diff options
author | zsloan | 2021-04-30 18:40:13 +0000 |
---|---|---|
committer | zsloan | 2021-04-30 18:40:13 +0000 |
commit | 21b2e2a552b8b6bedb789263543a4d6d039ac8a9 (patch) | |
tree | fe55511b99a522198c1b840909d7b91c9b45ab22 /wqflask/utility/genofile_parser.py | |
parent | 699b952c7bda5426f3f3e947454f656a4ec7538b (diff) | |
parent | 799b25481fffc97e2adb07004adf502096bf371c (diff) | |
download | genenetwork2-21b2e2a552b8b6bedb789263543a4d6d039ac8a9.tar.gz |
Merge branch 'testing' of github.com:genenetwork/genenetwork2 into testing
Diffstat (limited to 'wqflask/utility/genofile_parser.py')
-rw-r--r-- | wqflask/utility/genofile_parser.py | 151 |
1 files changed, 76 insertions, 75 deletions
diff --git a/wqflask/utility/genofile_parser.py b/wqflask/utility/genofile_parser.py index f8e96d19..86d9823e 100644 --- a/wqflask/utility/genofile_parser.py +++ b/wqflask/utility/genofile_parser.py @@ -12,88 +12,89 @@ import simplejson as json from pprint import pformat as pf + class Marker: - def __init__(self): - self.name = None - self.chr = None - self.cM = None - self.Mb = None - self.genotypes = [] + def __init__(self): + self.name = None + self.chr = None + self.cM = None + self.Mb = None + self.genotypes = [] class ConvertGenoFile: - def __init__(self, input_file): - self.mb_exists = False - self.cm_exists = False - self.markers = [] - - self.latest_row_pos = None - self.latest_col_pos = None + def __init__(self, input_file): + self.mb_exists = False + self.cm_exists = False + self.markers = [] - self.latest_row_value = None - self.latest_col_value = None - self.input_fh = open(input_file) - print("!!!!!!!!!!!!!!!!PARSER!!!!!!!!!!!!!!!!!!") - self.haplotype_notation = { - '@mat': "1", - '@pat': "2", - '@het': "-999", - '@unk': "-999" - } - self.configurations = {} + self.latest_row_pos = None + self.latest_col_pos = None - def process_rows(self): - for self.latest_row_pos, row in enumerate(self.input_fh): - self.latest_row_value = row - # Take care of headers - if not row.strip(): - continue - if row.startswith('#'): - continue - if row.startswith('Chr'): - if 'Mb' in row.split(): - self.mb_exists = True - if 'cM' in row.split(): - self.cm_exists = True - skip = 2 + self.cm_exists + self.mb_exists - self.individuals = row.split()[skip:] - continue - if row.startswith('@'): - key, _separater, value = row.partition(':') - key = key.strip() - value = value.strip() - if key in self.haplotype_notation: - self.configurations[value] = self.haplotype_notation[key] - continue - if not len(self.configurations): - raise EmptyConfigurations - yield row + self.latest_row_value = None + self.latest_col_value = None + self.input_fh = open(input_file) + print("!!!!!!!!!!!!!!!!PARSER!!!!!!!!!!!!!!!!!!") + self.haplotype_notation = { + '@mat': "1", + '@pat': "2", + '@het': "-999", + '@unk': "-999" + } + self.configurations = {} - def process_csv(self): - for row in self.process_rows(): - row_items = row.split("\t") + def process_rows(self): + for self.latest_row_pos, row in enumerate(self.input_fh): + self.latest_row_value = row + # Take care of headers + if not row.strip(): + continue + if row.startswith('#'): + continue + if row.startswith('Chr'): + if 'Mb' in row.split(): + self.mb_exists = True + if 'cM' in row.split(): + self.cm_exists = True + skip = 2 + self.cm_exists + self.mb_exists + self.individuals = row.split()[skip:] + continue + if row.startswith('@'): + key, _separater, value = row.partition(':') + key = key.strip() + value = value.strip() + if key in self.haplotype_notation: + self.configurations[value] = self.haplotype_notation[key] + continue + if not len(self.configurations): + raise EmptyConfigurations + yield row - this_marker = Marker() - this_marker.name = row_items[1] - this_marker.chr = row_items[0] - if self.cm_exists and self.mb_exists: - this_marker.cM = row_items[2] - this_marker.Mb = row_items[3] - genotypes = row_items[4:] - elif self.cm_exists: - this_marker.cM = row_items[2] - genotypes = row_items[3:] - elif self.mb_exists: - this_marker.Mb = row_items[2] - genotypes = row_items[3:] - else: - genotypes = row_items[2:] - for item_count, genotype in enumerate(genotypes): - if genotype.upper().strip() in self.configurations: - this_marker.genotypes.append(self.configurations[genotype.upper().strip()]) - else: - print("WARNING:", genotype.upper()) - this_marker.genotypes.append("NA") - self.markers.append(this_marker.__dict__) + def process_csv(self): + for row in self.process_rows(): + row_items = row.split("\t") + this_marker = Marker() + this_marker.name = row_items[1] + this_marker.chr = row_items[0] + if self.cm_exists and self.mb_exists: + this_marker.cM = row_items[2] + this_marker.Mb = row_items[3] + genotypes = row_items[4:] + elif self.cm_exists: + this_marker.cM = row_items[2] + genotypes = row_items[3:] + elif self.mb_exists: + this_marker.Mb = row_items[2] + genotypes = row_items[3:] + else: + genotypes = row_items[2:] + for item_count, genotype in enumerate(genotypes): + if genotype.upper().strip() in self.configurations: + this_marker.genotypes.append( + self.configurations[genotype.upper().strip()]) + else: + print("WARNING:", genotype.upper()) + this_marker.genotypes.append("NA") + self.markers.append(this_marker.__dict__) |