diff options
Diffstat (limited to 'wqflask')
| -rw-r--r-- | wqflask/maintenance/print_benchmark.py | 43 | ||||
| -rw-r--r-- | wqflask/maintenance/quick_search_table.py | 137 | ||||
| -rw-r--r-- | wqflask/other_config/pylintrc | 264 | ||||
| -rw-r--r-- | wqflask/wqflask/correlation/correlation_plot.py | 7 | ||||
| -rw-r--r-- | wqflask/wqflask/my_pylmm/pyLMM/lmm.py | 38 | ||||
| -rw-r--r-- | wqflask/wqflask/my_pylmm/pyLMM/process_plink.py | 28 |
6 files changed, 449 insertions, 68 deletions
diff --git a/wqflask/maintenance/print_benchmark.py b/wqflask/maintenance/print_benchmark.py new file mode 100644 index 00000000..540e0904 --- /dev/null +++ b/wqflask/maintenance/print_benchmark.py @@ -0,0 +1,43 @@ +#!/usr/bin/python + +from __future__ import absolute_import, print_function, division + +import time + +from pprint import pformat as pf + + +class TheCounter(object): + Counters = {} + + def __init__(self): + start_time = time.time() + for counter in range(170000): + self.print_it(counter) + self.time_took = time.time() - start_time + TheCounter.Counters[self.__class__.__name__] = self.time_took + +class PrintAll(TheCounter): + def print_it(self, counter): + print(counter) + +class PrintSome(TheCounter): + def print_it(self, counter): + if counter % 1000 == 0: + print(counter) + +class PrintNone(TheCounter): + def print_it(self, counter): + pass + + +def new_main(): + print("Running new_main") + tests = [PrintAll, PrintSome, PrintNone] + for test in tests: + test() + + print(pf(TheCounter.Counters)) + +if __name__ == '__main__': + new_main() \ No newline at end of file diff --git a/wqflask/maintenance/quick_search_table.py b/wqflask/maintenance/quick_search_table.py index 046a05c4..4f2cd8a9 100644 --- a/wqflask/maintenance/quick_search_table.py +++ b/wqflask/maintenance/quick_search_table.py @@ -1,17 +1,17 @@ -from __future__ import print_function, division, absolute_import +"""Creates a table used for the quick search feature. + +One column contains the terms to match the user's search against. Another contains the result +fields in json format -""" Results will be returned for each of several trait types: mRNA assays, phenotypes, genotypes, and (maybe later) genes -For each trait type, the results for each species should be given; for example, have a "Mouse" tab -with the mouse traits in a table inside it - -This table will then list each trait, its dataset, and several columns determined by its trait type -(phenotype, genotype, etc) +For each trait type, the results for each species should be given This table will then list +each trait, its dataset, and several columns determined by its trait type (phenotype, genotype, etc) """ +from __future__ import print_function, division, absolute_import import sys sys.path.append("../../..") @@ -19,19 +19,17 @@ sys.path.append("../../..") import simplejson as json import sqlalchemy as sa -from sqlalchemy.dialects import mysql -from sqlalchemy.orm import scoped_session, sessionmaker, relationship, backref -from sqlalchemy.orm.exc import NoResultFound +from sqlalchemy.orm import scoped_session, sessionmaker from sqlalchemy.ext.declarative import declarative_base -from pprint import pformat as pf +#from pprint import pformat as pf import zach_settings as settings Engine = sa.create_engine(settings.SQLALCHEMY_DATABASE_URI, #encoding='utf-8', #client_encoding='utf-8', - #echo="debug", + #echo="debug",w ) Session = scoped_session(sessionmaker(bind=Engine)) #, extension=VersionedListener())) @@ -41,6 +39,14 @@ Metadata = sa.MetaData() Metadata.bind = Engine class PublishXRef(Base): + """Class that corresponds with the PublishXRef table in the database. + + The PublishXRef table links phenotype traits and their publications. + + This class is used to add phenotype traits to the quick search table. + + """ + __tablename__ = 'PublishXRef' Id = sa.Column(sa.Integer, primary_key=True) @@ -56,15 +62,16 @@ class PublishXRef(Base): @classmethod def run(cls): + """Connects to database and inserts phenotype trait info into the Quicksearch table.""" conn = Engine.connect() counter = 0 - for ps in page_query(Session.query(cls)): #all() + for pub_row in page_query(Session.query(cls)): #all() values = {} values['table_name'] = cls.__tablename__ - values['the_key'] = json.dumps([ps.Id, ps.InbredSetId]) - values['terms'] = cls.get_unique_terms(ps.Id, ps.InbredSetId) + values['the_key'] = json.dumps([pub_row.Id, pub_row.InbredSetId]) + values['terms'] = cls.get_unique_terms(pub_row.Id, pub_row.InbredSetId) print("terms is:", values['terms']) - values['result_fields'] = cls.get_result_fields(ps.Id, ps.InbredSetId) + values['result_fields'] = cls.get_result_fields(pub_row.Id, pub_row.InbredSetId) ins = QuickSearch.insert().values(**values) conn.execute(ins) counter += 1 @@ -72,6 +79,7 @@ class PublishXRef(Base): @staticmethod def get_unique_terms(publishxref_id, inbredset_id): + """Finds unique terms for each item in the PublishXRef table to match a query against""" results = Session.query( "pre_publication_description", "post_publication_description", @@ -119,6 +127,7 @@ class PublishXRef(Base): @staticmethod def get_result_fields(publishxref_id, inbredset_id): + """Gets the result fields (columns) that appear on the result page as a json string""" results = Session.query( "phenotype_id", "species", @@ -136,7 +145,7 @@ class PublishXRef(Base): "Phenotype.Original_description as description, " "PublishXRef.LRS as lrs, " "PublishXRef.PublicationId as publication_id, " - "Publication.PubMed_ID" + "Publication.PubMed_ID as pubmed_id, " "Publication.Year as year, " "Publication.Authors as authors " "FROM PublishXRef, " @@ -150,17 +159,10 @@ class PublishXRef(Base): "PublishXRef.PublicationId = Publication.Id and " "InbredSet.Id = :inbredset_id and " "Species.Id = InbredSet.SpeciesId ").params(publishxref_id=publishxref_id, - inbredset_id=inbredset_id).all() - #"InbredSet.SpeciesId = Species.Id and " - #"Geno.SpeciesId = Species.Id and " - #"Geno.Name = PublishXRef.Locus ").params(publishxref_id=publishxref_id, - # inbredset_id=inbredset_id).all() - #for result in results: - # print("****", result) + inbredset_id=inbredset_id).all() assert len(set(result for result in results)) == 1, "Different results or no results" - #print("results are:", results) result = results[0] result = row2dict(result) try: @@ -176,7 +178,16 @@ class PublishXRef(Base): return json_results + class GenoXRef(Base): + """Class that corresponds with the GenoXRef table in the database. + + The GenoXRef table links genotype traits and their data. + + This class is used to add genotype traits to the quick search table. + + """ + __tablename__ = 'GenoXRef' GenoFreezeId = sa.Column(sa.Integer, primary_key=True) @@ -187,6 +198,7 @@ class GenoXRef(Base): @classmethod def run(cls): + """Connects to database and inserts genotype trait info into the Quicksearch table.""" conn = Engine.connect() counter = 0 for item in page_query(Session.query(cls)): #all() @@ -201,9 +213,10 @@ class GenoXRef(Base): conn.execute(ins) counter += 1 print("Done:", counter) - + @staticmethod def get_unique_terms(geno_id): + """Finds unique terms for each item in the GenoXRef table to match a query against""" print("geno_id: ", geno_id) results = Session.query( "name", @@ -214,8 +227,6 @@ class GenoXRef(Base): "FROM Geno " "WHERE Geno.Id = :geno_id ").params(geno_id=geno_id).all() - #print("results: ", pf(results)) - unique = set() if len(results): for item in results[0]: @@ -234,12 +245,12 @@ class GenoXRef(Base): continue unique.add(token) - #print("\nUnique terms are: {}\n".format(unique)) return " ".join(unique) @staticmethod def get_result_fields(geno_id, dataset_id): + """Gets the result fields (columns) that appear on the result page as a json string""" results = Session.query( "name", "marker_name", @@ -271,11 +282,8 @@ class GenoXRef(Base): "InbredSet.Id = GenoFreeze.InbredSetId and " "InbredSet.SpeciesId = Species.Id ").params(geno_id=geno_id, dataset_id=dataset_id).all() - #for result in results: - # print(result) assert len(set(result for result in results)) == 1, "Different results" - #print("results are:", results) result = results[0] result = row2dict(result) try: @@ -292,6 +300,14 @@ class GenoXRef(Base): return json_results class ProbeSetXRef(Base): + """Class that corresponds with the ProbeSetXRef table in the database. + + The ProbeSetXRef table links mRNA expression traits and their sample data. + + This class is used to add mRNA expression traits to the quick search table. + + """ + __tablename__ = 'ProbeSetXRef' ProbeSetFreezeId = sa.Column(sa.Integer, primary_key=True) @@ -310,16 +326,17 @@ class ProbeSetXRef(Base): @classmethod def run(cls): + """Connects to db and inserts mRNA expression trait info into the Quicksearch table.""" conn = Engine.connect() counter = 0 - for ps in page_query(Session.query(cls)): #all() + for ps_row in page_query(Session.query(cls)): #all() values = {} values['table_name'] = cls.__tablename__ - values['the_key'] = json.dumps([ps.ProbeSetId, ps.ProbeSetFreezeId]) - values['terms'] = cls.get_unique_terms(ps.ProbeSetId) + values['the_key'] = json.dumps([ps_row.ProbeSetId, ps_row.ProbeSetFreezeId]) + values['terms'] = cls.get_unique_terms(ps_row.ProbeSetId) print("terms is:", values['terms']) - #values['species'] = get_species("ProbeSet", ps.Id) - values['result_fields'] = cls.get_result_fields(ps.ProbeSetId, ps.ProbeSetFreezeId) + values['result_fields'] = cls.get_result_fields(ps_row.ProbeSetId, + ps_row.ProbeSetFreezeId) if values['result_fields'] == None: continue ins = QuickSearch.insert().values(**values) @@ -329,6 +346,7 @@ class ProbeSetXRef(Base): @staticmethod def get_unique_terms(probeset_id): + """Finds unique terms for each item in the ProbeSetXRef table to match a query against""" results = Session.query( "name", "symbol", @@ -345,7 +363,6 @@ class ProbeSetXRef(Base): unique = set() if len(results): for item in results[0]: - #print("locals:", locals()) if not item: continue for token in item.split(): @@ -366,12 +383,12 @@ class ProbeSetXRef(Base): continue unique.add(token) - #print("\nUnique terms are: {}\n".format(unique)) return " ".join(unique) @staticmethod def get_result_fields(probeset_id, dataset_id): + """Gets the result fields (columns) that appear on the result page as a json string""" print("probeset_id: ", probeset_id) print("dataset_id: ", dataset_id) results = Session.query( @@ -420,14 +437,10 @@ class ProbeSetXRef(Base): "ProbeFreeze.InbredSetId = InbredSet.Id and " "InbredSet.SpeciesId = Species.Id ").params(probeset_id=probeset_id, dataset_id=dataset_id).all() - #for result in results: - # print("-", result) if len(set(result for result in results)) != 1: return None - #assert len(set(result for result in results)) == 1, "Different results" - - #print("results are:", results) + result = results[0] result = row2dict(result) try: @@ -443,41 +456,47 @@ class ProbeSetXRef(Base): return json_results - QuickSearch = sa.Table("QuickSearch", Metadata, + # table_name is the table that item is inserted from sa.Column('table_name', sa.String(15), - primary_key=True, nullable=False, autoincrement=False), # table that item is inserted from + primary_key=True, nullable=False, autoincrement=False), sa.Column('the_key', sa.String(30), primary_key=True, nullable=False, autoincrement=False), # key in database table sa.Column('terms', sa.Text), # terms to compare search string with - sa.Column('result_fields', sa.Text) # json + sa.Column('result_fields', sa.Text), # json + mysql_engine = 'MyISAM', ) -QuickSearch.drop(Engine, checkfirst=True) -Metadata.create_all(Engine) +#QuickSearch.drop(Engine, checkfirst=True) +#Metadata.create_all(Engine) def row2dict(row): - """http://stackoverflow.com/a/2848519/1175849""" + """From http://stackoverflow.com/a/2848519/1175849""" return dict(zip(row.keys(), row)) -def page_query(q): - """http://stackoverflow.com/a/1217947/1175849""" +def page_query(query): + """From http://stackoverflow.com/a/1217947/1175849""" offset = 0 while True: - r = False - for elem in q.limit(1000).offset(offset): - r = True - yield elem + rrr = False + for elem in query.limit(1000).offset(offset): + rrr = True + yield elem offset += 1000 - if not r: + if not rrr: break def main(): - ProbeSetXRef.run() - GenoXRef.run() + """Populate the QuickSearch table that is used with the quick search features. + + Add all items from the ProbeSetXRef, GenoXRef, and PublishXRef tables to the QuickSearch tables. + + """ + #ProbeSetXRef.run() + #GenoXRef.run() PublishXRef.run() if __name__ == "__main__": diff --git a/wqflask/other_config/pylintrc b/wqflask/other_config/pylintrc new file mode 100644 index 00000000..b23af7a4 --- /dev/null +++ b/wqflask/other_config/pylintrc @@ -0,0 +1,264 @@ +[MASTER] + +# Specify a configuration file. +#rcfile= + +# Python code to execute, usually for sys.path manipulation such as +# pygtk.require(). +#init-hook= + +# Profiled execution. +profile=no + +# Add files or directories to the blacklist. They should be base names, not +# paths. +ignore=CVS + +# Pickle collected data for later comparisons. +persistent=yes + +# List of plugins (as comma separated values of python modules names) to load, +# usually to register additional checkers. +load-plugins= + + +[MESSAGES CONTROL] + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time. See also the "--disable" option for examples. +#enable= + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once).You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use"--disable=all --enable=classes +# --disable=W" +disable=no-init, star-args, no-member, import-error + + +[REPORTS] + +# Set the output format. Available formats are text, parseable, colorized, msvs +# (visual studio) and html. You can also give a reporter class, eg +# mypackage.mymodule.MyReporterClass. +output-format=text + +# Include message's id in output +include-ids=no + +# Include symbolic ids of messages in output +symbols=no + +# Put messages in a separate file for each module / package specified on the +# command line instead of printing them on stdout. Reports (if any) will be +# written in a file name "pylint_global.[txt|html]". +files-output=no + +# Tells whether to display a full report or only the messages +reports=yes + +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) + +# Add a comment according to your evaluation note. This is used by the global +# evaluation report (RP0004). +comment=no + + +[SIMILARITIES] + +# Minimum lines number of a similarity. +min-similarity-lines=4 + +# Ignore comments when computing similarities. +ignore-comments=yes + +# Ignore docstrings when computing similarities. +ignore-docstrings=yes + +# Ignore imports when computing similarities. +ignore-imports=no + + +[VARIABLES] + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# A regular expression matching the beginning of the name of dummy variables +# (i.e. not used). +dummy-variables-rgx=_|dummy + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid to define new builtins when possible. +additional-builtins= + + +[BASIC] + +# Required attributes for module, separated by a comma +required-attributes= + +# List of builtins function names that should not be used, separated by a comma +bad-functions=map,filter,apply,input + +# Regular expression which should only match correct module names +module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$ + +# Regular expression which should only match correct module level names +const-rgx=(([A-Z_][A-Za-z0-9_]*)|(__.*__))$ + +# Regular expression which should only match correct class names +class-rgx=[A-Z_][a-zA-Z0-9]+$ + +# Regular expression which should only match correct function names +function-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct method names +method-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct instance attribute names +attr-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct argument names +argument-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct variable names +variable-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct list comprehension / +# generator expression variable names +inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$ + +# Good variable names which should always be accepted, separated by a comma +good-names=i,j,k,ex,Run,_ + +# Bad variable names which should always be refused, separated by a comma +bad-names=foo,bar,baz,toto,tutu,tata + +# Regular expression which should only match functions or classes name which do +# not require a docstring +no-docstring-rgx=__.*__ + + +[FORMAT] + +# Maximum number of characters on a single line. +max-line-length=100 + +# Maximum number of lines in a module +max-module-lines=1000 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME,XXX,TODO + + +[TYPECHECK] + +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes + +# List of classes names for which member attributes should not be checked +# (useful for classes with attributes dynamically set). +ignored-classes=SQLObject + +# When zope mode is activated, add a predefined set of Zope acquired attributes +# to generated-members. +zope=no + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E0201 when accessed. Python regular +# expressions are accepted. +generated-members=REQUEST,acl_users,aq_parent + + +[DESIGN] + +# Maximum number of arguments for function / method +max-args=5 + +# Argument names that match this expression will be ignored. Default to name +# with leading underscore +ignored-argument-names=_.* + +# Maximum number of locals for function / method body +max-locals=15 + +# Maximum number of return / yield for function / method body +max-returns=6 + +# Maximum number of branch for function / method body +max-branchs=12 + +# Maximum number of statements in function / method body +max-statements=50 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of attributes for a class (see R0902). +max-attributes=7 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=20 + + +[IMPORTS] + +# Deprecated modules which should not be used, separated by a comma +deprecated-modules=regsub,string,TERMIOS,Bastion,rexec + +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled) +import-graph= + +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled) +ext-import-graph= + +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled) +int-import-graph= + + +[CLASSES] + +# List of interface methods to ignore, separated by a comma. This is used for +# instance to not check methods defines in Zope's Interface base class. +ignore-iface-methods=isImplementedBy,deferred,extends,names,namesAndDescriptions,queryDescriptionFor,getBases,getDescriptionFor,getDoc,getName,getTaggedValue,getTaggedValueTags,isEqualOrExtendedBy,setTaggedValue,isImplementedByInstancesOf,adaptWith,is_implemented_by + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__,__new__,setUp + +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls + +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=mcs + + +[EXCEPTIONS] + +# Exceptions that will emit a warning when being caught. Defaults to +# "Exception" +overgeneral-exceptions=Exception diff --git a/wqflask/wqflask/correlation/correlation_plot.py b/wqflask/wqflask/correlation/correlation_plot.py index 4b043fc3..c2b64d70 100644 --- a/wqflask/wqflask/correlation/correlation_plot.py +++ b/wqflask/wqflask/correlation/correlation_plot.py @@ -24,6 +24,10 @@ class CorrelationPlot(object): self.samples_1 = self.get_samples(self.dataset1, sample_names_1, self.trait1) self.samples_2 = self.get_samples(self.dataset2, sample_names_2, self.trait2) + coords = {} + for sample in self.samples_1: + coords[sample.name] = (sample.val) + def get_sample_names(self, dataset): if dataset.group.parlist: @@ -45,4 +49,5 @@ class CorrelationPlot(object): sample_group_type='primary', header="%s Only" % (dataset.group.name)) - return samples \ No newline at end of file + return samples + \ No newline at end of file diff --git a/wqflask/wqflask/my_pylmm/pyLMM/lmm.py b/wqflask/wqflask/my_pylmm/pyLMM/lmm.py index a3ba8fdb..10221a2e 100644 --- a/wqflask/wqflask/my_pylmm/pyLMM/lmm.py +++ b/wqflask/wqflask/my_pylmm/pyLMM/lmm.py @@ -28,6 +28,7 @@ from scipy import stats import pdb import gzip +import datetime import cPickle as pickle import simplejson as json @@ -38,6 +39,9 @@ from utility import temp_data from wqflask.my_pylmm.pyLMM import chunks +import redis +Redis = redis.Redis() + #np.seterr('raise') def run_human(pheno_vector, @@ -65,6 +69,7 @@ def run_human(pheno_vector, covariate_matrix) lmm_ob.fit() + # Buffers for pvalues and t-stats p_values = [] t_stats = [] @@ -86,19 +91,36 @@ def run_human(pheno_vector, with Bench("Create list of inputs"): inputs = list(plink_input) - + with Bench("Divide into chunks"): results = chunks.divide_into_chunks(inputs, 64) result_store = [] - identifier = uuid.uuid4() - for part, result in enumerate(results): - # todo: Don't use TempData here. Instead revert old one and store this stuff as a list - data_store = temp_data.TempData(identifier, "plink", part) - - data_store.store("data", pickle.dumps(result, pickle.HIGHEST_PROTOCOL)) - result_store.append(data_store) + identifier = str(uuid.uuid4()) + + lmm_vars = pickle.dumps(dict( + pheno_vector = pheno_vector, + covariate_matrix = covariate_matrix, + kinship_matrix = kinship_matrix + )) + Redis.hset(identifier, "lmm_vars", pickle.dumps(lmm_vars)) + + key = "plink_inputs" + timestamp = datetime.datetime.utcnow().isoformat() + + for part, result in enumerate(results): + #data = pickle.dumps(result, pickle.HIGHEST_PROTOCOL) + holder = pickle.dumps(dict( + identifier = identifier, + part = part, + timestamp = timestamp, + result = result + ), pickle.HIGHEST_PROTOCOL) + print("Adding:", part) + Redis.rpush(key, holder) + + print("***** Added to {} queue *****".format(key)) for snp, this_id in plink_input: with Bench("part before association"): if count > 2000: diff --git a/wqflask/wqflask/my_pylmm/pyLMM/process_plink.py b/wqflask/wqflask/my_pylmm/pyLMM/process_plink.py new file mode 100644 index 00000000..1274fe50 --- /dev/null +++ b/wqflask/wqflask/my_pylmm/pyLMM/process_plink.py @@ -0,0 +1,28 @@ +from __future__ import absolute_import, print_function, division + +import cPickle as pickle +import redis +Redis = redis.Redis() + +from wqflask.my_pylmm.pyLMM import lmm + +lmm_vars_pickled = Redis.get("lmm_vars") + + +plink_pickled = Redis.lpop("plink_inputs") + +plink_data = pickle.loads(plink_pickled) + +identifier = plink_data['identifier'] +print("identifier: ", identifier) + + + +ps, ts = lmm.human_association(snp, + n, + keep, + lmm_ob, + pheno_vector, + covariate_matrix, + kinship_matrix, + refit) |