def main(hdf, name):
f = open('{0}.csv'.format(name), 'w')
csvw = csv.writer(f)
# A header for the table
head = ["tau", "p_tau",
"r", "p_r",
"rho", "p_rho",
"cond",
"boldmeta",
"model"]
csvw.writerow(head)
models = get_model_names(hdf)
for model in models:
# Get model meta data
meta = get_model_meta(hdf, model)
boldmeta = "_".join([str(b) for b in meta["bold"]])
## meta['bold'] can be a list
## but we need a string....
# Get all the design matrices and
# Get all the bold signals as a 1d array
dm = np.array(read_hdf(hdf, '/' + model + '/dm'))
bold = np.array(read_hdf(hdf, '/' + model + '/bold')).flatten()
# Loop over the dm cols in the dm:
# axis 1 is a sim index/count,
# axis 2 is the dm row
# axis 3 is the dm cols
for jj in range(dm.shape[2]):
# Get all this cols in a 1d array
# matching what was done to
# bold above
x1 = dm[:, :, jj].flatten()
x1name = meta["dm"][jj]
# And calc the corr between
# the two 1d arrays
tau, p_tau = kendalltau(bold, x1)
r, p_r = pearsonr(bold, x1)
rho, p_rho = spearmanr(bold, x1)
# then write it all out.
csvw.writerow([
tau, p_tau,
r, p_r,
rho, p_rho,
x1name,
boldmeta,
model])
f.close()
def main(hdf, name):
# Create a csv file to tabulate into
f = open('{0}.csv'.format(name), 'w')
csvw = csv.writer(f)
# Make a header for the table
header = ["x", "count", "cond"]
csvw.writerow(header)
conds = set(["acc", "value", "rpe", "p", "rand", "box"])
# Find a dmcol from models,
# pick the first model with
# that dm cond. Conds across
# models are the same.
locations = {}
models = get_model_names(hdf)
for model in models:
# Get model meta data and compare it too conds
meta = get_model_meta(hdf, model)
for ii, dmname in enumerate(meta["dm"]):
if dmname in conds:
locations[dmname] = (model, ii)
conds.remove(dmname)
## conds loses elements!
# If conds is empty, stop
if not conds:
print("All conds found. {0}".format(model))
break
# Get each dm's data and pick a col using pos;
# pos matches cond.
dmdata = {}
for cond, loci in locations.items():
print("Getting {0}".format(cond))
model, pos = loci
dm = np.array(read_hdf(hdf, '/' + model + '/dm'))
dmdata[cond] = dm[:,:,pos].flatten()
# Create a histogram then write it out.
for cond, data in dmdata.items():
print("Histogramming {0}".format(cond))
# Instantiate a RHist instance and
# use it to make a histogram
hist = RHist(name=cond, decimals=2)
[hist.add(x) for x in data]
# Tell that textfile a tale.
[csvw.writerow([k, v, cond]) for k, v in hist.h.items()]
f.close()
def create_hist_list(hdf, model, stat):
""" Create a list of Rhist (histogram) objects for <model> and
<stat> in the given <hdf>.
If <stat> has only one entry (as is the case for 'aic') the list will have
only one entry. If however <stat> has n entries per model (like't')
the list will have n-1 entries. As n matches the number of columns in
the design matrix, the rightmost will always correspond to the dummy
predictor and is therefore discarded. """
hist_list = [] ## A list of RHist objects.
meta = get_model_meta(hdf, model) ## metadata for naming
# A handle on the hdf data
hdfdata = read_hdf(hdf, '/' + model + '/' + stat)
# Loop over the nodes, adding the data
# for each to a RHist.
for node in hdfdata:
# Some data will be list-like
# so try to iterate, if that fails
# assume the data is a single number
try:
for ii in range(len(node) - 1):
# Init entries in hist_list as needed
try:
hist_list[ii].add(node[ii])
except IndexError:
hist_list.append(RHist(name=meta['dm'][ii], decimals=2))
hist_list[ii].add(node[ii])
except TypeError:
# Assume a number so hist_list has only one
# entry (i.e. 0).
#
# Init entries in hist_list as needed
try:
hist_list[0].add(node)
except IndexError:
hist_list.append(RHist(name=stat, decimals=2))
hist_list[0].add(node)
return hist_list
def create_hist_list(hdf, model, stat):
""" Create a list of Rhist (histogram) objects for <model> and
<stat> in the given <hdf>.
If <stat> has only one entry (as is the case for 'aic') the list will have
only one entry. If however <stat> has n entries per model (like't')
the list will have n-1 entries. As n matches the number of columns in
the design matrix, the rightmost will always correspond to the dummy
predictor and is therefore discarded. """
hist_list = [] ## A list of RHist objects.
meta = get_model_meta(hdf, model) ## metadata for naming
# A handle on the hdf data
hdfdata = read_hdf(hdf, '/' + model + '/' + stat)
# Loop over the nodes, adding the data
# for each to a RHist.
for node in hdfdata:
# Some data will be list-like
# so try to iterate, if that fails
# assume the data is a single number
try:
for ii in range(len(node)-1):
# Init entries in hist_list as needed
try:
hist_list[ii].add(node[ii])
except IndexError:
hist_list.append(RHist(name=meta['dm'][ii], decimals=2))
hist_list[ii].add(node[ii])
except TypeError:
# Assume a number so hist_list has only one
# entry (i.e. 0).
#
# Init entries in hist_list as needed
try:
hist_list[0].add(node)
except IndexError:
hist_list.append(RHist(name=stat, decimals=2))
hist_list[0].add(node)
return hist_list
def main(hdf, name):
# Create a csv file to tabulate into
f = open('{0}.csv'.format(name), 'w')
csvw = csv.writer(f)
# A header for the table
head = ["tau", "p_tau",
"r", "p_r",
"rho", "p_rho",
"cond0",
"cond1"]
csvw.writerow(head)
conds = set(["acc", "value", "rpe", "p", "rand", "box"])
pairs = permutations(conds, 2)
# Find a dmcol from models,
# pick the first model with
# that dm cond. Conds across
# models are the same.
locations = {}
models = get_model_names(hdf)
for model in models:
# Get model meta data and compare it too conds
meta = get_model_meta(hdf, model)
for ii, dmname in enumerate(meta["dm"]):
if dmname in conds:
locations[dmname] = (model, ii)
conds.remove(dmname)
## conds loses elements!
# If conds is empty, stop
if not conds:
print("All conds found by {0}".format(model))
break
# Get the data
dmdata = {}
for cond, loci in locations.items():
print("Getting {0}".format(cond))
model, pos = loci
dm = np.array(read_hdf(hdf, '/' + model + '/dm'))
## Get all the dm's data
dmdata[cond] = dm[:,:,pos].flatten()
## pick a col using pos, as this is
## the data matching name
# Calculate all pair-wise correlations
for pair in pairs:
print("Correlate: {0}".format(pair))
cond0, cond1 = pair
x0 = dmdata[cond0]
x1 = dmdata[cond1]
tau, p_tau = kendalltau(x0, x1)
r, p_r = pearsonr(x0, x1)
rho, p_rho = spearmanr(x0, x1)
# then write it all out.
csvw.writerow([
tau, p_tau,
r, p_r,
rho, p_rho,
cond0,
cond1])
f.close()
