GP06: Visualizing The Gender Gap In College Degrees

1: Introduction


In [1]:
%matplotlib inline
import pandas as pd
import matplotlib.pyplot as plt

women_degrees = pd.read_csv('../data/GP06/percent-bachelors-degrees-women-usa.csv')
cb_dark_blue = (0/255,107/255,164/255)
cb_orange = (255/255, 128/255, 14/255)
stem_cats = ['Engineering', 'Computer Science', 'Psychology', 'Biology', 'Physical Sciences', 'Math and Statistics']

fig = plt.figure(figsize=(18, 3))

for sp in range(0,6):
    ax = fig.add_subplot(1,6,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(stem_cats[sp])
    ax.tick_params(bottom="off", top="off", left="off", right="off")
    
    if sp == 0:
        ax.text(2005, 87, 'Men')
        ax.text(2002, 8, 'Women')
    elif sp == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2001, 35, 'Women')
plt.show()


2: Comparing Across All Degrees


In [2]:
stem_cats = ['Psychology', 'Biology', 'Math and Statistics', 'Physical Sciences', 'Computer Science', 'Engineering', 'Computer Science']
lib_arts_cats = ['Foreign Languages', 'English', 'Communications and Journalism', 'Art and Performance', 'Social Sciences and History']
other_cats = ['Health Professions', 'Public Administration', 'Education', 'Agriculture','Business', 'Architecture']

In [3]:
fig = plt.figure(figsize=(16, 16))

## Generate first column of line charts. STEM degrees.
for sp in range(0,18,3):
    cat_index = int(sp/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(stem_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off")
    
    if cat_index == 0:
        ax.text(2003, 85, 'Women')
        ax.text(2005, 10, 'Men')
    elif cat_index == 5:
        ax.text(2005, 87, 'Men')
        ax.text(2003, 7, 'Women')

## Generate second column of line charts. Liberal arts degrees.
for sp in range(1,16,3):
    cat_index = int((sp-1)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[lib_arts_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[lib_arts_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(lib_arts_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off")
    
    if cat_index == 0:
        ax.text(2003, 78, 'Women')
        ax.text(2005, 18, 'Men')

## Generate third column of line charts. Other degrees.
for sp in range(2,20,3):
    cat_index = int((sp-2)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[other_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[other_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(other_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off")
    
    if cat_index == 0:
        ax.text(2003, 90, 'Women')
        ax.text(2005, 5, 'Men')
    elif cat_index == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2003, 30, 'Women')
        
plt.show()


3: Hiding X-Axis Labels


In [4]:
fig = plt.figure(figsize=(16, 16))

## Generate first column of line charts. STEM degrees.
for sp in range(0,18,3):
    cat_index = int(sp/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(stem_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    
    if cat_index == 0:
        ax.text(2003, 85, 'Women')
        ax.text(2005, 10, 'Men')
    elif cat_index == 5:
        ax.text(2005, 87, 'Men')
        ax.text(2003, 7, 'Women')
        ax.tick_params(labelbottom='on')

## Generate second column of line charts. Liberal arts degrees.
for sp in range(1,16,3):
    cat_index = int((sp-1)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[lib_arts_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[lib_arts_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(lib_arts_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    
    if cat_index == 0:
        ax.text(2003, 78, 'Women')
        ax.text(2005, 18, 'Men')
    elif cat_index == 4:
        ax.tick_params(labelbottom='on')

## Generate third column of line charts. Other degrees.
for sp in range(2,20,3):
    cat_index = int((sp-2)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[other_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[other_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(other_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    
    if cat_index == 0:
        ax.text(2003, 90, 'Women')
        ax.text(2005, 5, 'Men')
    elif cat_index == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2003, 30, 'Women')
        ax.tick_params(labelbottom='on')
        
plt.show()


4: Setting Y-Axis Labels


In [5]:
fig = plt.figure(figsize=(16, 16))

## Generate first column of line charts. STEM degrees.
for sp in range(0,18,3):
    cat_index = int(sp/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(stem_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    
    if cat_index == 0:
        ax.text(2003, 85, 'Women')
        ax.text(2005, 10, 'Men')
    elif cat_index == 5:
        ax.text(2005, 87, 'Men')
        ax.text(2003, 7, 'Women')
        ax.tick_params(labelbottom='on')

## Generate second column of line charts. Liberal arts degrees.
for sp in range(1,16,3):
    cat_index = int((sp-1)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[lib_arts_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[lib_arts_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(lib_arts_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    
    if cat_index == 0:
        ax.text(2003, 78, 'Women')
        ax.text(2005, 18, 'Men')
    elif cat_index == 4:
        ax.tick_params(labelbottom='on')

## Generate third column of line charts. Other degrees.
for sp in range(2,20,3):
    cat_index = int((sp-2)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[other_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[other_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(other_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    
    if cat_index == 0:
        ax.text(2003, 90, 'Women')
        ax.text(2005, 5, 'Men')
    elif cat_index == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2003, 30, 'Women')
        ax.tick_params(labelbottom='on')
        
plt.show()


5: Adding A Horizontal Line


In [6]:
fig = plt.figure(figsize=(16, 16))

## Generate first column of line charts. STEM degrees.
for sp in range(0,18,3):
    cat_index = int(sp/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(stem_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    ax.axhline(50, c=(171/255, 171/255, 171/255), alpha=0.3)
    
    if cat_index == 0:
        ax.text(2003, 85, 'Women')
        ax.text(2005, 10, 'Men')
    elif cat_index == 5:
        ax.text(2005, 87, 'Men')
        ax.text(2003, 7, 'Women')
        ax.tick_params(labelbottom='on')

## Generate second column of line charts. Liberal arts degrees.
for sp in range(1,16,3):
    cat_index = int((sp-1)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[lib_arts_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[lib_arts_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(lib_arts_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    ax.axhline(50, c=(171/255, 171/255, 171/255), alpha=0.3)
    
    if cat_index == 0:
        ax.text(2003, 78, 'Women')
        ax.text(2005, 18, 'Men')
    elif cat_index == 4:
        ax.tick_params(labelbottom='on')

## Generate third column of line charts. Other degrees.
for sp in range(2,20,3):
    cat_index = int((sp-2)/3)
    ax = fig.add_subplot(6,3,sp+1)
    ax.plot(women_degrees['Year'], women_degrees[other_cats[cat_index]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100-women_degrees[other_cats[cat_index]], c=cb_orange, label='Men', linewidth=3)
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(other_cats[cat_index])
    ax.tick_params(bottom="off", top="off", left="off", right="off", labelbottom='off')
    ax.set_yticks([0,100])
    ax.axhline(50, c=(171/255, 171/255, 171/255), alpha=0.3)
    
    if cat_index == 0:
        ax.text(2003, 90, 'Women')
        ax.text(2005, 5, 'Men')
    elif cat_index == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2003, 30, 'Women')
        ax.tick_params(labelbottom='on')
        
plt.show()



In [ ]: