aboutsummaryrefslogtreecommitdiff
path: root/wqflask/base/data_set
diff options
context:
space:
mode:
authorFrederick Muriuki Muriithi2023-06-15 14:40:37 +0300
committerFrederick Muriuki Muriithi2023-06-20 13:36:50 +0300
commitaa4d213692cb27a903fe1593e2dd3387e638b350 (patch)
treef41cfdf7e369cae767af5534cfc02c9998b9e4a2 /wqflask/base/data_set
parenta56d857dc1f6dbc25819a4af116139a2f3e14a68 (diff)
downloadgenenetwork2-aa4d213692cb27a903fe1593e2dd3387e638b350.tar.gz
Configs: Introduce Blueprints. Refactor configs in webqtlConfig.
* Introduce flask Blueprints to help with decoupling the various modules from the `wqflask/__init__.py` module * Refactor settings: Create a function `base.webqtlConfig.init_app(...)` to handle setting up the configurations on the app correctly. Call this function at app creation time. * Move configuration utility functions from `utility.tools` module to `utility.configuration` module. * Use the `get_setting(...)` function to retrieve configuration settings from the application.
Diffstat (limited to 'wqflask/base/data_set')
-rw-r--r--wqflask/base/data_set/__init__.py10
-rw-r--r--wqflask/base/data_set/datasetgroup.py22
-rw-r--r--wqflask/base/data_set/datasettype.py7
-rw-r--r--wqflask/base/data_set/markers.py10
-rw-r--r--wqflask/base/data_set/utils.py10
5 files changed, 33 insertions, 26 deletions
diff --git a/wqflask/base/data_set/__init__.py b/wqflask/base/data_set/__init__.py
index e49c6a93..ad51e47e 100644
--- a/wqflask/base/data_set/__init__.py
+++ b/wqflask/base/data_set/__init__.py
@@ -6,11 +6,14 @@ import pickle as pickle
# 3rd-party imports
from redis import Redis
+from flask import current_app as app
# local imports
-from .dataset import DataSet
from base import webqtlConfig
-from utility.tools import USE_REDIS
+from wqflask.database import database_connection
+from utility.configuration import get_setting_bool
+
+from .dataset import DataSet
from .datasettype import DatasetType
from .tempdataset import TempDataSet
from .datasetgroup import DatasetGroup
@@ -18,7 +21,6 @@ from .utils import query_table_timestamp
from .genotypedataset import GenotypeDataSet
from .phenotypedataset import PhenotypeDataSet
from .mrnaassaydataset import MrnaAssayDataSet
-from wqflask.database import database_connection
# Used by create_database to instantiate objects
# Each subclass will add to this
@@ -113,7 +115,7 @@ def datasets(group_name, this_group=None, redis_conn=Redis()):
dataset_menu.append(dict(tissue=tissue_name,
datasets=[(dataset, dataset_short)]))
- if USE_REDIS:
+ if get_setting_bool("USE_REDIS"):
redis_conn.set(key, pickle.dumps(dataset_menu, pickle.HIGHEST_PROTOCOL))
redis_conn.expire(key, 60 * 5)
diff --git a/wqflask/base/data_set/datasetgroup.py b/wqflask/base/data_set/datasetgroup.py
index 72577f38..90c59a1e 100644
--- a/wqflask/base/data_set/datasetgroup.py
+++ b/wqflask/base/data_set/datasetgroup.py
@@ -3,6 +3,7 @@
import os
import json
+from flask import current_app as app
from base import webqtlConfig
from .markers import Markers, HumanMarkers
@@ -11,11 +12,11 @@ from utility import gen_geno_ob
from db import webqtlDatabaseFunction
from maintenance import get_group_samplelists
from wqflask.database import database_connection
-from utility.tools import (
+from utility.configuration import (
locate,
- USE_REDIS,
flat_files,
flat_file_exists,
+ get_setting_bool,
locate_ignore_error)
class DatasetGroup:
@@ -87,8 +88,8 @@ class DatasetGroup:
def get_markers(self):
def check_plink_gemma():
- if flat_file_exists("mapping"):
- MAPPING_PATH = flat_files("mapping") + "/"
+ if flat_file_exists(app, "mapping"):
+ MAPPING_PATH = flat_files(app, "mapping") + "/"
if os.path.isfile(MAPPING_PATH + self.name + ".bed"):
return True
return False
@@ -117,6 +118,7 @@ class DatasetGroup:
def get_study_samplelists(self):
study_sample_file = locate_ignore_error(
+ app,
self.name + ".json", 'study_sample_lists')
try:
f = open(study_sample_file)
@@ -137,13 +139,15 @@ class DatasetGroup:
def get_samplelist(self, redis_conn):
result = None
key = "samplelist:v3:" + self.name
+ USE_REDIS = get_setting_bool(app, "USE_REDIS")
if USE_REDIS:
result = redis_conn.get(key)
if result is not None:
self.samplelist = json.loads(result)
else:
- genotype_fn = locate_ignore_error(self.name + ".geno", 'genotype')
+ genotype_fn = locate_ignore_error(
+ app, self.name + ".geno", 'genotype')
if genotype_fn:
self.samplelist = get_group_samplelists.get_samplelist(
"geno", genotype_fn)
@@ -168,12 +172,12 @@ class DatasetGroup:
# reaper barfs on unicode filenames, so here we ensure it's a string
if self.genofile:
if "RData" in self.genofile: # ZS: This is a temporary fix; I need to change the way the JSON files that point to multiple genotype files are structured to point to other file types like RData
- full_filename = str(
- locate(self.genofile.split(".")[0] + ".geno", 'genotype'))
+ full_filename = str(locate(
+ app, self.genofile.split(".")[0] + ".geno", 'genotype'))
else:
- full_filename = str(locate(self.genofile, 'genotype'))
+ full_filename = str(locate(app, self.genofile, 'genotype'))
else:
- full_filename = str(locate(self.name + '.geno', 'genotype'))
+ full_filename = str(locate(app, self.name + '.geno', 'genotype'))
genotype_1 = gen_geno_ob.genotype(full_filename)
if genotype_1.type == "group" and self.parlist:
diff --git a/wqflask/base/data_set/datasettype.py b/wqflask/base/data_set/datasettype.py
index 05f0f564..ab36a797 100644
--- a/wqflask/base/data_set/datasettype.py
+++ b/wqflask/base/data_set/datasettype.py
@@ -4,11 +4,10 @@ import json
import requests
from typing import Optional, Dict
-
from redis import Redis
+from flask import current_app as app
-
-from utility.tools import GN2_BASE_URL
+from utility.configuration import get_setting
from wqflask.database import database_connection
@@ -41,7 +40,7 @@ class DatasetType:
# emptied
try:
data = json.loads(requests.get(
- GN2_BASE_URL + "/api/v_pre1/gen_dropdown",
+ get_setting(app, "GN2_BASE_URL") + "/api/v_pre1/gen_dropdown",
timeout=5).content)
for _species in data['datasets']:
for group in data['datasets'][_species]:
diff --git a/wqflask/base/data_set/markers.py b/wqflask/base/data_set/markers.py
index 6f56445e..2fa7cce0 100644
--- a/wqflask/base/data_set/markers.py
+++ b/wqflask/base/data_set/markers.py
@@ -2,16 +2,18 @@
import math
-from utility.tools import locate, flat_files
+from flask import current_app as app
+
+from utility.configuration import locate, flat_files
class Markers:
"""Todo: Build in cacheing so it saves us reading the same file more than once"""
def __init__(self, name):
- json_data_fh = open(locate(name + ".json", 'genotype/json'))
+ json_data_fh = open(locate(app, name + ".json", 'genotype/json'))
markers = []
- with open("%s/%s_snps.txt" % (flat_files('genotype/bimbam'), name), 'r') as bimbam_fh:
+ with open("%s/%s_snps.txt" % (flat_files(app, 'genotype/bimbam'), name), 'r') as bimbam_fh:
if len(bimbam_fh.readline().split(", ")) > 2:
delimiter = ", "
elif len(bimbam_fh.readline().split(",")) > 2:
@@ -73,7 +75,7 @@ class HumanMarkers(Markers):
"Markers for humans ..."
def __init__(self, name, specified_markers=[]):
- marker_data_fh = open(flat_files('mapping') + '/' + name + '.bim')
+ marker_data_fh = open(flat_files(app, 'mapping') + '/' + name + '.bim')
self.markers = []
for line in marker_data_fh:
splat = line.strip().split()
diff --git a/wqflask/base/data_set/utils.py b/wqflask/base/data_set/utils.py
index 703fee04..465538af 100644
--- a/wqflask/base/data_set/utils.py
+++ b/wqflask/base/data_set/utils.py
@@ -6,9 +6,9 @@ import json
import hashlib
from typing import List
+from flask import current_app as app
-from utility.tools import SQL_URI
-from base.webqtlConfig import TMPDIR
+from utility.configuration import get_setting
from wqflask.database import parse_db_url, database_connection
def geno_mrna_confidentiality(ob):
@@ -27,7 +27,7 @@ def query_table_timestamp(dataset_type: str):
# computation data and actions
with database_connection() as conn, conn.cursor() as cursor:
- fetch_db_name = parse_db_url(SQL_URI)
+ fetch_db_name = parse_db_url(get_setting("SQL_URI"))
cursor.execute(
"SELECT UPDATE_TIME FROM "
"information_schema.tables "
@@ -57,7 +57,7 @@ def cache_dataset_results(dataset_name: str, dataset_type: str, samplelist: List
samplelist_as_str = ",".join(samplelist)
file_name = generate_hash_file(dataset_name, dataset_type, table_timestamp, samplelist_as_str)
- file_path = os.path.join(TMPDIR, f"{file_name}.json")
+ file_path = os.path.join(app.config["WEBQTL_TMPDIR"], f"{file_name}.json")
with open(file_path, "w") as file_handler:
json.dump(query_results, file_handler)
@@ -70,7 +70,7 @@ def fetch_cached_results(dataset_name: str, dataset_type: str, samplelist: List)
samplelist_as_str = ",".join(samplelist)
file_name = generate_hash_file(dataset_name, dataset_type, table_timestamp, samplelist_as_str)
- file_path = os.path.join(TMPDIR, f"{file_name}.json")
+ file_path = os.path.join(app.config["WEBQTL_TMPDIR"], f"{file_name}.json")
try:
with open(file_path, "r") as file_handler: