causality

In [1]:

    

import numpy
import pandas as pd

from causality.inference.search import IC
from causality.inference.independence_tests import RobustRegressionTest

# generate some toy data:
SIZE = 2000
x1 = numpy.random.normal(size=SIZE)
x2 = x1 + numpy.random.normal(size=SIZE)
x3 = x1 + numpy.random.normal(size=SIZE)
x4 = x2 + x3 + numpy.random.normal(size=SIZE)
x5 = x4 + numpy.random.normal(size=SIZE)

# load the data into a dataframe:
X = pd.DataFrame({'x1' : x1, 'x2' : x2, 'x3' : x3, 'x4' : x4, 'x5' : x5})

# define the variable types: 'c' is 'continuous'.  The variables defined here
# are the ones the search is performed over  -- NOT all the variables defined
# in the data frame.
variable_types = {'x1' : 'c', 'x2' : 'c', 'x3' : 'c', 'x4' : 'c', 'x5' : 'c'}

# run the search
ic_algorithm = IC(RobustRegressionTest)
graph = ic_algorithm.search(X, variable_types)


    

    




/Users/amir.ziai/anaconda/lib/python3.5/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
  from pandas.core import datetools

In [12]:

    

X.head()


    

    
Out[12]:







  

    

      

      
x1
      
x2
      
x3
      
x4
      
x5
    
  
  

    

      
0
      
-1.406695
      
-0.517982
      
0.142170
      
-1.816308
      
-2.210177
    
    

      
1
      
0.350395
      
0.899873
      
-0.267734
      
0.078581
      
1.170726
    
    

      
2
      
-0.861684
      
-0.558598
      
-0.075510
      
1.639826
      
2.057733
    
    

      
3
      
-0.334222
      
0.539190
      
0.020224
      
0.116004
      
0.310686
    
    

      
4
      
1.154677
      
0.647006
      
1.194869
      
2.751039
      
3.158303
    
  

In [2]:

    

graph.edges(data=True)


    

    
Out[2]:





[('x3', 'x4', {'arrows': ['x4'], 'marked': False}),
 ('x3', 'x1', {'arrows': [], 'marked': False}),
 ('x1', 'x2', {'arrows': [], 'marked': False}),
 ('x5', 'x4', {'arrows': ['x5'], 'marked': True}),
 ('x4', 'x2', {'arrows': ['x4'], 'marked': False})]

In [3]:

    

from causality.estimation.adjustments import AdjustForDirectCauses
from networkx import DiGraph

g = DiGraph()

g.add_nodes_from(['x1','x2','x3','x4', 'x5'])
g.add_edges_from([('x1','x2'),('x1','x3'),('x2','x4'),('x3','x4')])
adjustment = AdjustForDirectCauses()


    

In [5]:

    

print (adjustment.admissable_set(g, ['x2'], ['x3']))


    

    




{'x1'}

In [6]:

    

from causality.estimation.nonparametric import CausalEffect


    

In [7]:

    

admissable_set = adjustment.admissable_set(g,['x2'], ['x3'])


    

In [8]:

    

effect = CausalEffect(X, ['x2'], ['x3'], variable_types=variable_types, admissable_set=list(admissable_set))


    

In [9]:

    

x = pd.DataFrame({'x2' : [0.], 'x3' : [0.]})


    

In [10]:

    

effect.pdf(x)


    

    
Out[10]:





0.269858323490185

In [ ]: