def main():
import numpy as np
from rosetta_score_files import how_many_purples_in_file
import os
import re
global coh_names, doc_names
design_list = ['ct11', 'ct12', 'ct13', 'ct15', 'ct16', 'ct17', 'ct29', 'ct31', 'ct33', 'ct36', 'ct38', 'ct41',
'ct44', 'ct45', 'ct46', 'ct47', 'ct48', 'ct49', 'ct50', 'ct51', 'ct52', 'ct53', 'ct54', 'ct55',
'ct59']
# df = DataFrame({name: Series([-1 * len(design_list)], index=design_list) for name in design_list})
mtrx = np.zeros([len(design_list), len(design_list)], dtype=int)
score_file_list = [x for x in os.listdir(
'/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/')
if re.match('.*\.score', x)]
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
purple_num = int(how_many_purples_in_file(
'/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/' + score_file))
mtrx[design_list.index(coh_name)][design_list.index(doc_name)] = 1 if purple_num >= 12 else 0
dof_vec = find_degree_vector(mtrx)
print dof_vec
print mtrx
mtrx = clean_all_zeros(mtrx)
while not are_all_ones(dof_vec):
new_all_ones(dof_vec)
to_remove = dof_vec[-1].values()[0]
mtrx = remove_from_matrix(mtrx, to_remove)
mtrx = clean_all_zeros(mtrx)
dof_vec = find_degree_vector(mtrx)
# break
print mtrx
print dof_vec
print coh_names
print doc_names
def main():
from pandas import DataFrame, Series
from rosetta_score_files import how_many_purples_in_file
import os
import re
design_list = ['ct11', 'ct12', 'ct13', 'ct15', 'ct16', 'ct17', 'ct29', 'ct31', 'ct33', 'ct36', 'ct38', 'ct41',
'ct44', 'ct45', 'ct46', 'ct47', 'ct48', 'ct49', 'ct50', 'ct51', 'ct52', 'ct53', 'ct54', 'ct55',
'ct59']
# df = DataFrame({name: Series([-1 * len(design_list)], index=design_list) for name in design_list})
score_file_list = [x for x in os.listdir('.') if re.match('.*\.score', x)]
coh_name_list = sorted(list(set(['_'.join(a.split('_VS_')[0].split('_')[1:]) for a in score_file_list])))
doc_name_list = sorted(list(set(['_'.join(a.split('_VS_')[1].split('_')[:-1]) for a in score_file_list])))
# print coh_name_list
# print doc_name_list
df = DataFrame({coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list) for coh_name in coh_name_list})
for score_file in score_file_list:
# coh_name = score_file.split('_')[1]
# doc_name = score_file.split('_')[3]
coh_name = '_'.join(score_file.split('_VS_')[0].split('_')[1:])
doc_name = '_'.join(score_file.split('_VS_')[1].split('_')[:-1])
# print coh_name, doc_name
purple_num = int(how_many_purples_in_file(score_file))
df[coh_name][doc_name] = purple_num
# pandas.set_option('display.max_columns', None)
# print df
show_prediction_heat_map(df.copy())
def main():
from pandas import DataFrame, Series
from rosetta_score_files import how_many_purples_in_file
import os
import re
# from matplotlib import pyplot as plt
import networkx as nx
score_file_list = [x for x in os.listdir('./')
if re.match('.*\.score', x)]
coh_name_list = sorted(list(set([a.split('_')[1] for a in score_file_list])))
doc_name_list = sorted(list(set([a.split('_')[3] for a in score_file_list])))
df = DataFrame({coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list) for coh_name in coh_name_list})
df_true_score = DataFrame({coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list) for coh_name in coh_name_list})
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
purple_num = int(how_many_purples_in_file('./'+score_file))
df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
df_true_score[coh_name][doc_name] = purple_num
G = nx.Graph()
# labels = {}
for coh in coh_name_list:
for doc in doc_name_list:
if df[coh][doc] == 1:
G.add_node((coh, doc))
# labels[(coh, doc)] = '%s<>%s' % (coh, doc)
for c1, d1 in G.nodes_iter():
for c2, d2 in G.nodes_iter():
if df[c1][d2] == 0 and df[c2][d1] == 0:
G.add_edge((c1, d1), (c2, d2))
# pos = nx.spring_layout(G)
# for node in labels:
# plt.annotate(labels[node], xy=pos[node])
cliques = [a for a in nx.find_cliques(G)]
max_len = max([len(a) for a in cliques])
max_cliques = [a for a in cliques if len(a) == max_len]
print len(max_cliques)
clique_coh_list, clique_doc_list = coh_doc_set_span_maximal_cliques(max_cliques)
print 'cohs that span entire clique list', clique_coh_list
print 'docs that span entire clique list', clique_doc_list
# best_ranker, best_rank = best_clique_by_overlapp(max_cliques, clique_coh_list, clique_doc_list)
best_ranker, best_rank = best_clique_by_purples(max_cliques, df_true_score)
print 'best ranker\n', best_ranker, best_rank
### find least similar clique:
min_similarity = min(clique_similarity(best_ranker, a) for a in max_cliques)
min_similars = []
for clique in max_cliques:
similarity = clique_similarity(best_ranker, clique)
if similarity == min_similarity:
min_similars.append(clique)
best_min_similar_ranker, best_min_similar_rank = best_clique_by_purples(min_similars, df_true_score)
print best_min_similar_ranker, best_min_similar_rank
print min_similarity
### show true-score heat map for the best ranks clique:
show_clique_heatmap(best_ranker, df_true_score, coh_name_list, doc_name_list)
### show true-score heat map for the least similar clique:
show_clique_heatmap(best_min_similar_ranker, df_true_score, coh_name_list, doc_name_list)
def main():
import numpy as np
from rosetta_score_files import how_many_purples_in_file
import os
import re
global coh_names, doc_names
design_list = [
'ct11', 'ct12', 'ct13', 'ct15', 'ct16', 'ct17', 'ct29', 'ct31', 'ct33',
'ct36', 'ct38', 'ct41', 'ct44', 'ct45', 'ct46', 'ct47', 'ct48', 'ct49',
'ct50', 'ct51', 'ct52', 'ct53', 'ct54', 'ct55', 'ct59'
]
# df = DataFrame({name: Series([-1 * len(design_list)], index=design_list) for name in design_list})
mtrx = np.zeros([len(design_list), len(design_list)], dtype=int)
score_file_list = [
x for x in os.listdir(
'/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/'
) if re.match('.*\.score', x)
]
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
purple_num = int(
how_many_purples_in_file(
'/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/'
+ score_file))
mtrx[design_list.index(coh_name)][design_list.index(
doc_name)] = 1 if purple_num >= 12 else 0
dof_vec = find_degree_vector(mtrx)
print dof_vec
print mtrx
mtrx = clean_all_zeros(mtrx)
while not are_all_ones(dof_vec):
new_all_ones(dof_vec)
to_remove = dof_vec[-1].values()[0]
mtrx = remove_from_matrix(mtrx, to_remove)
mtrx = clean_all_zeros(mtrx)
dof_vec = find_degree_vector(mtrx)
# break
print mtrx
print dof_vec
print coh_names
print doc_names
def main():
from pandas import DataFrame, Series
from rosetta_score_files import how_many_purples_in_file
import os
import re
# design_list = ['ct11', 'ct12', 'ct13', 'ct15', 'ct16', 'ct17', 'ct29', 'ct31', 'ct33', 'ct36', 'ct38', 'ct41',
# 'ct44', 'ct45', 'ct46', 'ct47', 'ct48', 'ct49', 'ct50', 'ct51', 'ct52', 'ct53', 'ct54', 'ct55',
# 'ct59']
# df = DataFrame({name: Series([-1], index=design_list) for name in design_list})
# score_file_list = [x for x in os.listdir('/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/')
# if re.match('.*\.score', x)]
score_file_list = [x for x in os.listdir('./') if re.match('.*\.score', x)]
coh_name_list = sorted(
list(set([a.split('_')[1] for a in score_file_list])))
doc_name_list = sorted(
list(set([a.split('_')[3] for a in score_file_list])))
df = DataFrame({
coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list)
for coh_name in coh_name_list
})
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
# purple_num = int(how_many_purples_in_file('/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/'+score_file))
# df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
purple_num = int(how_many_purples_in_file('./' + score_file))
df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
i = 1
while not all_dof_ones(df):
dof_vec = find_degree_vector(df)
df = remove_from_df(df, dof_vec[-1].values()[0])
df = clean_zeroes(df)
print 'printing dof for %i time' % i
print dof_vec[-1]
print find_degree_vector(df)
if i > -1:
show_prediction_heat_map(df)
i += 1
def main():
from pandas import DataFrame, Series
from rosetta_score_files import how_many_purples_in_file
import os
import re
# design_list = ['ct11', 'ct12', 'ct13', 'ct15', 'ct16', 'ct17', 'ct29', 'ct31', 'ct33', 'ct36', 'ct38', 'ct41',
# 'ct44', 'ct45', 'ct46', 'ct47', 'ct48', 'ct49', 'ct50', 'ct51', 'ct52', 'ct53', 'ct54', 'ct55',
# 'ct59']
# df = DataFrame({name: Series([-1], index=design_list) for name in design_list})
# score_file_list = [x for x in os.listdir('/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/')
# if re.match('.*\.score', x)]
score_file_list = [x for x in os.listdir('./')
if re.match('.*\.score', x)]
coh_name_list = sorted(list(set([a.split('_')[1] for a in score_file_list])))
doc_name_list = sorted(list(set([a.split('_')[3] for a in score_file_list])))
df = DataFrame({coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list) for coh_name in coh_name_list})
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
# purple_num = int(how_many_purples_in_file('/Users/jonathan/eden/no_backup/designs/Ct_8parts_10.2/prediction/results/'+score_file))
# df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
purple_num = int(how_many_purples_in_file('./'+score_file))
df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
i = 1
while not all_dof_ones(df):
dof_vec = find_degree_vector(df)
df = remove_from_df(df, dof_vec[-1].values()[0])
df = clean_zeroes(df)
print 'printing dof for %i time' % i
print dof_vec[-1]
print find_degree_vector(df)
if i > -1:
show_prediction_heat_map(df)
i += 1
def main():
from pandas import DataFrame, Series
from rosetta_score_files import how_many_purples_in_file
import os
import re
# from matplotlib import pyplot as plt
import networkx as nx
score_file_list = [x for x in os.listdir('./') if re.match('.*\.score', x)]
coh_name_list = sorted(
list(set([a.split('_')[1] for a in score_file_list])))
doc_name_list = sorted(
list(set([a.split('_')[3] for a in score_file_list])))
df = DataFrame({
coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list)
for coh_name in coh_name_list
})
df_true_score = DataFrame({
coh_name: Series([-1 * len(doc_name_list)], index=doc_name_list)
for coh_name in coh_name_list
})
for score_file in score_file_list:
coh_name = score_file.split('_')[1]
doc_name = score_file.split('_')[3]
purple_num = int(how_many_purples_in_file('./' + score_file))
df[coh_name][doc_name] = 1 if purple_num >= 10 else 0
df_true_score[coh_name][doc_name] = purple_num
G = nx.Graph()
# labels = {}
for coh in coh_name_list:
for doc in doc_name_list:
if df[coh][doc] == 1:
G.add_node((coh, doc))
# labels[(coh, doc)] = '%s<>%s' % (coh, doc)
for c1, d1 in G.nodes_iter():
for c2, d2 in G.nodes_iter():
if df[c1][d2] == 0 and df[c2][d1] == 0:
G.add_edge((c1, d1), (c2, d2))
# pos = nx.spring_layout(G)
# for node in labels:
# plt.annotate(labels[node], xy=pos[node])
cliques = [a for a in nx.find_cliques(G)]
max_len = max([len(a) for a in cliques])
max_cliques = [a for a in cliques if len(a) == max_len]
print len(max_cliques)
clique_coh_list, clique_doc_list = coh_doc_set_span_maximal_cliques(
max_cliques)
print 'cohs that span entire clique list', clique_coh_list
print 'docs that span entire clique list', clique_doc_list
# best_ranker, best_rank = best_clique_by_overlapp(max_cliques, clique_coh_list, clique_doc_list)
best_ranker, best_rank = best_clique_by_purples(max_cliques, df_true_score)
print 'best ranker\n', best_ranker, best_rank
### find least similar clique:
min_similarity = min(
clique_similarity(best_ranker, a) for a in max_cliques)
min_similars = []
for clique in max_cliques:
similarity = clique_similarity(best_ranker, clique)
if similarity == min_similarity:
min_similars.append(clique)
best_min_similar_ranker, best_min_similar_rank = best_clique_by_purples(
min_similars, df_true_score)
print best_min_similar_ranker, best_min_similar_rank
print min_similarity
### show true-score heat map for the best ranks clique:
show_clique_heatmap(best_ranker, df_true_score, coh_name_list,
doc_name_list)
### show true-score heat map for the least similar clique:
show_clique_heatmap(best_min_similar_ranker, df_true_score, coh_name_list,
doc_name_list)
