#!/usr/bin/env python
# coding: utf-8

# # Single Variable Visualizations #
# 
# ## (Graphs) ##
# 
# In this notebook we will cover more thoroughly than before:
# 
# - How to make and interpret a bar graph or bar chart
# - How to make and interpret a histogram
# - The fundamental differences between bar charts and histograms
# - How to make and interpret boxplots
# - When possible how to make side-by-side or overlapping graphs to compare <u>two groups</u>
# 
# 

# In[ ]:


from datascience import *
import numpy as np
import warnings
warnings.filterwarnings("ignore")

get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plots
plots.style.use('fivethirtyeight')
plots.rcParams["patch.force_edgecolor"] = True


# ## Categorical Distribution ##

# In[ ]:


#help(Table.hist)


# ## Bar Charts ##

# In[ ]:


top_movies = Table.read_table('top_movies_2017.csv')
top_movies


# In[ ]:


top_movies = top_movies.with_column('Millions', np.round(top_movies.column('Gross')/1000000,3))
top_movies.take(np.arange(10)).barh('Title', 'Millions')


# When the bars of a bar graph are arranged from longest to shortest, that is called a *Pareto* chart.

# In[ ]:


top_movies.take(np.arange(10)).sort("Millions", descending=True).barh('Title', 'Millions')


# In[ ]:


studios = top_movies.select('Studio')
studios


# In[ ]:


studio_distribution = studios.group('Studio')


# In[ ]:


studio_distribution


# In[ ]:


sum(studio_distribution.column('count'))


# In[ ]:


studio_distribution.barh('Studio')


# In[ ]:


#Pareto

studio_distribution.sort('count', descending=True).barh('Studio')


# In[ ]:


baby = Table.read_table("baby.csv")
baby


# In[ ]:


baby.group("Maternal Smoker")


# In[ ]:


baby.group("Maternal Smoker").barh("Maternal Smoker")
plots.xlabel("Count", color = "blue")
plots.title("Counts of Mothers in \nBaby Dataset", color = "blue")
plots.yticks(make_array(.5, 1.5), make_array("Yes", "No"), color = "gold")
plots.ylabel("Smoker", color ="blue", size = 25);


# In[ ]:


help(plots)


# ## Numerical Distribution ##

# In[ ]:


ages = 2022 - top_movies.column('Year')
top_movies = top_movies.with_column('Age', ages)


# In[ ]:


top_movies


# ## Binning ##

# In[ ]:


min(ages), max(ages)


# In[ ]:


my_bins = make_array(0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110)


# In[ ]:


binned_data = top_movies.bin('Age', bins = my_bins)
binned_data


# In[ ]:


sum(binned_data.column('Age count'))


# In[ ]:


top_movies.bin('Age', bins = np.arange(0, 126, 25))


# In[ ]:


top_movies.bin('Age', bins = np.arange(0, 60, 25))


# In[ ]:


top_movies.where('Age', 52)


# ## Histograms ##

# In[ ]:


my_bins


# In[ ]:


binned_data


# In[ ]:


# Let's make our first histogram!
top_movies.hist('Age')


# In[ ]:


# Let's try picking our own bins instead.
top_movies.hist('Age', bins = np.arange(0, 100, 10),  unit = 'Year')


# In[ ]:


top_movies.hist('Age', bins = np.arange(0, 110, 10), unit = 'Year', density=False)


# In[ ]:


25/2


# In[ ]:


# Let's try not specifying any bins!
top_movies.hist('Age', unit='Year')


# In[ ]:


3*9.61+5


# In[ ]:


# Add a column containing what percent of movies are in each bin
binned_data = binned_data.with_column(
    'Percent', 100*binned_data.column('Age count')/200)


# In[ ]:


binned_data


# ## Height ##
# 
# ### Question: What is the height of the [42, 66] bin?

# In[ ]:


# Step 1: Calculate % of movies in the [40, 65) bin
percent = binned_data.where('bin', 42).column('Percent').item(0)
percent


# In[ ]:


# Step 2: Calculate the width of the 42-66 bin
width = 66 - 42
width


# In[ ]:


# Step 3: Area of rectangle = height * width
#         --> height = percent / width
height = percent / width
height


# ### What are the heights of the rest of the bins?

# In[ ]:


# Get the bin lefts
bin_lefts = binned_data.take(np.arange(binned_data.num_rows - 1))


# In[ ]:


# Get the bin widths
bin_widths = np.diff(binned_data.column('bin'))
bin_lefts = bin_lefts.with_column('Width', bin_widths)


# In[ ]:


# Get the bin heights
bin_heights = bin_lefts.column('Percent') / bin_widths
bin_lefts = bin_lefts.with_column('Height', bin_heights)


# In[ ]:


bin_lefts


# In[ ]:


top_movies.hist('Age', bins = my_bins, unit = 'Year')


# Please note that the example above is a bad example.  On a histogram, bins should be the **same** size.  Now, let's look at another example showing the impact of bins.  
# 
# ### The impact of bins ###

# In[ ]:


survey = Table.read_table('welcome_survey_v1.csv')
survey


# In[ ]:


sleep_bins = np.arange(4, 12, 0.5)
sleep_bins


# In[ ]:


survey.hist('Hours of sleep', bins=sleep_bins)


# In[ ]:


sleep_bins = np.arange(4,12, 1)
survey.hist('Hours of sleep', bins=sleep_bins)


# ## Boxplots
# 
# Box plots are a graphical display of the descriptive statistics that we know as the Five Number Summary.
# 
# Five Number Summary is as follows
# 
# - The minimum
# - The $25^{th}$ percentile, $Q_1$
# - The $50^{th}$ percentile, the median
# - The $75^{th}$ percentile, $Q_3$
# - The maximum
# 
# In one of the next couple of notebooks, we will discuss how to compute these.  

# In[ ]:


skyscrapers = Table.read_table('skyscrapers.csv')
ny = skyscrapers.where('city', "New York City")
la = skyscrapers.where('city', 'Los Angeles')
ny


# In[ ]:


plots.boxplot(ny.column(3), widths = 0.4);
#plots.xlabel("NYC");


# In[ ]:


plots.boxplot(ny.column(3), widths=.5 )
plots.xticks(make_array(1), make_array("NYC"))
plots.title("Heights of New York City \nSkyscrapers");


# ### Can we also display the mean on a boxplot? ###
# 
# Yes, if you set the value of **showmeans** equal to True.  

# In[ ]:


plots.boxplot(ny.column(3), widths=.5 , showmeans=True)
plots.xticks(make_array(1), make_array("NYC"));


# In[ ]:


plots.boxplot(ny.column(3), widths=.5 , showmeans=True, whis=10)
plots.xticks(make_array(1), make_array("NYC"));


# In[ ]:





# ## Comparing two groups numerically ##
# 
# We can use side-by-side boxplots to visually compare two groups.

# In[ ]:


ticks=make_array(2.5, 3.5)
labels=make_array("NYC", "LA")

plots.figure(figsize=(6, 6))
plots.boxplot(ny.column(3), widths=.5, positions=make_array(ticks.item(0)) )
plots.boxplot(la.column(3), widths=.5, positions=make_array(ticks.item(1)) )
plots.xticks(ticks, labels)
plots.title("Boxplots Comparing NYC and LA Skyscrapers");


# In[ ]:


ticks=make_array(2.5, 3.5)
labels=make_array("NYC", "LA")

plots.figure(figsize=(6, 6))
plots.boxplot(ny.column(3), widths=.5, positions=make_array(ticks.item(0)), showmeans=True)
plots.boxplot(la.column(3), widths=.5, positions=make_array(ticks.item(1)), showmeans=True)
plots.xticks(ticks, labels)
plots.title("Boxplots Comparing NYC and LA Skyscrapers");


# In[ ]:


smokers = baby.where("Maternal Smoker", True).column("Birth Weight")
nonsmokers = baby.where("Maternal Smoker", False).column("Birth Weight")


ticks=make_array(2.5, 3.5)
labels=make_array("Smokers", "Non-Smokers")

plots.figure(figsize=(6, 6))
plots.boxplot(smokers, widths=.5, positions=make_array(ticks.item(0)), showmeans=True)
plots.boxplot(nonsmokers, widths=.5, positions=make_array(ticks.item(1)), showmeans=True)
plots.xticks(ticks, labels)
plots.title("Comparing Birth Weights \nof Babies");


# Sometimes, overlapping histograms are also possible.  

# In[ ]:


galton = Table.read_table('galton.csv')


# In[ ]:


galton


# In[ ]:


galton.hist('midparentHeight')


# In[ ]:


galton.hist('childHeight')


# What part of this histogram is the children with heights above 70 inches?
# 

# In[ ]:


galton.hist('childHeight', left_end=70)


# In[ ]:


galton.hist('midparentHeight', 'childHeight')


# In[ ]:


galton.hist("mother", "father", "childHeight", "midparentHeight")


# In[ ]:


ticks=make_array(2.5, 3.5, 4.5, 5.5)
labels=make_array("Midparent", "Child", "Mother", "Father")

plots.figure(figsize=(6, 6))
plots.boxplot(galton.column("midparentHeight"), widths=.5, positions=make_array(ticks.item(0)), showmeans=True)
plots.boxplot(galton.column("childHeight"), widths=.5, positions=make_array(ticks.item(1)), showmeans=True)
plots.boxplot(galton.column("mother"), widths=.5, positions=make_array(ticks.item(2)), showmeans=True)
plots.boxplot(galton.column("father"), widths=.5, positions=make_array(ticks.item(3)), showmeans=True)
plots.xticks(ticks, labels)
plots.title("Comparing Heights");


# In[ ]: