def rank_test(data, value="Yes", tails="high"):
data.sort()
v_dist = []
non_v_dist = []
for d in data:
if d[1] == value:
v_dist.append(d[0])
else:
non_v_dist.append(d[0])
t, parametric_p, ts, non_parametric_p = mc_t_two_sample(v_dist, non_v_dist, tails=tails)
return t, parametric_p, non_parametric_p, v_dist, non_v_dist
def compare_alpha_diversities(rarefaction_lines, mapping_lines, category, depth,
test_type='nonparametric', num_permutations=999):
"""Compares alpha diversity values for differences per category treatment.
Notes:
Returns a defaultdict which as keys has the pairs of treatments being
compared, and as values, lists of (pval,tval) tuples for each comparison at
for a given iteration.
Inputs:
rarefaction_lines - list of lines, result of multiple rarefactions.
mapping_lines - list of lines, mapping file lines.
category - str, the category to be compared, eg 'Treatment' or 'Age'.
depth - int, depth of the rarefaction file to use.
test_type - str, the type of t-test to perform. Must be either
'parametric' or 'nonparametric'.
num_permutations - int, the number of Monte Carlo permutations to use if
test_type is 'nonparametric'.
"""
if test_type == 'nonparametric' and num_permutations < 1:
raise ValueError("Invalid number of permutations: %d. Must be greater "
"than zero." % num_permutations)
rarefaction_data = parse_rarefaction(rarefaction_lines)
mapping_data = parse_mapping_file_to_dict(mapping_lines)[0]
# samid_pairs, treatment_pairs are in the same order
samid_pairs, treatment_pairs = sampleId_pairs(mapping_data,
rarefaction_data, category)
# extract only rows of the rarefaction data that are at the given depth
rare_mat = array([row for row in rarefaction_data[3] if row[0]==depth])
# Average each col of the rarefaction mtx. Computing t test on averages over
# all iterations. Avoids more comps which kills signifigance.
rare_mat = (rare_mat.sum(0)/rare_mat.shape[0])[2:] #remove depth,iter cols
sids = rarefaction_data[0][3:] # 0-2 are header strings
results = {}
for sid_pair, treatment_pair in zip(samid_pairs, treatment_pairs):
# if there is only 1 sample for each treatment in a comparison, and mc
# using mc method, will error (e.g. mc_t_two_sample([1],[1]).
if len(sid_pair[0])==1 and len(sid_pair[1])==1:
t_key = '%s,%s' % (treatment_pair[0], treatment_pair[1])
results[t_key]= (None,None)
else:
pair0_indices = [sids.index(i) for i in sid_pair[0]]
pair1_indices = [sids.index(i) for i in sid_pair[1]]
t_key = '%s,%s' % (treatment_pair[0], treatment_pair[1])
i = rare_mat.take(pair0_indices)
j = rare_mat.take(pair1_indices)
# found discussion of how to quickly check an array for nan here:
# http://stackoverflow.com/questions/6736590/fast-check-for-nan-in-numpy
if isnan(np_min(i)) or isnan(np_min(j)):
results[t_key]= (None,None)
continue
if test_type == 'parametric':
obs_t, p_val = t_two_sample(i,j)
elif test_type == 'nonparametric':
obs_t, _, _, p_val = mc_t_two_sample(i,j,
permutations=num_permutations)
if p_val != None:
p_val = float(format_p_value_for_num_iters(p_val,
num_iters=num_permutations))
elif p_val == None: #None will error in format_p_val
obs_t, p_val = None, None
else:
raise ValueError("Invalid test type '%s'." % test_type)
results[t_key]= (obs_t,p_val)
return results
def compare_alpha_diversities(rarefaction_lines, mapping_lines,
category, depth, test_type='nonparametric',
num_permutations=999):
"""compares alpha diversities
inputs:
rarefaction_file - rarefaction file which gives scores for
various rarefactions and depths
mapping_file - file that has ID's and categories that the ID's
fall in
category - the category to be compared, is a string
depth - the depth of the rarefaction_file to use, is an integer
test_type - the type of t-test to perform, is a string. Must be either
'parametric' or 'nonparametric'
num_permutations - the number of Monte Carlo permutations to use if
test_type is 'nonparametric', is an integer
outputs:
results - a nested dictionary which specifies the category as
the top level key, and as its value, dictionaries which give the
results of the t_two_sample test for all unique pairs of values
in the specified category
"""
if test_type == 'nonparametric' and num_permutations < 1:
raise ValueError("Invalid number of permutations: %d. Must be greater "
"than zero." % num_permutations)
rarefaction_data = parse_rarefaction(rarefaction_lines)
mapping_data = parse_mapping_file_to_dict(mapping_lines)[0]
value_pairs = make_value_pairs_from_category(mapping_data, category)
category_values_Ids = make_category_values_Id_dict(mapping_data,
category)
SampleId_pairs = map_category_value_pairs_to_Ids(value_pairs,
category_values_Ids)
map_from_Id_to_col = make_SampleIds_rarefaction_columns_dict(
rarefaction_data)
reduced_rarefaction_mtx = extract_rarefaction_scores_at_depth(depth,
rarefaction_data)
results = {category:{}}
for pair in range(len(SampleId_pairs)):
# Must flatten the matrix because t_two_sample only operates on
# non-nested sequences (otherwise we'll get the wrong degrees of
# freedom).
i=(convert_SampleIds_to_rarefaction_mtx(SampleId_pairs[pair][0],
reduced_rarefaction_mtx,
map_from_Id_to_col)).flatten()
j=(convert_SampleIds_to_rarefaction_mtx(SampleId_pairs[pair][1],
reduced_rarefaction_mtx,
map_from_Id_to_col)).flatten()
if test_type == 'parametric':
obs_t, p_val = t_two_sample(i,j)
elif test_type == 'nonparametric':
obs_t, _, _, p_val = mc_t_two_sample(i,j,
permutations=num_permutations)
p_val = format_p_value_for_num_iters(p_val, num_permutations)
else:
raise ValueError("Invalid test type '%s'." % test_type)
results[category][(str(value_pairs[pair][0]),
str(value_pairs[pair][1]))] = obs_t, p_val
return results
