comparison vsnp_build_tables.py @ 1:b60858c3eb91 draft

Uploaded

0:38a38babcb31

INPUT_JSON_DIR = 'input_json_dir'
INPUT_NEWICK_DIR = 'input_newick_dir'
# Maximum columns allowed in a LibreOffice
# spreadsheet is 1024.  Excel allows for
# 16,384 columns, but we'll set the lower
# number as the maximum since Galaxy is
# mostly run on Linux.
MAXCOLS = 10000
OUTPUT_EXCEL_DIR = 'output_excel_dir'


def annotate_table(table_df, group, annotation_dict):
    for gbk_chrome, pro in list(annotation_dict.items()):

        snps_df = pandas.read_json(json_file, orient='split')
        with open(newick_file, 'r') as fh:
            for line in fh:
                line = re.sub('[:,]', '\n', line)
                line = re.sub('[)(]', '', line)
                line = re.sub('[0-9].*\.[0-9].*\n', '', line)
                line = re.sub('root\n', '', line)
        sample_order = line.split('\n')
        sample_order = list([_f for _f in sample_order if _f])
        sample_order.insert(0, 'root')
        tree_order = snps_df.loc[sample_order]

1:b60858c3eb91

INPUT_JSON_DIR = 'input_json_dir'
INPUT_NEWICK_DIR = 'input_newick_dir'
# Maximum columns allowed in a LibreOffice
# spreadsheet is 1024.  Excel allows for
# 16,384 columns, but we'll set the lower
# number as the maximum.  Some browsers
# (e.g., Firefox on Linux) are configured
# to use LibreOffice for Excel spreadsheets.
MAXCOLS = 1024
OUTPUT_EXCEL_DIR = 'output_excel_dir'


def annotate_table(table_df, group, annotation_dict):
    for gbk_chrome, pro in list(annotation_dict.items()):

        snps_df = pandas.read_json(json_file, orient='split')
        with open(newick_file, 'r') as fh:
            for line in fh:
                line = re.sub('[:,]', '\n', line)
                line = re.sub('[)(]', '', line)
                line = re.sub(r'[0-9].*\.[0-9].*\n', '', line)
                line = re.sub('root\n', '', line)
        sample_order = line.split('\n')
        sample_order = list([_f for _f in sample_order if _f])
        sample_order.insert(0, 'root')
        tree_order = snps_df.loc[sample_order]