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
#for plotting purposes:
medians = []
means = []
xvals = []
#how many simulations chose bigger, how many chose smaller
mode_bigger = {}
#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 = [{}, {}]
for ind in [0, 1]:#index of half
sub_stats = {}
sub_stats = get_numpy_statistics( map(lambda x: x[ind], \
all_results_modes), \
# for plotting purposes:
medians = []
means = []
xvals = []
# how many simulations chose bigger, how many chose smaller
mode_bigger = {}
# 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 for left and all results 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 = [{}, {}]
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)
