def __init__(self, config_file, mutation_ids, attribute_map, precision=False):
self.config_file = config_file
self.sample_ids = paths.get_sample_ids(config_file)
self.mutation_ids = mutation_ids
self.attribute_map = attribute_map
self.update_precision = precision
def _load_variant_allele_frequencies(config_file):
data = []
for sample_id, file_name in paths.get_mutations_files(config_file).items():
sample_data = _load_sample_variant_allele_frequencies(file_name)
sample_data['sample_id'] = sample_id
data.append(sample_data)
data = pd.concat(data, axis=0)
num_samples = len(paths.get_sample_ids(config_file))
# Filter for mutations in all samples
data = data.groupby('mutation_id').filter(lambda x: len(x) == num_samples)
return data
def _load_cellular_prevalences(config_file, burnin, thin):
data = []
for sample_id, file_name in paths.get_cellular_prevalence_trace_files(
config_file).items():
sample_data = _load_sample_cellular_prevalences(
file_name, burnin, thin)
sample_data['sample_id'] = sample_id
data.append(sample_data)
data = pd.concat(data, axis=0)
num_samples = len(paths.get_sample_ids(config_file))
# Filter for mutations in all samples
data = data.groupby('mutation_id').filter(lambda x: len(x) == num_samples)
return data