def __init__(self, **keywords):
"""
2008-11-10
"""
ProcessOptions.process_function_arguments(
keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self
)
if self.phenotype_method_id_ls:
self.phenotype_method_id_ls = getListOutOfStr(self.phenotype_method_id_ls, data_type=int)
self.which_PC_index_ls = getListOutOfStr(self.which_PC_index_ls, data_type=int)
self.run_whole_matrix = {
1: self._kruskal_wallis_whole_matrix,
2: self.LM_whole_matrix,
3: self.Emma_whole_matrix,
4: self.LM_with_PCs_whole_matrix,
5: self.LM_with_PCs_whole_matrix,
6: self.LM_with_PCs_whole_matrix,
7: self.Emma_whole_matrixForNoNAGenotypeMatrix,
8: self.EMMAX,
}
self.output_results = {
1: self.output_kw_results,
2: self.output_lm_results,
3: self.output_lm_results,
7: self.output_emma_results,
}
def __init__(self, **keywords):
"""
2008-07-09
"""
#2013.1.10 backwards compatibility
keywords = self._setInputArgumentsEquivalentValue(keywords=keywords, argument1Name='username', argument2Name='db_user')
keywords = self._setInputArgumentsEquivalentValue(keywords=keywords, argument1Name='password', argument2Name='db_passwd')
keywords = self._setInputArgumentsEquivalentValue(keywords=keywords, argument1Name='database', argument2Name='dbname')
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
if self.echo_pool: #2010-9-19 passing echo_pool to create_engine() causes error. all pool log disappeared.
#2010-9-19 Set up a specific logger with our desired output level
import logging
#import logging.handlers
logging.basicConfig()
#LOG_FILENAME = '/tmp/sqlalchemy_pool_log.out'
my_logger = logging.getLogger('sqlalchemy.pool')
# Add the log message handler to the logger
#handler = logging.handlers.RotatingFileHandler(LOG_FILENAME, maxBytes=1000000, backupCount=5)
# create formatter
#formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
# add formatter to handler
#handler.setFormatter(formatter)
#my_logger.addHandler(handler)
my_logger.setLevel(logging.DEBUG)
#self.setup_engine() #2012.12.18 it needs __metadata__ , __session__ from each db-definition file itself
self.READMEClass = None #2012.12.18 required to figure out data_dir
self._data_dir = None #2012.11.13
if hasattr(self, 'debug') and self.debug:
import pdb
pdb.set_trace()
def __init__(self, **keywords): """ 2009-4-18 """ from pymodule import ProcessOptions ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords): """ 2009-2-12 """ ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) if self.chromosome ==0 or self.chromosome=='0': self.chromosome = None
def __init__(self, **keywords): """ 2008-10-29 database to control cluster jobs """ from pymodule import ProcessOptions ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.setup_engine(metadata=__metadata__, session=__session__, entities=entities)
def __init__(self, **keywords):
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
self._threadlocal = threading.local()
self.tables = {}
self.mappers = {}
self._engine = None
def __init__(self, **keywords):
"""
2009-2-12
"""
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-04-28 use ProcessOptions, newer option handling class 2008-04-16 """ from pymodule import ProcessOptions ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-10-23 simplified, relegate stuff to ElixirDB 2008-07-09 """ from pymodule import ProcessOptions ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.setup_engine(metadata=__metadata__, session=__session__, entities=entities)
def __init__(self, **keywords):
"""
2009-4-18
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self._threadlocal = threading.local()
self.tables = {}
self.mappers = {}
self._engine = None
def __init__(self, **keywords): """ 2008-06-02 use ProcessOptions 2007-07-11 2007-07-13 input_fname is useless """ from pymodule import ProcessOptions ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords):
"""
2009-4-10
simplified further by moving db-common lines to ElixirDB
2008-08-11
"""
from pymodule.ProcessOptions import ProcessOptions
ProcessOptions.process_function_arguments(
keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self
)
self.setup_engine(metadata=__metadata__, session=__session__, entities=entities)
def __init__(self, **keywords):
"""
2008-05-01
use ProcessOptions
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(
keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self
)
if not self.output_fname:
self.output_fname = "%s_w%s.npute" % (self.input_fname, self.single_window_size)
def __init__(self, **keywords):
"""
2008-06-02
use ProcessOptions
2007-07-16
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
cutoff_ls = self.max_row_NA_max_col_NA_min_log_prob.split(',')
self.row_cutoff, self.col_cutoff, self.min_log_prob = map(float, cutoff_ls)
def __init__(self, **keywords):
"""
2008-05-01
use ProcessOptions
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if not self.output_fname:
self.output_fname = '%s_w%s.npute' % (self.input_fname,
self.single_window_size)
def __init__(self, **keywords):
"""
2008-11-10
"""
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
self.cofactors = getListOutOfStr(self.cofactors, data_type=str)
self.cofactor_phenotype_id_ls = getListOutOfStr(
self.cofactor_phenotype_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2008-06-02
use ProcessOptions
2007-07-11
2007-07-13
input_fname is useless
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-09-29 add option min_LD_to_output and min_MAF """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-05-27
add user & password
2007-12-29
add processing_bits
"""
ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
processing_bits = self.processing_bits
self.processing_bits = [0]*len(processing_bits)
for i in range(len(processing_bits)):
self.processing_bits[i] = int(processing_bits[i])
self.data_type2data_table = {0:'at.locus',
1:'chip.snp_combined_may_9_06_no_van'}
def __init__(self, inputFnameLs, **keywords): """ 2011-7-11 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-09-05 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.call_method_id_ls = getListOutOfStr(self.call_method_id_ls, data_type=int)
def __init__(self, **keywords): """ 2008-12-02 modelled after ConvertYuSNPFormat2Bjarni.py """ from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, refNameLs, **keywords): """ 2011-7-11 """ self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) self.refNameLs = refNameLs
def __init__(self, **keywords): """ 2008-09-29 add option min_LD_to_output and min_MAF """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords):
"""
2011-7-12
"""
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \
class_to_have_attr=self)
self.discoverFuncDict = {1: self.discoverFromVCF, 2: self.discoverFromBAM, 3:self.discoverFromVCFWithoutFilter}
def __init__(self, **keywords):
"""
2008-11-14
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
self.pic_area = self.pic_area.split(',')
self.pic_area = map(int, self.pic_area)
def __init__(self, **keywords): """ 2008-07-24 split results_method_id_ls if it exists, to accomodate MpiGeneListRankTest which removed this option 2008-07-10 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-10-19 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.output_dir and not os.path.isdir(self.output_dir): os.makedirs(self.output_dir)
def __init__(self, inputFnameLs=None, **keywords):
"""
"""
AbstractVervetMapper.__init__(self, inputFnameLs=inputFnameLs, **keywords)
listArgumentName_data_type_ls = [("site_id_ls", int), ('country_id_ls', int), ('tax_id_ls', int)]
listArgumentName2hasContent = ProcessOptions.processListArguments(listArgumentName_data_type_ls,\
emptyContent=[], class_to_have_attr=self)
def __init__(self, inputFnameLs=None, **keywords):
"""
"""
AbstractVCFMapper.__init__(self, inputFnameLs=inputFnameLs, **keywords)
listArgumentName_data_type_ls = [("inputHeaderLs", str)]
listArgumentName2hasContent = ProcessOptions.processListArguments(listArgumentName_data_type_ls,\
emptyContent=[], class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-05-11 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.ecotype_id_ls: self.ecotype_id_ls = getListOutOfStr(self.ecotype_id_ls, data_type=str) #str because ecotype ids in SNPData are not converted to integers
def __init__(self, **keywords): """ 2008-05-18 add argument array_id_2nd_column 2008-5-12 """ from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords): """ 2008-4-4 """ #argument dictionary #self.ad = process_function_arguments(keywords, argument_default_dict, error_doc=__doc__, class_to_have_attr=self) from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-06-02
use ProcessOptions
2007-07-13
add output_type, need_heterozygous_call, with_header_line, nt_alphabet
2007-07-16
change snpacc_fname to popid2snpid_table
2007-07-16
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
self.OutputPop_dict = {1: self.OutputPopMatrixFormat,
2: self.OutputPopRMES,
3: self.OutputPopMIH}
def __init__(self, **keywords): """ 2009-1-5 """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) self.get_closest = 1 #2011-01-26, the argument has been commented out. set it to 1 here.
def __init__(self, inputFnameLs, **keywords):
"""
2011-7-11
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \
class_to_have_attr=self)
self.inputFnameLs = inputFnameLs
def __init__(self, **keywords): """ 2008-04-08 """ from pymodule import ProcessOptions self.ad=ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) if self.array_id_ls: self.array_id_ls = getListOutOfStr(self.array_id_ls, data_type=str)
def __init__(self, **keywords):
'''
2009-10-6
self.snps is the data structure holding all the SNP data. It's a list of encoded (0,1, or ?)strings.
each string corresponds to alleles of one SNP across all accessions.
self.nucs is a list of tuples, which encode the major/minor alleles of each SNP. allele 0 (major) is the nucleotide at index 0 of the tuple.
self.sdps is a set of unique strings from self.snps.
05/09/08
change interface, inFile could be a data structure
Constructor reads in data file, generates mismatch vectors and upper
triangular matrix extract indices, and reports stats of data.
'''
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
start = time.time()
#if isinstance(inFile, str) and os.path.isfile(inFile):
if self.input_file_format == 2:
self.readInData(self.inFile)
elif self.input_file_format == 1:
self.snps, self.sdps, self.nucs, self.chosen_snps_name_ls = self.readOneChromosomeData(
self.snps_name_ls, self.data_matrix, self.chromosome)
self.numSamps = len(self.snps[0])
#elif isinstance(inFile, RawSnpsData): #05/07/08 it's snpsd data structure
elif self.input_file_format == 3:
snpsd = dataParsers.parseCSVData(self.inFile, withArrayIds=True)
self.input_NA_char = 'NA'
self.snps, self.sdps, self.nucs, self.numSamps = self.getDataStructureFromSNPsD(
snpsd[0])
elif self.input_file_format == 4:
self.snps, self.sdps, self.nucs, self.numSamps = self.getDataStructureFromSNPsD(
self.inFile)
else:
sys.stderr.write('unsupported inFile format: %s\n' %
self.input_file_format)
self.genMismatchVectors()
self.genExtractIndices()
t = int(time.time() - start + 0.5)
sys.stderr.write('Number of Samples: %d\n' % self.numSamps)
sys.stderr.write('Number of SNPs: %d\n' % len(self.snps))
sys.stderr.write('Number of SDPs: %d' % len(self.sdps))
sys.stderr.write('Time to Process: %d m %d s\n' % (t / 60, t % 60))
def __init__(self, **keywords): """ 2011-7-11 """ self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) if not self.outputFnamePrefix: self.outputFnamePrefix = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(self.inputFname)[0]
def __init__(self, inputFnameLs=None, **keywords):
"""
2011-7-12
"""
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \
class_to_have_attr=self)
self.originalHeaderLength = 0
self.originalHeader = None
self.col_name2index = {}
def __init__(self, **keywords):
"""
2008-05-13
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self)
plot_func_dict = {1:PlotQCCall._plot3D,\
2:PlotQCCall._plotContour}
self._plot = plot_func_dict[self.plot_type]
def __init__(self, inputFnameLs, **keywords): """ 2011-10-19 This class is the entry to all others. """ from pymodule import ProcessOptions self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, class_to_have_attr=self) self.inputFnameLs = inputFnameLs
def __init__(self, **keywords):
"""
2008-05-08
add self.output_matrix_type, self.delimiter
2008-04-28
use ProcessOptions, newer option handling class
2008-04-25 use new option handling
2007-02-25
add argument toss_out_rows
2007-07-11
add mysql_connection
2007-09-23
use processing_bits to control processing steps
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
#below are all default values, so that user doesn't have specify every bit in self.processing_bits on the commandline
processing_bits_ls = [0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0]
for i in range(len(self.processing_bits)):
processing_bits_ls[i] = int(self.processing_bits[i])
#now pass all values
self.only_include_strains_with_GPS,\
self.include_other_strain_info,\
self.resolve_duplicated_calls,\
self.toss_out_rows,\
self.need_heterozygous_call,\
self.with_header_line,\
self.nt_alphabet,\
self.discard_all_NA_strain,\
self.output_matrix_type, \
self.delimiter_type ,\
self.toss_contaminants = processing_bits_ls
delimiter_dict = {0: '\t', \
1: ','}
self.delimiter = delimiter_dict[self.delimiter_type]
def __init__(self, **keywords):
"""
2008-12-02
modelled after ConvertYuSNPFormat2Bjarni.py
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords): """ """ self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) self.inf = None self._initializeInput(inputFname=self.inputFname) self._seqTitle2sequence = None self._seqTitleList = None #2013.07.08 self.outf = None
def __init__(self, **keywords):
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.phenotype_method_id_ls is not None:
self.phenotype_method_id_ls = getListOutOfStr(
self.phenotype_method_id_ls, data_type=int)
def __init__(self, **keywords):
"""
2008-09-17
allow priority=3 or 4
2008-06-02
"""
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-12-05
This class is the entry to all others.
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-04-08
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.array_id_ls:
self.array_id_ls = getListOutOfStr(self.array_id_ls, data_type=str)
def __init__(self, **keywords):
"""
2008-07-24
split results_method_id_ls if it exists, to accomodate MpiGeneListRankTest which removed this option
2008-07-10
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-10-10
add option min_gap to draw LD between loci at least this apart
2008-09-24
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-10-19
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
if self.output_dir and not os.path.isdir(self.output_dir):
os.makedirs(self.output_dir)
def __init__(self, **keywords):
"""
2008-4-4
"""
#argument dictionary
#self.ad = process_function_arguments(keywords, argument_default_dict, error_doc=__doc__, class_to_have_attr=self)
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
def __init__(self, **keywords):
"""
2008-06-02
use ProcessOptions
2007-07-13
add output_type, need_heterozygous_call, with_header_line, nt_alphabet
2007-07-16
change snpacc_fname to popid2snpid_table
2007-07-16
"""
from pymodule import ProcessOptions
ProcessOptions.process_function_arguments(keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
self.OutputPop_dict = {
1: self.OutputPopMatrixFormat,
2: self.OutputPopRMES,
3: self.OutputPopMIH
}
def __init__(self, **keywords):
"""
2008-05-13
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
plot_func_dict = {1:PlotQCCall._plot3D,\
2:PlotQCCall._plotContour}
self._plot = plot_func_dict[self.plot_type]
def __init__(self, **keywords):
"""
2008-09-18
use pymodule.ProcessOptions
2008-01-21
ecotype_duplicate2tg_ecotypeid_table, snp_locus_table1 and snp_locus_table2 are useless
"""
from pymodule import ProcessOptions
self.ad = ProcessOptions.process_function_arguments(
keywords,
self.option_default_dict,
error_doc=self.__doc__,
class_to_have_attr=self)
QualityControl.__init__(self, debug=self.debug)