def gather_repeated_simulation_statistics(clab_fname, coordinate, cat):
'''
Gathers statistics from several repetitions of the same simulation.
Returns:
statistics - a dictionary: {chwila czasowa: {lewy: {stat1: , stat2: ...}, prawy: {}}, ...} lewy i prawy zamienione na 0/1
mode_bigger -
files - ids of consecutive time stamps, used in statistics dictionary
'''
import os
cats = map(lambda x: cat+"//"+x, os.listdir(cat))
#assume that in each catalogue there are files named the same, which correspond to one another
files = os.listdir(cats[0])
#how many simulations chose bigger, how many chose smaller
mode_bigger = {}
statistics = {} #
#list statistics for each file, gathering info from all catalogues:
for fname in sorted(files, key=lambda x: string2prefix_num(x)):
mode_bigger[fname] = [0, 0]
#all results_of_simulation for left and all results_of_simulation for right
all_results_modes = []
all_results_words = []
for cat in cats:
bigger_mode, smaller_mode, avg_wordnum1, avg_wordnum2 = \
get_mode_word_stats(cat+"/"+fname, clab_fname, coordinate)
if bigger_mode > smaller_mode:
mode_bigger[fname][0] += 1
elif bigger_mode < smaller_mode:
mode_bigger[fname][1] += 1
all_results_modes += [(bigger_mode, smaller_mode)]
all_results_words += [(avg_wordnum1, avg_wordnum2)]
#=====calculate statistics for current fname=====#
statistics[fname] = [{}, {}]
for ind in [0, 1]:#index of half
sub_stats = {}
sub_stats = get_numpy_statistics( map(lambda x: x[ind],
all_results_modes),
STATISTICS_MEASURES )
for key in sub_stats.iterkeys():
statistics[fname][ind]['mode_'+key] = sub_stats[key]
sub_stats = get_numpy_statistics( map(lambda x: x[ind],
all_results_words),
STATISTICS_MEASURES )
for key in sub_stats.iterkeys():
statistics[fname][ind]['wordnum_'+key] = sub_stats[key]
return statistics, mode_bigger, files
exit(1)
res_cat = sys.argv[3]#katalog z wynikami
print "res_cat:", res_cat
ensure_dir(res_cat)"""
position2coordinates = load_position2coordinates(chip_fname)
print "position2coordinates:", position2coordinates
min_x, max_x, min_y, max_y = get_borders_position2coordinates(position2coordinates)
print "min_x:", min_x
print "max_x:", max_x
print "min_y:", min_y
print "max_y:", max_y
files = get_files(cat)
matrices = {}
for fname in sorted(files, key=lambda x: string2prefix_num(x)):
######################################################################
#generate results for current fname
word_moda = get_moda_dict(cat, fname)
print "word_moda:", word_moda
#mtx = [[0]*(max_y-min_y+1)]*(max_x-min_x+1) VERY WRONG!! CHECK WHY
mtx = [[0 for _ in xrange(max_y-min_y+1)] for _ in xrange(max_x-min_x+1)]
for key, moda in word_moda.iteritems():
x, y = position2coordinates[key+1]
mtx[x][y] = moda
#print matrix(mtx)
#matrices[string2prefix_num(fname)] = ...
#scipy.misc.imsave(str(string2prefix_num(fname))+'.jpg', matrix(mtx))
ax = plt.gca()
ax.patch.set_alpha(0.0)
exit(1)
clab_fname = sys.argv[1]#plik z c-lab
if len(sys.argv) < 3:
print "Parameter 2: an integer corresponding to a coordinate by which colours are separated."
exit(1)
coordinate = int(sys.argv[2])#podzial wzgledem ktorej wspolrzednej
if len(sys.argv) < 4:
print "Parameter 3: catalogue, where results of a simulation are stored."
exit(1)
cat = sys.argv[3]#katalog z wynikami
statistics, mode_bigger, files = gather_repeated_simulation_statistics(clab_fname, coordinate, cat)
#=====print results=====#
for fname in sorted(files, key=lambda x: string2prefix_num(x)):
#=====print results for current fname=====#
print str(string2prefix_num(fname))+":"
#print header
res_line = ["Bigger_wins", "Smaller_wins", "|"] + \
map(lambda x: "mode_"+x, STATISTICS_MEASURES) + \
["|"] + \
map(lambda x: "word_number_"+x, STATISTICS_MEASURES)
print "\t".join([printable_elem(res) for res in res_line])
for ind in [0, 1]:#index of half
res_line = []
res_line.append( mode_bigger[fname][0] )
res_line.append( mode_bigger[fname][1] )
res_line.append( "|" )
print "Parameter 3: catalogue, where results of a simulation are stored."
exit(1)
cat = sys.argv[3]#katalog z wynikami
if len(sys.argv) < 5:
print "Parameter 4: measured statistic to plot, for example 'median'."
exit(1)
measured_statistic = sys.argv[4]
statistics, mode_bigger, files = gather_repeated_simulation_statistics(clab_fname, coordinate, cat)
x = []
y1 = []
y2 = []
ydiff = []
ydiffstd = []
for fname in sorted(files, key=lambda x: string2prefix_num(x)):
#=====print results for current fname=====#
x.append(string2prefix_num(fname))
for ind, y in enumerate([y1, y2]):
y.append(statistics[fname][ind]['mode_'+measured_statistic])
ydiffstd.append(statistics[fname][0]['mode_std']+statistics[fname][1]['mode_std'])
for i in xrange(len(x)):
ydiff.append(y1[i]-y2[i])
#===================================================================
#PLOT
#===================================================================
import numpy as np
import matplotlib.pyplot as plt
