In [1]:

%matplotlib inline

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import scipy
from scipy import stats
from sklearn.cluster import KMeans
from sklearn.metrics import davies_bouldin_score
import seaborn as sns
from mpl_toolkits.mplot3d import Axes3D
from collections import Counter
from nltk.corpus import stopwords
import pprint

In [2]:

features = ['Category',
'Item',
'Serving Size',
'Calories',
'Calories from Fat',
'Total Fat',
'Saturated Fat',
'Trans Fat',
'Cholesterol',
'Sodium',
'Carbohydrates',
'Dietary Fiber',
'Sugars',
'Protein',
'Vitamin A (% Daily Value)',
'Vitamin C (% Daily Value)',
'Calcium (% Daily Value)',
'Iron (% Daily Value)']

dataset = pd.read_csv('menu.csv',header=0,usecols=features)

In [3]:

dataset.head(5)

Out[3]:

	Category	Item	Serving Size	Calories	Calories from Fat	Total Fat	Saturated Fat	Cholesterol	Sodium	Carbohydrates	Dietary Fiber	Sugars	Protein	Vitamin A (% Daily Value)	Calcium (% Daily Value)	Iron (% Daily Value)
0	Breakfast	Egg McMuffin	4.8 oz (136 g)	300	120	13.0	5.0	260	750	31	4	3	17	10	25	15
1	Breakfast	Egg White Delight	4.8 oz (135 g)	250	70	8.0	3.0	25	770	30	4	3	18	6	25	8
2	Breakfast	Sausage McMuffin	3.9 oz (111 g)	370	200	23.0	8.0	45	780	29	4	2	14	8	25	10
3	Breakfast	Sausage McMuffin with Egg	5.7 oz (161 g)	450	250	28.0	10.0	285	860	30	4	2	21	15	30	15
4	Breakfast	Sausage McMuffin with Egg Whites	5.7 oz (161 g)	400	210	23.0	8.0	50	880	30	4	2	21	6	25	10

In [4]:

df = dataset.drop(["Category","Item","Serving Size"],axis=1)

In [5]:

z = np.abs(stats.zscore(df))
print(np.where(z > 7))

print(dataset.iloc[82])
dataset = dataset.drop([82],axis=0)
df = df.drop([82],axis=0)

(array([ 82,  82, 135]), array([ 1,  2, 12]))
Category                                   Chicken & Fish
Item                         Chicken McNuggets (40 piece)
Serving Size                              22.8 oz (646 g)
Calories                                             1880
Calories from Fat                                    1060
Total Fat                                             118
Saturated Fat                                          20
Trans Fat                                               1
Cholesterol                                           265
Sodium                                               3600
Carbohydrates                                         118
Dietary Fiber                                           6
Sugars                                                  1
Protein                                                87
Vitamin A (% Daily Value)                               0
Vitamin C (% Daily Value)                              15
Calcium (% Daily Value)                                 8
Iron (% Daily Value)                                   25
Name: 82, dtype: object

In [6]:

normalized_df=(df-df.mean())/df.std()
normalized_df["Category"] = dataset[["Category"]]
normalized_df.head(5)

Out[6]:

	Calories	Calories from Fat	Total Fat	Saturated Fat	Trans Fat	Cholesterol	Sodium	Carbohydrates	Dietary Fiber	Sugars	Protein	Vitamin A (% Daily Value)	Vitamin C (% Daily Value)	Calcium (% Daily Value)	Iron (% Daily Value)	Category
0	-0.281865	-0.030612	-0.060316	-0.181297	-0.470098	2.381337	0.488727	-0.574834	1.542477	-0.925115	0.376316	-0.142577	-0.322415	0.233469	0.845334	Breakfast
1	-0.507601	-0.468647	-0.454811	-0.561506	-0.470098	-0.336969	0.525441	-0.610597	1.542477	-0.925115	0.471683	-0.306517	-0.322415	0.233469	0.038283	Breakfast
2	0.034165	0.670245	0.728672	0.389017	-0.470098	-0.105624	0.543798	-0.646360	1.542477	-0.959981	0.090213	-0.224547	-0.322415	0.233469	0.268869	Breakfast
3	0.395343	1.108280	1.123166	0.769227	-0.470098	2.670519	0.690654	-0.610597	1.542477	-0.959981	0.757787	0.062348	-0.322415	0.527005	0.845334	Breakfast
4	0.169607	0.757852	0.728672	0.389017	-0.470098	-0.047788	0.727368	-0.610597	1.542477	-0.959981	0.757787	-0.306517	-0.322415	0.233469	0.268869	Breakfast

In [7]:

len(dataset)

Out[7]:

In [8]:

corr = df.corr()
sns.heatmap(corr,linewidths=.5, cmap="YlGnBu")

Out[8]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f600524f4e0>

In [9]:

plotData = normalized_df[["Category","Calories","Total Fat","Carbohydrates","Protein"]]

sns.set(style="ticks")
sns.pairplot(plotData, hue="Category")

Out[9]:

<seaborn.axisgrid.PairGrid at 0x7f600316bda0>

In [10]:

x = dataset["Total Fat"]
y = dataset["Carbohydrates"]
z = dataset["Protein"]
c = dataset["Calories"]

fig = plt.figure()
ax = plt.axes(projection='3d')
ax.scatter(x, y, z, c=c, cmap='viridis', linewidth=0.5);

ax.view_init(25,55)

In [11]:

plotData = normalized_df[["Category","Calories","Cholesterol","Sodium","Sugars"]]

sns.set(style="ticks")
sns.pairplot(plotData, hue="Category")

Out[11]:

<seaborn.axisgrid.PairGrid at 0x7f60029d1828>