Awesome Data Visualization - McDonlad's Menu

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt # draw graphs in Jupyter Notebook
import matplotlib as mpl  # visualization library in Python for 2D plots of arrays.
import seaborn as sns #beautiful statistics and visualization

menu = pd.read_csv('/kaggle/input/nutrition-facts/menu.csv') # read the csv file

menu.isnull().sum() # check for missing values, return the number of missing values

menu.head() # show us the top rows

menu.hist(column=['Calories','Cholesterol','Sugars','Protein','Total Fat'],bins=20, color='steelblue', edgecolor='black', linewidth=1.0,
           xlabelsize=8, ylabelsize=8, grid=False) # historam for each attribute. adjust size and colors
plt.tight_layout(rect=(0, 0, 1.2, 1.2))
plt.ylabel("Counter") # naming the y-axis
plt.xlabel("Values") # naming the x-axis

sns.set(font_scale=1.4)
menu['Category'].value_counts().plot(kind='bar', figsize=(7, 6)) # makes plot bar for each category
plt.xlabel("Categories", labelpad=5) # title for the x label
plt.ylabel("Count of items", labelpad=5) # title for the y label
plt.title("Count of items by its category", y=1.02); # title for the plot

# Histogram
fig = plt.figure(figsize = (6,4)) # adjust plot for size
title = fig.suptitle("Calories of each item", fontsize=14) # title for plot
fig.subplots_adjust(top=0.85, wspace=0.3) # Tune the subplot layout. adjust the placing

ax = fig.add_subplot(1,1, 1) # adds subplot to the figure
ax.set_xlabel("Calories") # naming the x-axis
ax.set_ylabel("Frequency") # naming the y-axis
freq, bins, patches = ax.hist(menu['Calories'], color='steelblue', bins=30,
                                    edgecolor='black', linewidth=1) # histogram for each category of calories
                                    

# Density Plot
fig = plt.figure(figsize = (6, 4)) # adjust plot for size
title = fig.suptitle("Calories of each item", fontsize=14) # title for plot
fig.subplots_adjust(top=0.85, wspace=0.3) # Tune the subplot layout. adjust the placing

ax1 = fig.add_subplot(1,1, 1) # adds the 2nd subplot to the figure
ax1.set_xlabel("Calories") # naming the x-axis
ax1.set_ylabel("Frequency") # naming the y-axis
sns.kdeplot(menu['Calories'], ax=ax1, shade=True, color='steelblue')  # Fit and plot a univariate or bivariate kernel density estimate.

menu[menu['Calories']==menu['Calories'].max()]['Item'] # gets the highest-calorie dish

sugars = menu['Sugars'] # sugars values column
calories = menu['Calories'] # calories values column
plt.scatter(calories, sugars) # scatter plot of calories vs sugars
plt.xlabel('calories') # naming the x-axis
plt.ylabel('sugars') naming the y-axis
plt.show()

menu.pivot_table('Trans Fat', 'Category').plot(kind='bar', stacked=True, color = 'c') # bar plot of each category and the mean of its Trans fat

Protein = menu['Protein'] # protein column
Calories = menu['Calories'] # calories column
Category = menu['Category'] # category column

df = pd.DataFrame(dict(Calories=Calories, Protein=Protein, Category=Category)) # data frame of the 3 column
sns.lmplot('Calories', 'Protein', data=df, hue='Category', fit_reg=False) # Plot data of Calories vs Protein, based on categories by colors
plt.show()

cols = ['Calories','Cholesterol','Trans Fat','Sugars','Dietary Fiber'] 
cm = np.corrcoef(menu[cols].values.T) # Return Pearson product-moment correlation coefficients on all the columns 
sns.set(font_scale = 1.5) # Set aesthetic parameters in one step.
hm = sns.heatmap(cm,cbar = True, annot = True,square = True, fmt = '.2f', annot_kws = {'size':15}, yticklabels = cols, xticklabels = cols) # correlation matrix between some main values

def plot(grouped):
    item = grouped["Item"].sum() # group items by names
    item_list = item.sort_index() # sort the items by sugar values
    item_list = item_list[-20:] # keeps only the 20 first items
    plt.figure(figsize=(9,10))
    graph = sns.barplot(item_list.index,item_list.values) #x is the sugar values, y is the item name
    labels = [aj.get_text()[-40:] for aj in graph.get_yticklabels()] # crop text to make it look better
    graph.set_yticklabels(labels)

    sugar = menu.groupby(menu["Sugars"]) # group by sugars
    plot(sugar)

protein = menu.groupby(menu["Protein"])
plot(protein)

Cholesterol = menu.groupby(menu["Cholesterol"])
plot(Cholesterol)

calories = menu.groupby(menu["Calories"])
plot(calories)

Saturated = menu.groupby(menu["Saturated Fat"])
plot(Saturated)

menu.corr()['Calories'].sort_values()