aboutsummaryrefslogtreecommitdiff
path: root/wqflask/maintenance
diff options
context:
space:
mode:
Diffstat (limited to 'wqflask/maintenance')
-rw-r--r--wqflask/maintenance/convert_dryad_to_bimbam.py3
-rw-r--r--wqflask/maintenance/convert_geno_to_bimbam.py4
-rw-r--r--wqflask/maintenance/gen_select_dataset.py5
-rw-r--r--wqflask/maintenance/generate_kinship_from_bimbam.py1
-rw-r--r--wqflask/maintenance/generate_probesetfreeze_file.py7
-rw-r--r--wqflask/maintenance/geno_to_json.py6
-rw-r--r--wqflask/maintenance/get_group_samplelists.py3
-rw-r--r--wqflask/maintenance/print_benchmark.py4
-rw-r--r--wqflask/maintenance/quantile_normalize.py6
-rw-r--r--wqflask/maintenance/set_resource_defaults.py7
10 files changed, 42 insertions, 4 deletions
diff --git a/wqflask/maintenance/convert_dryad_to_bimbam.py b/wqflask/maintenance/convert_dryad_to_bimbam.py
index 8eab66e8..e417c280 100644
--- a/wqflask/maintenance/convert_dryad_to_bimbam.py
+++ b/wqflask/maintenance/convert_dryad_to_bimbam.py
@@ -55,15 +55,18 @@ def read_dryad_file(filename):
#
# return geno_rows
+
def write_bimbam_files(geno_rows):
with open('/home/zas1024/cfw_data/CFW_geno.txt', 'w') as geno_fh:
for row in geno_rows:
geno_fh.write(", ".join(row) + "\n")
+
def convert_dryad_to_bimbam(filename):
geno_file_rows = read_dryad_file(filename)
write_bimbam_files(geno_file_rows)
+
if __name__ == "__main__":
input_filename = "/home/zas1024/cfw_data/" + sys.argv[1] + ".txt"
convert_dryad_to_bimbam(input_filename)
diff --git a/wqflask/maintenance/convert_geno_to_bimbam.py b/wqflask/maintenance/convert_geno_to_bimbam.py
index dc01cbb3..5b2369c9 100644
--- a/wqflask/maintenance/convert_geno_to_bimbam.py
+++ b/wqflask/maintenance/convert_geno_to_bimbam.py
@@ -20,8 +20,10 @@ import simplejson as json
from pprint import pformat as pf
+
class EmptyConfigurations(Exception): pass
+
class Marker:
def __init__(self):
self.name = None
@@ -30,6 +32,7 @@ class Marker:
self.Mb = None
self.genotypes = []
+
class ConvertGenoFile:
def __init__(self, input_file, output_files):
@@ -178,6 +181,7 @@ class ConvertGenoFile:
print(" Row is:", convertob.latest_row_value)
break
+
if __name__ == "__main__":
Old_Geno_Directory = """/export/local/home/zas1024/gn2-zach/genotype_files/genotype"""
New_Geno_Directory = """/export/local/home/zas1024/gn2-zach/genotype_files/genotype/bimbam"""
diff --git a/wqflask/maintenance/gen_select_dataset.py b/wqflask/maintenance/gen_select_dataset.py
index f480d63f..583a06e1 100644
--- a/wqflask/maintenance/gen_select_dataset.py
+++ b/wqflask/maintenance/gen_select_dataset.py
@@ -55,6 +55,7 @@ from pprint import pformat as pf
#conn = Engine.connect()
+
def parse_db_uri():
"""Converts a database URI to the db name, host name, user name, and password"""
@@ -143,6 +144,7 @@ def phenotypes_exist(group_name):
else:
return False
+
def genotypes_exist(group_name):
#print("group_name:", group_name)
Cursor.execute("""select Name from GenoFreeze
@@ -156,6 +158,7 @@ def genotypes_exist(group_name):
else:
return False
+
def build_types(species, group):
"""Fetches tissues
@@ -184,6 +187,7 @@ def build_types(species, group):
return results
+
def get_datasets(types):
"""Build datasets list"""
datasets = {}
@@ -308,6 +312,7 @@ def _test_it():
datasets = build_datasets("Mouse", "BXD", "Hippocampus")
#print("build_datasets:", pf(datasets))
+
if __name__ == '__main__':
Conn = MySQLdb.Connect(**parse_db_uri())
Cursor = Conn.cursor()
diff --git a/wqflask/maintenance/generate_kinship_from_bimbam.py b/wqflask/maintenance/generate_kinship_from_bimbam.py
index 664e9e48..7cc60c9e 100644
--- a/wqflask/maintenance/generate_kinship_from_bimbam.py
+++ b/wqflask/maintenance/generate_kinship_from_bimbam.py
@@ -13,6 +13,7 @@ sys.path.append("..")
import os
import glob
+
class GenerateKinshipMatrices:
def __init__(self, group_name, geno_file, pheno_file):
self.group_name = group_name
diff --git a/wqflask/maintenance/generate_probesetfreeze_file.py b/wqflask/maintenance/generate_probesetfreeze_file.py
index b1e41e9a..bd9c2ab4 100644
--- a/wqflask/maintenance/generate_probesetfreeze_file.py
+++ b/wqflask/maintenance/generate_probesetfreeze_file.py
@@ -23,10 +23,12 @@ def get_cursor():
cursor = con.cursor()
return cursor
+
def show_progress(process, counter):
if counter % 1000 == 0:
print("{}: {}".format(process, counter))
+
def get_strains(cursor):
cursor.execute("""select Strain.Name
from Strain, StrainXRef, InbredSet
@@ -42,6 +44,7 @@ def get_strains(cursor):
return strains
+
def get_probeset_vals(cursor, dataset_name):
cursor.execute(""" select ProbeSet.Id, ProbeSet.Name
from ProbeSetXRef,
@@ -77,6 +80,7 @@ def get_probeset_vals(cursor, dataset_name):
return probeset_vals
+
def trim_strains(strains, probeset_vals):
trimmed_strains = []
#print("probeset_vals is:", pf(probeset_vals))
@@ -89,6 +93,7 @@ def trim_strains(strains, probeset_vals):
print("trimmed_strains:", pf(trimmed_strains))
return trimmed_strains
+
def write_data_matrix_file(strains, probeset_vals, filename):
with open(filename, "wb") as fh:
csv_writer = csv.writer(fh, delimiter=",", quoting=csv.QUOTE_ALL)
@@ -103,6 +108,7 @@ def write_data_matrix_file(strains, probeset_vals, filename):
csv_writer.writerow(row_data)
show_progress("Writing", counter)
+
def main():
filename = os.path.expanduser("~/gene/wqflask/maintenance/" +
"ProbeSetFreezeId_210_FullName_Eye_AXBXA_Illumina_V6.2" +
@@ -117,5 +123,6 @@ def main():
trimmed_strains = trim_strains(strains, probeset_vals)
write_data_matrix_file(trimmed_strains, probeset_vals, filename)
+
if __name__ == '__main__':
main()
diff --git a/wqflask/maintenance/geno_to_json.py b/wqflask/maintenance/geno_to_json.py
index fa0dcebd..ad3f2b72 100644
--- a/wqflask/maintenance/geno_to_json.py
+++ b/wqflask/maintenance/geno_to_json.py
@@ -25,10 +25,10 @@ from pprint import pformat as pf
#from utility.tools import flat_files
+
class EmptyConfigurations(Exception): pass
-
class Marker:
def __init__(self):
self.name = None
@@ -37,6 +37,7 @@ class Marker:
self.Mb = None
self.genotypes = []
+
class ConvertGenoFile:
def __init__(self, input_file, output_file):
@@ -78,7 +79,6 @@ class ConvertGenoFile:
# elif self.file_type == "snps":
# self.process_snps_file()
-
def process_csv(self):
for row_count, row in enumerate(self.process_rows()):
row_items = row.split("\t")
@@ -121,7 +121,6 @@ class ConvertGenoFile:
# self.output_fh.write("\n")
-
def process_rows(self):
for self.latest_row_pos, row in enumerate(self.input_fh):
# if self.input_file.endswith(".geno.gz"):
@@ -182,7 +181,6 @@ class ConvertGenoFile:
# convertob = ConvertGenoFile(input_file, output_file)
-
if __name__ == "__main__":
Old_Geno_Directory = """/export/local/home/zas1024/gn2-zach/genotype_files/genotype"""
New_Geno_Directory = """/export/local/home/zas1024/gn2-zach/genotype_files/genotype/json"""
diff --git a/wqflask/maintenance/get_group_samplelists.py b/wqflask/maintenance/get_group_samplelists.py
index 3f9d0278..0a450d3f 100644
--- a/wqflask/maintenance/get_group_samplelists.py
+++ b/wqflask/maintenance/get_group_samplelists.py
@@ -4,12 +4,14 @@ import gzip
from base import webqtlConfig
+
def get_samplelist(file_type, geno_file):
if file_type == "geno":
return get_samplelist_from_geno(geno_file)
elif file_type == "plink":
return get_samplelist_from_plink(geno_file)
+
def get_samplelist_from_geno(genofilename):
if os.path.isfile(genofilename + '.gz'):
genofilename += '.gz'
@@ -33,6 +35,7 @@ def get_samplelist_from_geno(genofilename):
samplelist = headers[3:]
return samplelist
+
def get_samplelist_from_plink(genofilename):
genofile = open(genofilename)
diff --git a/wqflask/maintenance/print_benchmark.py b/wqflask/maintenance/print_benchmark.py
index a1046c86..9d12da8a 100644
--- a/wqflask/maintenance/print_benchmark.py
+++ b/wqflask/maintenance/print_benchmark.py
@@ -15,15 +15,18 @@ class TheCounter:
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
@@ -37,5 +40,6 @@ def new_main():
print(pf(TheCounter.Counters))
+
if __name__ == '__main__':
new_main()
diff --git a/wqflask/maintenance/quantile_normalize.py b/wqflask/maintenance/quantile_normalize.py
index 6751a8e5..1896bc52 100644
--- a/wqflask/maintenance/quantile_normalize.py
+++ b/wqflask/maintenance/quantile_normalize.py
@@ -14,6 +14,7 @@ from wqflask import app
from utility.elasticsearch_tools import get_elasticsearch_connection
from utility.tools import ELASTICSEARCH_HOST, ELASTICSEARCH_PORT, SQL_URI
+
def parse_db_uri():
"""Converts a database URI to the db name, host name, user name, and password"""
@@ -28,6 +29,7 @@ def parse_db_uri():
print(db_conn_info)
return db_conn_info
+
def create_dataframe(input_file):
with open(input_file) as f:
ncols = len(f.readline().split("\t"))
@@ -36,6 +38,8 @@ def create_dataframe(input_file):
return pd.DataFrame(input_array)
# This function taken from https://github.com/ShawnLYU/Quantile_Normalize
+
+
def quantileNormalize(df_input):
df = df_input.copy()
# compute rank
@@ -50,6 +54,7 @@ def quantileNormalize(df_input):
df[col] = [rank[i] for i in t]
return df
+
def set_data(dataset_name):
orig_file = "/home/zas1024/cfw_data/" + dataset_name + ".txt"
@@ -95,6 +100,7 @@ def set_data(dataset_name):
}
}
+
if __name__ == '__main__':
Conn = MySQLdb.Connect(**parse_db_uri())
Cursor = Conn.cursor()
diff --git a/wqflask/maintenance/set_resource_defaults.py b/wqflask/maintenance/set_resource_defaults.py
index 286094dd..c6c4f44c 100644
--- a/wqflask/maintenance/set_resource_defaults.py
+++ b/wqflask/maintenance/set_resource_defaults.py
@@ -37,6 +37,7 @@ import urllib.parse
from utility.logger import getLogger
logger = getLogger(__name__)
+
def parse_db_uri():
"""Converts a database URI to the db name, host name, user name, and password"""
@@ -51,6 +52,7 @@ def parse_db_uri():
print(db_conn_info)
return db_conn_info
+
def insert_probeset_resources(default_owner_id):
current_resources = Redis.hgetall("resources")
Cursor.execute(""" SELECT
@@ -77,6 +79,7 @@ def insert_probeset_resources(default_owner_id):
add_resource(resource_ob, update=False)
+
def insert_publish_resources(default_owner_id):
current_resources = Redis.hgetall("resources")
Cursor.execute(""" SELECT
@@ -110,6 +113,7 @@ def insert_publish_resources(default_owner_id):
else:
continue
+
def insert_geno_resources(default_owner_id):
current_resources = Redis.hgetall("resources")
Cursor.execute(""" SELECT
@@ -139,6 +143,7 @@ def insert_geno_resources(default_owner_id):
add_resource(resource_ob, update=False)
+
def insert_resources(default_owner_id):
current_resources = get_resources()
print("START")
@@ -149,6 +154,7 @@ def insert_resources(default_owner_id):
insert_probeset_resources(default_owner_id)
print("AFTER PROBESET")
+
def main():
"""Generates and outputs (as json file) the data for the main dropdown menus on the home page"""
@@ -158,6 +164,7 @@ def main():
insert_resources(owner_id)
+
if __name__ == '__main__':
Conn = MySQLdb.Connect(**parse_db_uri())
Cursor = Conn.cursor()
generated by cgit v1.2.3 (git 2.44.0) at 2024-11-22 17:26:37 +0000