本文整理匯總了Python中statsmodels.stats.multitest.multipletests方法的典型用法代碼示例。如果您正苦於以下問題:Python multitest.multipletests方法的具體用法?Python multitest.multipletests怎麽用?Python multitest.multipletests使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類statsmodels.stats.multitest
的用法示例。
在下文中一共展示了multitest.multipletests方法的6個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: correction
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def correction(self, method='hommel', alpha=None):
print('foo bar')
if alpha is None:
print('alpha is none')
alpha = self.alpha
print([enr.pvalue for enr in self.enrichments.values()])
pvals_corr = smm.multipletests(
[enr.pvalue for enr in self.enrichments.values()],
alpha=alpha,
method=method)[1]
for i, k in zip(xrange(len(pvals_corr)), self.enrichments.keys()):
setattr(self.enrichments[k], 'pval_adj', pvals_corr[i])
示例2: t_test_multi
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def t_test_multi(result, contrasts, method='hs', alpha=0.05, ci_method=None,
contrast_names=None):
"""perform t_test and add multiplicity correction to results dataframe
Parameters
----------
result results instance
results of an estimated model
contrasts : ndarray
restriction matrix for t_test
method : string or list of strings
method for multiple testing p-value correction, default is'hs'.
alpha : float
significance level for multiple testing reject decision.
ci_method : None
not used yet, will be for multiplicity corrected confidence intervals
contrast_names : list of strings or None
If contrast_names are provided, then they are used in the index of the
returned dataframe, otherwise some generic default names are created.
Returns
-------
res_df : pandas DataFrame
The dataframe contains the results of the t_test and additional columns
for multiplicity corrected p-values and boolean indicator for whether
the Null hypothesis is rejected.
"""
tt = result.t_test(contrasts)
res_df = tt.summary_frame(xname=contrast_names)
if type(method) is not list:
method = [method]
for meth in method:
mt = multipletests(tt.pvalue, method=meth, alpha=alpha)
res_df['pvalue-%s' % meth] = mt[1]
res_df['reject-%s' % meth] = mt[0]
return res_df
示例3: pval_corrected
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def pval_corrected(self, method=None):
'''p-values corrected for multiple testing problem
This uses the default p-value correction of the instance stored in
``self.multitest_method`` if method is None.
'''
import statsmodels.stats.multitest as smt
if method is None:
method = self.multitest_method
#TODO: breaks with method=None
return smt.multipletests(self.pvals_raw, method=method)[1]
示例4: _transform
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def _transform(self, result):
p = result.maps['p']
_, p_corr, _, _ = mc.multipletests(p, alpha=0.05, method=self.method,
is_sorted=False)
corr_maps = {'p': p_corr}
self._generate_secondary_maps(result, corr_maps)
return corr_maps
示例5: get_score_df
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def get_score_df(self, correction_method=None):
'''
Computes Mann Whitney corrected p, z-values. Falls back to normal approximation when numerical limits are reached.
:param correction_method: str or None, correction method from statsmodels.stats.multitest.multipletests
'fdr_bh' is recommended.
:return: pd.DataFrame
'''
X = self._get_X().astype(np.float64)
X = X / X.sum(axis=1)
cat_X, ncat_X = self._get_cat_and_ncat(X)
def normal_apx(u, x, y):
# from https://stats.stackexchange.com/questions/116315/problem-with-mann-whitney-u-test-in-scipy
m_u = len(x) * len(y) / 2
sigma_u = np.sqrt(len(x) * len(y) * (len(x) + len(y) + 1) / 12)
z = (u - m_u) / sigma_u
return 2*norm.cdf(z)
scores = []
for i in range(cat_X.shape[1]):
cat_list = cat_X.T[i].A1
ncat_list = ncat_X.T[i].A1
try:
if cat_list.mean() > ncat_list.mean():
mw = mannwhitneyu(cat_list, ncat_list, alternative='greater')
if mw.pvalue in (0, 1):
mw.pvalue = normal_apx(mw.staistic, cat_list, ncat_list)
scores.append({'mwu': mw.statistic, 'mwu_p': mw.pvalue, 'mwu_z': norm.isf(float(mw.pvalue)), 'valid':True})
else:
mw = mannwhitneyu(ncat_list, cat_list, alternative='greater')
if mw.pvalue in (0, 1):
mw.pvalue = normal_apx(mw.staistic, ncat_list, cat_list)
scores.append({'mwu': -mw.statistic, 'mwu_p': 1 - mw.pvalue, 'mwu_z': 1. - norm.isf(float(mw.pvalue)), 'valid':True})
except:
scores.append({'mwu': 0, 'mwu_p': 0, 'mwu_z': 0, 'valid':False})
score_df = pd.DataFrame(scores, index=self.corpus_.get_terms()).fillna(0)
if correction_method is not None:
from statsmodels.stats.multitest import multipletests
for method in ['mwu']:
valid_pvals = score_df[score_df.valid].mwu_p
valid_pvals_abs = np.min([valid_pvals, 1-valid_pvals], axis=0)
valid_pvals_abs_corr = multipletests(valid_pvals_abs, method=correction_method)[1]
score_df[method + '_p_corr'] = 0.5
valid_pvals_abs_corr[valid_pvals > 0.5] = 1. - valid_pvals_abs_corr[valid_pvals > 0.5]
valid_pvals_abs_corr[valid_pvals < 0.5] = valid_pvals_abs_corr[valid_pvals < 0.5]
score_df.loc[score_df.valid, method + '_p_corr'] = valid_pvals_abs_corr
score_df[method + '_z'] = -norm.ppf(score_df[method + '_p_corr'])
return score_df
示例6: compute_statistics
# 需要導入模塊: from statsmodels.stats import multitest [as 別名]
# 或者: from statsmodels.stats.multitest import multipletests [as 別名]
def compute_statistics(self, method, corr_method, n_genes_user, rankby_abs, **kwds):
if method in {'t-test', 't-test_overestim_var'}:
generate_test_results = self.t_test(method)
elif method == 'wilcoxon':
generate_test_results = self.wilcoxon()
elif method == 'logreg':
generate_test_results = self.logreg(**kwds)
for group_index, scores, pvals in generate_test_results:
group_name = str(self.groups_order[group_index])
if n_genes_user is not None:
scores_sort = np.abs(scores) if rankby_abs else scores
global_indices = _select_top_n(scores_sort, n_genes_user)
first_col = 'names'
else:
global_indices = slice(None)
first_col = 'scores'
if self.stats is None:
idx = pd.MultiIndex.from_tuples([(group_name, first_col)])
self.stats = pd.DataFrame(columns=idx)
if n_genes_user is not None:
self.stats[group_name, 'names'] = self.var_names[global_indices]
self.stats[group_name, 'scores'] = scores[global_indices]
if pvals is not None:
self.stats[group_name, 'pvals'] = pvals[global_indices]
if corr_method == 'benjamini-hochberg':
from statsmodels.stats.multitest import multipletests
pvals[np.isnan(pvals)] = 1
_, pvals_adj, _, _ = multipletests(
pvals, alpha=0.05, method='fdr_bh'
)
elif corr_method == 'bonferroni':
pvals_adj = np.minimum(pvals * n_genes, 1.0)
self.stats[group_name, 'pvals_adj'] = pvals_adj[global_indices]
if self.means is not None:
mean_group = self.means[group_index]
if self.ireference is None:
mean_rest = self.means_rest[group_index]
else:
mean_rest = self.means[self.ireference]
foldchanges = (self.expm1_func(mean_group) + 1e-9) / (
self.expm1_func(mean_rest) + 1e-9
) # add small value to remove 0's
self.stats[group_name, 'logfoldchanges'] = np.log2(
foldchanges[global_indices]
)
if n_genes_user is None:
self.stats.index = self.var_names
# TODO: Make arguments after groupby keyword only