Doing things with Pandas

In [2]:

    

import pandas as pd
%matplotlib inline


    

In [4]:

    

job_data = pd.read_csv("../web-scraping/jobs-data.csv")
job_data.head()


    

    
Out[4]:






  

    

      

      
company_link
      
company_name
      
job_link
      
job_location
      
job_summary
      
job_title
    
  
  

    

      
0
      
http://www.indeed.com/cmp/Allegheny-General-Ho...
      
Allegheny General Hospital
      
http://www.indeed.com/rc/clk?jk=805f6ed65b49dd...
      
Pittsburgh, PA
      
Allegheny Health Network’s clinical expertise ...
      
Research Data Analyst - Neurosurgery
    
    

      
1
      
http://www.indeed.com/cmp/Marathon-Oil
      
Marathon Petroleum Corporation
      
http://www.indeed.com/rc/clk?jk=b28767d68e08b1...
      
Findlay, OH
      
The vision for the Advanced Analytics team is ...
      
Data Scientist
    
    

      
2
      
http://www.indeed.com/cmp/Oracle
      
Oracle
      
http://www.indeed.com/rc/clk?jk=56e6eae3c307f9...
      
United States
      
The Cloud Data Curation team is looking for Sc...
      
Data Scientist 5
    
    

      
3
      
http://www.indeed.com/cmp/Google
      
Google
      
http://www.indeed.com/rc/clk?jk=35f4fa4d806cc9...
      
Mountain View, CA
      
From creating experiments and prototyping impl...
      
Research Scientist, Google Brain (United States)
    
    

      
4
      
http://www.indeed.com/cmp/Childrens-Hospital-L...
      
Childrens Hospital Los Angeles
      
http://www.indeed.com/rc/clk?jk=ff4d4e425d9c76...
      
Los Angeles, CA
      
The Data Scientist conducts research in medica...
      
Data Scientist, VPICU
    
  

In [5]:

    

job_data.dtypes


    

    
Out[5]:





company_link    object
company_name    object
job_link        object
job_location    object
job_summary     object
job_title       object
dtype: object

In [ ]:

    

job_data.shape


    

In [ ]:

    

job_data['job_title'].value_counts(ascending=False)


    

In [ ]:

    

job_data['company_name'].value_counts(ascending=False)


    

In [ ]:

    

job_data['job_location'].value_counts(ascending=False)


    

In [ ]:

    

job_data['state'] = job_data['job_location'].str.extract(', (\w{2})', expand=False)
job_data.head()


    

In [ ]:

    

ax = job_data['state'].value_counts(ascending=True).plot(kind="barh", figsize=(10,10), xlim=(0,450))
# add counts as annotations
# http://stackoverflow.com/questions/23591254/python-pandas-matplotlib-annotating-labels-above-bar-chart-columns
for p in ax.patches:
    ax.annotate("%d" % p.get_width(), (p.get_x() + p.get_width(), p.get_y()), xytext=(0, 0), textcoords='offset points')


    

In [ ]:

    

job_data[job_data['job_location'].str.contains("Pittsburgh")]


    

In [7]:

    

company_data = pd.read_csv("company-data.csv")
company_data.head()


    

    
Out[7]:






  

    

      

      
compensation_benefits_rating
      
culture_rating
      
js_advancement_rating
      
management_rating
      
overall_rating
      
url
      
wl_balanace_rating
    
  
  

    

      
0
      
3.9
      
3.5
      
3.3
      
3.4
      
3.9
      
http://www.indeed.com/cmp/Population-Council
      
3.8
    
    

      
1
      
3.6
      
3.8
      
3.2
      
3.9
      
4.0
      
http://www.indeed.com/cmp/Ensco,-Inc.
      
4.1
    
    

      
2
      
3.9
      
3.6
      
3.3
      
3.4
      
3.8
      
http://www.indeed.com/cmp/General-Dynamics-Inf...
      
3.7
    
    

      
3
      
3.2
      
3.8
      
2.9
      
3.4
      
3.5
      
http://www.indeed.com/cmp/Mintel
      
3.7
    
    

      
4
      
3.8
      
3.8
      
3.6
      
3.5
      
4.0
      
http://www.indeed.com/cmp/ADP
      
3.8
    
  

In [8]:

    

company_data.dtypes


    

    
Out[8]:





compensation_benefits_rating    float64
culture_rating                  float64
js_advancement_rating           float64
management_rating               float64
overall_rating                  float64
url                              object
wl_balanace_rating              float64
dtype: object

In [9]:

    

company_data.shape


    

    
Out[9]:





(399, 7)

In [10]:

    

company_data.describe()


    

    
Out[10]:






  

    

      

      
compensation_benefits_rating
      
culture_rating
      
js_advancement_rating
      
management_rating
      
overall_rating
      
wl_balanace_rating
    
  
  

    

      
count
      
399.000000
      
399.000000
      
399.000000
      
399.000000
      
399.000000
      
399.000000
    
    

      
mean
      
3.701504
      
3.680201
      
3.342607
      
3.421805
      
3.883208
      
3.782206
    
    

      
std
      
0.480941
      
0.486898
      
0.510532
      
0.502807
      
0.438297
      
0.488315
    
    

      
min
      
2.000000
      
1.600000
      
1.500000
      
1.500000
      
1.700000
      
1.000000
    
    

      
25%
      
3.400000
      
3.400000
      
3.100000
      
3.200000
      
3.700000
      
3.550000
    
    

      
50%
      
3.800000
      
3.700000
      
3.400000
      
3.400000
      
4.000000
      
3.800000
    
    

      
75%
      
4.000000
      
4.000000
      
3.600000
      
3.700000
      
4.200000
      
4.100000
    
    

      
max
      
5.000000
      
5.000000
      
5.000000
      
5.000000
      
5.000000
      
5.000000
    
  

In [11]:

    

company_data['overall_rating'].hist()


    

    
Out[11]:





<matplotlib.axes._subplots.AxesSubplot at 0x107278f28>






    

In [12]:

    

company_data['culture_rating'].hist()


    

    
Out[12]:





<matplotlib.axes._subplots.AxesSubplot at 0x10757e668>






    

In [13]:

    

company_data['compensation_benefits_rating'].hist()


    

    
Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x1076a4128>






    

In [14]:

    

company_data['management_rating'].hist()


    

    
Out[14]:





<matplotlib.axes._subplots.AxesSubplot at 0x1076b5438>






    

In [6]:

    

company_data['js_advancement_rating'].hist()


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-6-b363d602bc9f> in <module>()
----> 1 company_data['js_advancement_rating'].hist()

NameError: name 'company_data' is not defined

In [ ]: