notebook.community

Edit and run



In [1]:

    
import pandas as pd
import numpy as np
%matplotlib inline

import plotly.plotly as py
import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot

init_notebook_mode(connected=True)



In [2]:

    
df = pd.read_stata('~/../../statadata/IPEDSDirInfo02to18.dta')



In [8]:

    
state_counts_2018 = pd.DataFrame(df[df['isYr'] == 2018]['stabbr'].value_counts())
state_counts_2018.rename(columns = {'stabbr':'Total Institutions'}, inplace=True)
scratch = {}

for sec in df['sector'].unique():
    scratch[sec] = pd.DataFrame(df[(df['isYr'] == 2018) & 
                                   (df['sector'] == sec)]['stabbr'].value_counts())
    
    scratch[sec].rename(columns = {'stabbr':sec}, inplace=True)
    state_counts_2018 = pd.merge(state_counts_2018, scratch[sec], 
                                 left_index=True, 
                                 right_index=True,
                                 how='outer')

state_counts_2018.reset_index(inplace=True)



In [12]:

    
state_counts_2018.head()









    Out[12]:







  
    
      
      index
      Total Institutions
      Public, 2-year
      Sector unknown (not active)
      Public, 4-year or above
      Private not-for-profit, 4-year or above
      Administrative Unit
      Private for-profit, less-than 2-year
      Private for-profit, 4-year or above
      Private not-for-profit, 2-year
      Private for-profit, 2-year
      Public, less-than 2-year
      Private not-for-profit, less-than 2-year
    
  
  
    
      0
      AK
      10
      NaN
      NaN
      4.0
      2.0
      1.0
      NaN
      NaN
      1.0
      1.0
      1.0
      NaN
    
    
      1
      AL
      90
      26.0
      NaN
      14.0
      21.0
      1.0
      16.0
      4.0
      NaN
      7.0
      NaN
      1.0
    
    
      2
      AR
      87
      22.0
      NaN
      11.0
      14.0
      2.0
      29.0
      2.0
      4.0
      1.0
      2.0
      NaN
    
    
      3
      AS
      1
      NaN
      NaN
      1.0
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    
    
      4
      AZ
      122
      20.0
      2.0
      10.0
      12.0
      2.0
      37.0
      19.0
      NaN
      17.0
      2.0
      1.0



In [18]:

    
data = {'type':'choropleth', 
        'locations':state_counts_2018['index'],
        'locationmode':'USA-states',
        'colorscale':'Greens',
        'reversescale':True,
        'z':state_counts_2018['Total Institutions'],
        'colorbar':{'title':'Counts'}}

layout = {'geo':{'scope':'usa'}}

choromap = go.Figure(data=[data], layout=layout)



In [20]:

    
iplot(choromap)



In [ ]:

	index	Total Institutions	Public, 2-year	Sector unknown (not active)	Public, 4-year or above	Private not-for-profit, 4-year or above	Administrative Unit	Private for-profit, less-than 2-year	Private for-profit, 4-year or above	Private not-for-profit, 2-year	Private for-profit, 2-year	Public, less-than 2-year	Private not-for-profit, less-than 2-year
0	AK	10	NaN	NaN	4.0	2.0	1.0	NaN	NaN	1.0	1.0	1.0	NaN
1	AL	90	26.0	NaN	14.0	21.0	1.0	16.0	4.0	NaN	7.0	NaN	1.0
2	AR	87	22.0	NaN	11.0	14.0	2.0	29.0	2.0	4.0	1.0	2.0	NaN
3	AS	1	NaN	NaN	1.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	AZ	122	20.0	2.0	10.0	12.0	2.0	37.0	19.0	NaN	17.0	2.0	1.0