SI 330

import matplotlib.pyplot as plt import pandas as pd import numpy as np

menu = pd.read_csv('https://raw.githubusercontent.com/umsi-data-science/data/main/menu.csv') menu

Categoryobject

Coffee & Tea36.5%

Breakfast16.2%

7 others47.3%

Itemobject

Egg McMuffin0.4%

Egg White Delight0.4%

258 others99.2%

Breakfast

Sausage Biscuit (Regular Biscuit)

Breakfast

Sausage Biscuit (Large Biscuit)

Breakfast

Sausage Biscuit with Egg (Regular Biscuit)

Breakfast

Sausage Biscuit with Egg (Large Biscuit)

Breakfast

Sausage Biscuit with Egg Whites (Regular Biscuit)

Breakfast

Sausage Biscuit with Egg Whites (Large Biscuit)

Breakfast

Southern Style Chicken Biscuit (Regular Biscuit)

Breakfast

Southern Style Chicken Biscuit (Large Biscuit)

Breakfast

Steak & Egg Biscuit (Regular Biscuit)

Breakfast

Bacon, Egg & Cheese McGriddles

plt.plot(menu['Category'], menu['Total Fat'], 'o') plt.xticks(rotation=100) plt.title('Calories to Total Fat') plt.xlabel('Category') plt.ylabel('Total Fat') plt.annotate("Don't eat this", xy=(2, 118), xytext=(4, 100), arrowprops=dict(facecolor='black', shrink=0.10), ) plt.show()

plt.scatter(menu["Calories"],menu["Saturated Fat"]) plt.show()

plt.hist(menu['Calories']) plt.show()

plt.hist(menu['Total Fat']) plt.title('Total Fat') plt.xlabel('Total Fat') plt.show()

f = menu['Calories'].plot(kind='hist') type(f)

categories = menu.groupby('Category').size()

categories.plot(kind='barh')

categories_sorted = categories.sort_values(ascending=True)

categories_sorted.plot(kind='barh')

menu['Sugary'] = np.where(menu['Sugars'] > 20, 1,0) menu

Categoryobject

Coffee & Tea36.5%

Breakfast16.2%

7 others47.3%

Itemobject

Egg McMuffin0.4%

Egg White Delight0.4%

258 others99.2%

Breakfast

Big Breakfast with Egg Whites (Large Biscuit)

Breakfast

Big Breakfast with Hotcakes (Regular Biscuit)

Breakfast

Big Breakfast with Hotcakes (Large Biscuit)

Breakfast

Big Breakfast with Hotcakes and Egg Whites (Regular Biscuit)

Breakfast

Big Breakfast with Hotcakes and Egg Whites (Large Biscuit)

Breakfast

Hotcakes

Breakfast

Hotcakes and Sausage

Breakfast

Sausage Burrito

Breakfast

Hash Brown

Breakfast

Cinnamon Melts

menu.groupby(["Category", "Sugary"]).size().unstack().plot(kind = "bar")

menu.groupby(["Category", "Sugary"]).size().unstack().plot(kind = "bar", stacked = True)

menu.groupby(['Category', 'Sugary']).size().groupby(by='Category').apply( lambda x: 100 * x / x.sum() ).unstack().plot(kind='bar', stacked=True)

menu['Fatty'] = np.where(menu['Total Fat (% Daily Value)'] > 75, 1,0) menu.groupby(['Category', 'Fatty']).size().groupby(by='Category').apply( lambda x: 100 * x / x.sum() ).unstack().plot(kind='bar', stacked=True)

categories.plot(kind='pie', title='Menu Categories')

categories.plot(kind='bar', title='Menu Categories')

f, (ax1, ax2) = plt.subplots(2) # if only 1 argument, we assume it's the number of rows ax1.hist(menu['Calories']) plt.show()

f, (ax1, ax2) = plt.subplots(2) ax1.hist(menu['Calories']) ax2.plot(menu['Calories'],menu['Total Fat'],'bo') plt.show()

f, ((ax1, ax2),(ax3,ax4)) = plt.subplots(2,2) ax1.hist(menu['Calories']) ax2.plot(menu['Calories'],menu['Total Fat'],'bo') plt.show()

f, ((ax1, ax2),(ax3,ax4)) = plt.subplots(2,2) ax1.hist(menu['Total Fat']) ax2.plot(menu['Calories'],menu['Total Fat'],'bo') ax3.plot(menu['Total Fat'],menu['Calories'],'bo') ax4.hist(menu['Calories']) plt.show()

f, (ax1, ax2) = plt.subplots(2) menu['Calories'].plot(ax=ax1, kind='hist') menu['Dietary Fiber'].plot(ax = ax2,kind='hist') plt.show()

f, ((ax1, ax2),(ax3,ax4)) = plt.subplots(2,2) menu['Calories'].plot(ax=ax1, kind='barh') menu['Total Fat'].plot(ax=ax2, kind='line') menu['Sodium'].plot(ax=ax3, kind='hist') menu['Saturated Fat'].plot(ax=ax4, kind='box')

menu.Calories.plot(kind='hist')

menu.Calories.plot.hist()

menu.plot(kind="scatter", x='Calories', y='Total Fat')

menu.plot.scatter(x='Calories', y='Total Fat')

plt.figure(figsize=(12,5)) groups = menu.groupby('Category') for name, group in groups: plt.plot(group['Calories'], group['Total Fat'], marker='.', linestyle='', markersize=12, label=name) plt.legend() plt.show()