How to use looks_like method in Sure

Best Python code snippet using sure_python

detect_format.py

Source:detect_format.py

1#!/usr/bin/python2# Filename: detect_format.py3import csv4import re5import os6import sys7from optparse import OptionParser8# A bit of path manipulation to import autozip.py from ../utils/9GETEV_MAIN_PATH = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))10if not GETEV_MAIN_PATH in sys.path:11    sys.path.insert(1, GETEV_MAIN_PATH)12del GETEV_MAIN_PATH13from utils import autozip14MAX_LINES_CHECKED = 10015def detect_format(file_input):16    """Detect the genetic data format of a file.17    Takes a path to a file, or a string generator (e.g. a filehandle).18    Tries to match one of the following:19      23ANDME: 23andme (microarray genotyping)20      CGIVAR: Complete Genomics var file21      deCODEme: deCODEme (microarray genotyping)22      GFF: General Feature Format23      VCF: Variant Call Format (only tested for 23andme exome data)24    """25    looks_like = dict()26    if isinstance(file_input, str):27        try:28            f_in = autozip.file_open(file_input, 'r')29        except AssertionError:30            f_in = autozip.file_open(file_input, 'r', 'deCODEme_scan.csv')31            print "deCODEme archive (deCODEme) detected"32            looks_like['deCODEme'] = True33    else:34        f_in = file_input35    line_count = 036    for line in f_in:37        line_count += 138        if any([looks_like[x] for x in looks_like.keys()]):39            break    40        if line_count > MAX_LINES_CHECKED:41            break42        # Check comment lines, if they exist, for information on file type.43        if re.match('#', line):44            if re.match(r'#TYPE.*VAR-ANNOTATION', line):45                print "Complete Genomics var file format (CGIVAR) detected"46                looks_like['CGIVAR'] = True47            if re.match(r'##gff-version', line):48                print "General Feature Format (GFF) detected"49                looks_like['GFF'] = True50            if re.match(r'# This data file generated by 23andMe', line):51                print "23andme microarray genotyping data (23ANDME) detected"52                looks_like['23ANDME'] = True53            if re.match(r'##fileformat=VCFv4', line):54                print "Variant Call Format (VCF) detected"55                looks_like['VCF'] = True56        # Look at other lines and decide based on their format.57        tsv_data = line.split('\t')58        csv_data = list(csv.reader([line]))[0]59        if ( len(csv_data) > 5 and60             re.match(r'rs', csv_data[0]) and61             re.match(r'[ACGT]', csv_data[1]) and62             re.match(r'[0-9]', csv_data[3]) and63             re.match(r'[+-]', csv_data[4]) and64             re.match(r'[ACGT]', csv_data[5]) ):65            print "deCODEme microarray genotyping data (deCODEme) guessed"66            looks_like['deCODEme'] = True67        if ( len(csv_data) > 3 and68             re.match(r'rs', csv_data[0]) and69             re.match(r'[0-9]', csv_data[2]) and70             re.match(r'[ACGT]', csv_data[3]) ):71            print "Family Tree DNA genotyping data (FTDNA) guessed"72            looks_like['FTDNA'] = True73        if ( len(tsv_data) > 3 and74             re.match(r'rs', tsv_data[0]) and 75             re.match(r'[0-9]', tsv_data[2]) and76             re.match(r'[ACGT][ACGT]', tsv_data[3]) ):77            print "23andme microarray genotyping data (23ANDME) guessed"78            looks_like['23ANDME'] = True79        if ( len(tsv_data) > 6 and80             re.match(r'chr', tsv_data[3]) and 81             re.match(r'[0-9]', tsv_data[4]) and 82             re.match(r'[0-9]', tsv_data[5]) and83             (tsv_data[6] == "no-call" or tsv_data[6] == "ref") ):84            print "Complete Genomics var file format (CGIvar) guessed"85            looks_like['CGIVAR'] = True86        if ( len(tsv_data) > 6 and87             re.match(r'[0-9]', tsv_data[3]) and88             re.match(r'[0-9]', tsv_data[4]) and89             tsv_data[6] == "+" ):90            print "General Feature Format (GFF) guessed"91            looks_like['GFF'] = True92        if ( len(tsv_data) > 7 and93             re.match(r'[0-9]', tsv_data[1]) and94             re.match(r'[ACGT]', tsv_data[3]) and95             re.match(r'[ACGT]', tsv_data[4]) and96             len(tsv_data[7].split(';')) > 2 ):97            print "Variant Call Format (VCF) guessed"98            looks_like['VCF'] = True99    100    if isinstance(file_input, str):101        f_in.close()102    if any([looks_like[x] for x in looks_like.keys()]):103        return [x for x in looks_like.keys() if looks_like[x]][0]104    else:105        return 'UNKNOWN'106def main():107    # Parse options108    usage = ("\n%prog -i inputfile\n"109             "%prog < inputfile")110    parser = OptionParser(usage=usage)111    parser.add_option("-i", "--input", dest="inputfile",112                      help="Read genetic data from INFILE", metavar="INFILE")113    options, args = parser.parse_args()114    # Handle input115    if sys.stdin.isatty():  # false if data is piped in116        var_input = options.inputfile117    else:118        var_input = sys.stdin119    # Handle output120    format_type = detect_format(var_input)121    print format_type122if __name__ == "__main__":...

test_standardcomparator.py

Source:test_standardcomparator.py

...14    comp1 = InteratomicDistanceComparator(n_top=3,15                                          pair_cor_cum_diff=0.03,16                                          pair_cor_max=0.7,17                                          dE=0.3)18    assert comp1.looks_like(a1, a2)19    comp2 = InteratomicDistanceComparator(n_top=3,20                                          pair_cor_cum_diff=0.03,21                                          pair_cor_max=0.7,22                                          dE=0.15)23    assert not comp2.looks_like(a1, a2)24    comp3 = InteratomicDistanceComparator(n_top=3,25                                          pair_cor_cum_diff=0.02,26                                          pair_cor_max=0.7,27                                          dE=0.3)28    assert not comp3.looks_like(a1, a2)29    hard_E_comp = EnergyComparator(dE=1.0)30    assert hard_E_comp.looks_like(a1, a2)31    soft_E_comp = EnergyComparator(dE=.01)32    assert not soft_E_comp.looks_like(a1, a2)33    set_raw_score(a1, .1)34    set_raw_score(a2, .27)35    rs_comp = RawScoreComparator(0.15)36    assert not rs_comp.looks_like(a1, a2)37    comp1 = SequentialComparator([hard_E_comp, rs_comp], [0, 0])38    assert not comp1.looks_like(a1, a2)39    comp2 = SequentialComparator([hard_E_comp, rs_comp], [0, 1])...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.