def cmiR(x, y, z, k, data, discrete_dist=1):
'''
computes conditional mutual information, I(x,y|z)
input:
x: list of indices for x
y: list of indices for y
z: list of indices for z
k: hyper parameter for kNN
data: pandas dataframe
output:
scalar value of I(x,y|z) from Rahimzamani
'''
# compute CMI for I(x,y|z) using k-NN
n, p = data.shape
distArray = knncmi.getPairwiseDistArray(data, x + y + z, discrete_dist)
if len(z) > 0:
s = 0
for point in range(n):
s = s + cmiPointR(point, x, y, z, k, distArray)
return (s / n)
else:
s = 0
for point in range(n):
s = s + miPointR(point, x, y, k, distArray)
return (s / n)
def cmi4(x, y, z, k, data):
'''
Computes Prop, RAVK, FP CMI faster by not redoing computation
x: list of indices for x
y: list of indices for y
z: list of indices for z
k: hyper parameter for kNN
data: pandas dataframe
output:
tuple: (fp, ravk1, ravk2, prop), values of I(x,y|z)
'''
n, p = data.shape
if len(z) == 0:
data['z'] = 0
z = [p+1]
distArray = knncmi.getPairwiseDistArray(data, x + y + z)
ptEsts = map(lambda obs: cmi4point(obs, x, y, z, k, distArray), range(n))
return sum(ptEsts)/n
def create_sub_array(dat, var_list, size, seed):
np.random.seed(seed)
rand_obs = np.random.choice(dat.shape[0], size, replace = True)
sub_dat = dat.iloc[rand_obs]
distArray = knncmi.getPairwiseDistArray(sub_dat, var_list)
return distArray