def export_frequency_json(process, prefix, indent):
num_dp = 6
# construct a json file containing all frequency estimate
# the format is region_protein:159F for mutations and region_clade:123 for clades
if hasattr(process, 'pivots'):
freq_json = {'pivots':round_freqs(process.pivots, num_dp)}
if hasattr(process, 'mutation_frequencies'):
freq_json['counts'] = {x:list(counts) for x, counts in process.mutation_frequency_counts.iteritems()}
for (region, gene), tmp_freqs in process.mutation_frequencies.iteritems():
for mut, freq in tmp_freqs.iteritems():
label_str = region+"_"+ gene + ':' + str(mut[0]+1)+mut[1]
freq_json[label_str] = round_freqs(freq, num_dp)
# repeat for clade frequencies in trees
if hasattr(process, 'tree_frequencies'):
for region in process.tree_frequencies:
for clade, freq in process.tree_frequencies[region].iteritems():
label_str = region+'_clade:'+str(clade)
freq_json[label_str] = round_freqs(freq, num_dp)
# repeat for named clades
if hasattr(process, 'clades_to_nodes') and hasattr(process, 'tree_frequencies'):
for region in process.tree_frequencies:
for clade, node in process.clades_to_nodes.iteritems():
label_str = region+'_'+str(clade)
freq_json[label_str] = round_freqs(process.tree_frequencies[region][node.clade], num_dp)
# write to one frequency json
if hasattr(process, 'tree_frequencies') or hasattr(process, 'mutation_frequencies'):
write_json(freq_json, prefix+'_frequencies.json', indent=indent)
else:
process.log.notify("Cannot export frequencies - pivots do not exist")
def export(self, prefix='web/data/', extra_attr = []):
'''
export the tree, sequences, frequencies to json files for visualization
in the browser
'''
# export json file that contains alignment diversity column by column
self.seqs.export_diversity(prefix+'entropy.json')
# exports the tree and the sequences inferred for all clades in the tree
self.tree.export(path=prefix, extra_attr = extra_attr + ["subtype", "country", "region", "nuc_muts",
"ep", "ne", "rb", "aa_muts","lab", "accession","isolate_id"])
# local function or round frequency estimates to useful precision (reduces file size)
def process_freqs(freq):
return [round(x,4) for x in freq]
# construct a json file containing all frequency estimate
# the format is region_protein:159F for mutations and region_clade:123 for clades
freq_json = {'pivots':process_freqs(self.pivots)}
freq_json['counts'] = {x:list(counts) for x, counts in self.tip_count.iteritems()}
for (region, gene), tmp_freqs in self.frequencies.iteritems():
for mut, freq in tmp_freqs.iteritems():
label_str = region+"_"+ gene + ':' + str(mut[0]+1)+mut[1]
freq_json[label_str] = process_freqs(freq)
# repeat for clade frequencies in trees
for (region,clade), freq in self.tree_frequencies.iteritems():
label_str = region+'_clade:'+str(clade)
freq_json[label_str] = process_freqs(freq)
# write to one frequency json
write_json(freq_json, prefix+'frequencies.json', indent=None)
self.HI_export(prefix)
def titer_export(process):
from base.io_util import write_json
from itertools import chain
import pandas as pd
prefix = process.config["output"]["auspice"]+'/'+process.info["prefix"]+'_'
if hasattr(process, 'titer_tree'):
# export the raw titers
data = process.titer_tree.compile_titers()
write_json(data, prefix+'titers.json', indent=1)
# export the tree model
tree_model = {'potency':process.titer_tree.compile_potencies(),
'avidity':process.titer_tree.compile_virus_effects(),
'dTiter':{n.clade:n.dTiter for n in process.tree.tree.find_clades() if n.dTiter>1e-6}}
write_json(tree_model, prefix+'tree_model.json')
# export model performance on test set
if hasattr(process.titer_tree, 'cross_validation'):
predicted_values = list(chain.from_iterable([iteration.pop('values') for iteration in process.titer_tree.cross_validation ])) # flatten to one list of (actual, predicted) tuples
predicted_values = pd.DataFrame(predicted_values, columns=['actual', 'predicted']) # cast to df so we can easily write to csv
model_performance = pd.DataFrame(process.titer_tree.cross_validation) # list of dictionaries -> df
predicted_values.to_csv(prefix+'predicted_titers.csv', index=False)
model_performance.to_csv(prefix+'titer_model_performance.csv', index=False)
elif hasattr(process.titer_tree.hasattr, 'validation'):
predicted_values = pd.DataFrame(process.titer_tree.validation.pop('values'), columns=['actual', 'predicted'])
model_performance = pd.DataFrame(process.titer_tree.validation)
predicted_values.to_csv(prefix+'predicted_titers.csv', index=False)
model_performance.to_csv(prefix+'titer_model_performance.csv', index=False)
else:
print('Tree model not yet trained')
def titer_export(process):
from base.io_util import write_json
from itertools import chain
import pandas as pd
prefix = process.config["output"]["auspice"] + '/' + process.info[
"prefix"] + '_'
if hasattr(process, 'titer_tree'):
# export the raw titers
data = process.titer_tree.compile_titers()
write_json(data, prefix + 'titers.json', indent=1)
# export the tree model
tree_model = {
'potency': process.titer_tree.compile_potencies(),
'avidity': process.titer_tree.compile_virus_effects(),
'dTiter': {
n.clade: n.dTiter
for n in process.tree.tree.find_clades() if n.dTiter > 1e-6
}
}
write_json(tree_model, prefix + 'tree_model.json')
# export model performance on test set
if hasattr(process.titer_tree, 'cross_validation'):
predicted_values = list(
chain.from_iterable([
iteration.pop('values')
for iteration in process.titer_tree.cross_validation
])) # flatten to one list of (actual, predicted) tuples
predicted_values = pd.DataFrame(
predicted_values,
columns=['actual', 'predicted'
]) # cast to df so we can easily write to csv
model_performance = pd.DataFrame(
process.titer_tree.cross_validation
) # list of dictionaries -> df
predicted_values.to_csv(prefix + 'predicted_titers.csv',
index=False)
model_performance.to_csv(prefix + 'titer_model_performance.csv',
index=False)
elif hasattr(process.titer_tree.hasattr, 'validation'):
predicted_values = pd.DataFrame(
process.titer_tree.validation.pop('values'),
columns=['actual', 'predicted'])
model_performance = pd.DataFrame(process.titer_tree.validation)
predicted_values.to_csv(prefix + 'predicted_titers.csv',
index=False)
model_performance.to_csv(prefix + 'titer_model_performance.csv',
index=False)
else:
print('Tree model not yet trained')
def export_metadata_json(process, prefix, indent):
process.log.notify("Writing out metaprocess")
meta_json = {}
# count number of tip nodes
virus_count = 0
for node in process.tree.tree.get_terminals():
virus_count += 1
meta_json["virus_count"] = virus_count
author_info = summarise_publications_from_tree(process.tree.tree)
meta_json["author_info"] = author_info
# join up config color options with those in the input JSONs.
col_opts = process.config["auspice"]["color_options"]
if process.colors:
for trait, col in process.colors.iteritems():
if trait in col_opts:
col_opts[trait]["color_map"] = col
else:
process.log.warn("{} in colors (input JSON) but not auspice/color_options. Ignoring".format(trait))
meta_json["color_options"] = col_opts
if "date_range" in process.config["auspice"]:
meta_json["date_range"] = process.config["auspice"]["date_range"]
if "analysisSlider" in process.config["auspice"]:
meta_json["analysisSlider"] = process.config["auspice"]["analysisSlider"]
meta_json["panels"] = process.config["auspice"]["panels"]
meta_json["updated"] = time.strftime("X%d %b %Y").replace('X0','X').replace('X','')
meta_json["title"] = process.info["title"]
meta_json["maintainer"] = process.info["maintainer"]
meta_json["filters"] = process.info["auspice_filters"]
meta_json["annotations"] = extract_annotations(process)
# pass through flu specific information (if present)
if "vaccine_choices" in process.info:
meta_json["vaccine_choices"] = process.info["vaccine_choices"]
## ignore frequency params for now until they are implemented in nextstrain/auspice
if "defaults" in process.config["auspice"]:
meta_json["defaults"] = process.config["auspice"]["defaults"]
try:
import git
meta_json["commit"] = git.Repo(search_parent_directories=True).head.object.hexsha
except ImportError:
meta_json["commit"] = "unknown"
meta_json["geo"] = process.lat_longs
write_json(meta_json, prefix+'_meta.json')
def export_tip_frequency_json(process, prefix, indent):
if not (hasattr(process, 'pivots') and hasattr(process, 'kde_frequencies')):
process.log.notify("Cannot export tip frequencies - pivots and/or kde_frequencies do not exist")
return
num_dp = 6
freq_json = {'pivots':round_freqs(process.pivots, num_dp)}
for n in process.tree.tree.get_terminals():
freq_json[n.name] = {
"frequencies" : round_freqs(process.kde_frequencies["global"][n.clade], num_dp),
"weight": 1.0
}
write_json(freq_json, prefix+'_tip-frequencies.json', indent=indent)
def main(params):
import time
from io_util import read_json
from io_util import write_json
from tree_util import json_to_dendropy, dendropy_to_json
print "--- Start fitness model optimization at " + time.strftime(
"%H:%M:%S") + " ---"
tree_fname = 'data/tree_refine.json'
tree = json_to_dendropy(read_json(tree_fname))
fm = fitness_model(tree, predictors=params['predictors'], verbose=1)
fm.predict(niter=params['niter'])
out_fname = "data/tree_fitness.json"
write_json(dendropy_to_json(tree.root), out_fname)
return out_fname
def HI_export(self):
from base.io_util import write_json
prefix = os.path.join(self.config["output"]["auspice"],
self.info["prefix"])
if hasattr(self, 'HI_tree'):
# export the raw titers
hi_data = self.HI_tree.compile_titers()
write_json(hi_data, prefix + '_titers.json')
# export the tree model (avidities and potencies only)
tree_model = {
'potency': self.HI_tree.compile_potencies(),
'avidity': self.HI_tree.compile_virus_effects(),
'dTiter': {
n.clade: n.dTiter
for n in self.tree.tree.find_clades() if n.dTiter > 1e-6
}
}
write_json(tree_model, prefix + '_titer_tree_model.json')
else:
print('Tree model not yet trained')
if hasattr(self, 'HI_subs'):
# export the substitution model
subs_model = {
'potency': self.HI_subs.compile_potencies(),
'avidity': self.HI_subs.compile_virus_effects(),
'substitution': self.HI_subs.compile_substitution_effects()
}
write_json(subs_model, prefix + '_titer_subs_model.json')
else:
print('Substitution model not yet trained')
def to_json(self, filename):
"""Export fitness model parameters, data, and accuracy statistics to JSON.
"""
# Convert predictor parameters to a data frame to easily export as
# records.
params_df = pd.DataFrame({
"predictor": self.predictors,
"param": self.model_params.tolist(),
"global_sd": self.global_sds.tolist()
})
rho_null, rho_raw, rho_rel = self.get_correlation()
data = {
"params": params_df.to_dict(orient="records"),
"data": self.pred_vs_true_df.to_dict(orient="records"),
"accuracy": {
"clade_error": self.clade_fit(self.model_params),
"rho_rel": rho_rel[0]
}
}
write_json(data, filename)
def titer_export(process, model_type='tree'):
from base.io_util import write_json
from itertools import chain
import pandas as pd
prefix = process.config["output"]["auspice"] + '/' + process.info["prefix"]
if hasattr(process, 'titer_model'):
# export the raw titers
data = process.titer_model.compile_titers()
write_json(data, prefix + 'titers.json', indent=1)
if model_type == 'tree':
for n in process.tree.tree.find_clades():
n.attr['cTiter'] = n.cTiter
n.attr['dTiter'] = n.dTiter
process.tree.export(
path=prefix,
extra_attr=process.config["auspice"]["extra_attr"] +
["muts", "aa_muts", "attr", "clade", "cTiter", "dTiter"],
indent=1,
write_seqs_json=
False #"sequences" in self.config["auspice"]["extra_jsons"]
)
titer_model = {
'potency': process.titer_model.compile_potencies(),
'avidity': process.titer_model.compile_virus_effects(),
'dTiter': {
n.clade: n.dTiter
for n in process.tree.tree.find_clades() if n.dTiter > 1e-6
}
}
write_json(titer_model, prefix + 'tree_model.json')
elif model_type == 'substitution':
titer_model = {
'potency': process.titer_model.compile_potencies(),
'avidity': process.titer_model.compile_virus_effects(),
'mutations':
process.titer_model.compile_substitution_effects()
}
write_json(titer_model, prefix + 'substitution_model.json')
else:
print('Tree model not yet trained')
def HI_export(self, prefix):
if hasattr(self, 'HI_tree'):
# export the raw titers
hi_data = self.HI_tree.compile_titers()
write_json(hi_data, prefix+'titers.json')
# export the tree model (avidities and potencies only)
tree_model = {'potency':self.HI_tree.compile_potencies(),
'avidities':self.HI_tree.compile_virus_effects()}
write_json(tree_model, prefix+'titer_tree_model.json')
else:
print('Tree model not yet trained')
if hasattr(self, 'HI_tree'):
# export the substitution model
subs_model = {'potency':self.HI_subs.compile_potencies(),
'avidity':self.HI_subs.compile_virus_effects(),
'substitution':self.HI_subs.compile_substitution_effects()}
write_json(subs_model, prefix+'titer_subs_model.json')
else:
print('Substitution model not yet trained')
def HI_export(process):
prefix = os.path.join(process.config["output"]["auspice"], process.info["prefix"])
if hasattr(process, 'HI_tree'):
# export the raw titers
hi_data = process.HI_tree.compile_titers()
write_json(hi_data, prefix+'_titers.json')
# export the tree model (avidities and potencies only)
tree_model = {'potency':process.HI_tree.compile_potencies(),
'avidity':process.HI_tree.compile_virus_effects(),
'dTiter':{n.clade:n.dTiter for n in process.tree.tree.find_clades() if n.dTiter>1e-6}}
write_json(tree_model, prefix+'_titer_tree_model.json')
else:
print('Tree model not yet trained')
if hasattr(process, 'HI_subs'):
# export the substitution model
subs_model = {'potency':process.HI_subs.compile_potencies(),
'avidity':process.HI_subs.compile_virus_effects(),
'substitution':process.HI_subs.compile_substitution_effects()}
write_json(subs_model, prefix+'_titer_subs_model.json')
else:
print('Substitution model not yet trained')
def titer_export(self):
from base.io_util import write_json
prefix = self.build_data_path
if hasattr(self, 'titer_tree'):
# export the raw titers
data = self.titer_tree.compile_titers()
write_json(data, prefix+'titers.json', indent=1)
# export the tree model (avidities and potencies only)
tree_model = {'potency':self.titer_tree.compile_potencies(),
'avidity':self.titer_tree.compile_virus_effects(),
'dTiter':{n.clade:n.dTiter for n in self.tree.tree.find_clades() if n.dTiter>1e-6}}
write_json(tree_model, prefix+'tree_model.json')
else:
print('Tree model not yet trained')
if hasattr(self, 'titer_tree'):
# export the substitution model
titer_subs_model = {'potency':self.titer_subs.compile_potencies(),
'avidity':self.titer_subs.compile_virus_effects(),
'substitution':self.titer_subs.compile_substitution_effects()}
write_json(titer_subs_model, prefix+'titer_subs_model.json')
else:
print('Substitution model not yet trained')
"legendTitle": "Receptor binding mutations",
"key": "rb"
}
# titers
if hasattr(runner, "titers") and runner.info["segment"] == "ha":
HI_model(runner)
if runner.config["auspice"]["titers_export"]:
HI_export(runner)
vaccine_distance_json = vaccine_distance(
titer_tree=runner.tree.tree,
vaccine_strains=vaccine_choices[runner.info['lineage']],
attributes=['dTiter', 'dTiterSub'])
write_json(
vaccine_distance_json,
os.path.join(runner.config["output"]["auspice"],
runner.info["prefix"]) + '_vaccine_dist.json')
if runner.info["segment"] == 'ha':
plot_titers(runner.HI_subs,
runner.HI_subs.titers.titers,
fname='processed/%s_raw_titers.png' %
runner.info["prefix"],
title=runner.info["prefix"],
mean='geometric')
plot_titers(runner.HI_subs,
runner.HI_subs.titers.titers_normalized,
fname='processed/%s_normalized_titers.png' %
runner.info["prefix"],
title=runner.info["prefix"],
mean='arithmetric')
def export(self,
extra_attr=[],
controls={},
geo_attributes=[],
color_options={
"num_date": {
"key": "num_date",
"legendTitle": "Sampling date",
"menuItem": "date",
"type": "continuous"
}
},
panels=['tree', 'entropy'],
indent=None):
'''
export the tree, sequences, frequencies to json files for visualization
in the browser
'''
prefix = self.build_data_path
# export json file that contains alignment diversity column by column
self.seqs.export_diversity(prefix + 'entropy.json')
# exports the tree and the sequences inferred for all clades in the tree
if hasattr(self, 'tree') and self.tree is not None:
self.tree.export(path=prefix,
extra_attr=extra_attr +
["muts", "aa_muts", "attr", "clade"],
indent=indent)
# local function or round frequency estimates to useful precision (reduces file size)
def process_freqs(freq):
return [round(x, 4) for x in freq]
# construct a json file containing all frequency estimate
# the format is region_protein:159F for mutations and region_clade:123 for clades
if hasattr(self, 'pivots'):
freq_json = {'pivots': process_freqs(self.pivots)}
if hasattr(self, 'mutation_frequencies'):
freq_json['counts'] = {
x: list(counts)
for x, counts in self.mutation_frequency_counts.iteritems()
}
for (region,
gene), tmp_freqs in self.mutation_frequencies.iteritems():
for mut, freq in tmp_freqs.iteritems():
label_str = region + "_" + gene + ':' + str(mut[0] +
1) + mut[1]
freq_json[label_str] = process_freqs(freq)
# repeat for clade frequencies in trees
if hasattr(self, 'tree_frequencies'):
for region in self.tree_frequencies:
for clade, freq in self.tree_frequencies[region].iteritems():
label_str = region + '_clade:' + str(clade)
freq_json[label_str] = process_freqs(freq)
# repeat for named clades
if hasattr(self, 'clades_to_nodes') and hasattr(
self, 'tree_frequencies'):
for region in self.tree_frequencies:
for clade, node in self.clades_to_nodes.iteritems():
label_str = region + '_' + str(clade)
freq_json[label_str] = process_freqs(
self.tree_frequencies[region][node.clade])
# write to one frequency json
if hasattr(self, 'tree_frequencies') or hasattr(
self, 'mutation_frequencies'):
write_json(freq_json, prefix + 'frequencies.json', indent=indent)
# write out metadata json# Write out metadata
print("Writing out metadata")
meta_json = {}
meta_json["color_options"] = color_options
meta_json["panels"] = panels
meta_json["updated"] = time.strftime("X%d %b %Y").replace('X0',
'X').replace(
'X', '')
try:
from pygit2 import Repository, discover_repository
current_working_directory = os.getcwd()
repository_path = discover_repository(current_working_directory)
repo = Repository(repository_path)
commit_id = repo[repo.head.target].id
meta_json["commit"] = str(commit_id)
except ImportError:
meta_json["commit"] = "unknown"
if len(controls):
meta_json["controls"] = self.make_control_json(controls)
if len(geo_attributes):
meta_json["geo"] = self.make_geo_lookup_json(geo_attributes)
write_json(meta_json, prefix + 'meta.json')
def export_metadata_json(process, prefix, indent):
process.log.notify("Writing out metaprocess")
meta_json = {}
# count number of tip nodes
virus_count = 0
for node in process.tree.tree.get_terminals():
virus_count += 1
meta_json["virus_count"] = virus_count
(author_info,
seq_to_author) = summarise_publications_from_tree(process.tree.tree)
meta_json["author_info"] = author_info
meta_json["seq_author_map"] = seq_to_author
# join up config color options with those in the input JSONs.
col_opts = process.config["auspice"]["color_options"]
if process.colors:
for trait, col in process.colors.iteritems():
if trait in col_opts:
col_opts[trait]["color_map"] = col
else:
process.log.warn(
"{} in colors (input JSON) but not auspice/color_options. Ignoring"
.format(trait))
meta_json["color_options"] = col_opts
if "date_range" in process.config["auspice"]:
meta_json["date_range"] = process.config["auspice"]["date_range"]
if "analysisSlider" in process.config["auspice"]:
meta_json["analysisSlider"] = process.config["auspice"][
"analysisSlider"]
meta_json["panels"] = process.config["auspice"]["panels"]
meta_json["updated"] = time.strftime("X%d %b %Y").replace('X0',
'X').replace(
'X', '')
# meta_json["title"] = process.info["title"]
# meta_json["maintainer"] = process.info["maintainer"]
# meta_json["filters"] = process.info["auspice_filters"]
# meta_json["annotations"] = extract_annotations(process)
# pass through flu specific information (if present)
if "vaccine_choices" in process.info:
meta_json["vaccine_choices"] = process.info["vaccine_choices"]
## ignore frequency params for now until they are implemented in nextstrain/auspice
if "defaults" in process.config["auspice"]:
meta_json["defaults"] = process.config["auspice"]["defaults"]
# try:
# from pygit2 import Repository, discover_repository
# current_working_directory = os.getcwd()
# repository_path = discover_repository(current_working_directory)
# repo = Repository(repository_path)
# # commit_id = repo[repo.head.target].id
# # meta_json["commit"] = str(commit_id)
# except ImportError:
# meta_json["commit"] = "unknown"
if len(process.config["auspice"]["controls"]):
meta_json["controls"] = process.make_control_json(
process.config["auspice"]["controls"])
meta_json["geo"] = process.lat_longs
write_json(meta_json, prefix + '_meta.json')
def auspice_export(self):
'''
export the tree, sequences, frequencies to json files for auspice visualization
'''
prefix = os.path.join(self.config["output"]["auspice"],
self.info["prefix"])
indent = 2
# export json file that contains alignment diversity column by column
self.seqs.export_diversity(fname=prefix + '_entropy.json', indent=2)
# exports the tree and the sequences inferred for all clades in the tree
if hasattr(self, 'tree') and self.tree is not None:
self.tree.export(path=prefix,
extra_attr=self.config["auspice"]["extra_attr"] +
["muts", "aa_muts", "attr", "clade"],
indent=indent)
# local function or round frequency estimates to useful precision (reduces file size)
def process_freqs(freq):
return [round(x, 4) for x in freq]
# construct a json file containing all frequency estimate
# the format is region_protein:159F for mutations and region_clade:123 for clades
if hasattr(self, 'pivots'):
freq_json = {'pivots': process_freqs(self.pivots)}
if hasattr(self, 'mutation_frequencies'):
freq_json['counts'] = {
x: list(counts)
for x, counts in self.mutation_frequency_counts.iteritems()
}
for (region,
gene), tmp_freqs in self.mutation_frequencies.iteritems():
for mut, freq in tmp_freqs.iteritems():
label_str = region + "_" + gene + ':' + str(mut[0] +
1) + mut[1]
freq_json[label_str] = process_freqs(freq)
# repeat for clade frequencies in trees
if hasattr(self, 'tree_frequencies'):
for region in self.tree_frequencies:
for clade, freq in self.tree_frequencies[region].iteritems():
label_str = region + '_clade:' + str(clade)
freq_json[label_str] = process_freqs(freq)
# repeat for named clades
if hasattr(self, 'clades_to_nodes') and hasattr(
self, 'tree_frequencies'):
for region in self.tree_frequencies:
for clade, node in self.clades_to_nodes.iteritems():
label_str = region + '_' + str(clade)
freq_json[label_str] = process_freqs(
self.tree_frequencies[region][node.clade])
# write to one frequency json
if hasattr(self, 'tree_frequencies') or hasattr(
self, 'mutation_frequencies'):
write_json(freq_json, prefix + '_frequencies.json', indent=indent)
# count number of tip nodes
virus_count = 0
for node in self.tree.tree.get_terminals():
virus_count += 1
# write out metadata json# Write out metadata
print("Writing out metadata")
meta_json = {}
# join up config color options with those in the input JSONs.
col_opts = self.config["auspice"]["color_options"]
if self.colors:
for trait, data in self.colors.iteritems():
if trait in col_opts:
col_opts[trait]["color_map"] = data
else:
self.log.warn(
"{} in colors (input JSON) but not auspice/color_options. Ignoring"
.format(trait))
meta_json["color_options"] = col_opts
if "date_range" in self.config["auspice"]:
meta_json["date_range"] = self.config["auspice"]["date_range"]
if "analysisSlider" in self.config["auspice"]:
meta_json["analysisSlider"] = self.config["auspice"][
"analysisSlider"]
meta_json["panels"] = self.config["auspice"]["panels"]
meta_json["updated"] = time.strftime("X%d %b %Y").replace('X0',
'X').replace(
'X', '')
meta_json["virus_count"] = virus_count
if "defaults" in self.config["auspice"]:
meta_json["defaults"] = self.config["auspice"]["defaults"]
# TODO: move these to base/config
# valid_defaults = {'colorBy': ['region', 'country', 'num_date', 'ep', 'ne', 'rb', 'genotype', 'cHI'],
# 'layout': ['radial', 'rectangular', 'unrooted'],
# 'geoResolution': ['region', 'country', 'division'],
# 'distanceMeasure': ['num_date', 'div']}
# for param, value in defaults.items():
# try:
# assert param in valid_defaults and value in valid_defaults[param]
# except:
# print('ERROR: invalid default options provided. Try one of the following instead:', valid_defaults)
# print('Export will continue; default display options can be corrected in the meta.JSON file.')
# continue
# meta_json["defaults"] = defaults
try:
from pygit2 import Repository, discover_repository
current_working_directory = os.getcwd()
repository_path = discover_repository(current_working_directory)
repo = Repository(repository_path)
commit_id = repo[repo.head.target].id
meta_json["commit"] = str(commit_id)
except ImportError:
meta_json["commit"] = "unknown"
if len(self.config["auspice"]["controls"]):
meta_json["controls"] = self.make_control_json(
self.config["auspice"]["controls"])
meta_json["geo"] = self.lat_longs
write_json(meta_json, prefix + '_meta.json')
