def generate_plots_from_pickle(limit_to, report_dir, target_profiles, profile2def, gid2arcog_cdd, neighborhood_files_path):
data_path = os.path.join(gv.project_data_path, 'Archea/pickle/')
fname = os.path.join(data_path, str(limit_to), 'pentaplets_merged_within.p.bz2')
pentaplets = t.load_compressed_pickle(fname)
# fname = os.path.join(data_path, str(limit_to), 'quadruplets_merged_within.p.bz2')
# quadruplets = t.load_compressed_pickle(fname)
# fname = os.path.join(data_path, str(limit_to), 'triplets_merged_within.p.bz2')
# triplets = t.load_compressed_pickle(fname)
# fname = os.path.join(data_path, str(limit_to), 'duplets_merged_within.p.bz2')
# duplets = t.load_compressed_pickle(fname)
print 'Generationg reports for within orders merged lists'
report_files_dir = os.path.join(gv.project_data_path, 'Archea/reports/merged_within_orders/', report_dir)
if not os.path.exists(report_files_dir):
os.mkdir(report_files_dir)
for i, kplet_pool in zip([5, 4, 3, 2], [pentaplets, pentaplets, pentaplets, pentaplets]):
print 'Starting for', i
j = 0
profile2counts_pool = dist.get_flank_distributions(kplet_pool, neighborhood_files_path, target_profiles)
for k in range(len(kplet_pool)):
kplet_sublist = kplet_pool[k]
cur_reports_folder = os.path.join(report_files_dir, str(i))
if not os.path.exists(cur_reports_folder):
os.mkdir(cur_reports_folder)
src2org, file_summaries, community, community_count, community_count_with_flanks = \
merging.merge_into_file_summaries(kplet_sublist,
neighborhood_files_path,
file2src_src2org_map,
'archaea')
if not src2org:
continue
xls_file_name = os.path.join(cur_reports_folder, "%d_%d.xls" % (j+1, i))
class2counts, class2profiles = merging.arcog_profile_count_into_class_count(community_count)
class2counts_flank, class2profiles_flank = merging.arcog_profile_count_into_class_count(community_count_with_flanks)
profile2counts = profile2counts_pool[k]
j += 1
params = dict()
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
params['class2counts'] = class2counts
params['class2profiles'] = class2profiles
params['class2counts_flank'] = class2counts_flank
params['profile2counts'] = profile2counts
r.write_to_xls(params)
def generate_plots_from_pickle(limit_to, report_dir, target_profiles,
profile2def, gid2arcog_cdd,
neighborhood_files_path):
data_path = os.path.join(gv.project_data_path, 'Bacteria/pickle/')
fname = os.path.join(data_path, str(limit_to),
'pentaplets_merged_within.p.bz2')
pentaplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to),
'quadruplets_merged_within.p.bz2')
quadruplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to),
'triplets_merged_within.p.bz2')
triplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to),
'duplets_merged_within.p.bz2')
duplets = t.load_compressed_pickle(fname)
print 'Generationg reports for across orders merged lists'
flank_report_fnames = ['pentaplets_flank_counts.xls', 'quadruplets_flank_counts.xls', \
'triplets_flank_counts.xls', 'duplets_flank_counts.xls']
kplets = [pentaplets, quadruplets, triplets, duplets]
titles = ['Pentaplets', 'Quadruplets', 'Triplets', 'Duplets']
report_files_dir = os.path.join(gv.project_data_path,
'Bacteria/reports/merged_within_orders/',
report_dir)
for i in range(len(flank_report_fnames)):
_fname = flank_report_fnames[i]
_kplet_list = kplets[i]
_title = titles[i]
flank_counts, cog2gids, gid2weight = dist.get_flank_distributions(
_kplet_list, neighborhood_files_path, target_profiles)
universal_flank_counts = t.merge_dict_set_list(cog2gids, gid2weight)
params = dict()
params['xls_file_name'] = os.path.join(report_files_dir, _fname)
params['profile2def'] = profile2def
params['flank_counts'] = universal_flank_counts
params['title'] = _title
params['target_profiles'] = target_profiles
r.write_flanking_count_xls(params)
sys.exit()
if not os.path.exists(report_files_dir):
os.mkdir(report_files_dir)
for i, kplet_pool in zip([5, 4, 3, 2],
[pentaplets, quadruplets, triplets, duplets]):
print i
j = 0
# flank_counts_pool = dist.get_flank_distributions(kplet_pool, neighborhood_files_path, target_profiles)
for k in range(len(kplet_pool)):
kplet_sublist = kplet_pool[k]
cur_reports_folder = os.path.join(report_files_dir, str(i))
if not os.path.exists(cur_reports_folder):
os.mkdir(cur_reports_folder)
src2org, file_summaries, community, community_count, community_count_with_flanks\
= merging.merge_into_file_summaries(kplet_sublist,
neighborhood_files_path,
file2src_src2org_map)
if not src2org:
continue
xls_file_name = os.path.join(cur_reports_folder,
"%d_%d.xls" % (j + 1, i))
class2counts, class2profiles = merging.cdd_profile_count_into_class_count(
community_count)
class2counts_flank, class2profiles_flank = merging.cdd_profile_count_into_class_count(
community_count_with_flanks)
# profile2counts = flank_counts_pool[k]
j += 1
params = dict()
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
params['class2counts'] = class2counts
params['class2profiles'] = class2profiles
params['class2counts_flank'] = class2counts_flank
# params['profile2counts'] = profile2counts
r.write_to_xls(params)
fname = os.path.join(data_path, str(limit_to),
'pentaplets_merged_across.p.bz2')
pentaplets = t.load_compressed_pickle(fname)
report_dir = 'all'
report_files_dir = os.path.join(gv.project_data_path,
'Archea/reports/merged_across_orders/',
report_dir)
j = 0
for kplet_sublist in pentaplets:
cur_reports_folder = os.path.join(report_files_dir, str(5))
src2org, file_summaries, community, community_count, community_count_with_flanks = \
merging.merge_into_file_summaries(kplet_sublist,
neighborhood_files_path,
file2src_src2org_map,
'archaea')
if not src2org:
continue
community_classes = merging.arcog_profile_count_into_class_count(
community_count)
community_flank_classes = merging.arcog_profile_count_into_class_count(
community_count_with_flanks)
xls_file_name = os.path.join(cur_reports_folder,
"%d_%d.xls" % (j + 1, 5))
print xls_file_name
j += 1
params = dict()
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
if len(pivot.codes.intersection(_kplet.codes)) == 4:
_orgs = set([file2organism[f] for f in _kplet.files])
print i+1, len(set(pivot.files).intersection(set(_kplet.files))), len(_kplet.files), len(pivot_orgs), len(_orgs), len(pivot_orgs.intersection(_orgs)), _kplet.codes
profile2counts_pool = dist.get_flank_distributions(pentaplets, neighborhood_files_path, target_profiles)
j = 0
for k in range(len(pentaplets)):
kplet_sublist = pentaplets[k]
cur_reports_folder = os.path.join(report_files_dir, str(5))
src2org, file_summaries, community, community_count, community_count_with_flanks = \
merging.merge_into_file_summaries(kplet_sublist,
neighborhood_files_path,
file2src_src2org_map,
'archaea')
if not src2org:
continue
class2counts, class2profiles = merging.arcog_profile_count_into_class_count(community_count)
class2counts_flank, class2profiles_flank = merging.arcog_profile_count_into_class_count(community_count_with_flanks)
profile2counts = profile2counts_pool[k]
xls_file_name = os.path.join(cur_reports_folder, "%d_%d.xls" % (j+1, 5))
print xls_file_name
j += 1
params = dict()
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
profiles = {}
for kplet in merged_kplets[0]:
for code in kplet.codes:
if code in target_profiles:
if code in profiles:
profiles[code] += 1
else:
profiles[code] = 1
fname = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/pickle/100000/merged_kplets.p.bz2'
dest_dir = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/reports/tmp/'
for cnt, kplet_sublist in enumerate(merged_kplets):
print cnt + 1
xls_file_name = os.path.join(dest_dir, "%d.xls" % (cnt + 1))
src2org, file_summaries, community, community_count = merging.merge_into_file_summaries(
kplet_sublist, neighborhood_files_path, file2src_src2org_map)
params = {}
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
r.write_to_xls(params)
if cnt == 200:
break
profiles = {}
for kplet in merged_kplets[0]:
for code in kplet.codes:
if code in target_profiles:
if code in profiles:
profiles[code] += 1
else:
profiles[code] = 1
fname = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/pickle/100000/merged_kplets.p.bz2'
dest_dir = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/reports/tmp/'
for cnt, kplet_sublist in enumerate(merged_kplets):
print cnt+1
xls_file_name = os.path.join(dest_dir, "%d.xls" % (cnt+1))
src2org, file_summaries, community, community_count = merging.merge_into_file_summaries(kplet_sublist, neighborhood_files_path, file2src_src2org_map)
params = {}
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
r.write_to_xls(params)
if cnt == 200:
break
def generate_plots_from_pickle(limit_to, report_dir, target_profiles, profile2def, gid2arcog_cdd, neighborhood_files_path):
data_path = os.path.join(gv.project_data_path, 'Bacteria/pickle/')
fname = os.path.join(data_path, str(limit_to), 'pentaplets_merged_within.p.bz2')
pentaplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to), 'quadruplets_merged_within.p.bz2')
quadruplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to), 'triplets_merged_within.p.bz2')
triplets = t.load_compressed_pickle(fname)
fname = os.path.join(data_path, str(limit_to), 'duplets_merged_within.p.bz2')
duplets = t.load_compressed_pickle(fname)
print 'Generationg reports for across orders merged lists'
flank_report_fnames = ['pentaplets_flank_counts.xls', 'quadruplets_flank_counts.xls', \
'triplets_flank_counts.xls', 'duplets_flank_counts.xls']
kplets = [pentaplets, quadruplets, triplets, duplets]
titles = ['Pentaplets', 'Quadruplets', 'Triplets', 'Duplets']
report_files_dir = os.path.join(gv.project_data_path, 'Bacteria/reports/merged_within_orders/', report_dir)
for i in range(len(flank_report_fnames)):
_fname = flank_report_fnames[i]
_kplet_list = kplets[i]
_title = titles[i]
flank_counts, cog2gids, gid2weight = dist.get_flank_distributions(_kplet_list, neighborhood_files_path, target_profiles)
universal_flank_counts = t.merge_dict_set_list(cog2gids, gid2weight)
params = dict()
params['xls_file_name'] = os.path.join(report_files_dir, _fname)
params['profile2def'] = profile2def
params['flank_counts'] = universal_flank_counts
params['title'] = _title
params['target_profiles'] = target_profiles
r.write_flanking_count_xls(params)
sys.exit()
if not os.path.exists(report_files_dir):
os.mkdir(report_files_dir)
for i, kplet_pool in zip([5, 4, 3, 2], [pentaplets, quadruplets, triplets, duplets]):
print i
j = 0
# flank_counts_pool = dist.get_flank_distributions(kplet_pool, neighborhood_files_path, target_profiles)
for k in range(len(kplet_pool)):
kplet_sublist = kplet_pool[k]
cur_reports_folder = os.path.join(report_files_dir, str(i))
if not os.path.exists(cur_reports_folder):
os.mkdir(cur_reports_folder)
src2org, file_summaries, community, community_count, community_count_with_flanks\
= merging.merge_into_file_summaries(kplet_sublist,
neighborhood_files_path,
file2src_src2org_map)
if not src2org:
continue
xls_file_name = os.path.join(cur_reports_folder, "%d_%d.xls" % (j+1, i))
class2counts, class2profiles = merging.cdd_profile_count_into_class_count(community_count)
class2counts_flank, class2profiles_flank = merging.cdd_profile_count_into_class_count(community_count_with_flanks)
# profile2counts = flank_counts_pool[k]
j += 1
params = dict()
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
params['class2counts'] = class2counts
params['class2profiles'] = class2profiles
params['class2counts_flank'] = class2counts_flank
# params['profile2counts'] = profile2counts
r.write_to_xls(params)
if not os.path.exists(reports_dir):
os.mkdir(reports_dir)
ind = 0
for kplet in kplet_list[:1000]:
codes = list(kplet.codes)
suffix = ['s' if code in target_profiles else 'n' for code in codes]
if 's' not in suffix:
continue
xls_file_name = os.path.join(reports_dir, '%d_%s.xls' % (ind+1, "".join(suffix)))
ind += 1
src2org, file_summaries, community, community_count, community_count_with_flanks, weight = \
merging.merge_into_file_summaries([kplet],
neighborhood_files_path,
file2src_src2org_map)
# xls_file_name = os.path.join(reports_dir, '%d.xls' % (ind+1))
params = dict()
params[ 'xls_file_name'] = xls_file_name
params[ 'src2org'] = src2org
params[ 'file_summaries'] = file_summaries
params[ 'target_profiles'] = target_profiles
params[ 'profile2def'] = profile2def
params[ 'gid2arcog_cdd'] = gid2arcog_cdd
# print "Writing", ind, xls_file_name
r.write_to_xls_raw_kplet(params)
# profile_id2code = map_id2cdd()
# pickle.dump(profile_id2code, open('profile_id2code.p','w'))
profile_id2code = cPickle.load(open('/Users/hudaiber/Projects/NewSystems/code/Bacteria/profile_id2code.p'))
# fname = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/pickle/100000/pentaplets_merged_across.p.bz2'
fname = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/pickle/100000/merged_kplets.p.bz2'
f = bz2.BZ2File(fname, 'rb')
merged_kplets = cPickle.load(f)
dest_dir = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/reports/tmp/'
print 'starting reports'
for cnt, kplet_sublist in enumerate(merged_kplets):
print cnt+1
xls_file_name = os.path.join(dest_dir, "%d.xls" % (cnt+1))
src2org, file_summaries, community = merging.merge_into_file_summaries(kplet_sublist, neighborhood_files_path, file2src_src2org_map, 'bacteria')
params = {}
params['xls_file_name'] = xls_file_name
params['src2org'] = src2org
params['file_summaries'] = file_summaries
params['community'] = community
params['target_profiles'] = target_profiles
params['profile2def'] = profile2def
params['gid2arcog_cdd'] = gid2arcog_cdd
r.write_to_xls(params)
break
if cnt == 200:
break
