oil_tags', 'ingredients_that_may_be_from_palm_oil_n', 'ingredients_that_may_be_from_palm_oil', 'ingredients_that_may_be_from_palm_oil_tags', 'nutrition_grade_uk', 'nutrition_grade_fr', 'pnns_groups_1', 'pnns_groups_2', 'states', 'states_tags', 'states_en', 'main_category', 'main_category_en', 'image_url', 'image_small_url', 'energy-from-fat_100g', 'saturated-fat_100g', '-butyric-acid_100g', '-caproic-acid_100g', '-caprylic-acid_100g', '-capric-acid_100g', '-lauric-acid_100g', '-myristic-acid_100g', '-palmitic-acid_100g', '-stearic-acid_100g', '-arachidic-acid_100g', '-behenic-acid_100g', '-lignoceric-acid_100g', '-cerotic-acid_100g', '-montanic-acid_100g', '-melissic-acid_100g', 'monounsaturated-fat_100g', 'polyunsaturated-fat_100g', 'omega-3-fat_100g', '-alpha-linolenic-acid_100g', '-eicosapentaenoic-acid_100g', '-docosahexaenoic-acid_100g', 'omega-6-fat_100g', '-linoleic-acid_100g', '-arachidonic-acid_100g', '-gamma-linolenic-acid_100g', '-dihomo-gamma-linolenic-acid_100g', 'omega-9-fat_100g', '-oleic-acid_100g', '-elaidic-acid_100g', '-gondoic-acid_100g', '-mead-acid_100g', '-erucic-acid_100g', '-nervonic-acid_100g', 'trans-fat_100g', '-sucrose_100g', '-glucose_100g', '-fructose_100g', '-lactose_100g', '-maltose_100g', '-maltodextrins_100g', 'starch_100g', 'polyols_100g', 'casein_100g', 'serum-proteins_100g', 'nucleotides_100g', 'salt_100g', 'alcohol_100g', 'vitamin-a_100g', 'beta-carotene_100g', 'vitamin-d_100g', 'vitamin-e_100g', 'vitamin-k_100g', 'vitamin-c_100g', 'vitamin-b1_100g', 'vitamin-b2_100g', 'vitamin-pp_100g', 'vitamin-b6_100g', 'vitamin-b9_100g', 'folates_100g', 'vitamin-b12_100g', 'biotin_100g', 'pantothenic-acid_100g', 'silica_100g', 'bicarbonate_100g', 'potassium_100g', 'chloride_100g', 'calcium_100g', 'phosphorus_100g', 'iron_100g', 'magnesium_100g', 'zinc_100g', 'copper_100g', 'manganese_100g', 'fluoride_100g', 'selenium_100g', 'chromium_100g', 'molybdenum_100g', 'iodine_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', 'glycemic-index_100g', 'water-hardness_100g']
In [5]:
# Pull in full dataset, only the columns we want
df = pd.read_csv(data_dir+"en.openfoodfacts.org.products.csv", sep = "\t")
/Users/seddont/anaconda/lib/python3.5/site-packages/IPython/core/interactiveshell.py:2717: DtypeWarning: Columns (0,3,5,19,20,24,25,26,27,28,35,36,37,38,39,48) have mixed types. Specify dtype option on import or set low_memory=False.
interactivity=interactivity, compiler=compiler, result=result)
In [6]:
# Drop unwanted columns
df.drop(drop_cols, axis = 1, inplace = True)
In [7]:
# Take a quick look
df
Out[7]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
0
3087
openfoodfacts-contributors
Farine de blé noir
Ferme t'y R'nao
ferme-t-y-r-nao
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
1
4530
usda-ndb-import
Banana Chips Sweetened (Whole)
NaN
NaN
28 g (1 ONZ)
2243.0
28.57
0.018
64.29
14.29
3.6
3.57
0.000000
2
4559
usda-ndb-import
Peanuts
Torn & Glasser
torn-glasser
28 g (0.25 cup)
1941.0
17.86
0.000
60.71
17.86
7.1
17.86
0.250000
3
16087
usda-ndb-import
Organic Salted Nut Mix
Grizzlies
grizzlies
28 g (0.25 cup)
2540.0
57.14
NaN
17.86
3.57
7.1
17.86
0.482000
4
16094
usda-ndb-import
Organic Polenta
Bob's Red Mill
bob-s-red-mill
35 g (0.25 cup)
1552.0
1.43
NaN
77.14
NaN
5.7
8.57
NaN
5
16100
usda-ndb-import
Breadshop Honey Gone Nuts Granola
Unfi
unfi
52 g (0.5 cup)
1933.0
18.27
NaN
63.46
11.54
7.7
13.46
NaN
6
16117
usda-ndb-import
Organic Long Grain White Rice
Lundberg
lundberg
45 g (0.25 cup)
1490.0
NaN
NaN
80.00
NaN
NaN
8.89
NaN
7
16124
usda-ndb-import
Organic Muesli
Daddy's Muesli
daddy-s-muesli
64 g (0.5 cup)
1833.0
18.75
NaN
57.81
15.62
9.4
14.06
0.055000
8
16193
usda-ndb-import
Organic Dark Chocolate Minis
Equal Exchange
equal-exchange
40 g (40 g)
2406.0
37.50
NaN
55.00
42.50
7.5
5.00
NaN
9
16513
usda-ndb-import
Organic Sunflower Oil
Napa Valley Naturals
napa-valley-naturals
14 g (1 Tbsp)
3586.0
100.00
NaN
NaN
NaN
NaN
NaN
NaN
10
16612
usda-ndb-import
Organic Adzuki Beans
Unfi
unfi
48 g (0.25 cup)
1393.0
1.04
NaN
62.50
NaN
12.5
22.92
NaN
11
16650
usda-ndb-import
Organic Penne Pasta
Gardentime
gardentime
57 g (0.5 cup)
1540.0
1.75
NaN
73.68
NaN
1.8
14.04
NaN
12
16872
usda-ndb-import
Zen Party Mix
Sunridge
sunridge
30 g (0.25 cup)
2230.0
36.67
NaN
36.67
3.33
6.7
16.67
0.633000
13
16933
usda-ndb-import
Organic Golden Flax Seeds
Unfi
unfi
21 g (2 Tbsp)
2590.0
42.86
NaN
38.10
NaN
38.1
19.05
0.038000
14
17497
usda-ndb-import
Organic Spicy Punks
Eden
eden
33 g (0.25 cup)
2536.0
48.48
NaN
15.15
NaN
15.2
30.30
0.227000
15
18012
usda-ndb-import
Cinnamon Nut Granola
Grizzlies
grizzlies
55 g (0.5 cup)
1824.0
18.18
NaN
60.00
21.82
9.1
14.55
0.009000
16
18050
usda-ndb-import
Organic Hazelnuts
Grizzlies
grizzlies
28 g (0.25 cup)
2632.0
60.71
NaN
17.86
3.57
10.7
14.29
0.004000
17
18173
usda-ndb-import
Organic Sweetened Banana Chips
Unfi
unfi
30 g (0.25 cup)
2092.0
26.67
NaN
66.67
16.67
3.3
3.33
NaN
18
18197
usda-ndb-import
Lotus Organic Brown Jasmine Rice
Unfi
unfi
45 g (0.25 cup)
1582.0
2.22
NaN
77.78
2.22
2.2
8.89
NaN
19
18227
usda-ndb-import
Organic Oat Groats
Pcc
pcc
42 g (0.25 cup)
1096.0
5.95
NaN
66.67
2.38
9.5
16.67
0.010000
20
18265
usda-ndb-import
Energy Power Mix
Sunridge
sunridge
40 g (0.25 cup)
1464.0
17.50
NaN
42.50
32.50
5.0
7.50
0.112000
21
18289
usda-ndb-import
Antioxidant Mix - Berries & Chocolate
Sunridge
sunridge
30 g (0.25 cup)
2092.0
33.33
NaN
46.67
30.00
6.7
13.33
0.183000
22
18319
usda-ndb-import
Organic Quinoa Coconut Granola With Mango
Sunridge
sunridge
55 g (0.5 cup)
1674.0
10.91
NaN
69.09
27.27
9.1
10.91
0.009000
23
18340
usda-ndb-import
Fire Roasted Hatch Green Chile Almonds
Sunridge
sunridge
30 g (0.25 cup)
2372.0
50.00
NaN
23.33
6.67
10.0
6.67
0.500000
24
18357
usda-ndb-import
Peanut Butter Power Chews
Sunridge
sunridge
45 g (45 GRM)
1954.0
20.00
NaN
60.00
33.33
4.4
8.89
0.078000
25
18371
usda-ndb-import
Real Salt Granular
Redmond
redmond
1.4 g (0.25 tsp)
NaN
NaN
NaN
NaN
NaN
NaN
NaN
37.857000
26
18388
usda-ndb-import
Organic Unswt Berry Coconut Granola
New England Naturals
new-england-naturals
54 g (0.5 cup)
1548.0
22.22
NaN
57.41
5.56
9.3
12.96
0.111000
27
18395
usda-ndb-import
Roasted Salted Black Pepper Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
46.67
NaN
30.00
6.67
3.3
16.67
0.400000
28
18401
usda-ndb-import
Thai Curry Roasted Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
43.33
NaN
30.00
6.67
3.3
16.67
0.533000
29
18418
usda-ndb-import
Wasabi Tamari Almonds
Sunridge
sunridge
30 g (30 g)
2230.0
46.67
NaN
23.33
3.33
10.0
20.00
0.800000
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
330420
9789961637609
openfoodfacts-contributors
Tarifs djoghrafia
Chihab
chihab
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330421
9791463741241
scailyna
Gingembre
Terre exotique
terre-exotique
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330422
9800120499
openfoodfacts-contributors
Ferrero Rocher
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330423
9800801107
tacite-mass-editor
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330424
9800895007
tacite-mass-editor
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330425
9800895250
tacite-mass-editor
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330426
9802735
date-limite-app
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330427
9820111458900
openfoodfacts-contributors
Les Belles Tranches Bacon fumé
Justin Bridou
justin-bridou
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330428
9836654056565
usda-ndb-import
Raspados Ice Bars
Jarritos, The Jel Sert Company
jarritos,the-jel-sert-company
57 g (57 g)
368.0
0.00
NaN
21.05
19.30
NaN
0.00
0.018000
330429
9847548283004
drmalabar
Tartines craquantes bio au sarrasin
Le Pain des fleurs
le-pain-des-fleurs
NaN
1643.0
2.80
NaN
74.80
2.60
5.9
13.00
0.267717
330430
98709870987
openfoodfacts-contributors
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330431
9871311007
aleene
Lager
Carib
carib
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330432
9876567898765
openfoodfacts-contributors
nf test
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330433
988639
tacite-mass-editor
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330434
9900000000233
kiliweb
Amandes
Biosic
biosic
NaN
2406.0
NaN
NaN
NaN
3.89
12.2
21.22
0.039370
330435
9900010011557
jeanbono
Miel de Camargue
L. Boulaire
l-boulaire
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330436
9901198001583
openfoodfacts-contributors
Лимон — лайм
Пеликан
пеликан
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330437
9901942000794
gaspardbenoit
Mleko wiejskie
Piątnica
piątnica
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330438
99044169
date-limite-app
Poireaux
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330439
9906410000009
agamitsudo
Roussette du Bugey (2011)
Roussette du Bugey
roussette-du-bugey
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330440
9908278636246
andre
Szprot w oleju roslinnym
EvraFish
evrafish
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330441
99111250
balooval
Thé vert Earl grey
Lobodis
lobodis
NaN
21.0
0.20
NaN
0.50
0.50
0.2
0.50
0.010000
330442
9918
woshilapin
Cheese cake thé vert, yuzu
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330443
9935010000003
sebleouf
Rillette d'oie
Sans marque,D.Lambert
sans-marque,d-lambert
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330444
99410148
date-limite-app
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330445
9948282780603
openfoodfacts-contributors
Tomato & ricotta
Panzani
panzani
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330446
99567453
usda-ndb-import
Mint Melange Tea A Blend Of Peppermint, Lemon ...
Trader Joe's
trader-joe-s
20 g (0.7 oz)
0.0
0.00
0.000
0.00
0.00
0.0
0.00
0.000000
330447
9970229501521
tomato
乐吧泡菜味薯片
乐吧
乐吧
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330448
9980282863788
openfoodfacts-contributors
Tomates aux Vermicelles
Knorr
knorr
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
NaN
330449
999990026839
usda-ndb-import
Sugar Free Drink Mix, Peach Tea
Market Pantry
market-pantry
1 g (0.5 PACKET)
2092.0
0.00
NaN
0.00
0.00
NaN
0.00
0.000000
330450 rows × 14 columns
In [8]:
# Drop all rows that are not from the usda ndb import
df = df[df.creator == "usda-ndb-import"]
# Drop all rows where Brands == Nan as we can't really identify those products
df = df[df.brands.notnull()]
In [9]:
df
Out[9]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
2
4559
usda-ndb-import
Peanuts
Torn & Glasser
torn-glasser
28 g (0.25 cup)
1941.0
17.86
0.000
60.71
17.86
7.1
17.86
0.250
3
16087
usda-ndb-import
Organic Salted Nut Mix
Grizzlies
grizzlies
28 g (0.25 cup)
2540.0
57.14
NaN
17.86
3.57
7.1
17.86
0.482
4
16094
usda-ndb-import
Organic Polenta
Bob's Red Mill
bob-s-red-mill
35 g (0.25 cup)
1552.0
1.43
NaN
77.14
NaN
5.7
8.57
NaN
5
16100
usda-ndb-import
Breadshop Honey Gone Nuts Granola
Unfi
unfi
52 g (0.5 cup)
1933.0
18.27
NaN
63.46
11.54
7.7
13.46
NaN
6
16117
usda-ndb-import
Organic Long Grain White Rice
Lundberg
lundberg
45 g (0.25 cup)
1490.0
NaN
NaN
80.00
NaN
NaN
8.89
NaN
7
16124
usda-ndb-import
Organic Muesli
Daddy's Muesli
daddy-s-muesli
64 g (0.5 cup)
1833.0
18.75
NaN
57.81
15.62
9.4
14.06
0.055
8
16193
usda-ndb-import
Organic Dark Chocolate Minis
Equal Exchange
equal-exchange
40 g (40 g)
2406.0
37.50
NaN
55.00
42.50
7.5
5.00
NaN
9
16513
usda-ndb-import
Organic Sunflower Oil
Napa Valley Naturals
napa-valley-naturals
14 g (1 Tbsp)
3586.0
100.00
NaN
NaN
NaN
NaN
NaN
NaN
10
16612
usda-ndb-import
Organic Adzuki Beans
Unfi
unfi
48 g (0.25 cup)
1393.0
1.04
NaN
62.50
NaN
12.5
22.92
NaN
11
16650
usda-ndb-import
Organic Penne Pasta
Gardentime
gardentime
57 g (0.5 cup)
1540.0
1.75
NaN
73.68
NaN
1.8
14.04
NaN
12
16872
usda-ndb-import
Zen Party Mix
Sunridge
sunridge
30 g (0.25 cup)
2230.0
36.67
NaN
36.67
3.33
6.7
16.67
0.633
13
16933
usda-ndb-import
Organic Golden Flax Seeds
Unfi
unfi
21 g (2 Tbsp)
2590.0
42.86
NaN
38.10
NaN
38.1
19.05
0.038
14
17497
usda-ndb-import
Organic Spicy Punks
Eden
eden
33 g (0.25 cup)
2536.0
48.48
NaN
15.15
NaN
15.2
30.30
0.227
15
18012
usda-ndb-import
Cinnamon Nut Granola
Grizzlies
grizzlies
55 g (0.5 cup)
1824.0
18.18
NaN
60.00
21.82
9.1
14.55
0.009
16
18050
usda-ndb-import
Organic Hazelnuts
Grizzlies
grizzlies
28 g (0.25 cup)
2632.0
60.71
NaN
17.86
3.57
10.7
14.29
0.004
17
18173
usda-ndb-import
Organic Sweetened Banana Chips
Unfi
unfi
30 g (0.25 cup)
2092.0
26.67
NaN
66.67
16.67
3.3
3.33
NaN
18
18197
usda-ndb-import
Lotus Organic Brown Jasmine Rice
Unfi
unfi
45 g (0.25 cup)
1582.0
2.22
NaN
77.78
2.22
2.2
8.89
NaN
19
18227
usda-ndb-import
Organic Oat Groats
Pcc
pcc
42 g (0.25 cup)
1096.0
5.95
NaN
66.67
2.38
9.5
16.67
0.010
20
18265
usda-ndb-import
Energy Power Mix
Sunridge
sunridge
40 g (0.25 cup)
1464.0
17.50
NaN
42.50
32.50
5.0
7.50
0.112
21
18289
usda-ndb-import
Antioxidant Mix - Berries & Chocolate
Sunridge
sunridge
30 g (0.25 cup)
2092.0
33.33
NaN
46.67
30.00
6.7
13.33
0.183
22
18319
usda-ndb-import
Organic Quinoa Coconut Granola With Mango
Sunridge
sunridge
55 g (0.5 cup)
1674.0
10.91
NaN
69.09
27.27
9.1
10.91
0.009
23
18340
usda-ndb-import
Fire Roasted Hatch Green Chile Almonds
Sunridge
sunridge
30 g (0.25 cup)
2372.0
50.00
NaN
23.33
6.67
10.0
6.67
0.500
24
18357
usda-ndb-import
Peanut Butter Power Chews
Sunridge
sunridge
45 g (45 GRM)
1954.0
20.00
NaN
60.00
33.33
4.4
8.89
0.078
25
18371
usda-ndb-import
Real Salt Granular
Redmond
redmond
1.4 g (0.25 tsp)
NaN
NaN
NaN
NaN
NaN
NaN
NaN
37.857
26
18388
usda-ndb-import
Organic Unswt Berry Coconut Granola
New England Naturals
new-england-naturals
54 g (0.5 cup)
1548.0
22.22
NaN
57.41
5.56
9.3
12.96
0.111
27
18395
usda-ndb-import
Roasted Salted Black Pepper Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
46.67
NaN
30.00
6.67
3.3
16.67
0.400
28
18401
usda-ndb-import
Thai Curry Roasted Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
43.33
NaN
30.00
6.67
3.3
16.67
0.533
29
18418
usda-ndb-import
Wasabi Tamari Almonds
Sunridge
sunridge
30 g (30 g)
2230.0
46.67
NaN
23.33
3.33
10.0
20.00
0.800
30
18449
usda-ndb-import
Organic Medium Shredded Coconut
Unfi
unfi
30 g (0.25 cup)
2230.0
30.00
NaN
53.33
6.67
6.7
6.67
NaN
31
18456
usda-ndb-import
Organic Red Quinoa
Pcc
pcc
45 g (0.25 cup)
1490.0
6.67
NaN
64.44
11.11
8.9
13.33
0.004
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
330245
9556041600040
usda-ndb-import
Sardines In Chili Oil
Ayam Brand
ayam-brand
56 g (2 oz)
1343.0
23.21
0.009
7.14
0.00
0.0
19.64
0.464
330246
9556041600057
usda-ndb-import
Sardines In Kung Pao Sauce
Ayam Brand
ayam-brand
56 g (2 oz)
820.0
10.71
0.009
8.93
5.36
0.0
19.64
0.607
330248
9556041600255
usda-ndb-import
Mackerel In Tomato Sauce
Ayam Brand
ayam-brand
56 g (2 oz)
820.0
14.29
0.054
1.79
1.79
1.8
12.50
0.268
330249
9556041600293
usda-ndb-import
Sardines In Extra Virgin Olive Oil
Ayam Brand
ayam-brand
56 g (56 g)
1197.0
23.21
0.036
7.14
0.00
0.0
14.29
0.357
330250
9556041602143
usda-ndb-import
Ayam, Satay Peanut Sauce
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
70 g (2.5 oz)
1017.0
17.14
0.000
17.14
8.57
2.9
5.71
0.343
330251
9556041602211
usda-ndb-import
Baked Beans In Tomato Sauce
Ayam
ayam
130 g (4.6 oz)
418.0
0.77
0.000
19.23
7.69
3.8
3.85
0.300
330258
9556041608947
usda-ndb-import
Ayam, Malaysian Satay Sauce, Mild
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
85 g (3 oz)
837.0
12.94
0.000
16.47
4.71
2.4
5.88
0.247
330259
9556041608954
usda-ndb-import
Ayam, Medium Thai Satay Sauce, Lemongrass And ...
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
85 g (3 oz)
937.0
11.76
0.000
21.18
9.41
3.5
7.06
0.282
330266
9556041610940
usda-ndb-import
Coconut Spread (Kaya)
Ayam
ayam
18.5 g (2.6 oz)
1356.0
10.81
0.054
48.65
43.24
0.0
5.41
0.054
330273
9556041612593
usda-ndb-import
Malaysian Curry Paste, Mild
Ayam
ayam
46 g (46 g)
820.0
13.04
0.000
17.39
6.52
4.3
2.17
1.630
330274
9556041612609
usda-ndb-import
Curry Paste For Beef Rendang, Medium
Ayam
ayam
46 g (46 g)
820.0
13.04
0.000
19.57
8.70
4.3
2.17
1.609
330276
9556041620369
usda-ndb-import
Sardines In Spicy Tomato Sauce, Chili And Lime
Ayam Brand
ayam-brand
56 g (56 g)
598.0
7.14
0.071
1.79
1.79
0.0
17.86
0.411
330284
9556107022601
usda-ndb-import
Goldwilly, Original Instant Chrysanthemum Tea,...
Hsc International Pte. Ltd.
hsc-international-pte-ltd
18 g (18 g)
1628.0
0.00
0.000
100.00
22.22
0.0
0.00
0.000
330297
9556173386461
usda-ndb-import
Chewy Candy
Fruit Plus
fruit-plus
12.5 g (0.45 oz)
1674.0
8.00
0.000
88.00
56.00
0.0
0.00
0.000
330311
9556390158162
usda-ndb-import
Lee, Special Crackers
Lee Biscuits (Pte.) Ltd.
lee-biscuits-pte-ltd
22 g (22 g)
1979.0
18.18
0.009
68.18
13.64
4.5
9.09
0.400
330312
9556390178160
usda-ndb-import
Sugar Crackers
Lee Biscuits (Pte.) Ltd.
lee-biscuits-pte-ltd
22 g (3 PCS)
1845.0
13.64
0.009
72.73
9.09
4.6
9.09
0.718
330331
956088003170
usda-ndb-import
Blueberry Chia Buckwheat Muesli
Seven Sundays, Seven Sundays Llc
seven-sundays,seven-sundays-llc
57 g (0.5 cup)
1690.0
10.53
0.000
66.67
15.79
8.8
12.28
0.018
330332
95656335
usda-ndb-import
Chipotle Peppers In Adobo Sauce
La Costena
la-costena
30 g (30 g)
280.0
0.00
0.000
16.67
6.67
10.0
0.00
1.267
330333
95659305
usda-ndb-import
Dal Makhani
Truly Indian
truly-indian
150 g (150 g)
502.0
5.33
0.007
13.33
0.00
2.0
4.67
0.540
330345
9603636634635
usda-ndb-import
Smoked Gouda Cheese
Specially Selected
specially-selected
28 g (1 oz)
1644.0
32.14
0.107
NaN
NaN
NaN
25.00
0.929
330355
96083338
usda-ndb-import
Haywards, Baby Beetroot
Mizkan Euro Ltd.
mizkan-euro-ltd
100 g (100 g)
866.0
0.50
NaN
11.00
NaN
1.5
0.90
NaN
330363
96092613
usda-ndb-import
Umami Pepper, Hot
Taste #5
taste-5
100 g (100 g)
1243.0
4.80
NaN
35.70
5.30
NaN
16.00
NaN
330375
9644000330654
usda-ndb-import
Balsamic Vinegar Of Modena Glaze
Monari Fererzoni
monari-fererzoni
18 g (1 Tbsp)
929.0
0.00
NaN
50.00
33.33
NaN
0.00
0.056
330398
9755635018555
usda-ndb-import
Sour Licorice Twists, Sour Cherry
Newman's Own
newman-s-own
40 g (40 g)
1360.0
1.25
NaN
72.50
32.50
0.0
2.50
0.000
330399
9763556636543
usda-ndb-import
Taco Seasoning Mix
Mccormick & Company Inc.
mccormick-company-inc
6 g (2 tsp)
1393.0
0.00
NaN
66.67
16.67
NaN
16.67
6.333
330406
9780803738782
usda-ndb-import
Organic Z Bar
Clif Kid
clif-kid
36 g (1 BAR)
1393.0
9.72
0.000
61.11
30.56
8.3
5.56
0.375
330419
9787461062105
usda-ndb-import
Natural Cassava
Industria De Casabe Paul
industria-de-casabe-paul
85 g (85 GRM)
1477.0
0.00
0.000
87.06
2.35
4.7
1.18
0.012
330428
9836654056565
usda-ndb-import
Raspados Ice Bars
Jarritos, The Jel Sert Company
jarritos,the-jel-sert-company
57 g (57 g)
368.0
0.00
NaN
21.05
19.30
NaN
0.00
0.018
330446
99567453
usda-ndb-import
Mint Melange Tea A Blend Of Peppermint, Lemon ...
Trader Joe's
trader-joe-s
20 g (0.7 oz)
0.0
0.00
0.000
0.00
0.00
0.0
0.00
0.000
330449
999990026839
usda-ndb-import
Sugar Free Drink Mix, Peach Tea
Market Pantry
market-pantry
1 g (0.5 PACKET)
2092.0
0.00
NaN
0.00
0.00
NaN
0.00
0.000
169012 rows × 14 columns
In [ ]:
The code column can be problematic as it's a long number that can be truncated to a floating point representation when manipulated by certain programs. Going to convert it to append a character at the start to it will be read unambiguously as a string.
First convert the code column to a string
In [10]:
df.code.apply(str)
Out[10]:
2 4559
3 16087
4 16094
5 16100
6 16117
7 16124
8 16193
9 16513
10 16612
11 16650
12 16872
13 16933
14 17497
15 18012
16 18050
17 18173
18 18197
19 18227
20 18265
21 18289
22 18319
23 18340
24 18357
25 18371
26 18388
27 18395
28 18401
29 18418
30 18449
31 18456
...
330245 9556041600040
330246 9556041600057
330248 9556041600255
330249 9556041600293
330250 9556041602143
330251 9556041602211
330258 9556041608947
330259 9556041608954
330266 9556041610940
330273 9556041612593
330274 9556041612609
330276 9556041620369
330284 9556107022601
330297 9556173386461
330311 9556390158162
330312 9556390178160
330331 956088003170
330332 95656335
330333 95659305
330345 9603636634635
330355 96083338
330363 96092613
330375 9644000330654
330398 9755635018555
330399 9763556636543
330406 9780803738782
330419 9787461062105
330428 9836654056565
330446 99567453
330449 999990026839
Name: code, dtype: object
In [11]:
# Add an N in front of the number string
df.code = "N"+df.code.astype(str)
Quick check for NA values
In [12]:
df.isnull().sum(axis = 0)
Out[12]:
code 0
creator 0
product_name 45
brands 0
brands_tags 0
serving_size 2
energy_100g 396
fat_100g 399
cholesterol_100g 28029
carbohydrates_100g 273
sugars_100g 11314
fiber_100g 31282
proteins_100g 891
sodium_100g 790
dtype: int64
Need to get rid of rows with null product_name as we will be using that later for display etc.
In [13]:
df = df[df.product_name.notnull()]
Now going to want to try and find similar products to a specific item. In the demo, did this by just pulling items with certain text in the name and then doing some hand sorting. Can't scale that approach. Going to try to do it based on a combination of words in the name and the ingredients.
Try out the approach of using CountVectorizer on the product_name field to see how it does.
In [14]:
df
Out[14]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
2
N4559
usda-ndb-import
Peanuts
Torn & Glasser
torn-glasser
28 g (0.25 cup)
1941.0
17.86
0.000
60.71
17.86
7.1
17.86
0.250
3
N16087
usda-ndb-import
Organic Salted Nut Mix
Grizzlies
grizzlies
28 g (0.25 cup)
2540.0
57.14
NaN
17.86
3.57
7.1
17.86
0.482
4
N16094
usda-ndb-import
Organic Polenta
Bob's Red Mill
bob-s-red-mill
35 g (0.25 cup)
1552.0
1.43
NaN
77.14
NaN
5.7
8.57
NaN
5
N16100
usda-ndb-import
Breadshop Honey Gone Nuts Granola
Unfi
unfi
52 g (0.5 cup)
1933.0
18.27
NaN
63.46
11.54
7.7
13.46
NaN
6
N16117
usda-ndb-import
Organic Long Grain White Rice
Lundberg
lundberg
45 g (0.25 cup)
1490.0
NaN
NaN
80.00
NaN
NaN
8.89
NaN
7
N16124
usda-ndb-import
Organic Muesli
Daddy's Muesli
daddy-s-muesli
64 g (0.5 cup)
1833.0
18.75
NaN
57.81
15.62
9.4
14.06
0.055
8
N16193
usda-ndb-import
Organic Dark Chocolate Minis
Equal Exchange
equal-exchange
40 g (40 g)
2406.0
37.50
NaN
55.00
42.50
7.5
5.00
NaN
9
N16513
usda-ndb-import
Organic Sunflower Oil
Napa Valley Naturals
napa-valley-naturals
14 g (1 Tbsp)
3586.0
100.00
NaN
NaN
NaN
NaN
NaN
NaN
10
N16612
usda-ndb-import
Organic Adzuki Beans
Unfi
unfi
48 g (0.25 cup)
1393.0
1.04
NaN
62.50
NaN
12.5
22.92
NaN
11
N16650
usda-ndb-import
Organic Penne Pasta
Gardentime
gardentime
57 g (0.5 cup)
1540.0
1.75
NaN
73.68
NaN
1.8
14.04
NaN
12
N16872
usda-ndb-import
Zen Party Mix
Sunridge
sunridge
30 g (0.25 cup)
2230.0
36.67
NaN
36.67
3.33
6.7
16.67
0.633
13
N16933
usda-ndb-import
Organic Golden Flax Seeds
Unfi
unfi
21 g (2 Tbsp)
2590.0
42.86
NaN
38.10
NaN
38.1
19.05
0.038
14
N17497
usda-ndb-import
Organic Spicy Punks
Eden
eden
33 g (0.25 cup)
2536.0
48.48
NaN
15.15
NaN
15.2
30.30
0.227
15
N18012
usda-ndb-import
Cinnamon Nut Granola
Grizzlies
grizzlies
55 g (0.5 cup)
1824.0
18.18
NaN
60.00
21.82
9.1
14.55
0.009
16
N18050
usda-ndb-import
Organic Hazelnuts
Grizzlies
grizzlies
28 g (0.25 cup)
2632.0
60.71
NaN
17.86
3.57
10.7
14.29
0.004
17
N18173
usda-ndb-import
Organic Sweetened Banana Chips
Unfi
unfi
30 g (0.25 cup)
2092.0
26.67
NaN
66.67
16.67
3.3
3.33
NaN
18
N18197
usda-ndb-import
Lotus Organic Brown Jasmine Rice
Unfi
unfi
45 g (0.25 cup)
1582.0
2.22
NaN
77.78
2.22
2.2
8.89
NaN
19
N18227
usda-ndb-import
Organic Oat Groats
Pcc
pcc
42 g (0.25 cup)
1096.0
5.95
NaN
66.67
2.38
9.5
16.67
0.010
20
N18265
usda-ndb-import
Energy Power Mix
Sunridge
sunridge
40 g (0.25 cup)
1464.0
17.50
NaN
42.50
32.50
5.0
7.50
0.112
21
N18289
usda-ndb-import
Antioxidant Mix - Berries & Chocolate
Sunridge
sunridge
30 g (0.25 cup)
2092.0
33.33
NaN
46.67
30.00
6.7
13.33
0.183
22
N18319
usda-ndb-import
Organic Quinoa Coconut Granola With Mango
Sunridge
sunridge
55 g (0.5 cup)
1674.0
10.91
NaN
69.09
27.27
9.1
10.91
0.009
23
N18340
usda-ndb-import
Fire Roasted Hatch Green Chile Almonds
Sunridge
sunridge
30 g (0.25 cup)
2372.0
50.00
NaN
23.33
6.67
10.0
6.67
0.500
24
N18357
usda-ndb-import
Peanut Butter Power Chews
Sunridge
sunridge
45 g (45 GRM)
1954.0
20.00
NaN
60.00
33.33
4.4
8.89
0.078
25
N18371
usda-ndb-import
Real Salt Granular
Redmond
redmond
1.4 g (0.25 tsp)
NaN
NaN
NaN
NaN
NaN
NaN
NaN
37.857
26
N18388
usda-ndb-import
Organic Unswt Berry Coconut Granola
New England Naturals
new-england-naturals
54 g (0.5 cup)
1548.0
22.22
NaN
57.41
5.56
9.3
12.96
0.111
27
N18395
usda-ndb-import
Roasted Salted Black Pepper Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
46.67
NaN
30.00
6.67
3.3
16.67
0.400
28
N18401
usda-ndb-import
Thai Curry Roasted Cashews
Sunridge
sunridge
30 g (30 g)
2372.0
43.33
NaN
30.00
6.67
3.3
16.67
0.533
29
N18418
usda-ndb-import
Wasabi Tamari Almonds
Sunridge
sunridge
30 g (30 g)
2230.0
46.67
NaN
23.33
3.33
10.0
20.00
0.800
30
N18449
usda-ndb-import
Organic Medium Shredded Coconut
Unfi
unfi
30 g (0.25 cup)
2230.0
30.00
NaN
53.33
6.67
6.7
6.67
NaN
31
N18456
usda-ndb-import
Organic Red Quinoa
Pcc
pcc
45 g (0.25 cup)
1490.0
6.67
NaN
64.44
11.11
8.9
13.33
0.004
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
330245
N9556041600040
usda-ndb-import
Sardines In Chili Oil
Ayam Brand
ayam-brand
56 g (2 oz)
1343.0
23.21
0.009
7.14
0.00
0.0
19.64
0.464
330246
N9556041600057
usda-ndb-import
Sardines In Kung Pao Sauce
Ayam Brand
ayam-brand
56 g (2 oz)
820.0
10.71
0.009
8.93
5.36
0.0
19.64
0.607
330248
N9556041600255
usda-ndb-import
Mackerel In Tomato Sauce
Ayam Brand
ayam-brand
56 g (2 oz)
820.0
14.29
0.054
1.79
1.79
1.8
12.50
0.268
330249
N9556041600293
usda-ndb-import
Sardines In Extra Virgin Olive Oil
Ayam Brand
ayam-brand
56 g (56 g)
1197.0
23.21
0.036
7.14
0.00
0.0
14.29
0.357
330250
N9556041602143
usda-ndb-import
Ayam, Satay Peanut Sauce
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
70 g (2.5 oz)
1017.0
17.14
0.000
17.14
8.57
2.9
5.71
0.343
330251
N9556041602211
usda-ndb-import
Baked Beans In Tomato Sauce
Ayam
ayam
130 g (4.6 oz)
418.0
0.77
0.000
19.23
7.69
3.8
3.85
0.300
330258
N9556041608947
usda-ndb-import
Ayam, Malaysian Satay Sauce, Mild
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
85 g (3 oz)
837.0
12.94
0.000
16.47
4.71
2.4
5.88
0.247
330259
N9556041608954
usda-ndb-import
Ayam, Medium Thai Satay Sauce, Lemongrass And ...
Guinea Foods Sdn Bhd
guinea-foods-sdn-bhd
85 g (3 oz)
937.0
11.76
0.000
21.18
9.41
3.5
7.06
0.282
330266
N9556041610940
usda-ndb-import
Coconut Spread (Kaya)
Ayam
ayam
18.5 g (2.6 oz)
1356.0
10.81
0.054
48.65
43.24
0.0
5.41
0.054
330273
N9556041612593
usda-ndb-import
Malaysian Curry Paste, Mild
Ayam
ayam
46 g (46 g)
820.0
13.04
0.000
17.39
6.52
4.3
2.17
1.630
330274
N9556041612609
usda-ndb-import
Curry Paste For Beef Rendang, Medium
Ayam
ayam
46 g (46 g)
820.0
13.04
0.000
19.57
8.70
4.3
2.17
1.609
330276
N9556041620369
usda-ndb-import
Sardines In Spicy Tomato Sauce, Chili And Lime
Ayam Brand
ayam-brand
56 g (56 g)
598.0
7.14
0.071
1.79
1.79
0.0
17.86
0.411
330284
N9556107022601
usda-ndb-import
Goldwilly, Original Instant Chrysanthemum Tea,...
Hsc International Pte. Ltd.
hsc-international-pte-ltd
18 g (18 g)
1628.0
0.00
0.000
100.00
22.22
0.0
0.00
0.000
330297
N9556173386461
usda-ndb-import
Chewy Candy
Fruit Plus
fruit-plus
12.5 g (0.45 oz)
1674.0
8.00
0.000
88.00
56.00
0.0
0.00
0.000
330311
N9556390158162
usda-ndb-import
Lee, Special Crackers
Lee Biscuits (Pte.) Ltd.
lee-biscuits-pte-ltd
22 g (22 g)
1979.0
18.18
0.009
68.18
13.64
4.5
9.09
0.400
330312
N9556390178160
usda-ndb-import
Sugar Crackers
Lee Biscuits (Pte.) Ltd.
lee-biscuits-pte-ltd
22 g (3 PCS)
1845.0
13.64
0.009
72.73
9.09
4.6
9.09
0.718
330331
N956088003170
usda-ndb-import
Blueberry Chia Buckwheat Muesli
Seven Sundays, Seven Sundays Llc
seven-sundays,seven-sundays-llc
57 g (0.5 cup)
1690.0
10.53
0.000
66.67
15.79
8.8
12.28
0.018
330332
N95656335
usda-ndb-import
Chipotle Peppers In Adobo Sauce
La Costena
la-costena
30 g (30 g)
280.0
0.00
0.000
16.67
6.67
10.0
0.00
1.267
330333
N95659305
usda-ndb-import
Dal Makhani
Truly Indian
truly-indian
150 g (150 g)
502.0
5.33
0.007
13.33
0.00
2.0
4.67
0.540
330345
N9603636634635
usda-ndb-import
Smoked Gouda Cheese
Specially Selected
specially-selected
28 g (1 oz)
1644.0
32.14
0.107
NaN
NaN
NaN
25.00
0.929
330355
N96083338
usda-ndb-import
Haywards, Baby Beetroot
Mizkan Euro Ltd.
mizkan-euro-ltd
100 g (100 g)
866.0
0.50
NaN
11.00
NaN
1.5
0.90
NaN
330363
N96092613
usda-ndb-import
Umami Pepper, Hot
Taste #5
taste-5
100 g (100 g)
1243.0
4.80
NaN
35.70
5.30
NaN
16.00
NaN
330375
N9644000330654
usda-ndb-import
Balsamic Vinegar Of Modena Glaze
Monari Fererzoni
monari-fererzoni
18 g (1 Tbsp)
929.0
0.00
NaN
50.00
33.33
NaN
0.00
0.056
330398
N9755635018555
usda-ndb-import
Sour Licorice Twists, Sour Cherry
Newman's Own
newman-s-own
40 g (40 g)
1360.0
1.25
NaN
72.50
32.50
0.0
2.50
0.000
330399
N9763556636543
usda-ndb-import
Taco Seasoning Mix
Mccormick & Company Inc.
mccormick-company-inc
6 g (2 tsp)
1393.0
0.00
NaN
66.67
16.67
NaN
16.67
6.333
330406
N9780803738782
usda-ndb-import
Organic Z Bar
Clif Kid
clif-kid
36 g (1 BAR)
1393.0
9.72
0.000
61.11
30.56
8.3
5.56
0.375
330419
N9787461062105
usda-ndb-import
Natural Cassava
Industria De Casabe Paul
industria-de-casabe-paul
85 g (85 GRM)
1477.0
0.00
0.000
87.06
2.35
4.7
1.18
0.012
330428
N9836654056565
usda-ndb-import
Raspados Ice Bars
Jarritos, The Jel Sert Company
jarritos,the-jel-sert-company
57 g (57 g)
368.0
0.00
NaN
21.05
19.30
NaN
0.00
0.018
330446
N99567453
usda-ndb-import
Mint Melange Tea A Blend Of Peppermint, Lemon ...
Trader Joe's
trader-joe-s
20 g (0.7 oz)
0.0
0.00
0.000
0.00
0.00
0.0
0.00
0.000
330449
N999990026839
usda-ndb-import
Sugar Free Drink Mix, Peach Tea
Market Pantry
market-pantry
1 g (0.5 PACKET)
2092.0
0.00
NaN
0.00
0.00
NaN
0.00
0.000
168967 rows × 14 columns
In [15]:
# Get all the non-null product name fields
name_data = df.product_name
# Pass them to the Count Vectorizer
vectorizer = CountVectorizer()
wv = vectorizer.fit_transform(name_data)
# Get some basic stats
print("Size of vocabulary:", wv.shape[1],"words")
print("Average non-zero entries per example:%5.2f" % (1.0*wv.nnz/wv.shape[0]))
Size of vocabulary: 19299 words
Average non-zero entries per example: 3.99
Get the extracted words
In [16]:
a = vectorizer.get_feature_names()
print("First feature string:", sorted(a)[0])
print("Last feature string:", sorted(a)[len(a)-1])
First feature string: 00
Last feature string: zymbom
Count occurences by word
In [17]:
fn = vectorizer.get_feature_names()
wc = wv.sum(axis = 0)
word_frame = pd.DataFrame({"word": fn, "count":np.ravel(wc)})
In [18]:
word_frame.sort_values(by = ["count"], ascending = False)
Out[18]:
count
word
3523
10278
chocolate
3247
9972
cheese
12211
9052
organic
18888
7899
with
15012
7646
sauce
11097
6765
mix
4348
5740
cream
10976
4825
milk
8889
4200
juice
6662
4178
fruit
3468
3979
chips
3360
3933
chicken
4134
3774
cookies
2752
3722
candy
2510
3697
butter
18772
3606
whole
16899
3543
sweet
8355
3439
ice
16650
3406
style
19120
3399
yogurt
8426
3396
in
1405
3239
beans
18754
3185
white
14457
3139
roasted
11593
3115
natural
13527
3063
premium
12043
2978
oil
12236
2976
original
14331
2913
rice
18622
2882
water
...
...
...
9043
1
kasih
9045
1
kasmati
9046
1
kasondra
9047
1
kasseri
9049
1
kasza
9051
1
katchup
9054
1
kathleen
9021
1
karamah
9018
1
kapoya
9017
1
kapalua
9001
1
kama
8986
1
kalasan
8990
1
kaleifornia
8991
1
kalekopita
8992
1
kalenola
8994
1
kalinga
8995
1
kalmes
8996
1
kalocsa
8999
1
kalua
9002
1
kamaboko
9016
1
kanu
9003
1
kamoi
9006
1
kan
9007
1
kancho
9009
1
kandylas
9010
1
kane
9011
1
kaneli
9012
1
kani
9013
1
kanikama
19298
1
zymbom
19299 rows × 2 columns
Ok -- challenge here is that many of the words are descriptive adjectives vs nouns. Even the ones that are nouns are going to be hard to separate e.g. rice could be rice crackers, chicken and rice, etc.
Wonder if I can get anywhere with bigrams or trigrams...try again
In [19]:
# Get all the non-null product name fields
name_data = df.product_name[df.product_name.notnull()]
# Pass them to the Count Vectorizer
vectorizer = CountVectorizer(analyzer = "word", ngram_range = (3,3))
wv = vectorizer.fit_transform(name_data)
# Get some basic stats
print("Size of vocabulary:", wv.shape[1],"words")
print("Average non-zero entries per example:%5.2f" % (1.0*wv.nnz/wv.shape[0]))
fn = vectorizer.get_feature_names()
wc = wv.sum(axis = 0)
word_frame = pd.DataFrame({"word": fn, "count":np.ravel(wc)})
word_frame.sort_values(by = ["count"], ascending = False)
Size of vocabulary: 192887 words
Average non-zero entries per example: 2.09
Out[19]:
count
word
182900
810
virgin olive oil
60742
807
extra virgin olive
59799
750
enriched macaroni product
134808
558
premium ice cream
152804
367
sharp cheddar cheese
79494
358
greek nonfat yogurt
42253
303
cooked potato chips
160718
296
sparkling water beverage
88910
280
in light syrup
142163
268
reduced fat milk
178619
250
tuna in water
88866
242
in heavy syrup
94633
240
kettle cooked potato
45911
222
cream cheese spread
50406
221
cut green beans
189478
216
with other natural
110324
208
monterey jack cheese
34208
208
chocolate chip cookies
93176
200
juice from concentrate
47205
198
creamy peanut butter
141617
193
red kidney beans
189934
185
with sea salt
98665
180
light ice cream
62518
178
fat free milk
35265
175
chocolate peanut butter
70329
174
frosted sugar cookies
36563
171
chunk light tuna
106539
171
mild cheddar cheese
98847
165
light tuna in
137309
165
pudding pie filling
...
...
...
72497
1
fully cooked smoke
72499
1
fully cooked tequila
72500
1
fully cooked teriyaki
72501
1
fully cooked traditional
72504
1
fully cooked white
72505
1
fully cooked whole
72506
1
fully cooked wieners
72507
1
fully cooked wild
72508
1
fully cooked with
72481
1
fully cooked mini
72480
1
fully cooked mesquite
72479
1
fully cooked menudo
72466
1
fully cooked duck
72455
1
fully cooked black
72457
1
fully cooked bratwurst
72459
1
fully cooked burgers
72461
1
fully cooked cheese
72463
1
fully cooked chorizo
72464
1
fully cooked coated
72465
1
fully cooked cured
72467
1
fully cooked frozen
72477
1
fully cooked meat
72469
1
fully cooked ham
72470
1
fully cooked hatch
72471
1
fully cooked heat
72473
1
fully cooked kicking
72474
1
fully cooked kneidlach
72475
1
fully cooked liverwurst
72476
1
fully cooked maple
192886
1
zymbom energy drink
192887 rows × 2 columns
So some kind of bigram and trigram approach might be scalable here. But don't really have a lot of time to perfect that. However, could use these trigrams to expand the simple 'demo cat' approach by picking only certain bigrams and then using the simple algorithm from the demo approach to find a range of other products with that bigram.
Going to write out the trigrams, do some hand coding of which ones we want to use, then bring the results back in
In [20]:
word_frame.to_csv(data_dir+"trigrams_uncoded.csv")
In [81]:
tri_w = pd.read_csv(code_dir+"trigrams_wanted_v2.csv")
In [82]:
tri_w
Out[82]:
count
word
wanted
0
811
virgin olive oil
NaN
1
808
extra virgin olive
NaN
2
751
enriched macaroni product
NaN
3
558
premium ice cream
1.0
4
369
sharp cheddar cheese
NaN
5
358
greek nonfat yogurt
1.0
6
303
cooked potato chips
1.0
7
296
sparkling water beverage
NaN
8
285
in light syrup
NaN
9
268
reduced fat milk
NaN
10
250
tuna in water
NaN
11
244
in heavy syrup
NaN
12
240
kettle cooked potato
NaN
13
224
cut green beans
NaN
14
223
cream cheese spread
1.0
15
216
with other natural
NaN
16
209
chocolate chip cookies
NaN
17
209
monterey jack cheese
NaN
18
204
creamy peanut butter
NaN
19
200
juice from concentrate
NaN
20
197
red kidney beans
1.0
21
185
with sea salt
NaN
22
180
light ice cream
NaN
23
178
fat free milk
NaN
24
175
chocolate peanut butter
NaN
25
174
frosted sugar cookies
1.0
26
173
chunk light tuna
1.0
27
173
mild cheddar cheese
NaN
28
166
light tuna in
NaN
29
165
pudding pie filling
NaN
...
...
...
...
969
22
corn on the
NaN
970
22
country fresh premium
NaN
971
22
craisins dried cranberries
NaN
972
22
cream ice cream
NaN
973
22
dark chocolate cherry
NaN
974
22
decorated shortbread cookie
NaN
975
22
diet iced tea
NaN
976
22
energy bar chocolate
NaN
977
22
flavored juice blend
NaN
978
22
frozen greek yogurt
NaN
979
22
fruit grain cereal
NaN
980
22
fruit yogurt smoothie
NaN
981
22
garden of eatin
NaN
982
22
garlic pasta sauce
NaN
983
22
garlic sea salt
NaN
984
22
gelatin dessert lime
NaN
985
22
grape soda grape
NaN
986
22
greek low fat
NaN
987
22
honey mustard onion
NaN
988
22
honey nut toasted
NaN
989
22
ice cream banana
NaN
990
22
iced oatmeal cookies
NaN
991
22
in tomato and
NaN
992
22
instant lunch ramen
NaN
993
22
italian waffle cookie
NaN
994
22
lime soda lemon
NaN
995
22
milk chocolate almonds
NaN
996
22
milk chocolate bars
NaN
997
22
movie theater butter
NaN
998
22
naturally flavored sparkling
NaN
999 rows × 3 columns
Can drop all the rows where wanted is NaN
In [83]:
tri_w = tri_w[tri_w.wanted.notnull()]
tri_w
Out[83]:
count
word
wanted
3
558
premium ice cream
1.0
5
358
greek nonfat yogurt
1.0
6
303
cooked potato chips
1.0
14
223
cream cheese spread
1.0
20
197
red kidney beans
1.0
25
174
frosted sugar cookies
1.0
26
173
chunk light tuna
1.0
39
144
roasted turkey breast
1.0
40
142
organic baby food
1.0
42
136
chocolate chip cookie
1.0
43
135
whole wheat bread
1.0
45
129
hot dog buns
1.0
47
126
pureed baby food
1.0
49
122
ice cream sandwiches
1.0
50
121
cookies chocolate chip
1.0
52
120
ice cream bars
1.0
55
116
crunchy peanut butter
1.0
57
116
pancake waffle mix
1.0
60
113
chewy granola bars
1.0
61
111
dry roasted peanuts
1.0
67
108
dairy frozen dessert
1.0
73
102
thin crust pizza
1.0
74
101
caffeine free soda
1.0
75
101
macaroni cheese dinner
1.0
83
98
iced tea mix
1.0
85
98
vegetable oil spread
1.0
91
95
chili with beans
1.0
96
93
whole kernel corn
1.0
97
92
chicken noodle soup
1.0
98
92
peanut butter cups
1.0
...
...
...
...
454
36
white corn tortilla
1.0
461
35
corn puff cereal
1.0
467
35
organic black beans
1.0
499
33
beans in tomato
1.0
510
33
frosted shredded wheat
1.0
527
33
sweet potato chips
1.0
551
32
puffed wheat cereal
1.0
555
32
style potato chips
1.0
564
31
black bean soup
1.0
567
31
classic potato chips
1.0
576
31
ice cream sandwich
1.0
582
31
pico de gallo
1.0
597
30
beef ravioli in
1.0
600
30
chunk white albacore
1.0
607
30
green split peas
1.0
630
30
sloppy joe sauce
1.0
642
29
chicken breast nuggets
1.0
643
29
chocolate covered pretzels
1.0
645
29
corned beef hash
1.0
654
29
hot italian sausage
1.0
689
28
noodles with vegetables
1.0
698
28
soft baked cookies
1.0
702
28
sweet italian sausage
1.0
707
28
tomato sauce with
1.0
710
28
yellow corn tortilla
1.0
715
27
chicken gravy mix
1.0
716
27
chocolate chunk cookies
1.0
724
27
instant mashed potatoes
1.0
743
27
tomato basil soup
1.0
758
26
instant hot cereal
1.0
123 rows × 3 columns
So now got an identifier to use to append wanted categories from
Want to append the trigram as the 'demo category' for any product which contains that trigram. It is possible that a product will fit into multiple trigrams, in which case I will choose to put it in the lowest total count trigram category. Going to do this by looping through the wanted trigrams from highest to lowest and updating the product's category as needed.
In [84]:
# Initialize demo category with None
df["demo_cat"] = "None"
# loop over each trigram
for trigram in tri_w.word:
# get the index of the correct column for that trigram in the vectorized output
wv_index = fn.index(trigram)
# Get locations of matches and convert to a dense representation for indexing
matches = wv[:,wv_index] == 1
matches = np.ravel(sparse.csr_matrix.todense(matches))
# Set the 'demo_cat' field to that trigram value
df.loc[matches, ["demo_cat"]] = trigram
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:2: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
from ipykernel import kernelapp as app
/Users/seddont/anaconda/lib/python3.5/site-packages/pandas/core/indexing.py:477: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
self.obj[item] = s
In [85]:
df[df.demo_cat != "None"]
Out[85]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
39
N18708
usda-ndb-import
Organic Black Beans
Unfi
unfi
45 g (0.25 cup)
1393.0
NaN
NaN
62.22
2.22
24.4
22.22
NaN
organic black beans
51
N30557
usda-ndb-import
Organic Green Split Peas
Coombs Family
coombs-family
45 g (0.25 cup)
1582.0
1.11
NaN
68.89
NaN
28.9
28.89
0.022
green split peas
130
N38713
usda-ndb-import
Organic Steel-Cut Oats
Unfi
unfi
40 g (0.25 cup)
1778.0
7.50
NaN
72.50
NaN
12.5
17.50
NaN
steel cut oats
139
N39536
usda-ndb-import
Organic Short Grain Brown Rice
Lundberg
lundberg
51 g (0.25 cup)
1393.0
2.94
NaN
78.43
NaN
5.9
5.88
NaN
grain brown rice
292
N433821494
usda-ndb-import
Oatmeal Raisin Cookies
Bart & Judy's
bart-judy-s
28 g (6 COOKIES)
1552.0
21.43
0.036
67.86
28.57
3.6
7.14
0.214
oatmeal raisin cookies
417
N901000017
usda-ndb-import
Yellow Corn Tortilla Chips
Guiltless Gourmet
guiltless-gourmet
28 g (1 oz)
1795.0
10.71
0.000
78.57
0.00
7.1
7.14
0.643
yellow corn tortilla
483
N16056
usda-ndb-import
Whole Kernel Corn
Trader Joe's
trader-joe-s
125 g (0.5 cup)
201.0
1.20
0.000
7.20
5.60
1.6
1.60
0.160
whole kernel corn
671
N70662455029
usda-ndb-import
Top Ramen Noodle Soup
Nissin
nissin
42 g (0.5 DRY NOODLE BLOCK AND 1 TSP SEASONING...
1891.0
16.67
0.000
64.29
0.00
4.8
11.90
1.810
ramen noodle soup
718
N79969
usda-ndb-import
Dry Roasted & Salted Almonds
Trader Joe's
trader-joe-s
30 g (0.25 cup)
2372.0
50.00
0.000
16.67
3.33
13.3
23.33
0.383
roasted salted almonds
720
N8001000661
usda-ndb-import
Cool Beans, Red Pepper Hummus
Bobbi's Best Inc.
bobbi-s-best-inc
28 g (2 Tbsp)
895.0
21.43
0.000
10.71
0.00
3.6
3.57
0.375
red pepper hummus
893
N8725247052
usda-ndb-import
Dark Chocolate Almonds
Long Grove Confectionery Co.
long-grove-confectionery-co
37 g (5 cup)
2264.0
40.54
0.014
45.95
32.43
8.1
10.81
0.000
dark chocolate almonds
959
N9300000765
usda-ndb-import
Kosher Dill Spears
Mt. Olive Pickle Company Inc.
mt-olive-pickle-company-inc
28 g (1 oz)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.929
kosher dill spears
961
N9300000802
usda-ndb-import
Kosher Dill Spears
Mt. Olive
mt-olive
28 g (1 oz)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.929
kosher dill spears
965
N9300000888
usda-ndb-import
Kosher Dill Spears
Mt. Olive
mt-olive
28 g (1 oz)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.929
kosher dill spears
997
N9300003506
usda-ndb-import
Kosher Dill Spears Pickles
Mt. Olive, Mount Olive Pickle Company Inc.
mt-olive,mount-olive-pickle-company-inc
28 g (1 SPEAR | ABOUT)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.714
kosher dill spears
1022
N9300006507
usda-ndb-import
Kosher Dill Spears Made With Sea Salt
Mt. Olive
mt-olive
28 g (1 oz)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.929
kosher dill spears
1030
N9300006811
usda-ndb-import
Simply Pickles, Kosher Dill Spears
Mt. Olive
mt-olive
28 g (1 oz)
75.0
0.00
NaN
3.57
NaN
NaN
0.00
0.857
kosher dill spears
1366
N98601
usda-ndb-import
Chicken Noodle Soup
Trader Joe's
trader-joe-s
248 g (1 cup)
151.0
0.40
0.008
5.65
0.40
0.4
2.42
0.294
chicken noodle soup
1552
N10374168084
usda-ndb-import
The Father's Table, Peanut Butter Cup Cheesecake
The Father's Table Llc
the-father-s-table-llc
113 g (1 SLICE)
1665.0
23.01
0.040
38.05
25.66
1.8
5.31
0.301
peanut butter cup
1573
N10374727014
usda-ndb-import
The Father's Table, Red Velvet Cake Roll
The Father's Table Llc
the-father-s-table-llc
113 g (113 GRM)
1481.0
13.27
0.075
54.87
38.94
0.9
4.42
0.248
red velvet cake
1602
N10449777227
usda-ndb-import
Flavored Popcorn, White Cheddar
Rocky Mountain Popcorn
rocky-mountain-popcorn
28 g (2 cup)
2389.0
39.29
0.018
42.86
7.14
7.1
10.71
0.929
popcorn white cheddar
1746
N11110002532
usda-ndb-import
Psst..., Enriched Hot Dog Buns
Psst...
psst
39 g (39 g)
1180.0
3.85
0.000
53.85
7.69
2.6
7.69
0.487
hot dog buns
1750
N11110002853
usda-ndb-import
Hot Dog Buns
Psst
psst
43 g (1 BUN)
1167.0
3.49
0.000
53.49
6.98
2.3
9.30
0.488
hot dog buns
1771
N11110004666
usda-ndb-import
Ice Cream, Chocolate Chip Cookie Dough
Private Selection
private-selection
84 g (0.5 cup)
1146.0
14.29
0.048
30.95
23.81
0.0
4.76
0.089
chocolate chip cookie
1859
N11110015907
usda-ndb-import
Chipmates, Chunky Chocolate Chip Cookies, Pean...
Kroger
kroger
26 g (26 g)
1933.0
26.92
0.000
57.69
26.92
0.0
7.69
0.288
cookies peanut butter
1865
N11110016195
usda-ndb-import
Crunchy Peanut Butter
Kroger
kroger
32 g (2 Tbsp)
2351.0
46.88
0.000
28.12
12.50
6.2
21.88
0.469
crunchy peanut butter
1867
N11110016508
usda-ndb-import
Crunchy Peanut Butter
Kroger
kroger
32 g (2 Tbsp)
2485.0
50.00
0.000
21.88
3.12
9.4
25.00
0.391
crunchy peanut butter
1889
N11110017734
usda-ndb-import
Ice Cream Sandwiches
Kroger
kroger
74 g (1 SANDWICH)
1188.0
10.81
0.027
41.89
21.62
1.4
4.05
0.203
ice cream sandwiches
1910
N11110018649
usda-ndb-import
P$$T..., Sandwich Cookies, Peanut Butter
P$$T...
p-t
33 g (33 g)
2029.0
18.18
0.000
72.73
33.33
3.0
6.06
0.303
cookies peanut butter
1927
N11110019073
usda-ndb-import
Crunchy Peanut Butter
Fred Meyer
fred-meyer
32 g (2 Tbsp)
2485.0
50.00
0.000
21.88
3.12
9.4
25.00
0.391
crunchy peanut butter
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
293542
N7411000500347
usda-ndb-import
Refried Black Beans
San Francisco
san-francisco
113 g (4 oz)
854.0
9.73
0.000
17.70
0.88
7.1
7.96
0.412
refried black beans
293560
N74164300819
usda-ndb-import
Premium Ice Cream
Lowes Foods
lowes-foods
67 g (0.5 cup)
874.0
10.45
0.045
26.87
23.88
0.0
2.99
0.075
premium ice cream
293561
N74164300820
usda-ndb-import
Premium Ice Cream
Lowes Foods
lowes-foods
67 g (0.5 cup)
874.0
10.45
0.037
28.36
25.37
0.0
2.99
0.075
premium ice cream
293575
N74164303635
usda-ndb-import
Traditional Pasta Sauce
Lowes Foods
lowes-foods
127 g (0.5 cup)
230.0
0.79
0.000
9.45
4.72
2.4
1.57
0.386
traditional pasta sauce
293817
N7501088109980
usda-ndb-import
Pico De Gallo Seasoning Mix
Terana
terana
0.5 g (0.25 tsp)
0.0
0.00
NaN
0.00
NaN
NaN
0.00
0.000
pico de gallo
294045
N760712090012
usda-ndb-import
Boylan Bottling Co, Cane Sugar Soda, Root Beer
Grip Inc.
grip-inc
355 ml (1 BOTTLE)
201.0
0.00
0.000
11.83
11.83
0.0
0.00
0.010
soda root beer
313056
N8018759000198
usda-ndb-import
Tomato Sauce With Basil
Laselva
laselva
124 g (0.5 cup)
117.0
0.00
0.000
4.84
3.23
1.6
0.81
0.016
tomato sauce with
314068
N8056457280368
usda-ndb-import
Niasca Portofino, Tomato Sauce With Basil
Niasca Portofino S.R.L.
niasca-portofino-s-r-l
61 g (0.25 cup)
96.0
0.00
0.000
2.95
2.95
2.1
1.31
0.020
tomato sauce with
314147
N806800
usda-ndb-import
Chunk White Albacore Tuna In Water
Starkist Selects
starkist-selects
56 g (2 oz)
448.0
0.89
0.045
0.00
NaN
0.0
25.00
0.062
chunk white albacore
315418
N8410111005573
usda-ndb-import
Pasta Salad With Chunk Light Tuna
Isabel
isabel
85 g (3 oz)
887.0
15.29
0.028
10.59
2.35
1.2
8.24
0.388
chunk light tuna
315419
N8410111005580
usda-ndb-import
Isabel, Vegetable Medley With Chunk Light Tuna
Isabela North America Inc
isabela-north-america-inc
85 g (3 oz)
402.0
4.71
0.020
7.06
4.71
2.4
4.71
0.329
chunk light tuna
315421
N8410111005627
usda-ndb-import
Pasta Salad With Chunk Light Tuna
Isabel
isabel
85 g (3 oz)
887.0
15.29
0.028
10.59
2.35
1.2
8.24
0.388
chunk light tuna
315426
N8410111006785
usda-ndb-import
Solid White Albacore Tuna In Olive Oil
Isabel
isabel
76 g (1 CAN DRAINED)
824.0
10.53
0.032
0.00
0.00
0.0
27.63
0.553
albacore tuna in
315432
N8410111633301
usda-ndb-import
Sardines In Tomato Sauce
Isabel
isabel
56 g (2 ONZ)
649.0
8.93
0.080
1.79
1.79
0.0
16.07
0.500
sardines in tomato
315437
N8410111903800
usda-ndb-import
Vegetable Medley With Chunk Light Tuna
Isabel
isabel
85 g (3 ONZ)
402.0
4.71
0.020
0.00
4.71
2.4
4.71
0.329
chunk light tuna
318211
N8426920635009
usda-ndb-import
Sardines In Tomato Sauce
Isabel
isabel
80 g (0.5 PIECE)
649.0
8.75
0.056
2.50
2.50
0.0
16.25
0.350
sardines in tomato
321354
N84873700722
usda-ndb-import
Organic Thousand Island Dressing
Wild Oats
wild-oats
30 ml (2 Tbsp)
975.0
20.00
0.033
10.00
6.67
3.3
6.67
0.733
thousand island dressing
321466
N853186066119
usda-ndb-import
Steel Cut Meals, Steel Cut Oats For Dinner, Ch...
Grainful
grainful
283 g (283 g)
490.0
6.01
0.012
10.25
0.35
1.8
4.95
0.170
steel cut oats
321834
N8595645935654
usda-ndb-import
Caffeine Free Soda, Apple
Sidral Mundet
sidral-mundet
240 ml (8 fl oz)
159.0
0.00
NaN
10.42
10.00
NaN
0.00
0.038
caffeine free soda
325687
N876958618376
usda-ndb-import
Organic Steel Cut Oats
Whole Foods Market
whole-foods-market
45 g (0.33 cup)
1582.0
6.67
0.000
68.89
2.22
8.9
13.33
0.000
steel cut oats
326816
N88670009963
usda-ndb-import
French Fried Potatoes
Wellsley Farms
wellsley-farms
85 g (18 PIECES | ABOUT)
540.0
4.12
0.000
22.35
0.00
2.4
2.35
0.053
french fried potatoes
326993
N890180001984
usda-ndb-import
Organic Baby Food, Just Prunes
Plum Organics
plum-organics
99 g (99 g)
255.0
0.00
NaN
15.15
13.13
1.0
1.01
0.005
organic baby food
327082
N89107100498
usda-ndb-import
Authentic French Brioche Hot Dog Buns
Euro Classics
euro-classics
45 g (1 HOT DOG)
1322.0
6.67
0.056
51.11
11.11
2.2
8.89
0.467
hot dog buns
328879
N9305033434565
usda-ndb-import
Simply 100, Non Fat Greek Yogurt, Pineapple Co...
Chobani
chobani
150 g (150 g)
280.0
0.00
0.005
10.00
4.67
3.3
8.00
0.040
fat greek yogurt
329871
N9348603001811
usda-ndb-import
Greek Nonfat Yogurt
Welch's
welch-s
150 g (1 CONTAINER)
305.0
0.00
0.003
10.00
8.67
0.0
8.67
0.030
greek nonfat yogurt
329872
N9348603001828
usda-ndb-import
Greek Nonfat Yogurt
Welch's
welch-s
150 g (1 CONTAINER)
305.0
0.00
0.003
10.00
8.67
0.0
8.67
0.030
greek nonfat yogurt
329873
N9348603001842
usda-ndb-import
Greek Nonfat Yogurt
Welch's
welch-s
150 g (1 CONTAINER)
335.0
0.00
0.003
11.33
10.67
0.0
8.67
0.030
greek nonfat yogurt
329874
N9348603001859
usda-ndb-import
Greek Nonfat Yogurt With Fruit On The Bottom
Welch's
welch-s
150 g (1 CONTAINER)
305.0
0.00
0.003
10.00
9.33
0.0
8.67
0.030
greek nonfat yogurt
329875
N9348603001866
usda-ndb-import
Greek Nonfat Yogurt
Welch's
welch-s
150 g (1 CONTAINER)
305.0
0.00
0.003
10.00
9.33
0.0
8.67
0.030
greek nonfat yogurt
330251
N9556041602211
usda-ndb-import
Baked Beans In Tomato Sauce
Ayam
ayam
130 g (4.6 oz)
418.0
0.77
0.000
19.23
7.69
3.8
3.85
0.300
beans in tomato
8647 rows × 15 columns
Some categories have very little variation in them. Going to check for that and drop them.
In [86]:
# loop over each trigram
enough_variance = []
for trigram in tri_w.word:
fat_var = df[df.demo_cat == trigram]["fat_100g"].var()
if fat_var > 2:
enough_variance.append(trigram)
print(enough_variance)
print(len(enough_variance))
['premium ice cream', 'cooked potato chips', 'cream cheese spread', 'frosted sugar cookies', 'chunk light tuna', 'roasted turkey breast', 'chocolate chip cookie', 'hot dog buns', 'ice cream sandwiches', 'cookies chocolate chip', 'ice cream bars', 'crunchy peanut butter', 'pancake waffle mix', 'chewy granola bars', 'dry roasted peanuts', 'dairy frozen dessert', 'thin crust pizza', 'macaroni cheese dinner', 'vegetable oil spread', 'chili with beans', 'chicken noodle soup', 'peanut butter cups', 'albacore tuna in', 'dark chocolate bar', 'potato chips original', 'honey roasted peanuts', 'roasted salted almonds', 'ramen noodle soup', 'fat greek yogurt', 'whole grain bread', 'smoked turkey breast', 'marinara pasta sauce', 'wavy potato chips', 'dark chocolate almonds', 'peanut butter cup', 'high protein bar', 'french fried potatoes', 'organic pasta sauce', 'sardines in tomato', 'italian style meatballs', 'fruit nut bar', 'thousand island dressing', 'baked snack crackers', 'cookies peanut butter', 'chips salt vinegar', 'mushroom condensed soup', 'refried black beans', 'steel cut oats', 'chocolate ice cream', 'whipped cream cheese', 'oatmeal raisin cookies', 'salsa con queso', 'popcorn white cheddar', 'chicken condensed soup', 'greek style yogurt', 'red velvet cake', 'potato chips cheddar', 'salad with chicken', 'cinnamon rolls with', 'red pepper hummus', 'white corn tortilla', 'corn puff cereal', 'sweet potato chips', 'style potato chips', 'classic potato chips', 'ice cream sandwich', 'pico de gallo', 'chunk white albacore', 'chicken breast nuggets', 'chocolate covered pretzels', 'corned beef hash', 'hot italian sausage', 'noodles with vegetables', 'soft baked cookies', 'sweet italian sausage', 'tomato sauce with', 'yellow corn tortilla', 'chicken gravy mix', 'chocolate chunk cookies', 'instant mashed potatoes', 'tomato basil soup', 'instant hot cereal']
82
Now got a category applied to a subset of the database. Can run the same code as before to use that category to create a subset of recommendations for each category picked...
In [87]:
# What we want to get variation on
pick_factors = ['fat_100g', 'sugars_100g', 'proteins_100g', 'sodium_100g']
# Points we want to pick (percentiles). Can tune this to get more or fewer picks.
pick_percentiles = [0.1, 0.5, 0.9]
# pick_percentiles = [0, 0.25, 0.5, 0.75, 1.0]
demo_picks = []
# loop over each trigram that has enough variance in it
for cat in enough_variance:
# first get all the items containing the cat word
catf = df[df["demo_cat"] == cat]
# Identify what rank each product is in that category, for each main factor
for p in pick_factors:
catf[p + "_rank"] = catf[p].rank(method = "first")
# Select products at chosen percentiles on each
high = catf[p + "_rank"].max()
pick_index = [max(1, round(n * high)) for n in pick_percentiles]
# add codes for those products
demo_picks.extend(catf[catf[p+"_rank"].isin(pick_index)].code)
demo_df = df[df.code.isin(demo_picks)]
demo_df
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:21: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
Out[87]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
417
N901000017
usda-ndb-import
Yellow Corn Tortilla Chips
Guiltless Gourmet
guiltless-gourmet
28 g (1 oz)
1795.0
10.71
0.000
78.57
0.00
7.1
7.14
0.643
yellow corn tortilla
1366
N98601
usda-ndb-import
Chicken Noodle Soup
Trader Joe's
trader-joe-s
248 g (1 cup)
151.0
0.40
0.008
5.65
0.40
0.4
2.42
0.294
chicken noodle soup
2267
N11110197900
usda-ndb-import
Triple Layer Red Velvet Cake, Peppermint
Bakery Fresh Goodness, The Kroger Co.
bakery-fresh-goodness,the-kroger-co
85 g (1 SLICE)
1971.0
17.65
0.024
77.65
65.88
0.0
1.18
0.353
red velvet cake
2669
N11110577276
usda-ndb-import
Ice Cream Sandwich
The Kroger Co.
the-kroger-co
63 g (1 SANDWICH)
1130.0
9.52
0.032
44.44
20.63
1.6
4.76
0.238
ice cream sandwich
3172
N11110791559
usda-ndb-import
Crunchy Peanut Butter
Simple Truth Organic
simple-truth-organic
32 g (2 Tbsp)
2615.0
50.00
0.000
18.75
6.25
9.4
25.00
0.375
crunchy peanut butter
3187
N11110796486
usda-ndb-import
Kettle Cooked Potato Chips, Sea Salt & Cracked...
Kroger
kroger
28 g (1 oz)
2243.0
32.14
0.000
53.57
0.00
3.6
7.14
0.393
cooked potato chips
3427
N11110819376
usda-ndb-import
Dry Roasted Peanuts
Kroger
kroger
28 g (1 oz)
2389.0
46.43
0.000
21.43
3.57
7.1
21.43
0.607
dry roasted peanuts
3638
N11110836281
usda-ndb-import
53% Vegetable Oil Spread
P$$T... Big Savings... Pass It On
p-t-big-savings-pass-it-on
14 g (1 Tbsp)
2092.0
50.00
0.000
0.00
0.00
0.0
0.00
0.643
vegetable oil spread
3654
N11110837158
usda-ndb-import
98% Fat Free Cream Of Mushroom Condensed Soup
Kroger
kroger
125 g (0.5 cup)
268.0
2.00
0.004
8.80
1.60
0.0
1.60
0.640
mushroom condensed soup
3701
N11110839305
usda-ndb-import
Chili With Beans
Kroger
kroger
250 g (1 cup)
502.0
4.00
0.010
14.00
2.00
4.4
6.80
0.496
chili with beans
3705
N11110839510
usda-ndb-import
Corned Beef Hash
Kroger
kroger
236 g (1 cup)
707.0
10.17
0.030
8.90
0.42
0.8
9.32
0.390
corned beef hash
3926
N11110852748
usda-ndb-import
Instant Mashed Potatoes
Kroger
kroger
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
4151
N11110863997
usda-ndb-import
Cream Cheese Spread, Whipped Strawberry
Kroger, The Kroger Co.
kroger,the-kroger-co
22 g (2 Tbsp)
1331.0
22.73
0.068
18.18
13.64
0.0
4.55
0.227
cream cheese spread
4664
N11110888082
usda-ndb-import
Chunk Light Tuna In Oil
The Kroger Co.
the-kroger-co
56 g (2 OZ DRAINED)
523.0
4.46
0.045
0.00
0.00
0.0
19.64
0.321
chunk light tuna
5052
N11115224274
usda-ndb-import
Imperial, 30% Vegetable Oil Spread
Unilever
unilever
14 g (1 Tbsp)
1197.0
28.57
NaN
0.00
NaN
NaN
0.00
0.643
vegetable oil spread
5061
N11115621240
usda-ndb-import
Promise, Buttery, 60% Vegetable Oil Spread
Unilever
unilever
14 g (1 Tbsp)
2389.0
57.14
0.000
0.00
NaN
NaN
0.00
0.607
vegetable oil spread
5113
N11150001298
usda-ndb-import
Chunk White Albacore Tuna In Water
Roundy's
roundy-s
56 g (0.25 cup)
523.0
0.89
0.045
0.00
0.00
0.0
25.00
0.464
chunk white albacore
5252
N11150040419
usda-ndb-import
Organic Yellow Corn Tortilla Chips
Simply Roundy's
simply-roundy-s
28 g (1 oz)
2092.0
25.00
0.000
57.14
0.00
7.1
7.14
0.571
yellow corn tortilla
5271
N11150041430
usda-ndb-import
Potato Chips, Cheddar & Sour Cream
Roundy's
roundy-s
57 g (1 PACKAGE)
2201.0
31.58
0.000
54.39
1.75
3.5
7.02
0.596
potato chips cheddar
5500
N11150100205
usda-ndb-import
Cream Of Chicken Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
268.0
2.00
0.004
9.60
0.80
0.8
1.60
0.640
chicken condensed soup
5504
N11150100304
usda-ndb-import
Cream Of Mushroom Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
234.0
2.00
0.008
7.20
0.00
1.6
2.40
0.360
mushroom condensed soup
5732
N11150183482
usda-ndb-import
Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
5733
N11150183499
usda-ndb-import
Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
6111
N11150538008
usda-ndb-import
Hot Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
4.29
4.29
0.0
20.00
1.043
hot italian sausage
6113
N11150538022
usda-ndb-import
Sweet Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
2.86
2.86
0.0
20.00
0.871
sweet italian sausage
6164
N11150550086
usda-ndb-import
Curly French Fried Potatoes
Roundy's
roundy-s
85 g (3 ONZ)
787.0
9.41
0.000
24.71
0.00
2.4
2.35
0.435
french fried potatoes
6247
N11150589147
usda-ndb-import
Ice Cream Bars, Orange
Roundy's
roundy-s
54 g (54 g)
699.0
5.56
0.019
27.78
18.52
0.0
1.85
0.065
ice cream bars
6254
N11150590037
usda-ndb-import
Ice Cream Bars
Roundy's
roundy-s
77 g (77 g)
1795.0
29.87
0.026
36.36
31.17
2.6
3.90
0.117
ice cream bars
6928
N11161030577
usda-ndb-import
Baked Snack Crackers
Shurfine, Topco Associates Inc.
shurfine,topco-associates-inc
30 g (40 CRACKERS)
1674.0
15.00
0.000
56.67
3.33
0.0
6.67
0.733
baked snack crackers
6934
N11161031352
usda-ndb-import
Classic Potato Chips
Shurfine
shurfine
28 g (17 CHIPS)
2389.0
35.71
0.000
57.14
0.00
3.6
7.14
0.643
classic potato chips
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
169098
N869955000011
usda-ndb-import
Chicken Noodle Soup
Daily Bread
daily-bread
53 g (1 CUP PREPARED) | (MAKES)
1577.0
3.77
0.028
66.04
1.89
1.9
18.87
1.717
chicken noodle soup
169233
N872181000069
usda-ndb-import
Milk Chocolate Covered Pretzels
Flipz
flipz
28 g (1 oz)
1941.0
17.86
0.000
71.43
39.29
3.6
7.14
0.500
chocolate covered pretzels
169598
N875343000099
usda-ndb-import
Cream Cheese Spread With Garden Vegetables
Einstein Noah Restaurant Group Inc.
einstein-noah-restaurant-group-inc
20 g (2 Tbsp)
1255.0
25.00
0.075
15.00
5.00
0.0
5.00
0.500
cream cheese spread
169611
N875386000667
usda-ndb-import
Dairy-Free Greek Style Yogurt, Raspberry
Tempt
tempt
150 g (1 CONTAINER)
364.0
2.67
0.000
10.00
6.00
2.0
5.33
0.017
greek style yogurt
169800
N876314002340
usda-ndb-import
Tomato & Basil Soup With Fresh Calabrian Basil
Zuppa Rustica
zuppa-rustica
245 g (1 cup)
255.0
1.84
0.000
9.80
4.49
2.4
1.63
0.216
tomato basil soup
170020
N877245006056
usda-ndb-import
Dutch Valley Food Distributors, Dark Chocolate...
Dutch Valley Food Distributors Inc.
dutch-valley-food-distributors-inc
40 g (40 GRM)
2301.0
37.50
NaN
50.00
37.50
NaN
10.00
0.000
dark chocolate almonds
170688
N883967381319
usda-ndb-import
Creme Sandwich Cookies, Peanut Butter
Smart Sense
smart-sense
25 g (25 g)
2176.0
24.00
0.000
64.00
20.00
4.0
8.00
0.340
cookies peanut butter
170750
N883967392087
usda-ndb-import
Macaroni & Cheese Dinner
Smart Sense
smart-sense
58 g (1 PKG)
1586.0
6.03
0.000
70.69
8.62
1.7
10.34
0.810
macaroni cheese dinner
171181
N886002506517
usda-ndb-import
Milk Chocolate Chip Soft Baked Cookies
Mrs. Fields
mrs-fields
28 g (1 oz)
1941.0
17.86
0.036
67.86
39.29
3.6
3.57
0.411
soft baked cookies
171313
N886926014211
usda-ndb-import
Bistro Style, Bistro Style Spicy Thai-Style Ch...
Meijer
meijer
245 g (1 cup)
172.0
0.41
0.006
6.12
0.00
0.4
2.86
0.282
chicken noodle soup
171447
N886926296648
usda-ndb-import
Kettle Cooked Crinkle Cut Potato Chips, Chedda...
Meijer
meijer
28 g (1 oz)
2092.0
28.57
0.000
60.71
7.14
3.6
7.14
0.679
potato chips cheddar
171854
N888670019573
usda-ndb-import
Albacore Tuna In Water
Wellsley Farms
wellsley-farms
56 g (0.25 CUP | ABOUT)
448.0
0.00
0.045
0.00
0.00
0.0
23.21
0.250
albacore tuna in
171915
N888670025505
usda-ndb-import
Italian Style Meatballs
Wellsley Farms, Bj's Wholesale Club / Corpora...
wellsley-farms,bj-s-wholesale-club-corporate-b...
88 g (5 MEATBALLS)
1142.0
19.32
0.040
6.82
2.27
1.1
17.05
0.545
italian style meatballs
171946
N888670029633
usda-ndb-import
Organic Thin Crust Pizza
Wellsley Farms
wellsley-farms
112 g (0.33 PIZZA)
971.0
8.04
0.022
27.68
0.89
1.8
10.71
0.455
thin crust pizza
172760
N891991007082
usda-ndb-import
Waffle Lady, Organic Gingerbread Pancake & Waf...
Waffle Lady Inc.
waffle-lady-inc
46 g (8 THICK BELGIAN STYLE WAFFLES | PANCAKES...
1456.0
0.00
0.000
80.43
26.09
2.2
6.52
0.696
pancake waffle mix
173109
N893913001840
usda-ndb-import
Leaf Cuisine, Not Cream Cheese Spread, Classic...
Rod Rotondi Enterprises Llc
rod-rotondi-enterprises-llc
28 g (1 ONZ)
895.0
16.07
0.000
14.29
3.57
3.6
7.14
0.500
cream cheese spread
173808
N896767001219
usda-ndb-import
Larry's, Coconut Bliss, Organic Non-Dairy Froz...
Luna, Luna & Larry's
luna,luna-larry-s
95 g (0.5 cup)
1059.0
17.89
0.000
21.05
13.68
2.1
4.21
0.042
dairy frozen dessert
173854
N896859000588
usda-ndb-import
Organic Non Dairy Thousand Island Dressing
Organic Ville, Sky Valley Foods Inc.
organic-ville,sky-valley-foods-inc
30 ml (2 Tbsp)
1393.0
33.33
0.000
13.33
10.00
0.0
0.00
0.467
thousand island dressing
174070
N897552001469
usda-ndb-import
Chicken Gravy Mix
Full Flavor Foods
full-flavor-foods
6 g (1 Tbsp)
1745.0
0.00
0.000
100.00
16.67
0.0
16.67
4.500
chicken gravy mix
174431
N898575001368
usda-ndb-import
Sea Salt & Nibs Dark Chocolate Bar
Madecasse
madecasse
75 g (2.64 oz)
1226.0
20.00
0.000
24.00
18.67
1.3
4.00
0.020
dark chocolate bar
174839
N939662096321
usda-ndb-import
Bowl Noodles, Ramen Noodle Soup With Shrimp Co...
Nissin, Nissin Foods (Usa) Co. Inc.
nissin,nissin-foods-usa-co-inc
46 g (46 g)
1912.0
19.57
0.011
60.87
6.52
4.3
10.87
1.913
ramen noodle soup
177933
N20032319
usda-ndb-import
Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
170 g (6 ONZ)
343.0
0.00
0.000
11.76
10.59
0.0
8.24
0.041
fat greek yogurt
270315
N4178900121
usda-ndb-import
Instant Lunch, Ramen Noodles With Vegetables, ...
Maruchan, Maruchan Inc.
maruchan,maruchan-inc
64 g (1 CONTAINER, PER CONTAINER)
1895.0
18.75
0.000
60.94
3.12
3.1
10.94
1.859
noodles with vegetables
280147
N5051379022655
usda-ndb-import
Ice Cream Sandwiches
Fresh & Easy
fresh-easy
60 g (1 SANDWICH)
1117.0
8.33
0.025
41.67
21.67
1.7
5.00
0.167
ice cream sandwiches
280344
N5051379079499
usda-ndb-import
Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
150 g (1 CONTAINER)
335.0
0.00
0.003
12.00
10.00
0.0
8.00
0.033
fat greek yogurt
290879
N60788003540
usda-ndb-import
Ultra Thin Crust Pizza
Southern Home
southern-home
140 g (0.333 PIZZA)
808.0
8.57
0.021
20.71
2.14
0.7
8.57
0.364
thin crust pizza
290956
N6078802558
usda-ndb-import
Chunk Light Tuna In Water
Southern Home
southern-home
56 g (0.25 CUP | DRAINED, ANOUT)
372.0
0.89
0.036
0.00
0.00
0.0
19.64
0.321
chunk light tuna
292097
N68826717758
usda-ndb-import
Twisted Chocolate Jumbo Cinnamon Rolls With Icing
Ahold
ahold
99 g (1 ROLL WITH ICING)
1310.0
10.10
0.000
50.51
21.21
2.0
5.05
0.677
cinnamon rolls with
292898
N725493300360
usda-ndb-import
Thousand Island Dressing
Cha Ching
cha-ching
30 ml (2 Tbsp)
1117.0
20.00
0.017
20.00
16.67
0.0
0.00
1.000
thousand island dressing
293817
N7501088109980
usda-ndb-import
Pico De Gallo Seasoning Mix
Terana
terana
0.5 g (0.25 tsp)
0.0
0.00
NaN
0.00
NaN
NaN
0.00
0.000
pico de gallo
906 rows × 15 columns
In [88]:
demo_df[demo_df.demo_cat == "pasta enriched macaroni"]
Out[88]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
In [89]:
df[df.demo_cat == "pasta enriched macaroni"]
Out[89]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
3846
N11110849168
usda-ndb-import
Pot-Ready Angel Hair Half Length Pasta, Enrich...
Kroger
kroger
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5688
N11150175951
usda-ndb-import
No Boil Lasagna Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5691
N11150175999
usda-ndb-import
Orzo Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5693
N11150176040
usda-ndb-import
Spaghetti Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5694
N11150176095
usda-ndb-import
Thin Spaghetti Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5695
N11150176125
usda-ndb-import
Mostaccioli Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5696
N11150176132
usda-ndb-import
Angel Hair Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5697
N11150176156
usda-ndb-import
Medium Shells Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5698
N11150176163
usda-ndb-import
Penne Rigate Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5699
N11150176170
usda-ndb-import
Farfalle Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5700
N11150176422
usda-ndb-import
Fettuccine Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5701
N11150176460
usda-ndb-import
Rigatoni Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
5705
N11150178006
usda-ndb-import
Lasagna Pasta, Enriched Macaroni Product
Roundy's
roundy-s
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
7159
N11161150787
usda-ndb-import
Fettuccine Pasta, Enriched Macaroni Product
Shurfine
shurfine
56 g (45 PIECES)
1494.0
0.89
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
10564
N12700000150
usda-ndb-import
Skinner, Texas Shape Pasta, Enriched Macaroni ...
New World Pasta Company
new-world-pasta-company
56 g (0.75 cup)
1494.0
1.79
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
18374
N21130506286
usda-ndb-import
Kitchens, Angel Hair Pasta, Enriched Macaroni ...
Signature
signature
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
22940
N26800002464
usda-ndb-import
Large Elbows Pasta, Enriched Macaroni Product
American Beauty, New World Pasta Company
american-beauty,new-world-pasta-company
56 g (0.667 CUP)
1494.0
1.79
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
22951
N26800006363
usda-ndb-import
Mostaccioli Pasta, Enriched Macaroni Product
American Beauty, New World Pasta Company
american-beauty,new-world-pasta-company
56 g (0.667 CUP)
1494.0
1.79
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
22953
N26800006387
usda-ndb-import
Angel Hair Pasta, Enriched Macaroni Product
American Beauty
american-beauty
56 g (0.125 OF PACKAGE)
1569.0
1.79
0.0
75.00
3.57
3.6
12.50
0.000
pasta enriched macaroni
25809
N30034091415
usda-ndb-import
Gemelli Pasta, Enriched Macaroni Product
Giant Eagle Inc.
giant-eagle-inc
56 g (2 ONZ)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
30361
N35826041104
usda-ndb-import
Ziti Pasta, Enriched Macaroni Product
Food Lion
food-lion
56 g (0.666 cup)
1569.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
30671
N35826079442
usda-ndb-import
Classic Angel Hair Pasta, Enriched Macaroni Pr...
Food Lion
food-lion
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
38958
N41190035717
usda-ndb-import
Angel Hair No. 11 Pasta, Enriched Macaroni Pro...
Shoprite
shoprite
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
39237
N41190048472
usda-ndb-import
Pennoni Italian Pasta, Enriched Macaroni Product
Shoprite
shoprite
56 g (0.75 cup)
1569.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
48339
N41486001242
usda-ndb-import
Luigi Vitelli, Rotini Pasta, Enriched Macaroni...
Vitelli Foods Llc
vitelli-foods-llc
55 g (0.75 cup)
1490.0
1.82
0.0
72.73
3.09
2.9
11.82
0.000
pasta enriched macaroni
49867
N41497279944
usda-ndb-import
Classic Pasta, Enriched Macaroni Product
Weis Quality
weis-quality
56 g (0.75 " CIRCLE)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
49868
N41497279951
usda-ndb-import
Farfalle Classic Pasta, Enriched Macaroni Product
Weis Quality
weis-quality
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
49870
N41497279975
usda-ndb-import
Classic Spaghetti Pasta, Enriched Macaroni Pro...
Weis Quality
weis-quality
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
49878
N41497280056
usda-ndb-import
Classic Rigatoni Pasta, Enriched Macaroni Product
Weis Quality
weis-quality
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
49886
N41497280148
usda-ndb-import
Classic Linguine Pasta, Enriched Macaroni Product
Weis Quality
weis-quality
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
70074
N70253469916
usda-ndb-import
Fusilli Pasta, Enriched Macaroni Product
Our Family
our-family
56 g (0.75 CUP)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
73134
N70796330506
usda-ndb-import
Shells #50 Pasta, Enriched Macaroni Product
Anna
anna
56 g (2 oz)
1494.0
1.79
0.0
73.21
1.79
3.6
12.50
0.000
pasta enriched macaroni
73138
N70796330810
usda-ndb-import
Elbows Pasta, Enriched Macaroni Product
Anna
anna
56 g (2 oz)
1494.0
1.79
0.0
73.21
1.79
3.6
12.50
0.000
pasta enriched macaroni
75942
N71403033087
usda-ndb-import
Linguine Fine #8 Pasta, Enriched Macaroni Product
Ferrara
ferrara
56 g (2 oz)
1569.0
1.79
0.0
73.21
5.36
3.6
NaN
0.000
pasta enriched macaroni
80542
N72368510538
usda-ndb-import
Penne Rigate No. 36 Pasta, Enriched Macaroni P...
Delallo, George Delallo Co. Inc.
delallo,george-delallo-co-inc
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
80554
N72368512006
usda-ndb-import
Pasta, Enriched Macaroni Product
Delallo
delallo
56 g (2 oz)
1644.0
1.79
0.0
78.57
3.57
3.6
12.50
0.000
pasta enriched macaroni
80555
N72368512044
usda-ndb-import
La Famiglia Rigatoni #21 Pasta, Enriched Macar...
Delallo
delallo
56 g (0.75 cup)
1644.0
1.79
0.0
78.57
3.57
3.6
12.50
0.000
pasta enriched macaroni
80557
N72368512181
usda-ndb-import
Elbows #68 Family Pasta, Enriched Macaroni Pro...
Delallo
delallo
56 g (0.75 cup)
1644.0
1.79
0.0
78.57
3.57
3.6
12.50
0.000
pasta enriched macaroni
84041
N73324000780
usda-ndb-import
Pasta, Enriched Macaroni Product
Baresi
baresi
56 g (2 oz)
1494.0
1.79
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
92544
N76808006223
usda-ndb-import
Penne Pasta, Enriched Macaroni Product
Barilla G & R F.Lli S.P.A.
barilla-g-r-f-lli-s-p-a
56 g (0.125 BOX | ABOUT)
1494.0
1.79
0.0
75.00
3.57
3.6
12.50
0.000
pasta enriched macaroni
92548
N76808006469
usda-ndb-import
Thin Spaghetti Pasta, Enriched Macaroni Product
Barilla
barilla
56 g (0.125 BOX) | (ABOUT)
1494.0
1.79
0.0
75.00
3.57
3.6
12.50
0.000
pasta enriched macaroni
92552
N76808006513
usda-ndb-import
Angel Hair Pasta, Enriched Macaroni Product
Barilla G & R F.Lli S.P.A.
barilla-g-r-f-lli-s-p-a
56 g (2 ONZ)
1343.0
2.68
0.0
69.64
3.57
10.7
14.29
0.000
pasta enriched macaroni
92556
N76808006568
usda-ndb-import
Organic Penne Pasta, Enriched Macaroni Product
Barilla G & R F.Lli S.P.A.
barilla-g-r-f-lli-s-p-a
56 g (0.125 BOX | ABOUT)
1494.0
1.79
0.0
75.00
3.57
3.6
12.50
0.000
pasta enriched macaroni
92567
N76808034295
usda-ndb-import
Linguine Pasta, Enriched Macaroni Product
Barilla, Barilla G & R F.Lli S.P.A.
barilla,barilla-g-r-f-lli-s-p-a
56 g (0.125 BOX | ABOUT)
1494.0
1.79
0.0
75.00
3.57
3.6
12.50
0.000
pasta enriched macaroni
94550
N77890233894
usda-ndb-import
Elbows Pasta, Enriched Macaroni Product
Wegmans
wegmans
56 g (0.5 cup)
1569.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
94553
N77890234037
usda-ndb-import
Spaghetti Pasta, Enriched Macaroni Product
Wegmans
wegmans
56 g (0.125 BOX)
1569.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
94554
N77890234044
usda-ndb-import
Thin Spaghetti Pasta, Enriched Macaroni Product
Wegmans
wegmans
56 g (0.125 BOX DRY)
1569.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
94922
N77890362792
usda-ndb-import
Half-Sized Thin Spaghetti Pasta, Enriched Maca...
Wegmans
wegmans
56 g (0.125 BOX DRY | ABOUT)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
94983
N77890365595
usda-ndb-import
Spaghetti Pasta, Enriched Macaroni Product
Wegmans
wegmans
56 g (0.03 OF PKG)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
96800
N78742036991
usda-ndb-import
Pot-Sized Angel Hair Pasta, Enriched Macaroni ...
Great Value
great-value
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
97814
N78742085845
usda-ndb-import
Fettuccine Pasta, Enriched Macaroni Product
Great Value
great-value
56 g (2 oz)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
102479
N85164444174
usda-ndb-import
Penne Ziti Rigate Pasta, Enriched Macaroni Pro...
Garofalo
garofalo
56 g (0.66 cup)
1569.0
1.79
0.0
78.57
3.57
3.6
12.50
0.000
pasta enriched macaroni
104153
N85239381861
usda-ndb-import
Manicotti Pasta, Enriched Macaroni Product
Market Pantry, Target Stores
market-pantry,target-stores
56 g (0.25 PKG.) DRY | ()
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
104158
N85239382806
usda-ndb-import
Ziti Pasta, Enriched Macaroni Product
Market Pantry, Target Stores
market-pantry,target-stores
56 g (0.666 cup)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
104162
N85239382912
usda-ndb-import
Vegetable Rotini Pasta, Enriched Macaroni Product
Market Pantry, Target Stores
market-pantry,target-stores
56 g (0.75 cup)
1494.0
1.79
0.0
71.43
3.57
5.4
12.50
0.062
pasta enriched macaroni
104168
N85239385869
usda-ndb-import
Small Shells Pasta, Enriched Macaroni Product
Market Pantry, Target Stores
market-pantry,target-stores
56 g (0.5 cup)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
111564
N01121307483
usda-ndb-import
Mostaccioli Pasta, Enriched Macaroni Product
Spartan
spartan
56 g (0.75 CUP DRY)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
113838
N021333400547
usda-ndb-import
Thin Spaghetti Pasta, Enriched Macaroni Product
Fareway
fareway
56 g (0.5 " CIRDE)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
142181
N75450134488
usda-ndb-import
Pot Sized Linguine Pasta, Enriched Macaroni Pr...
Hy-Vee
hy-vee
56 g (1.5 CIRCLE)
1494.0
1.79
0.0
73.21
3.57
3.6
12.50
0.000
pasta enriched macaroni
175137
N1041498152628
usda-ndb-import
Elbow Macaroni Pasta, Enriched Macaroni Product
Reggano
reggano
56 g (0.5 cup)
1494.0
1.79
0.0
75.00
1.79
3.6
12.50
0.000
pasta enriched macaroni
70 rows × 15 columns
Now need to try some processing on product name as many will be too similar and uninformative without brand name.
In [90]:
def truncate_brand(s):
if type(s) != str:
return ""
elif s.find(",") == -1:
return s
else:
return s[:s.find(",")]
print(truncate_brand("Kroger, The Kroger Co."))
print(truncate_brand("Roundy's"))
Kroger
Roundy's
In [91]:
demo_df.dtypes
Out[91]:
code object
creator object
product_name object
brands object
brands_tags object
serving_size object
energy_100g float64
fat_100g float64
cholesterol_100g float64
carbohydrates_100g float64
sugars_100g float64
fiber_100g float64
proteins_100g float64
sodium_100g float64
demo_cat object
dtype: object
In [92]:
demo_df["short_brand"] = demo_df.brands.apply(truncate_brand)
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
if __name__ == '__main__':
In [93]:
demo_df
Out[93]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
short_brand
417
N901000017
usda-ndb-import
Yellow Corn Tortilla Chips
Guiltless Gourmet
guiltless-gourmet
28 g (1 oz)
1795.0
10.71
0.000
78.57
0.00
7.1
7.14
0.643
yellow corn tortilla
Guiltless Gourmet
1366
N98601
usda-ndb-import
Chicken Noodle Soup
Trader Joe's
trader-joe-s
248 g (1 cup)
151.0
0.40
0.008
5.65
0.40
0.4
2.42
0.294
chicken noodle soup
Trader Joe's
2267
N11110197900
usda-ndb-import
Triple Layer Red Velvet Cake, Peppermint
Bakery Fresh Goodness, The Kroger Co.
bakery-fresh-goodness,the-kroger-co
85 g (1 SLICE)
1971.0
17.65
0.024
77.65
65.88
0.0
1.18
0.353
red velvet cake
Bakery Fresh Goodness
2669
N11110577276
usda-ndb-import
Ice Cream Sandwich
The Kroger Co.
the-kroger-co
63 g (1 SANDWICH)
1130.0
9.52
0.032
44.44
20.63
1.6
4.76
0.238
ice cream sandwich
The Kroger Co.
3172
N11110791559
usda-ndb-import
Crunchy Peanut Butter
Simple Truth Organic
simple-truth-organic
32 g (2 Tbsp)
2615.0
50.00
0.000
18.75
6.25
9.4
25.00
0.375
crunchy peanut butter
Simple Truth Organic
3187
N11110796486
usda-ndb-import
Kettle Cooked Potato Chips, Sea Salt & Cracked...
Kroger
kroger
28 g (1 oz)
2243.0
32.14
0.000
53.57
0.00
3.6
7.14
0.393
cooked potato chips
Kroger
3427
N11110819376
usda-ndb-import
Dry Roasted Peanuts
Kroger
kroger
28 g (1 oz)
2389.0
46.43
0.000
21.43
3.57
7.1
21.43
0.607
dry roasted peanuts
Kroger
3638
N11110836281
usda-ndb-import
53% Vegetable Oil Spread
P$$T... Big Savings... Pass It On
p-t-big-savings-pass-it-on
14 g (1 Tbsp)
2092.0
50.00
0.000
0.00
0.00
0.0
0.00
0.643
vegetable oil spread
P$$T... Big Savings... Pass It On
3654
N11110837158
usda-ndb-import
98% Fat Free Cream Of Mushroom Condensed Soup
Kroger
kroger
125 g (0.5 cup)
268.0
2.00
0.004
8.80
1.60
0.0
1.60
0.640
mushroom condensed soup
Kroger
3701
N11110839305
usda-ndb-import
Chili With Beans
Kroger
kroger
250 g (1 cup)
502.0
4.00
0.010
14.00
2.00
4.4
6.80
0.496
chili with beans
Kroger
3705
N11110839510
usda-ndb-import
Corned Beef Hash
Kroger
kroger
236 g (1 cup)
707.0
10.17
0.030
8.90
0.42
0.8
9.32
0.390
corned beef hash
Kroger
3926
N11110852748
usda-ndb-import
Instant Mashed Potatoes
Kroger
kroger
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
Kroger
4151
N11110863997
usda-ndb-import
Cream Cheese Spread, Whipped Strawberry
Kroger, The Kroger Co.
kroger,the-kroger-co
22 g (2 Tbsp)
1331.0
22.73
0.068
18.18
13.64
0.0
4.55
0.227
cream cheese spread
Kroger
4664
N11110888082
usda-ndb-import
Chunk Light Tuna In Oil
The Kroger Co.
the-kroger-co
56 g (2 OZ DRAINED)
523.0
4.46
0.045
0.00
0.00
0.0
19.64
0.321
chunk light tuna
The Kroger Co.
5052
N11115224274
usda-ndb-import
Imperial, 30% Vegetable Oil Spread
Unilever
unilever
14 g (1 Tbsp)
1197.0
28.57
NaN
0.00
NaN
NaN
0.00
0.643
vegetable oil spread
Unilever
5061
N11115621240
usda-ndb-import
Promise, Buttery, 60% Vegetable Oil Spread
Unilever
unilever
14 g (1 Tbsp)
2389.0
57.14
0.000
0.00
NaN
NaN
0.00
0.607
vegetable oil spread
Unilever
5113
N11150001298
usda-ndb-import
Chunk White Albacore Tuna In Water
Roundy's
roundy-s
56 g (0.25 cup)
523.0
0.89
0.045
0.00
0.00
0.0
25.00
0.464
chunk white albacore
Roundy's
5252
N11150040419
usda-ndb-import
Organic Yellow Corn Tortilla Chips
Simply Roundy's
simply-roundy-s
28 g (1 oz)
2092.0
25.00
0.000
57.14
0.00
7.1
7.14
0.571
yellow corn tortilla
Simply Roundy's
5271
N11150041430
usda-ndb-import
Potato Chips, Cheddar & Sour Cream
Roundy's
roundy-s
57 g (1 PACKAGE)
2201.0
31.58
0.000
54.39
1.75
3.5
7.02
0.596
potato chips cheddar
Roundy's
5500
N11150100205
usda-ndb-import
Cream Of Chicken Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
268.0
2.00
0.004
9.60
0.80
0.8
1.60
0.640
chicken condensed soup
Roundy's
5504
N11150100304
usda-ndb-import
Cream Of Mushroom Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
234.0
2.00
0.008
7.20
0.00
1.6
2.40
0.360
mushroom condensed soup
Roundy's
5732
N11150183482
usda-ndb-import
Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
Roundy's
5733
N11150183499
usda-ndb-import
Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
Roundy's
6111
N11150538008
usda-ndb-import
Hot Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
4.29
4.29
0.0
20.00
1.043
hot italian sausage
Roundy's
6113
N11150538022
usda-ndb-import
Sweet Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
2.86
2.86
0.0
20.00
0.871
sweet italian sausage
Roundy's
6164
N11150550086
usda-ndb-import
Curly French Fried Potatoes
Roundy's
roundy-s
85 g (3 ONZ)
787.0
9.41
0.000
24.71
0.00
2.4
2.35
0.435
french fried potatoes
Roundy's
6247
N11150589147
usda-ndb-import
Ice Cream Bars, Orange
Roundy's
roundy-s
54 g (54 g)
699.0
5.56
0.019
27.78
18.52
0.0
1.85
0.065
ice cream bars
Roundy's
6254
N11150590037
usda-ndb-import
Ice Cream Bars
Roundy's
roundy-s
77 g (77 g)
1795.0
29.87
0.026
36.36
31.17
2.6
3.90
0.117
ice cream bars
Roundy's
6928
N11161030577
usda-ndb-import
Baked Snack Crackers
Shurfine, Topco Associates Inc.
shurfine,topco-associates-inc
30 g (40 CRACKERS)
1674.0
15.00
0.000
56.67
3.33
0.0
6.67
0.733
baked snack crackers
Shurfine
6934
N11161031352
usda-ndb-import
Classic Potato Chips
Shurfine
shurfine
28 g (17 CHIPS)
2389.0
35.71
0.000
57.14
0.00
3.6
7.14
0.643
classic potato chips
Shurfine
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
169098
N869955000011
usda-ndb-import
Chicken Noodle Soup
Daily Bread
daily-bread
53 g (1 CUP PREPARED) | (MAKES)
1577.0
3.77
0.028
66.04
1.89
1.9
18.87
1.717
chicken noodle soup
Daily Bread
169233
N872181000069
usda-ndb-import
Milk Chocolate Covered Pretzels
Flipz
flipz
28 g (1 oz)
1941.0
17.86
0.000
71.43
39.29
3.6
7.14
0.500
chocolate covered pretzels
Flipz
169598
N875343000099
usda-ndb-import
Cream Cheese Spread With Garden Vegetables
Einstein Noah Restaurant Group Inc.
einstein-noah-restaurant-group-inc
20 g (2 Tbsp)
1255.0
25.00
0.075
15.00
5.00
0.0
5.00
0.500
cream cheese spread
Einstein Noah Restaurant Group Inc.
169611
N875386000667
usda-ndb-import
Dairy-Free Greek Style Yogurt, Raspberry
Tempt
tempt
150 g (1 CONTAINER)
364.0
2.67
0.000
10.00
6.00
2.0
5.33
0.017
greek style yogurt
Tempt
169800
N876314002340
usda-ndb-import
Tomato & Basil Soup With Fresh Calabrian Basil
Zuppa Rustica
zuppa-rustica
245 g (1 cup)
255.0
1.84
0.000
9.80
4.49
2.4
1.63
0.216
tomato basil soup
Zuppa Rustica
170020
N877245006056
usda-ndb-import
Dutch Valley Food Distributors, Dark Chocolate...
Dutch Valley Food Distributors Inc.
dutch-valley-food-distributors-inc
40 g (40 GRM)
2301.0
37.50
NaN
50.00
37.50
NaN
10.00
0.000
dark chocolate almonds
Dutch Valley Food Distributors Inc.
170688
N883967381319
usda-ndb-import
Creme Sandwich Cookies, Peanut Butter
Smart Sense
smart-sense
25 g (25 g)
2176.0
24.00
0.000
64.00
20.00
4.0
8.00
0.340
cookies peanut butter
Smart Sense
170750
N883967392087
usda-ndb-import
Macaroni & Cheese Dinner
Smart Sense
smart-sense
58 g (1 PKG)
1586.0
6.03
0.000
70.69
8.62
1.7
10.34
0.810
macaroni cheese dinner
Smart Sense
171181
N886002506517
usda-ndb-import
Milk Chocolate Chip Soft Baked Cookies
Mrs. Fields
mrs-fields
28 g (1 oz)
1941.0
17.86
0.036
67.86
39.29
3.6
3.57
0.411
soft baked cookies
Mrs. Fields
171313
N886926014211
usda-ndb-import
Bistro Style, Bistro Style Spicy Thai-Style Ch...
Meijer
meijer
245 g (1 cup)
172.0
0.41
0.006
6.12
0.00
0.4
2.86
0.282
chicken noodle soup
Meijer
171447
N886926296648
usda-ndb-import
Kettle Cooked Crinkle Cut Potato Chips, Chedda...
Meijer
meijer
28 g (1 oz)
2092.0
28.57
0.000
60.71
7.14
3.6
7.14
0.679
potato chips cheddar
Meijer
171854
N888670019573
usda-ndb-import
Albacore Tuna In Water
Wellsley Farms
wellsley-farms
56 g (0.25 CUP | ABOUT)
448.0
0.00
0.045
0.00
0.00
0.0
23.21
0.250
albacore tuna in
Wellsley Farms
171915
N888670025505
usda-ndb-import
Italian Style Meatballs
Wellsley Farms, Bj's Wholesale Club / Corpora...
wellsley-farms,bj-s-wholesale-club-corporate-b...
88 g (5 MEATBALLS)
1142.0
19.32
0.040
6.82
2.27
1.1
17.05
0.545
italian style meatballs
Wellsley Farms
171946
N888670029633
usda-ndb-import
Organic Thin Crust Pizza
Wellsley Farms
wellsley-farms
112 g (0.33 PIZZA)
971.0
8.04
0.022
27.68
0.89
1.8
10.71
0.455
thin crust pizza
Wellsley Farms
172760
N891991007082
usda-ndb-import
Waffle Lady, Organic Gingerbread Pancake & Waf...
Waffle Lady Inc.
waffle-lady-inc
46 g (8 THICK BELGIAN STYLE WAFFLES | PANCAKES...
1456.0
0.00
0.000
80.43
26.09
2.2
6.52
0.696
pancake waffle mix
Waffle Lady Inc.
173109
N893913001840
usda-ndb-import
Leaf Cuisine, Not Cream Cheese Spread, Classic...
Rod Rotondi Enterprises Llc
rod-rotondi-enterprises-llc
28 g (1 ONZ)
895.0
16.07
0.000
14.29
3.57
3.6
7.14
0.500
cream cheese spread
Rod Rotondi Enterprises Llc
173808
N896767001219
usda-ndb-import
Larry's, Coconut Bliss, Organic Non-Dairy Froz...
Luna, Luna & Larry's
luna,luna-larry-s
95 g (0.5 cup)
1059.0
17.89
0.000
21.05
13.68
2.1
4.21
0.042
dairy frozen dessert
Luna
173854
N896859000588
usda-ndb-import
Organic Non Dairy Thousand Island Dressing
Organic Ville, Sky Valley Foods Inc.
organic-ville,sky-valley-foods-inc
30 ml (2 Tbsp)
1393.0
33.33
0.000
13.33
10.00
0.0
0.00
0.467
thousand island dressing
Organic Ville
174070
N897552001469
usda-ndb-import
Chicken Gravy Mix
Full Flavor Foods
full-flavor-foods
6 g (1 Tbsp)
1745.0
0.00
0.000
100.00
16.67
0.0
16.67
4.500
chicken gravy mix
Full Flavor Foods
174431
N898575001368
usda-ndb-import
Sea Salt & Nibs Dark Chocolate Bar
Madecasse
madecasse
75 g (2.64 oz)
1226.0
20.00
0.000
24.00
18.67
1.3
4.00
0.020
dark chocolate bar
Madecasse
174839
N939662096321
usda-ndb-import
Bowl Noodles, Ramen Noodle Soup With Shrimp Co...
Nissin, Nissin Foods (Usa) Co. Inc.
nissin,nissin-foods-usa-co-inc
46 g (46 g)
1912.0
19.57
0.011
60.87
6.52
4.3
10.87
1.913
ramen noodle soup
Nissin
177933
N20032319
usda-ndb-import
Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
170 g (6 ONZ)
343.0
0.00
0.000
11.76
10.59
0.0
8.24
0.041
fat greek yogurt
Fresh & Easy
270315
N4178900121
usda-ndb-import
Instant Lunch, Ramen Noodles With Vegetables, ...
Maruchan, Maruchan Inc.
maruchan,maruchan-inc
64 g (1 CONTAINER, PER CONTAINER)
1895.0
18.75
0.000
60.94
3.12
3.1
10.94
1.859
noodles with vegetables
Maruchan
280147
N5051379022655
usda-ndb-import
Ice Cream Sandwiches
Fresh & Easy
fresh-easy
60 g (1 SANDWICH)
1117.0
8.33
0.025
41.67
21.67
1.7
5.00
0.167
ice cream sandwiches
Fresh & Easy
280344
N5051379079499
usda-ndb-import
Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
150 g (1 CONTAINER)
335.0
0.00
0.003
12.00
10.00
0.0
8.00
0.033
fat greek yogurt
Fresh & Easy
290879
N60788003540
usda-ndb-import
Ultra Thin Crust Pizza
Southern Home
southern-home
140 g (0.333 PIZZA)
808.0
8.57
0.021
20.71
2.14
0.7
8.57
0.364
thin crust pizza
Southern Home
290956
N6078802558
usda-ndb-import
Chunk Light Tuna In Water
Southern Home
southern-home
56 g (0.25 CUP | DRAINED, ANOUT)
372.0
0.89
0.036
0.00
0.00
0.0
19.64
0.321
chunk light tuna
Southern Home
292097
N68826717758
usda-ndb-import
Twisted Chocolate Jumbo Cinnamon Rolls With Icing
Ahold
ahold
99 g (1 ROLL WITH ICING)
1310.0
10.10
0.000
50.51
21.21
2.0
5.05
0.677
cinnamon rolls with
Ahold
292898
N725493300360
usda-ndb-import
Thousand Island Dressing
Cha Ching
cha-ching
30 ml (2 Tbsp)
1117.0
20.00
0.017
20.00
16.67
0.0
0.00
1.000
thousand island dressing
Cha Ching
293817
N7501088109980
usda-ndb-import
Pico De Gallo Seasoning Mix
Terana
terana
0.5 g (0.25 tsp)
0.0
0.00
NaN
0.00
NaN
NaN
0.00
0.000
pico de gallo
Terana
906 rows × 16 columns
Now going to save original product name and replace with a combination of that plus the brand
In [94]:
demo_df["orig_product_name"] = demo_df.product_name
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
if __name__ == '__main__':
In [95]:
demo_df["new_product_name"] = demo_df.short_brand + " " + demo_df.product_name
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
if __name__ == '__main__':
In [96]:
demo_df.product_name = demo_df.new_product_name
/Users/seddont/anaconda/lib/python3.5/site-packages/pandas/core/generic.py:2773: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
self[name] = value
Need to add blanks for the other columns which only exist in the hand-curated demo data.
In [97]:
demo_df["hos"] = 0
demo_df["image_url"] = None
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:1: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
if __name__ == '__main__':
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:2: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
from ipykernel import kernelapp as app
Now want to append the original demo data products and their hall of shame status so we always have them in too.
In [98]:
orig_demo = pd.read_csv(data_dir+"demo_food_data_latest.csv")
In [99]:
# Specify what columns we need to keep to match the regular dataframe above.
wanted_cols = ['code', 'creator', 'hos', 'image_url', 'product_name', 'brands', 'brands_tags', 'serving_size',
'serving_size', 'energy_100g', 'fat_100g', 'cholesterol_100g',
'carbohydrates_100g', 'sugars_100g', 'fiber_100g', 'proteins_100g', 'sodium_100g',
'demo_cat']
# Create a list of columns to drop to check it worked ok
drop_cols = [c for c in orig_demo.columns if c not in wanted_cols]
print(drop_cols)
['generic_name', 'quantity', 'categories', 'categories_tags', 'starch_100g', 'salt_100g', 'alcohol_100g', 'folates_100g', 'bicarbonate_100g', 'potassium_100g', 'chloride_100g', 'calcium_100g', 'iron_100g', 'fluoride_100g', 'iodine_100g', 'caffeine_100g', 'cocoa_100g']
In [100]:
# Drop unwanted columns in orig demo
orig_demo.drop(drop_cols, axis = 1, inplace = True)
orig_demo
Out[100]:
code
creator
hos
product_name
image_url
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
0
N713733903387
usda-ndb-import
1
Low Sodium Applause Crackers
https://static.meijer.com/Media/007/13733/0071...
Meijer
meijer
16 g (16 g)
2092
28.12
0.000
62.50
6.25
0.0
6.25
0.188
cracker
1
N876274001858
usda-ndb-import
0
Snack Time, Stack Pack Salted Crackers
NaN
Global
global
28 g (28 g)
2092
21.43
0.000
71.43
7.14
0.0
7.14
0.304
cracker
2
N888109050023
usda-ndb-import
1
Donettes, Mini Donuts, Frosted
https://s-media-cache-ak0.pinimg.com/originals...
Hostess
hostess
85 g (3 oz)
2017
30.59
0.012
48.24
30.59
1.2
3.53
0.306
donut
3
N72030015712
usda-ndb-import
0
Frosted Donuts
http://www.shugarysweets.com/wp-content/upload...
Entenmann's
entenmann-s
48 g (48 g)
2004
31.25
0.021
47.92
27.08
2.1
4.17
0.375
donut
4
N24300806247
usda-ndb-import
1
Mini Donuts
http://bitemefoods.com.au/wp-content/uploads/2...
Little Debbie, Mckee Foods Corporation
little-debbie,mckee-foods-corporation
122 g (8 DONUTS)
1987
27.05
0.020
55.74
30.33
1.6
4.10
0.418
donut
5
N72030021645
usda-ndb-import
0
Pop'Ettes Powdered Donuts
https://jpg.seasonskosher.com/content/images/t...
Entenmann's, Bimbo Bakeries Usa Inc.
entenmann-s,bimbo-bakeries-usa-inc
57 g (57 g)
1983
28.07
0.026
52.63
26.32
1.8
3.51
0.368
donut
6
N11150146098
usda-ndb-import
1
Kids Graham Crackers, Chocolate
http://www.candywarehouse.com/assets/item/regu...
Roundy's
roundy-s
30 g (19 COOKIES)
1954
15.00
0.000
73.33
23.33
3.3
6.67
0.417
cracker
7
N76606720956
usda-ndb-import
0
Savory Snack Cracker, Celery & Onion
http://www.baldersonvillagecheese.com/gourmet-...
Medford Farms
medford-farms
15 g (15 g)
1954
26.67
0.000
60.00
0.00
0.0
6.67
1.000
cracker
8
N76265185905
usda-ndb-import
0
Plain Cake Mini Donuts
http://www.fridaycakenight.com/wp-content/uplo...
Maple Donuts Inc
maple-donuts-inc
45 g (2 DONUTS)
1858
28.89
0.011
40.00
11.11
2.2
2.22
0.511
donut
9
N41224710146
usda-ndb-import
0
Roland Water Crackers
http://www.rolandfood.com/i/product_images/l/0...
Roland
roland
16 g (16 g)
1833
6.25
0.000
75.00
0.00
6.2
6.25
0.750
cracker
10
N78742129082
usda-ndb-import
0
Baked Buttery Crackers, Naturally Flavored
NaN
Great Value, Wal-Mart Stores Inc.
great-value,wal-mart-stores-inc
16 g (5 CRACKERS)
1833
25.00
0.000
50.00
6.25
0.0
6.25
0.656
cracker
11
N11110008817
usda-ndb-import
0
Maple Glazed Cake Donuts
NaN
Kroger, The Kroger Co.
kroger,the-kroger-co
71 g (1 DONUT)
1828
19.72
0.000
59.15
35.21
1.4
4.23
0.451
donut
12
N708820381599
usda-ndb-import
0
Woven Wheats, Baked Whole Wheat Crackers, Rose...
NaN
Meijer
meijer
28 g (28 g)
1795
14.29
0.000
71.43
3.57
10.7
7.14
0.536
cracker
13
N888109111298
usda-ndb-import
0
Red Velvet Mini Donuts
NaN
Hostess
hostess
53 g (3 DONUTS)
1736
20.75
0.009
52.83
30.19
1.9
3.77
0.255
donut
14
N42400109754
usda-ndb-import
0
Cocoa Dyno-Bites, Sweetened Rice Cereal With R...
http://media.fooducate.com/products/images/180...
Mom Brands
mom-brands
29 g (0.75 cup)
1732
3.45
0.000
89.66
44.83
0.0
3.45
0.517
cereal
15
N51933150546
usda-ndb-import
0
Sweetened Puffed Wheat Cereal, Honey
NaN
Kiggins
kiggins
27 g (0.75 cup)
1703
0.00
0.000
88.89
55.56
0.0
7.41
0.241
cereal
16
N35826097101
usda-ndb-import
0
Sweet & Crispy Graham Crackers
NaN
Food Lion, Food Town Stores Inc.
food-lion,food-town-stores-inc
35 g (2 FULL CRACKER SHEETS)
1674
5.71
0.000
80.00
22.86
5.7
5.71
0.514
cracker
17
N42400060024
usda-ndb-import
0
Naturally & Artificially Flavored Sweetened Co...
NaN
Chocolatey Colossal Crunch
chocolatey-colossal-crunch
30 g (0.75 cup)
1674
5.00
0.000
86.67
43.33
3.3
3.33
0.667
cereal
18
N42400236245
usda-ndb-import
0
Berry Bunch Crunch, Sweetened Corn & Oat Cereal
https://www.postconsumerbrands.com/wp-content/...
Mom Brands
mom-brands
30 g (0.75 cup)
1674
3.33
0.000
86.67
46.67
3.3
3.33
0.467
cereal
19
N42400240815
usda-ndb-import
0
Honey Graham Cereal
https://s-media-cache-ak0.pinimg.com/736x/63/e...
Honey Graham Toasters
honey-graham-toasters
30 g (0.75 cup)
1674
10.00
0.000
76.67
33.33
3.3
6.67
0.867
cereal
20
N980125260001
usda-ndb-import
0
Quinoa Hot Cereal Flakes
NaN
Ancient Harvest
ancient-harvest
34 g (0.33 cup)
1611
5.88
0.000
67.65
5.88
7.1
12.65
0.006
cereal
21
N7750106000048
usda-ndb-import
0
San Jorge Water Crackers
NaN
Panaderia San Jorge S.A.
panaderia-san-jorge-s-a
30 g (30 GRM)
1602
3.33
0.000
76.67
3.33
NaN
13.33
0.600
cracker
22
N11153041949
usda-ndb-import
1
Crunchy Oat Squares With Cinnamon Cereal
https://www.dlmdriveup.com/img/CentralOrdering...
Foodtown, Foodtown Inc.
foodtown,foodtown-inc
32 g (0.75 cup)
1569
3.12
0.000
81.25
25.00
6.2
9.38
0.422
cereal
23
N21130281022
usda-ndb-import
0
Corn Flakes Cereal
NaN
Safeway Kitchens, Safeway Inc.
safeway-kitchens,safeway-inc
28 g (1 cup)
1494
0.00
0.000
85.71
7.14
3.6
7.14
0.571
cereal
24
N76185003815
usda-ndb-import
0
Variety Pack Donut Holes
NaN
Arnie's
arnie-s
71 g (71 g)
1473
16.90
0.028
43.66
18.31
1.4
5.63
0.493
donut
25
N5051379078669
usda-ndb-import
0
Baked Donuts
NaN
Fresh & Easy
fresh-easy
57 g (1 DONUT)
1469
14.04
0.070
56.14
36.84
0.0
7.02
0.140
donut
26
N58449620020
usda-ndb-import
0
Eco Pac, Cereal, Millet Puffs
NaN
Nature's Path
nature-s-path
16 g (1 cup)
1305
0.00
0.000
87.50
0.00
6.2
12.50
0.000
cereal
In [101]:
# Drop unwanted columns in demo_df
# Create a list of columns to drop to check it worked ok
drop_cols = [c for c in demo_df.columns if c not in wanted_cols]
print(drop_cols)
demo_df.drop(drop_cols, axis = 1, inplace = True)
demo_df
['short_brand', 'orig_product_name', 'new_product_name']
/Users/seddont/anaconda/lib/python3.5/site-packages/ipykernel/__main__.py:5: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
Out[101]:
code
creator
product_name
brands
brands_tags
serving_size
energy_100g
fat_100g
cholesterol_100g
carbohydrates_100g
sugars_100g
fiber_100g
proteins_100g
sodium_100g
demo_cat
hos
image_url
417
N901000017
usda-ndb-import
Guiltless Gourmet Yellow Corn Tortilla Chips
Guiltless Gourmet
guiltless-gourmet
28 g (1 oz)
1795.0
10.71
0.000
78.57
0.00
7.1
7.14
0.643
yellow corn tortilla
0
None
1366
N98601
usda-ndb-import
Trader Joe's Chicken Noodle Soup
Trader Joe's
trader-joe-s
248 g (1 cup)
151.0
0.40
0.008
5.65
0.40
0.4
2.42
0.294
chicken noodle soup
0
None
2267
N11110197900
usda-ndb-import
Bakery Fresh Goodness Triple Layer Red Velvet ...
Bakery Fresh Goodness, The Kroger Co.
bakery-fresh-goodness,the-kroger-co
85 g (1 SLICE)
1971.0
17.65
0.024
77.65
65.88
0.0
1.18
0.353
red velvet cake
0
None
2669
N11110577276
usda-ndb-import
The Kroger Co. Ice Cream Sandwich
The Kroger Co.
the-kroger-co
63 g (1 SANDWICH)
1130.0
9.52
0.032
44.44
20.63
1.6
4.76
0.238
ice cream sandwich
0
None
3172
N11110791559
usda-ndb-import
Simple Truth Organic Crunchy Peanut Butter
Simple Truth Organic
simple-truth-organic
32 g (2 Tbsp)
2615.0
50.00
0.000
18.75
6.25
9.4
25.00
0.375
crunchy peanut butter
0
None
3187
N11110796486
usda-ndb-import
Kroger Kettle Cooked Potato Chips, Sea Salt & ...
Kroger
kroger
28 g (1 oz)
2243.0
32.14
0.000
53.57
0.00
3.6
7.14
0.393
cooked potato chips
0
None
3427
N11110819376
usda-ndb-import
Kroger Dry Roasted Peanuts
Kroger
kroger
28 g (1 oz)
2389.0
46.43
0.000
21.43
3.57
7.1
21.43
0.607
dry roasted peanuts
0
None
3638
N11110836281
usda-ndb-import
P$$T... Big Savings... Pass It On 53% Vegetabl...
P$$T... Big Savings... Pass It On
p-t-big-savings-pass-it-on
14 g (1 Tbsp)
2092.0
50.00
0.000
0.00
0.00
0.0
0.00
0.643
vegetable oil spread
0
None
3654
N11110837158
usda-ndb-import
Kroger 98% Fat Free Cream Of Mushroom Condense...
Kroger
kroger
125 g (0.5 cup)
268.0
2.00
0.004
8.80
1.60
0.0
1.60
0.640
mushroom condensed soup
0
None
3701
N11110839305
usda-ndb-import
Kroger Chili With Beans
Kroger
kroger
250 g (1 cup)
502.0
4.00
0.010
14.00
2.00
4.4
6.80
0.496
chili with beans
0
None
3705
N11110839510
usda-ndb-import
Kroger Corned Beef Hash
Kroger
kroger
236 g (1 cup)
707.0
10.17
0.030
8.90
0.42
0.8
9.32
0.390
corned beef hash
0
None
3926
N11110852748
usda-ndb-import
Kroger Instant Mashed Potatoes
Kroger
kroger
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
0
None
4151
N11110863997
usda-ndb-import
Kroger Cream Cheese Spread, Whipped Strawberry
Kroger, The Kroger Co.
kroger,the-kroger-co
22 g (2 Tbsp)
1331.0
22.73
0.068
18.18
13.64
0.0
4.55
0.227
cream cheese spread
0
None
4664
N11110888082
usda-ndb-import
The Kroger Co. Chunk Light Tuna In Oil
The Kroger Co.
the-kroger-co
56 g (2 OZ DRAINED)
523.0
4.46
0.045
0.00
0.00
0.0
19.64
0.321
chunk light tuna
0
None
5052
N11115224274
usda-ndb-import
Unilever Imperial, 30% Vegetable Oil Spread
Unilever
unilever
14 g (1 Tbsp)
1197.0
28.57
NaN
0.00
NaN
NaN
0.00
0.643
vegetable oil spread
0
None
5061
N11115621240
usda-ndb-import
Unilever Promise, Buttery, 60% Vegetable Oil S...
Unilever
unilever
14 g (1 Tbsp)
2389.0
57.14
0.000
0.00
NaN
NaN
0.00
0.607
vegetable oil spread
0
None
5113
N11150001298
usda-ndb-import
Roundy's Chunk White Albacore Tuna In Water
Roundy's
roundy-s
56 g (0.25 cup)
523.0
0.89
0.045
0.00
0.00
0.0
25.00
0.464
chunk white albacore
0
None
5252
N11150040419
usda-ndb-import
Simply Roundy's Organic Yellow Corn Tortilla C...
Simply Roundy's
simply-roundy-s
28 g (1 oz)
2092.0
25.00
0.000
57.14
0.00
7.1
7.14
0.571
yellow corn tortilla
0
None
5271
N11150041430
usda-ndb-import
Roundy's Potato Chips, Cheddar & Sour Cream
Roundy's
roundy-s
57 g (1 PACKAGE)
2201.0
31.58
0.000
54.39
1.75
3.5
7.02
0.596
potato chips cheddar
0
None
5500
N11150100205
usda-ndb-import
Roundy's Cream Of Chicken Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
268.0
2.00
0.004
9.60
0.80
0.8
1.60
0.640
chicken condensed soup
0
None
5504
N11150100304
usda-ndb-import
Roundy's Cream Of Mushroom Condensed Soup
Roundy's
roundy-s
125 g (0.5 cup)
234.0
2.00
0.008
7.20
0.00
1.6
2.40
0.360
mushroom condensed soup
0
None
5732
N11150183482
usda-ndb-import
Roundy's Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
0
None
5733
N11150183499
usda-ndb-import
Roundy's Instant Mashed Potatoes
Roundy's
roundy-s
19 g (0.33 cup)
1540.0
0.00
0.000
78.95
0.00
5.3
10.53
0.079
instant mashed potatoes
0
None
6111
N11150538008
usda-ndb-import
Roundy's Hot Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
4.29
4.29
0.0
20.00
1.043
hot italian sausage
0
None
6113
N11150538022
usda-ndb-import
Roundy's Sweet Italian Sausage
Roundy's
roundy-s
70 g (1 GRILLED LINK)
1377.0
25.71
0.086
2.86
2.86
0.0
20.00
0.871
sweet italian sausage
0
None
6164
N11150550086
usda-ndb-import
Roundy's Curly French Fried Potatoes
Roundy's
roundy-s
85 g (3 ONZ)
787.0
9.41
0.000
24.71
0.00
2.4
2.35
0.435
french fried potatoes
0
None
6247
N11150589147
usda-ndb-import
Roundy's Ice Cream Bars, Orange
Roundy's
roundy-s
54 g (54 g)
699.0
5.56
0.019
27.78
18.52
0.0
1.85
0.065
ice cream bars
0
None
6254
N11150590037
usda-ndb-import
Roundy's Ice Cream Bars
Roundy's
roundy-s
77 g (77 g)
1795.0
29.87
0.026
36.36
31.17
2.6
3.90
0.117
ice cream bars
0
None
6928
N11161030577
usda-ndb-import
Shurfine Baked Snack Crackers
Shurfine, Topco Associates Inc.
shurfine,topco-associates-inc
30 g (40 CRACKERS)
1674.0
15.00
0.000
56.67
3.33
0.0
6.67
0.733
baked snack crackers
0
None
6934
N11161031352
usda-ndb-import
Shurfine Classic Potato Chips
Shurfine
shurfine
28 g (17 CHIPS)
2389.0
35.71
0.000
57.14
0.00
3.6
7.14
0.643
classic potato chips
0
None
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
169098
N869955000011
usda-ndb-import
Daily Bread Chicken Noodle Soup
Daily Bread
daily-bread
53 g (1 CUP PREPARED) | (MAKES)
1577.0
3.77
0.028
66.04
1.89
1.9
18.87
1.717
chicken noodle soup
0
None
169233
N872181000069
usda-ndb-import
Flipz Milk Chocolate Covered Pretzels
Flipz
flipz
28 g (1 oz)
1941.0
17.86
0.000
71.43
39.29
3.6
7.14
0.500
chocolate covered pretzels
0
None
169598
N875343000099
usda-ndb-import
Einstein Noah Restaurant Group Inc. Cream Che...
Einstein Noah Restaurant Group Inc.
einstein-noah-restaurant-group-inc
20 g (2 Tbsp)
1255.0
25.00
0.075
15.00
5.00
0.0
5.00
0.500
cream cheese spread
0
None
169611
N875386000667
usda-ndb-import
Tempt Dairy-Free Greek Style Yogurt, Raspberry
Tempt
tempt
150 g (1 CONTAINER)
364.0
2.67
0.000
10.00
6.00
2.0
5.33
0.017
greek style yogurt
0
None
169800
N876314002340
usda-ndb-import
Zuppa Rustica Tomato & Basil Soup With Fresh C...
Zuppa Rustica
zuppa-rustica
245 g (1 cup)
255.0
1.84
0.000
9.80
4.49
2.4
1.63
0.216
tomato basil soup
0
None
170020
N877245006056
usda-ndb-import
Dutch Valley Food Distributors Inc. Dutch Val...
Dutch Valley Food Distributors Inc.
dutch-valley-food-distributors-inc
40 g (40 GRM)
2301.0
37.50
NaN
50.00
37.50
NaN
10.00
0.000
dark chocolate almonds
0
None
170688
N883967381319
usda-ndb-import
Smart Sense Creme Sandwich Cookies, Peanut Butter
Smart Sense
smart-sense
25 g (25 g)
2176.0
24.00
0.000
64.00
20.00
4.0
8.00
0.340
cookies peanut butter
0
None
170750
N883967392087
usda-ndb-import
Smart Sense Macaroni & Cheese Dinner
Smart Sense
smart-sense
58 g (1 PKG)
1586.0
6.03
0.000
70.69
8.62
1.7
10.34
0.810
macaroni cheese dinner
0
None
171181
N886002506517
usda-ndb-import
Mrs. Fields Milk Chocolate Chip Soft Baked Coo...
Mrs. Fields
mrs-fields
28 g (1 oz)
1941.0
17.86
0.036
67.86
39.29
3.6
3.57
0.411
soft baked cookies
0
None
171313
N886926014211
usda-ndb-import
Meijer Bistro Style, Bistro Style Spicy Thai-S...
Meijer
meijer
245 g (1 cup)
172.0
0.41
0.006
6.12
0.00
0.4
2.86
0.282
chicken noodle soup
0
None
171447
N886926296648
usda-ndb-import
Meijer Kettle Cooked Crinkle Cut Potato Chips,...
Meijer
meijer
28 g (1 oz)
2092.0
28.57
0.000
60.71
7.14
3.6
7.14
0.679
potato chips cheddar
0
None
171854
N888670019573
usda-ndb-import
Wellsley Farms Albacore Tuna In Water
Wellsley Farms
wellsley-farms
56 g (0.25 CUP | ABOUT)
448.0
0.00
0.045
0.00
0.00
0.0
23.21
0.250
albacore tuna in
0
None
171915
N888670025505
usda-ndb-import
Wellsley Farms Italian Style Meatballs
Wellsley Farms, Bj's Wholesale Club / Corpora...
wellsley-farms,bj-s-wholesale-club-corporate-b...
88 g (5 MEATBALLS)
1142.0
19.32
0.040
6.82
2.27
1.1
17.05
0.545
italian style meatballs
0
None
171946
N888670029633
usda-ndb-import
Wellsley Farms Organic Thin Crust Pizza
Wellsley Farms
wellsley-farms
112 g (0.33 PIZZA)
971.0
8.04
0.022
27.68
0.89
1.8
10.71
0.455
thin crust pizza
0
None
172760
N891991007082
usda-ndb-import
Waffle Lady Inc. Waffle Lady, Organic Gingerbr...
Waffle Lady Inc.
waffle-lady-inc
46 g (8 THICK BELGIAN STYLE WAFFLES | PANCAKES...
1456.0
0.00
0.000
80.43
26.09
2.2
6.52
0.696
pancake waffle mix
0
None
173109
N893913001840
usda-ndb-import
Rod Rotondi Enterprises Llc Leaf Cuisine, Not ...
Rod Rotondi Enterprises Llc
rod-rotondi-enterprises-llc
28 g (1 ONZ)
895.0
16.07
0.000
14.29
3.57
3.6
7.14
0.500
cream cheese spread
0
None
173808
N896767001219
usda-ndb-import
Luna Larry's, Coconut Bliss, Organic Non-Dairy...
Luna, Luna & Larry's
luna,luna-larry-s
95 g (0.5 cup)
1059.0
17.89
0.000
21.05
13.68
2.1
4.21
0.042
dairy frozen dessert
0
None
173854
N896859000588
usda-ndb-import
Organic Ville Organic Non Dairy Thousand Islan...
Organic Ville, Sky Valley Foods Inc.
organic-ville,sky-valley-foods-inc
30 ml (2 Tbsp)
1393.0
33.33
0.000
13.33
10.00
0.0
0.00
0.467
thousand island dressing
0
None
174070
N897552001469
usda-ndb-import
Full Flavor Foods Chicken Gravy Mix
Full Flavor Foods
full-flavor-foods
6 g (1 Tbsp)
1745.0
0.00
0.000
100.00
16.67
0.0
16.67
4.500
chicken gravy mix
0
None
174431
N898575001368
usda-ndb-import
Madecasse Sea Salt & Nibs Dark Chocolate Bar
Madecasse
madecasse
75 g (2.64 oz)
1226.0
20.00
0.000
24.00
18.67
1.3
4.00
0.020
dark chocolate bar
0
None
174839
N939662096321
usda-ndb-import
Nissin Bowl Noodles, Ramen Noodle Soup With Sh...
Nissin, Nissin Foods (Usa) Co. Inc.
nissin,nissin-foods-usa-co-inc
46 g (46 g)
1912.0
19.57
0.011
60.87
6.52
4.3
10.87
1.913
ramen noodle soup
0
None
177933
N20032319
usda-ndb-import
Fresh & Easy Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
170 g (6 ONZ)
343.0
0.00
0.000
11.76
10.59
0.0
8.24
0.041
fat greek yogurt
0
None
270315
N4178900121
usda-ndb-import
Maruchan Instant Lunch, Ramen Noodles With Veg...
Maruchan, Maruchan Inc.
maruchan,maruchan-inc
64 g (1 CONTAINER, PER CONTAINER)
1895.0
18.75
0.000
60.94
3.12
3.1
10.94
1.859
noodles with vegetables
0
None
280147
N5051379022655
usda-ndb-import
Fresh & Easy Ice Cream Sandwiches
Fresh & Easy
fresh-easy
60 g (1 SANDWICH)
1117.0
8.33
0.025
41.67
21.67
1.7
5.00
0.167
ice cream sandwiches
0
None
280344
N5051379079499
usda-ndb-import
Fresh & Easy Non Fat Greek Yogurt
Fresh & Easy
fresh-easy
150 g (1 CONTAINER)
335.0
0.00
0.003
12.00
10.00
0.0
8.00
0.033
fat greek yogurt
0
None
290879
N60788003540
usda-ndb-import
Southern Home Ultra Thin Crust Pizza
Southern Home
southern-home
140 g (0.333 PIZZA)
808.0
8.57
0.021
20.71
2.14
0.7
8.57
0.364
thin crust pizza
0
None
290956
N6078802558
usda-ndb-import
Southern Home Chunk Light Tuna In Water
Southern Home
southern-home
56 g (0.25 CUP | DRAINED, ANOUT)
372.0
0.89
0.036
0.00
0.00
0.0
19.64
0.321
chunk light tuna
0
None
292097
N68826717758
usda-ndb-import
Ahold Twisted Chocolate Jumbo Cinnamon Rolls W...
Ahold
ahold
99 g (1 ROLL WITH ICING)
1310.0
10.10
0.000
50.51
21.21
2.0
5.05
0.677
cinnamon rolls with
0
None
292898
N725493300360
usda-ndb-import
Cha Ching Thousand Island Dressing
Cha Ching
cha-ching
30 ml (2 Tbsp)
1117.0
20.00
0.017
20.00
16.67
0.0
0.00
1.000
thousand island dressing
0
None
293817
N7501088109980
usda-ndb-import
Terana Pico De Gallo Seasoning Mix
Terana
terana
0.5 g (0.25 tsp)
0.0
0.00
NaN
0.00
NaN
NaN
0.00
0.000
pico de gallo
0
None
906 rows × 17 columns
In [102]:
missing_cols = [col for col in demo_df.columns if col not in orig_demo.columns]
print("Missing columns", missing_cols)
Missing columns []
Now want to append the original demo data to the other data
In [103]:
finished = demo_df.append(orig_demo)
finished
Out[103]:
brands
brands_tags
carbohydrates_100g
cholesterol_100g
code
creator
demo_cat
energy_100g
fat_100g
fiber_100g
hos
image_url
product_name
proteins_100g
serving_size
sodium_100g
sugars_100g
417
Guiltless Gourmet
guiltless-gourmet
78.57
0.000
N901000017
usda-ndb-import
yellow corn tortilla
1795.0
10.71
7.1
0
None
Guiltless Gourmet Yellow Corn Tortilla Chips
7.14
28 g (1 oz)
0.643
0.00
1366
Trader Joe's
trader-joe-s
5.65
0.008
N98601
usda-ndb-import
chicken noodle soup
151.0
0.40
0.4
0
None
Trader Joe's Chicken Noodle Soup
2.42
248 g (1 cup)
0.294
0.40
2267
Bakery Fresh Goodness, The Kroger Co.
bakery-fresh-goodness,the-kroger-co
77.65
0.024
N11110197900
usda-ndb-import
red velvet cake
1971.0
17.65
0.0
0
None
Bakery Fresh Goodness Triple Layer Red Velvet ...
1.18
85 g (1 SLICE)
0.353
65.88
2669
The Kroger Co.
the-kroger-co
44.44
0.032
N11110577276
usda-ndb-import
ice cream sandwich
1130.0
9.52
1.6
0
None
The Kroger Co. Ice Cream Sandwich
4.76
63 g (1 SANDWICH)
0.238
20.63
3172
Simple Truth Organic
simple-truth-organic
18.75
0.000
N11110791559
usda-ndb-import
crunchy peanut butter
2615.0
50.00
9.4
0
None
Simple Truth Organic Crunchy Peanut Butter
25.00
32 g (2 Tbsp)
0.375
6.25
3187
Kroger
kroger
53.57
0.000
N11110796486
usda-ndb-import
cooked potato chips
2243.0
32.14
3.6
0
None
Kroger Kettle Cooked Potato Chips, Sea Salt & ...
7.14
28 g (1 oz)
0.393
0.00
3427
Kroger
kroger
21.43
0.000
N11110819376
usda-ndb-import
dry roasted peanuts
2389.0
46.43
7.1
0
None
Kroger Dry Roasted Peanuts
21.43
28 g (1 oz)
0.607
3.57
3638
P$$T... Big Savings... Pass It On
p-t-big-savings-pass-it-on
0.00
0.000
N11110836281
usda-ndb-import
vegetable oil spread
2092.0
50.00
0.0
0
None
P$$T... Big Savings... Pass It On 53% Vegetabl...
0.00
14 g (1 Tbsp)
0.643
0.00
3654
Kroger
kroger
8.80
0.004
N11110837158
usda-ndb-import
mushroom condensed soup
268.0
2.00
0.0
0
None
Kroger 98% Fat Free Cream Of Mushroom Condense...
1.60
125 g (0.5 cup)
0.640
1.60
3701
Kroger
kroger
14.00
0.010
N11110839305
usda-ndb-import
chili with beans
502.0
4.00
4.4
0
None
Kroger Chili With Beans
6.80
250 g (1 cup)
0.496
2.00
3705
Kroger
kroger
8.90
0.030
N11110839510
usda-ndb-import
corned beef hash
707.0
10.17
0.8
0
None
Kroger Corned Beef Hash
9.32
236 g (1 cup)
0.390
0.42
3926
Kroger
kroger
78.95
0.000
N11110852748
usda-ndb-import
instant mashed potatoes
1540.0
0.00
5.3
0
None
Kroger Instant Mashed Potatoes
10.53
19 g (0.33 cup)
0.079
0.00
4151
Kroger, The Kroger Co.
kroger,the-kroger-co
18.18
0.068
N11110863997
usda-ndb-import
cream cheese spread
1331.0
22.73
0.0
0
None
Kroger Cream Cheese Spread, Whipped Strawberry
4.55
22 g (2 Tbsp)
0.227
13.64
4664
The Kroger Co.
the-kroger-co
0.00
0.045
N11110888082
usda-ndb-import
chunk light tuna
523.0
4.46
0.0
0
None
The Kroger Co. Chunk Light Tuna In Oil
19.64
56 g (2 OZ DRAINED)
0.321
0.00
5052
Unilever
unilever
0.00
NaN
N11115224274
usda-ndb-import
vegetable oil spread
1197.0
28.57
NaN
0
None
Unilever Imperial, 30% Vegetable Oil Spread
0.00
14 g (1 Tbsp)
0.643
NaN
5061
Unilever
unilever
0.00
0.000
N11115621240
usda-ndb-import
vegetable oil spread
2389.0
57.14
NaN
0
None
Unilever Promise, Buttery, 60% Vegetable Oil S...
0.00
14 g (1 Tbsp)
0.607
NaN
5113
Roundy's
roundy-s
0.00
0.045
N11150001298
usda-ndb-import
chunk white albacore
523.0
0.89
0.0
0
None
Roundy's Chunk White Albacore Tuna In Water
25.00
56 g (0.25 cup)
0.464
0.00
5252
Simply Roundy's
simply-roundy-s
57.14
0.000
N11150040419
usda-ndb-import
yellow corn tortilla
2092.0
25.00
7.1
0
None
Simply Roundy's Organic Yellow Corn Tortilla C...
7.14
28 g (1 oz)
0.571
0.00
5271
Roundy's
roundy-s
54.39
0.000
N11150041430
usda-ndb-import
potato chips cheddar
2201.0
31.58
3.5
0
None
Roundy's Potato Chips, Cheddar & Sour Cream
7.02
57 g (1 PACKAGE)
0.596
1.75
5500
Roundy's
roundy-s
9.60
0.004
N11150100205
usda-ndb-import
chicken condensed soup
268.0
2.00
0.8
0
None
Roundy's Cream Of Chicken Condensed Soup
1.60
125 g (0.5 cup)
0.640
0.80
5504
Roundy's
roundy-s
7.20
0.008
N11150100304
usda-ndb-import
mushroom condensed soup
234.0
2.00
1.6
0
None
Roundy's Cream Of Mushroom Condensed Soup
2.40
125 g (0.5 cup)
0.360
0.00
5732
Roundy's
roundy-s
78.95
0.000
N11150183482
usda-ndb-import
instant mashed potatoes
1540.0
0.00
5.3
0
None
Roundy's Instant Mashed Potatoes
10.53
19 g (0.33 cup)
0.079
0.00
5733
Roundy's
roundy-s
78.95
0.000
N11150183499
usda-ndb-import
instant mashed potatoes
1540.0
0.00
5.3
0
None
Roundy's Instant Mashed Potatoes
10.53
19 g (0.33 cup)
0.079
0.00
6111
Roundy's
roundy-s
4.29
0.086
N11150538008
usda-ndb-import
hot italian sausage
1377.0
25.71
0.0
0
None
Roundy's Hot Italian Sausage
20.00
70 g (1 GRILLED LINK)
1.043
4.29
6113
Roundy's
roundy-s
2.86
0.086
N11150538022
usda-ndb-import
sweet italian sausage
1377.0
25.71
0.0
0
None
Roundy's Sweet Italian Sausage
20.00
70 g (1 GRILLED LINK)
0.871
2.86
6164
Roundy's
roundy-s
24.71
0.000
N11150550086
usda-ndb-import
french fried potatoes
787.0
9.41
2.4
0
None
Roundy's Curly French Fried Potatoes
2.35
85 g (3 ONZ)
0.435
0.00
6247
Roundy's
roundy-s
27.78
0.019
N11150589147
usda-ndb-import
ice cream bars
699.0
5.56
0.0
0
None
Roundy's Ice Cream Bars, Orange
1.85
54 g (54 g)
0.065
18.52
6254
Roundy's
roundy-s
36.36
0.026
N11150590037
usda-ndb-import
ice cream bars
1795.0
29.87
2.6
0
None
Roundy's Ice Cream Bars
3.90
77 g (77 g)
0.117
31.17
6928
Shurfine, Topco Associates Inc.
shurfine,topco-associates-inc
56.67
0.000
N11161030577
usda-ndb-import
baked snack crackers
1674.0
15.00
0.0
0
None
Shurfine Baked Snack Crackers
6.67
30 g (40 CRACKERS)
0.733
3.33
6934
Shurfine
shurfine
57.14
0.000
N11161031352
usda-ndb-import
classic potato chips
2389.0
35.71
3.6
0
None
Shurfine Classic Potato Chips
7.14
28 g (17 CHIPS)
0.643
0.00
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
292097
Ahold
ahold
50.51
0.000
N68826717758
usda-ndb-import
cinnamon rolls with
1310.0
10.10
2.0
0
None
Ahold Twisted Chocolate Jumbo Cinnamon Rolls W...
5.05
99 g (1 ROLL WITH ICING)
0.677
21.21
292898
Cha Ching
cha-ching
20.00
0.017
N725493300360
usda-ndb-import
thousand island dressing
1117.0
20.00
0.0
0
None
Cha Ching Thousand Island Dressing
0.00
30 ml (2 Tbsp)
1.000
16.67
293817
Terana
terana
0.00
NaN
N7501088109980
usda-ndb-import
pico de gallo
0.0
0.00
NaN
0
None
Terana Pico De Gallo Seasoning Mix
0.00
0.5 g (0.25 tsp)
0.000
NaN
0
Meijer
meijer
62.50
0.000
N713733903387
usda-ndb-import
cracker
2092.0
28.12
0.0
1
https://static.meijer.com/Media/007/13733/0071...
Low Sodium Applause Crackers
6.25
16 g (16 g)
0.188
6.25
1
Global
global
71.43
0.000
N876274001858
usda-ndb-import
cracker
2092.0
21.43
0.0
0
NaN
Snack Time, Stack Pack Salted Crackers
7.14
28 g (28 g)
0.304
7.14
2
Hostess
hostess
48.24
0.012
N888109050023
usda-ndb-import
donut
2017.0
30.59
1.2
1
https://s-media-cache-ak0.pinimg.com/originals...
Donettes, Mini Donuts, Frosted
3.53
85 g (3 oz)
0.306
30.59
3
Entenmann's
entenmann-s
47.92
0.021
N72030015712
usda-ndb-import
donut
2004.0
31.25
2.1
0
http://www.shugarysweets.com/wp-content/upload...
Frosted Donuts
4.17
48 g (48 g)
0.375
27.08
4
Little Debbie, Mckee Foods Corporation
little-debbie,mckee-foods-corporation
55.74
0.020
N24300806247
usda-ndb-import
donut
1987.0
27.05
1.6
1
http://bitemefoods.com.au/wp-content/uploads/2...
Mini Donuts
4.10
122 g (8 DONUTS)
0.418
30.33
5
Entenmann's, Bimbo Bakeries Usa Inc.
entenmann-s,bimbo-bakeries-usa-inc
52.63
0.026
N72030021645
usda-ndb-import
donut
1983.0
28.07
1.8
0
https://jpg.seasonskosher.com/content/images/t...
Pop'Ettes Powdered Donuts
3.51
57 g (57 g)
0.368
26.32
6
Roundy's
roundy-s
73.33
0.000
N11150146098
usda-ndb-import
cracker
1954.0
15.00
3.3
1
http://www.candywarehouse.com/assets/item/regu...
Kids Graham Crackers, Chocolate
6.67
30 g (19 COOKIES)
0.417
23.33
7
Medford Farms
medford-farms
60.00
0.000
N76606720956
usda-ndb-import
cracker
1954.0
26.67
0.0
0
http://www.baldersonvillagecheese.com/gourmet-...
Savory Snack Cracker, Celery & Onion
6.67
15 g (15 g)
1.000
0.00
8
Maple Donuts Inc
maple-donuts-inc
40.00
0.011
N76265185905
usda-ndb-import
donut
1858.0
28.89
2.2
0
http://www.fridaycakenight.com/wp-content/uplo...
Plain Cake Mini Donuts
2.22
45 g (2 DONUTS)
0.511
11.11
9
Roland
roland
75.00
0.000
N41224710146
usda-ndb-import
cracker
1833.0
6.25
6.2
0
http://www.rolandfood.com/i/product_images/l/0...
Roland Water Crackers
6.25
16 g (16 g)
0.750
0.00
10
Great Value, Wal-Mart Stores Inc.
great-value,wal-mart-stores-inc
50.00
0.000
N78742129082
usda-ndb-import
cracker
1833.0
25.00
0.0
0
NaN
Baked Buttery Crackers, Naturally Flavored
6.25
16 g (5 CRACKERS)
0.656
6.25
11
Kroger, The Kroger Co.
kroger,the-kroger-co
59.15
0.000
N11110008817
usda-ndb-import
donut
1828.0
19.72
1.4
0
NaN
Maple Glazed Cake Donuts
4.23
71 g (1 DONUT)
0.451
35.21
12
Meijer
meijer
71.43
0.000
N708820381599
usda-ndb-import
cracker
1795.0
14.29
10.7
0
NaN
Woven Wheats, Baked Whole Wheat Crackers, Rose...
7.14
28 g (28 g)
0.536
3.57
13
Hostess
hostess
52.83
0.009
N888109111298
usda-ndb-import
donut
1736.0
20.75
1.9
0
NaN
Red Velvet Mini Donuts
3.77
53 g (3 DONUTS)
0.255
30.19
14
Mom Brands
mom-brands
89.66
0.000
N42400109754
usda-ndb-import
cereal
1732.0
3.45
0.0
0
http://media.fooducate.com/products/images/180...
Cocoa Dyno-Bites, Sweetened Rice Cereal With R...
3.45
29 g (0.75 cup)
0.517
44.83
15
Kiggins
kiggins
88.89
0.000
N51933150546
usda-ndb-import
cereal
1703.0
0.00
0.0
0
NaN
Sweetened Puffed Wheat Cereal, Honey
7.41
27 g (0.75 cup)
0.241
55.56
16
Food Lion, Food Town Stores Inc.
food-lion,food-town-stores-inc
80.00
0.000
N35826097101
usda-ndb-import
cracker
1674.0
5.71
5.7
0
NaN
Sweet & Crispy Graham Crackers
5.71
35 g (2 FULL CRACKER SHEETS)
0.514
22.86
17
Chocolatey Colossal Crunch
chocolatey-colossal-crunch
86.67
0.000
N42400060024
usda-ndb-import
cereal
1674.0
5.00
3.3
0
NaN
Naturally & Artificially Flavored Sweetened Co...
3.33
30 g (0.75 cup)
0.667
43.33
18
Mom Brands
mom-brands
86.67
0.000
N42400236245
usda-ndb-import
cereal
1674.0
3.33
3.3
0
https://www.postconsumerbrands.com/wp-content/...
Berry Bunch Crunch, Sweetened Corn & Oat Cereal
3.33
30 g (0.75 cup)
0.467
46.67
19
Honey Graham Toasters
honey-graham-toasters
76.67
0.000
N42400240815
usda-ndb-import
cereal
1674.0
10.00
3.3
0
https://s-media-cache-ak0.pinimg.com/736x/63/e...
Honey Graham Cereal
6.67
30 g (0.75 cup)
0.867
33.33
20
Ancient Harvest
ancient-harvest
67.65
0.000
N980125260001
usda-ndb-import
cereal
1611.0
5.88
7.1
0
NaN
Quinoa Hot Cereal Flakes
12.65
34 g (0.33 cup)
0.006
5.88
21
Panaderia San Jorge S.A.
panaderia-san-jorge-s-a
76.67
0.000
N7750106000048
usda-ndb-import
cracker
1602.0
3.33
NaN
0
NaN
San Jorge Water Crackers
13.33
30 g (30 GRM)
0.600
3.33
22
Foodtown, Foodtown Inc.
foodtown,foodtown-inc
81.25
0.000
N11153041949
usda-ndb-import
cereal
1569.0
3.12
6.2
1
https://www.dlmdriveup.com/img/CentralOrdering...
Crunchy Oat Squares With Cinnamon Cereal
9.38
32 g (0.75 cup)
0.422
25.00
23
Safeway Kitchens, Safeway Inc.
safeway-kitchens,safeway-inc
85.71
0.000
N21130281022
usda-ndb-import
cereal
1494.0
0.00
3.6
0
NaN
Corn Flakes Cereal
7.14
28 g (1 cup)
0.571
7.14
24
Arnie's
arnie-s
43.66
0.028
N76185003815
usda-ndb-import
donut
1473.0
16.90
1.4
0
NaN
Variety Pack Donut Holes
5.63
71 g (71 g)
0.493
18.31
25
Fresh & Easy
fresh-easy
56.14
0.070
N5051379078669
usda-ndb-import
donut
1469.0
14.04
0.0
0
NaN
Baked Donuts
7.02
57 g (1 DONUT)
0.140
36.84
26
Nature's Path
nature-s-path
87.50
0.000
N58449620020
usda-ndb-import
cereal
1305.0
0.00
6.2
0
NaN
Eco Pac, Cereal, Millet Puffs
12.50
16 g (1 cup)
0.000
0.00
933 rows × 17 columns
Can now write this out to file.
In [104]:
# finished.to_csv(code_dir+"demo_food_data_final.csv", index = False)
finished.to_csv(code_dir+"demo_food_data_final2.csv", index = False)
Content source: dorairajsanjay/w209finalproject
Similar notebooks: