In [28]:

    

%pylab inline
plot(arange(5))


    

    




Populating the interactive namespace from numpy and matplotlib






    
Out[28]:





[<matplotlib.lines.Line2D at 0x10b33d390>]






    

In [11]:

    

%pylab inline
plot(arange(5))


    

    




Populating the interactive namespace from numpy and matplotlib






    
Out[11]:





[<matplotlib.lines.Line2D at 0x106f8ee10>]






    

In [29]:

    

import pandas as pd
import numpy as np
import matplotlib as plt

dataframe = pd.read_csv("/Users/potty/Documents/GitHub/uip-pc4/07.Data.Science/Ejemplo/train.csv")


    

In [6]:

    

dataframe.head(5)


    

    
Out[6]:







  

    

      

      
Loan_ID
      
Gender
      
Married
      
Dependents
      
Education
      
Self_Employed
      
ApplicantIncome
      
CoapplicantIncome
      
LoanAmount
      
Loan_Amount_Term
      
Credit_History
      
Property_Area
      
Loan_Status
    
  
  

    

      
0
      
LP001002
      
Male
      
No
      
0
      
Graduate
      
No
      
5849
      
0.0
      
NaN
      
360.0
      
1.0
      
Urban
      
Y
    
    

      
1
      
LP001003
      
Male
      
Yes
      
1
      
Graduate
      
No
      
4583
      
1508.0
      
128.0
      
360.0
      
1.0
      
Rural
      
N
    
    

      
2
      
LP001005
      
Male
      
Yes
      
0
      
Graduate
      
Yes
      
3000
      
0.0
      
66.0
      
360.0
      
1.0
      
Urban
      
Y
    
    

      
3
      
LP001006
      
Male
      
Yes
      
0
      
Not Graduate
      
No
      
2583
      
2358.0
      
120.0
      
360.0
      
1.0
      
Urban
      
Y
    
    

      
4
      
LP001008
      
Male
      
No
      
0
      
Graduate
      
No
      
6000
      
0.0
      
141.0
      
360.0
      
1.0
      
Urban
      
Y
    
  

In [7]:

    

dataframe.describe()


    

    
Out[7]:







  

    

      

      
ApplicantIncome
      
CoapplicantIncome
      
LoanAmount
      
Loan_Amount_Term
      
Credit_History
    
  
  

    

      
count
      
614.000000
      
614.000000
      
592.000000
      
600.00000
      
564.000000
    
    

      
mean
      
5403.459283
      
1621.245798
      
146.412162
      
342.00000
      
0.842199
    
    

      
std
      
6109.041673
      
2926.248369
      
85.587325
      
65.12041
      
0.364878
    
    

      
min
      
150.000000
      
0.000000
      
9.000000
      
12.00000
      
0.000000
    
    

      
25%
      
2877.500000
      
0.000000
      
100.000000
      
360.00000
      
1.000000
    
    

      
50%
      
3812.500000
      
1188.500000
      
128.000000
      
360.00000
      
1.000000
    
    

      
75%
      
5795.000000
      
2297.250000
      
168.000000
      
360.00000
      
1.000000
    
    

      
max
      
81000.000000
      
41667.000000
      
700.000000
      
480.00000
      
1.000000
    
  

In [8]:

    

dataframe['Property_Area'].value_counts()


    

    
Out[8]:





Semiurban    233
Urban        202
Rural        179
Name: Property_Area, dtype: int64

In [9]:

    

dataframe['Gender'].value_counts()


    

    
Out[9]:





Male      489
Female    112
Name: Gender, dtype: int64

In [22]:

    

dataframe['ApplicantIncome'].hist()


    

    
Out[22]:





<matplotlib.axes._subplots.AxesSubplot at 0x1090ba978>






    

In [21]:

    

dataframe.boxplot(column='ApplicantIncome')


    

    
Out[21]:





<matplotlib.axes._subplots.AxesSubplot at 0x10923c0f0>






    

In [17]:

    

import plotly.plotly as py
import plotly.figure_factory as ff


    

In [18]:

    

tabla = ff.create_table(dataframe)


    

In [19]:

    

py.iplot(tabla)


    

    




Aw, snap! We don't have an account for ''. Want to try again? You can authenticate with your email address or username. Sign in is not case sensitive.

Don't have an account? plot.ly

Questions? support@plot.ly






    




---------------------------------------------------------------------------
PlotlyError                               Traceback (most recent call last)
<ipython-input-19-960144c2bb2e> in <module>()
----> 1 py.iplot(tabla)

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/plotly/plotly/plotly.py in iplot(figure_or_data, **plot_options)
    162         embed_options['height'] = str(embed_options['height']) + 'px'
    163 
--> 164     return tools.embed(url, **embed_options)
    165 
    166 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/plotly/tools.py in embed(file_owner_or_url, file_id, width, height)
    388         else:
    389             url = file_owner_or_url
--> 390         return PlotlyDisplay(url, width, height)
    391     else:
    392         if (get_config_defaults()['plotly_domain']

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/plotly/tools.py in __init__(self, url, width, height)
   1363         def __init__(self, url, width, height):
   1364             self.resource = url
-> 1365             self.embed_code = get_embed(url, width=width, height=height)
   1366             super(PlotlyDisplay, self).__init__(data=self.embed_code)
   1367 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/plotly/tools.py in get_embed(file_owner_or_url, file_id, width, height)
    293                 "'{1}'."
    294                 "\nRun help on this function for more information."
--> 295                 "".format(url, plotly_rest_url))
    296         urlsplit = six.moves.urllib.parse.urlparse(url)
    297         file_owner = urlsplit.path.split('/')[1].split('~')[1]

PlotlyError: Because you didn't supply a 'file_id' in the call, we're assuming you're trying to snag a figure from a url. You supplied the url, '', we expected it to start with 'https://plot.ly'.
Run help on this function for more information.

In [30]:

    

%matplotlib inline


    

In [23]:

    

dataframe.boxplot(column='ApplicantIncome', by='Gender')


    

    
Out[23]:





<matplotlib.axes._subplots.AxesSubplot at 0x10b7f0e80>






    

In [25]:

    

dataframe.boxplot(column='ApplicantIncome', by='Married')


    

    
Out[25]:





<matplotlib.axes._subplots.AxesSubplot at 0x10b2fba58>






    

In [31]:

    

temporal1 = dataframe['Credit_History'].value_counts(ascending=True)
temporal2 = dataframe.pivot_table(values='Loan_Status', index=['Credit_History'], aggfunc=lambda x: x.map({'Y':1, 'N':0}).mean())
print("Tabla de Frecuencia de Historial Crediticio")
print(temporal1)
print("Tabla de Probabilidad de Obtener un Prestamo por cada clas de Historial de Credito")
print(temporal2)


    

    




Tabla de Frecuencia de Historial Crediticio
0.0     89
1.0    475
Name: Credit_History, dtype: int64
Tabla de Probabilidad de Obtener un Prestamo por cada clas de Historial de Credito
                Loan_Status
Credit_History             
0.0                0.078652
1.0                0.795789

In [39]:

    

import matplotlib.pyplot as plt
figura = plt.figure(figsize=(8,4))
eje1 = figura.add_subplot(121)
eje1.set_xlabel('Historial de Credito')
eje1.set_ylabel('Conteo de Aplicantes')
eje1.set_title('Aplicantes por Historial de Credito')
temporal1.plot(kind='bar')

eje2 = figura.add_subplot(121)
eje2.set_xlabel('Historial de Credito')
eje2.set_ylabel('Probabilidad de Obtener Prestamo')
eje2.set_title('Probabilidad de Obtener Prestamos por Historial Crediticio')
temporal2.plot(kind='bar')


    

    




/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/matplotlib/cbook/deprecation.py:106: MatplotlibDeprecationWarning:

Adding an axes using the same arguments as a previous axes currently reuses the earlier instance.  In a future version, a new instance will always be created and returned.  Meanwhile, this warning can be suppressed, and the future behavior ensured, by passing a unique label to each axes instance.







    
Out[39]:





<matplotlib.axes._subplots.AxesSubplot at 0x10ca4c3c8>






    













    

In [ ]:

    

dataframe.apply(lambda x: sum(x.isnull(),axis=0))