def test_pdf_no_adjustment(self):
causes = ['c']
effects = ['d']
admissable_set = []
variable_types={'a': 'u','b': 'u','c': 'u','d' : 'u'}
effect = CausalEffect(self.discrete,causes,effects,admissable_set,variable_types)
# p(d=1|do(c=0) = 0.45, p(d=1|b=0) = 0.40
p = effect.pdf(pd.DataFrame({ 'd' : [1], 'c' : [0]}))
print p
assert( abs( 0.40 - p ) < 0.02 )
def test_pdf_no_adjustment(self):
causes = ['c']
effects = ['d']
admissable_set = []
variable_types = {'a': 'u', 'b': 'u', 'c': 'u', 'd': 'u'}
effect = CausalEffect(self.discrete, causes, effects, admissable_set,
variable_types)
# p(d=1|do(c=0) = 0.45, p(d=1|b=0) = 0.40
p = effect.pdf(pd.DataFrame({'d': [1], 'c': [0]}))
print p
assert (abs(0.40 - p) < 0.02)
def test_pdf_continuous(self):
causes = ["c"]
effects = ["d"]
admissable_set = ["a"]
variable_types = {"a": "c", "b": "c", "c": "c", "d": "c"}
effect = CausalEffect(self.X, causes, effects, admissable_set, variable_types)
c = np.mean(effect.support["c"])
d = np.mean(effect.support["d"])
e1 = effect.pdf(pd.DataFrame({"d": [d], "c": [0.9 * c]}))
e2 = effect.pdf(pd.DataFrame({"d": [d], "c": [1.1 * c]}))
print(e2, e1, e2 - e1, (e2 - e1) / e2)
assert abs(e2 - e1) / e2 < 0.05
def test_pdf_no_adjustment(self):
causes = ["c"]
effects = ["d"]
admissable_set = []
variable_types = {"a": "u", "b": "u", "c": "u", "d": "u"}
effect = CausalEffect(
self.discrete, causes, effects, admissable_set, variable_types
)
# p(d=1|do(c=0) = 0.45, p(d=1|b=0) = 0.40
p = effect.pdf(pd.DataFrame({"d": [1], "c": [0]}))
print(p)
assert abs(0.40 - p) < 0.02
def test_pdf_continuous(self):
causes = ['c']
effects = ['d']
admissable_set = ['a']
variable_types={'a': 'c','b': 'c','c': 'c','d' : 'c'}
effect = CausalEffect(self.X,causes,effects,admissable_set,variable_types)
c = np.mean(effect.support['c'])
d = np.mean(effect.support['d'])
e1 = effect.pdf(pd.DataFrame({ 'd' : [d], 'c' : [ 0.9 * c]}))
e2 = effect.pdf(pd.DataFrame({ 'd' : [d], 'c' : [ 1.1 * c]}))
print e2, e1, e2 - e1, (e2 - e1) / e2
assert( abs(e2 - e1) / e2 < 0.05 )
def test_pdf_continuous(self):
causes = ['c']
effects = ['d']
admissable_set = ['a']
variable_types = {'a': 'c', 'b': 'c', 'c': 'c', 'd': 'c'}
effect = CausalEffect(self.X, causes, effects, admissable_set,
variable_types)
c = np.mean(effect.support['c'])
d = np.mean(effect.support['d'])
e1 = effect.pdf(pd.DataFrame({'d': [d], 'c': [0.9 * c]}))
e2 = effect.pdf(pd.DataFrame({'d': [d], 'c': [1.1 * c]}))
print e2, e1, e2 - e1, (e2 - e1) / e2
assert (abs(e2 - e1) / e2 < 0.05)
g.add_edges_from([('x1', 'x2'), ('x1', 'x3'), ('x2', 'x4'), ('x3', 'x4')])
adjustment = AdjustForDirectCauses()
admissable_set = adjustment.admissable_set(g, ['x2'], ['x3'])
print(admissable_set)
# 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'}
effect = CausalEffect(X, ['x2'], ['x3'],
variable_types=variable_types,
admissable_set=list(admissable_set))
x = pd.DataFrame({'x2': [0.], 'x3': [0.]})
print(effect.pdf(x))
# in the data frame.
variable_types = {'x1': 'c', 'x2': 'c', 'x3': 'c', 'x4': 'c', 'x5': 'c'}
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()
print(adjustment.admissable_set(g, ['x2'], ['x3']))
# set(['x1'])
from causality.estimation.nonparametric import CausalEffect
admissable_set = adjustment.admissable_set(g, ['x2'], ['x3'])
effect = CausalEffect(X, ['x2'], ['x3'],
variable_types=variable_types,
admissable_set=list(admissable_set))
x = pd.DataFrame({'x2': [0.], 'x3': [0.]})
res = effect.pdf(x)
print(res)
# 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
