analyze.py

"""
analyze.py
Spring 2021 PJW

Aggregate and analyze the educational attainment data.
"""

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

#
#  Set up defaults for matplotlib, seaborn and pandas
#

plt.rcParams['figure.dpi'] = 300
sns.set_theme(style="white")

pd.set_option('display.max_rows',None)

#
#  Read information about how to group the variables
#

var_info = pd.read_csv('census-variables.csv',index_col='variable')
var_group = var_info['group']

print( "\nGroups:" )
print(var_group)

#
#  Read the actual data
#

attain = pd.read_csv('census-data.csv',index_col='NAME')

print( "\nAttainment:")
print( attain )

#
#  Aggregate the columns using the grouping information
#

group_by_level = attain.groupby( var_group, axis='columns', sort=False )
by_level = group_by_level.sum()

#
#  Extract the colum of totals and make sure remaining data adds up
#

total = by_level['total']
by_level = by_level.drop(columns='total')

error = by_level.sum(axis='columns') - total

print( "\nCheck sum:" )
print(error)

#
#  Build a dataframe with percentages of the total
#

pct = 100*by_level.div(total,axis='index')

#
#  Print a sorted list of counties ordered by percent of
#  the population with less than a HS education
#

print( "\nPercent