def get_interaction(a, b, surv, int_direction='both'):
'''
Get test statistic (chi2 distributed) of interaction between
two event vectors.
We define 3 models:
1) a + b
2) a:b
3) a + b + a:b
We return the improvement of fit from 2 to 1 minus the
improvement of fit from 3 to 2. That is we want to capture
as much of the information in the interaction term as possible.
'''
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv,
covariates=[a, b],
formula='Surv(days, event) ~ a + b')
int_var = 1. * (combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
m3 = get_cox_ph(surv, combine(a, b))
chi2_a = extract_chi2(m2, m1)
chi2_b = extract_chi2(m3, m2)
return chi2_a - chi2_b
def get_interaction(a, b, surv, int_direction='both'):
'''
Get test statistic (chi2 distributed) of interaction between
two event vectors.
We define 3 models:
1) a + b
2) a:b
3) a + b + a:b
We return the improvement of fit from 2 to 1 minus the
improvement of fit from 3 to 2. That is we want to capture
as much of the information in the interaction term as possible.
'''
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv, covariates=[a, b],
formula='Surv(days, event) ~ a + b')
int_var = 1.*(combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
m3 = get_cox_ph(surv, combine(a, b))
chi2_a = extract_chi2(m2, m1)
chi2_b = extract_chi2(m3, m2)
return chi2_a - chi2_b
def get_interactions(df, cov_df, surv, test):
binary = df[df.T.describe().ix['unique'] == 2]
'''drop redundant features within a data-type'''
s = {b for i, (a, v1) in enumerate(binary.iterrows())
for j, (b, v2) in enumerate(binary.iterrows())
if (i < j)
and a[0] == b[0]
and np.log2(fisher_exact_test(v1, v2)['odds_ratio']) > 4}
binary = binary.ix[binary.index.diff(s)]
n_tests = (len(binary) * (len(binary) - 1)) / 2
s = pd.DataFrame({(a, b): interaction_empirical_p(v1, v2, surv, num_perm=101)
for a, v1 in binary.iterrows()
for b, v2 in binary.iterrows()
if (a < b)
and fisher_exact_test(v1, v2).ix['p'] < (.05 / n_tests)
and fisher_exact_test(v1, v2).ix['odds_ratio'] != np.inf
and a[0] != b[0]}).T
int_pairs = s.ix[s.p < .1].sort('p')
int_associations = {}
for p, vals in int_pairs.iterrows():
combo = combine(binary.ix[p[0]], binary.ix[p[1]])
vec = combo == vals['interaction']
int_associations[p] = test(vec, surv, cov_df)
int_associations = pd.DataFrame(int_associations).T
return s, int_associations
def get_interactions(df, cov_df, surv, test):
binary = df[df.T.describe().ix['unique'] == 2]
#drop redundant features within a data-type
s = {
b
for i, (a, v1) in enumerate(binary.iterrows())
for j, (b, v2) in enumerate(binary.iterrows())
if (i < j) and a[0] == b[0]
and np.log2(fisher_exact_test(v1, v2)['odds_ratio']) > 4
}
binary = binary.ix[binary.index.diff(s)]
n_tests = (len(binary) * (len(binary) - 1)) / 2
s = pd.DataFrame({
(a, b): interaction_empirical_p(v1, v2, surv, num_perm=101)
for a, v1 in binary.iterrows() for b, v2 in binary.iterrows()
if (a < b) and fisher_exact_test(v1, v2).ix['p'] < (.05 / n_tests) and
fisher_exact_test(v1, v2).ix['odds_ratio'] != np.inf and a[0] != b[0]
}).T
int_pairs = s.ix[s.p < .1].sort('p')
int_associations = {}
for p, vals in int_pairs.iterrows():
combo = combine(binary.ix[p[0]], binary.ix[p[1]])
vec = combo == vals['interaction']
int_associations[p] = test(vec, surv, cov_df)
int_associations = pd.DataFrame(int_associations).T
return s, int_associations
def _interaction(a, b, surv):
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv, covariates=[a, b], formula='Surv(days, event) ~ a + b')
if fisher_exact_test(a, b)['odds_ratio'] > 1:
int_direction = 'both'
else:
int_direction = 'neither'
int_var = 1.*(combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
return pd.Series({'interaction': int_direction, 'p': LR_test(m2, m1)})
def get_interaction_simple(a, b, surv, int_direction='both'):
'''
Get test statistic (chi2 distributed) of interaction between
two event vectors.
'''
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv, covariates=[a, b],
formula='Surv(days, event) ~ a + b')
int_var = 1.*(combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
chi2 = extract_chi2(m2, m1)
return chi2
def _interaction(a, b, surv):
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv,
covariates=[a, b],
formula='Surv(days, event) ~ a + b')
if fisher_exact_test(a, b)['odds_ratio'] > 1:
int_direction = 'both'
else:
int_direction = 'neither'
int_var = 1. * (combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
return pd.Series({'interaction': int_direction, 'p': LR_test(m2, m1)})
def get_interaction_simple(a, b, surv, int_direction='both'):
'''
Get test statistic (chi2 distributed) of interaction between
two event vectors.
'''
a, b = a.copy(), b.copy()
a.name, b.name = 'a', 'b'
m1 = get_cox_ph(surv,
covariates=[a, b],
formula='Surv(days, event) ~ a + b')
int_var = 1. * (combine(a, b) == int_direction)
int_var.name = 'interaction'
m2 = get_cox_ph(surv, int_var)
chi2 = extract_chi2(m2, m1)
return chi2
