In [10]:

    

import pandas as pd
%matplotlib inline


    

In [11]:

    

recent_grads = pd.read_csv("../data/grad/recent-grads.csv")


    

In [12]:

    

recent_grads.head()


    

    
Out[12]:






  

    

      

      
Rank
      
Major_code
      
Major
      
Major_category
      
Total
      
Sample_size
      
Men
      
Women
      
ShareWomen
      
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
      
Engineering
      
2339
      
36
      
2057
      
282
      
0.120564
      
1976
      
...
      
270
      
1207
      
37
      
0.018381
      
110000
      
95000
      
125000
      
1534
      
364
      
193
    
    

      
1
      
2
      
2416
      
MINING AND MINERAL ENGINEERING
      
Engineering
      
756
      
7
      
679
      
77
      
0.101852
      
640
      
...
      
170
      
388
      
85
      
0.117241
      
75000
      
55000
      
90000
      
350
      
257
      
50
    
    

      
2
      
3
      
2415
      
METALLURGICAL ENGINEERING
      
Engineering
      
856
      
3
      
725
      
131
      
0.153037
      
648
      
...
      
133
      
340
      
16
      
0.024096
      
73000
      
50000
      
105000
      
456
      
176
      
0
    
    

      
3
      
4
      
2417
      
NAVAL ARCHITECTURE AND MARINE ENGINEERING
      
Engineering
      
1258
      
16
      
1123
      
135
      
0.107313
      
758
      
...
      
150
      
692
      
40
      
0.050125
      
70000
      
43000
      
80000
      
529
      
102
      
0
    
    

      
4
      
5
      
2405
      
CHEMICAL ENGINEERING
      
Engineering
      
32260
      
289
      
21239
      
11021
      
0.341631
      
25694
      
...
      
5180
      
16697
      
1672
      
0.061098
      
65000
      
50000
      
75000
      
18314
      
4440
      
972
    
  

5 rows × 21 columns

In [13]:

    

recent_grads.hist('Median')


    

    
Out[13]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x112d6e198>]], dtype=object)






    

In [14]:

    

recent_grads.hist('Median', bins=20, grid=False)


    

    
Out[14]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x112dd05c0>]], dtype=object)






    

In [19]:

    

columns = ['Median', 'Sample_size']
recent_grads.hist(column=columns, layout=(2,1) ,grid=False)


    

    
Out[19]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x112341320>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x1133c0358>]], dtype=object)






    

In [21]:

    

import matplotlib.pyplot as plt
sample_size = recent_grads[['Sample_size', 'Major_category']]
sample_size.boxplot(by='Major_category')
plt.xticks(rotation=90)


    

    
Out[21]:





(array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16]),
 <a list of 16 Text xticklabel objects>)






    

In [22]:

    

import matplotlib.pyplot as plt
plt.scatter(recent_grads['Unemployment_rate'], recent_grads['Median'], color='red')
plt.scatter(recent_grads['ShareWomen'], recent_grads['Median'], color='blue')
plt.show()


    

In [ ]: