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 hist_t(hdf, model, name=None):
"""
Plot histograms of the t values in <hdf> for each condition in
<model>.
If <name> is not None the plot is saved as <name>.pdf.
"""
meta = get_model_meta(hdf, model)
hist_list = []
for dm_col in meta['dm']:
# Make an instance RHist for the list.
hist = RHist(name=dm_col, decimals=1)
hist_list.append(hist)
# read_hdf_inc returns a generator so....
tdata = read_hdf_inc(hdf, '/' + model + '/t')
for ts in tdata:
# get the tvals for each instance of model
# and add them to the hist_list,
[hist_list[ii].add(ts[ii]) for ii in range(len(ts) - 1)]
## The last t in ts is the constant, which we
## do not want to plot.
# Create a fig, loop over the hist_list
# plotting each on fig.axes = 0.
fig = plt.figure()
fig.add_subplot(111)
colors = itertools.cycle(
['DarkGray', 'DarkBlue', 'DarkGreen', 'MediumSeaGreen'])
## Using html colors...
[h.plot(fig=fig, color=colors.next(), norm=True) for h in hist_list]
# Prettify the plot
ax = fig.axes[0]
ax.set_xlabel('t-values')
ax.set_ylabel('P(t)')
# Add vetical lines representing significance tresholds
ax.axvline(x=1.7822, label='p < 0.05', color='red', linewidth=4)
ax.axvline(x=2.6810, label='p < 0.01', color='red', linewidth=3)
ax.axvline(x=3.0545, label='p < 0.005', color='red', linewidth=2)
ax.axvline(x=4.3178, label='p < 0.0005', color='red', linewidth=1)
## tval lines assume N=12 subjects
plt.xlim(-10, 15)
plt.legend()
plt.title('{0} -- BOLD: {1}'.format(model, meta['bold']))
if name != None:
plt.savefig(name, format="pdf")
def test_RHist():
import numpy as np
import scipy.stats as stats
from bigstats.hist import RHist
xs = stats.norm.rvs(size=10000)
rh = RHist(name='test',decimals=1)
[rh.incr(x) for x in xs]
print('The normal distribution was sampled 10,000 times....')
print('Est. Mean (0): {0}'.format(rh.mean()))
print('Est. Var (1): {0}'.format(rh.var()))
print('Est. Stdev (0.01): {0}'.format(rh.stdev()))
print('N (10000): {0}'.format(rh.n()))
print('** Decimals should be precise to 1 place.**')
fig = rh.plot(fig=None,norm=True)
# TODO: Add a uniform and some asymmetric dist too.
