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

%matplotlib inline
In [2]:
recent_grads = pd.read_csv('recent-grads.csv')
In [3]:
recent_grads.iloc[0]
Out[3]:
Rank                                        1
Major_code                               2419
Major                   PETROLEUM ENGINEERING
Total                                    2339
Men                                      2057
Women                                     282
Major_category                    Engineering
ShareWomen                           0.120564
Sample_size                                36
Employed                                 1976
Full_time                                1849
Part_time                                 270
Full_time_year_round                     1207
Unemployed                                 37
Unemployment_rate                   0.0183805
Median                                 110000
P25th                                   95000
P75th                                  125000
College_jobs                             1534
Non_college_jobs                          364
Low_wage_jobs                             193
Name: 0, dtype: object
In [4]:
recent_grads.head()
Out[4]:
Rank Major_code Major Total Men Women Major_category ShareWomen Sample_size Employed ... Part_time Full_time_year_round Unemployed Unemployment_rate Median P25th P75th College_jobs Non_college_jobs Low_wage_jobs
0 1 2419 PETROLEUM ENGINEERING 2339.0 2057.0 282.0 Engineering 0.120564 36 1976 ... 270 1207 37 0.018381 110000 95000 125000 1534 364 193
1 2 2416 MINING AND MINERAL ENGINEERING 756.0 679.0 77.0 Engineering 0.101852 7 640 ... 170 388 85 0.117241 75000 55000 90000 350 257 50
2 3 2415 METALLURGICAL ENGINEERING 856.0 725.0 131.0 Engineering 0.153037 3 648 ... 133 340 16 0.024096 73000 50000 105000 456 176 0
3 4 2417 NAVAL ARCHITECTURE AND MARINE ENGINEERING 1258.0 1123.0 135.0 Engineering 0.107313 16 758 ... 150 692 40 0.050125 70000 43000 80000 529 102 0
4 5 2405 CHEMICAL ENGINEERING 32260.0 21239.0 11021.0 Engineering 0.341631 289 25694 ... 5180 16697 1672 0.061098 65000 50000 75000 18314 4440 972

5 rows × 21 columns

In [5]:
recent_grads.tail()
Out[5]:
Rank Major_code Major Total Men Women Major_category ShareWomen Sample_size Employed ... Part_time Full_time_year_round Unemployed Unemployment_rate Median P25th P75th College_jobs Non_college_jobs Low_wage_jobs
168 169 3609 ZOOLOGY 8409.0 3050.0 5359.0 Biology & Life Science 0.637293 47 6259 ... 2190 3602 304 0.046320 26000 20000 39000 2771 2947 743
169 170 5201 EDUCATIONAL PSYCHOLOGY 2854.0 522.0 2332.0 Psychology & Social Work 0.817099 7 2125 ... 572 1211 148 0.065112 25000 24000 34000 1488 615 82
170 171 5202 CLINICAL PSYCHOLOGY 2838.0 568.0 2270.0 Psychology & Social Work 0.799859 13 2101 ... 648 1293 368 0.149048 25000 25000 40000 986 870 622
171 172 5203 COUNSELING PSYCHOLOGY 4626.0 931.0 3695.0 Psychology & Social Work 0.798746 21 3777 ... 965 2738 214 0.053621 23400 19200 26000 2403 1245 308
172 173 3501 LIBRARY SCIENCE 1098.0 134.0 964.0 Education 0.877960 2 742 ... 237 410 87 0.104946 22000 20000 22000 288 338 192

5 rows × 21 columns

In [6]:
recent_grads.describe(include='all')
Out[6]:
Rank Major_code Major Total Men Women Major_category ShareWomen Sample_size Employed ... Part_time Full_time_year_round Unemployed Unemployment_rate Median P25th P75th College_jobs Non_college_jobs Low_wage_jobs
count 173.000000 173.000000 173 172.000000 172.000000 172.000000 173 172.000000 173.000000 173.000000 ... 173.000000 173.000000 173.000000 173.000000 173.000000 173.000000 173.000000 173.000000 173.000000 173.000000
unique NaN NaN 173 NaN NaN NaN 16 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
top NaN NaN FRENCH GERMAN LATIN AND OTHER COMMON FOREIGN L... NaN NaN NaN Engineering NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
freq NaN NaN 1 NaN NaN NaN 29 NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
mean 87.000000 3879.815029 NaN 39370.081395 16723.406977 22646.674419 NaN 0.522223 356.080925 31192.763006 ... 8832.398844 19694.427746 2416.329480 0.068191 40151.445087 29501.445087 51494.219653 12322.635838 13284.497110 3859.017341
std 50.084928 1687.753140 NaN 63483.491009 28122.433474 41057.330740 NaN 0.231205 618.361022 50675.002241 ... 14648.179473 33160.941514 4112.803148 0.030331 11470.181802 9166.005235 14906.279740 21299.868863 23789.655363 6944.998579
min 1.000000 1100.000000 NaN 124.000000 119.000000 0.000000 NaN 0.000000 2.000000 0.000000 ... 0.000000 111.000000 0.000000 0.000000 22000.000000 18500.000000 22000.000000 0.000000 0.000000 0.000000
25% 44.000000 2403.000000 NaN 4549.750000 2177.500000 1778.250000 NaN 0.336026 39.000000 3608.000000 ... 1030.000000 2453.000000 304.000000 0.050306 33000.000000 24000.000000 42000.000000 1675.000000 1591.000000 340.000000
50% 87.000000 3608.000000 NaN 15104.000000 5434.000000 8386.500000 NaN 0.534024 130.000000 11797.000000 ... 3299.000000 7413.000000 893.000000 0.067961 36000.000000 27000.000000 47000.000000 4390.000000 4595.000000 1231.000000
75% 130.000000 5503.000000 NaN 38909.750000 14631.000000 22553.750000 NaN 0.703299 338.000000 31433.000000 ... 9948.000000 16891.000000 2393.000000 0.087557 45000.000000 33000.000000 60000.000000 14444.000000 11783.000000 3466.000000
max 173.000000 6403.000000 NaN 393735.000000 173809.000000 307087.000000 NaN 0.968954 4212.000000 307933.000000 ... 115172.000000 199897.000000 28169.000000 0.177226 110000.000000 95000.000000 125000.000000 151643.000000 148395.000000 48207.000000

11 rows × 21 columns

Clean the data by removing rows with missing values

In [7]:
raw_data_count = recent_grads.shape[0]
recent_grads = recent_grads.dropna()
cleaned_data_count = recent_grads.shape[0]
print(raw_data_count, cleaned_data_count)
173 172
In [8]:
ax = recent_grads.plot(x='Sample_size', y='Employed', kind='scatter', title='Employed vs. Sample_size', figsize=(5,10))
In [9]:
recent_grads.plot(x='Sample_size', y='Median', kind='scatter')
Out[9]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40c1e01e80>
In [10]:
recent_grads.plot(x='Sample_size', y='Unemployment_rate', kind='scatter')
Out[10]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40c1db61d0>
In [11]:
recent_grads.plot(x='Full_time', y='Median', kind='scatter')
Out[11]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfd08898>
In [12]:
recent_grads.plot(x='ShareWomen', y='Unemployment_rate', kind='scatter')
Out[12]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfcef4e0>
In [13]:
recent_grads.plot(x='Men', y='Median', kind='scatter')
Out[13]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfc56470>
In [14]:
recent_grads.plot(x='Women', y='Median', kind='scatter')
Out[14]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfc2ed30>

Do students in more popular majors make more money?

  • No Do students that majored in subjects that were majority female make more money?
  • No Is there any link between the number of full-time employees and median salary?
  • Highest salaries are with small amount of employees
In [15]:
recent_grads['Sample_size'].hist(bins=25, range=(0,5000))
Out[15]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfcc0ac8>
In [16]:
recent_grads['Median'].hist(bins=25, range=(20000, 50000))
Out[16]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfaeb470>
In [17]:
recent_grads['Employed'].hist(bins=25)
Out[17]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bfa22fd0>
In [18]:
recent_grads['Full_time'].hist(bins=25)
Out[18]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf964828>
In [19]:
recent_grads['ShareWomen'].hist(bins=25)
Out[19]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf9235f8>
In [20]:
recent_grads['Unemployment_rate'].hist(bins=25)
Out[20]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf7d5f60>
In [21]:
recent_grads['Men'].hist(bins=25, range=(0,75000))
Out[21]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf710780>
In [22]:
recent_grads['Women'].hist(bins=25, range=(0,75000))
Out[22]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf60d6a0>

What percent of majors are predominantly male?

  • ? Predominantly female?
  • ? What's the most common median salary range?
  • 20000, 50000
In [23]:
from pandas.plotting import scatter_matrix

scatter_matrix(recent_grads[['Sample_size','Median']], figsize=(10,10))
Out[23]:
array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf555208>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf512080>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf4dc208>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf4963c8>]],
      dtype=object)
In [24]:
scatter_matrix(recent_grads[['Sample_size','Median','Unemployment_rate']], figsize=(10,10))
Out[24]:
array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf3c8240>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf3b2e80>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf300898>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf33b438>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf285588>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf241f60>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf210c50>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf1c5da0>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x7f40bf194fd0>]],
      dtype=object)
In [25]:
recent_grads[:10].plot.bar(x='Major', y='ShareWomen')
Out[25]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf0a2390>
In [26]:
recent_grads[-10:].plot.bar(x='Major', y='ShareWomen')
Out[26]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40beffe940>
In [27]:
recent_grads[:10].plot.bar(x='Major', y='Unemployment_rate')
Out[27]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bef8b4a8>
In [28]:
recent_grads[-10:].plot.bar(x='Major', y='Unemployment_rate')
Out[28]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bf295ac8>

Other visualization explored on my own

Grouped bar plot

This plot shows quantity of men and women in each category of majors

In [29]:
(recent_grads[['Major_category','Men','Women']]
    .groupby(['Major_category'])
    .sum()
    .plot.bar())
Out[29]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bef88e10>

Box plot

Distributions of median salaries and unemployment rate

In [30]:
recent_grads[['Median']].boxplot()
Out[30]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bed46470>
In [31]:
recent_grads[['Unemployment_rate']].boxplot()
Out[31]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40bed0c320>

Hexagonal bin plot

In [34]:
recent_grads.plot.hexbin(x='Women', y='Median',gridsize=25)
Out[34]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40beaf0a20>
In [37]:
recent_grads.plot.hexbin(x='Men', y='Median',gridsize=25)
Out[37]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f40be896d30>
In [ ]: