black formatting

Author: Ben Elsworth

Diff for: demo/scripts/source/get_opengwas.py

@@ -17,6 +17,7 @@
 gwas_data_file = f"/tmp/opengwas-metadata-{today}.csv"
 gwas_tophits = f"/tmp/opengwas-tophits-{today}.csv"
 
+
 def get_gwas_data():
     # create the data
     gwas_api_url = "http://gwasapi.mrcieu.ac.uk/gwasinfo"
@@ -29,11 +30,11 @@ def get_gwas_data():
     logger.info(df["year"].describe())
     df.to_csv(outData, index=False)
     outData.close()
-    copy_source_data(data_name=data_name,filename=gwas_data_file)
+    copy_source_data(data_name=data_name, filename=gwas_data_file)
 
 
 def get_top_hits():
-    df = pd.read_csv(gwas_data_file,low_memory=False)
+    df = pd.read_csv(gwas_data_file, low_memory=False)
     gwas_ids = list(df.id)
     logger.info(gwas_ids[0:10])
     gwas_api_url = "http://gwasapi.mrcieu.ac.uk/tophits"
@@ -42,7 +43,7 @@ def get_top_hits():
     res = response.json()
     th_df = pd.json_normalize(res)
     th_df.to_csv(gwas_tophits, index=False)
-    copy_source_data(data_name=data_name,filename=gwas_tophits)
+    copy_source_data(data_name=data_name, filename=gwas_tophits)
 
 
 if __name__ == "__main__":

Diff for: demo/scripts/source/get_opentargets.py

@@ -124,7 +124,7 @@ def main(oFile) -> None:
 
     OPENTARGETS_DIR.mkdir(parents=True, exist_ok=True)
     ot_df.to_csv(oFile, index=False)
-    copy_source_data(data_name=data_name,filename=oFile)
+    copy_source_data(data_name=data_name, filename=oFile)
 
 
 if __name__ == "__main__":

Diff for: demo/scripts/source/get_reactome.py

@@ -29,10 +29,9 @@ def protein_to_pathway():
     logger.info(df.head())
     filename = f"/tmp/UniProt2Reactome_All_Levels_human_{today}.csv"
     df.to_csv(
-        filename,
-        index=False,
+        filename, index=False,
     )
-    copy_source_data(data_name=data_name,filename=filename)
+    copy_source_data(data_name=data_name, filename=filename)
 
 
 def pathways():
@@ -45,10 +44,8 @@ def pathways():
     df1 = df1[df1["species"] == "Homo sapiens"]
     logger.info(df1.head())
     filename = f"/tmp/ReactomePathways_human_{today}.csv"
-    df1.to_csv(
-        filename, index=False
-    )
-    copy_source_data(data_name=data_name,filename=filename)
+    df1.to_csv(filename, index=False)
+    copy_source_data(data_name=data_name, filename=filename)
 
     # hierarchy
     url = "https://reactome.org/download/current/ReactomePathwaysRelation.txt"
@@ -64,10 +61,10 @@ def pathways():
     logger.info(df2.shape)
     filename = f"/tmp/ReactomePathwaysRelation_human_{today}.csv"
     df2.to_csv(
-        filename,
-        index=False,
+        filename, index=False,
     )
-    copy_source_data(data_name=data_name,filename=filename)
+    copy_source_data(data_name=data_name, filename=filename)
+
 
 if __name__ == "__main__":
     protein_to_pathway()

Diff for: demo/scripts/source/variant_vep.py

@@ -19,17 +19,17 @@
 
 vep_data_dir = "/data/vep_data"
 
+
 def process_variants(variant_file):
     df = pd.read_csv(variant_file, low_memory=False)
     df = df["rsid"]
     df.drop_duplicates(inplace=True)
     logger.info(df.head())
     # in this example, only run 100 variants as can be quite slow
     filename = f"{vep_data_dir}/variants-{today}.txt"
-    df.head(n=100).to_csv(
-        filename, index=False, header=False
-    )
-    copy_source_data(data_name=data_name,filename=filename)
+    df.head(n=100).to_csv(filename, index=False, header=False)
+    copy_source_data(data_name=data_name, filename=filename)
+
 
 def run_vep(variant_dir, variant_file):
     com = """
@@ -46,9 +46,9 @@ def run_vep(variant_dir, variant_file):
     logger.info(com)
     subprocess.call(com, shell=True)
     # copy results
-    #com = f"cp /data/vep_data/vep-{today}.txt {env_configs['data_dir']}/vep/"
-    #subprocess.call(com, shell=True)
-    copy_source_data(data_name=data_name,filename=f'{vep_data_dir}/vep-{today}.txt')
+    # com = f"cp /data/vep_data/vep-{today}.txt {env_configs['data_dir']}/vep/"
+    # subprocess.call(com, shell=True)
+    copy_source_data(data_name=data_name, filename=f"{vep_data_dir}/vep-{today}.txt")
 
 
 if __name__ == "__main__":

Diff for: tests/utils/__init__.py

@@ -11,7 +11,9 @@ def is_prop_array(prop: Dict) -> bool:
     return prop["type"] == "array"
 
 
-def group_props_by_type(entity: Dict, column_prefix: Optional[str], is_rel: bool = False) -> Tuple:
+def group_props_by_type(
+    entity: Dict, column_prefix: Optional[str], is_rel: bool = False
+) -> Tuple:
     """
     Group props by scalar and array props.
     If `is_rel`, remove source and target from props

Diff for: tests/utils/models.py

@@ -2,6 +2,7 @@
 
 from pydantic import BaseModel, ValidationError, validator
 
+
 class PropertyScalar(BaseModel):
     doc: str
     type: str
@@ -16,6 +17,7 @@ class PropertyArray(BaseModel):
 class MetaNodeMetaField(BaseModel):
     id: str
     name: str
+
     class Config:
         fields = {"id": "_id", "name": "_name"}
 

Diff for: workflow/scripts/utils/general.py

@@ -137,7 +137,7 @@ def get_schema_data(meta_name="all"):
             elif meta_name in schema_data["meta_rels"]:
                 schema_data = schema_data["meta_rels"][meta_name]
         except:
-            logger.error('Something is wrong with db_schema.yaml')
+            logger.error("Something is wrong with db_schema.yaml")
             exit()
     return schema_data
 
@@ -256,30 +256,31 @@ def create_df(data_dir, name, nrows=None):
     return df
 
 
-def copy_source_data(data_name,filename):
+def copy_source_data(data_name, filename):
     # make sure graph directory exists
     server = env_configs["server_name"]
-    data_dir  = os.path.join(env_configs["data_dir"],data_name)
+    data_dir = os.path.join(env_configs["data_dir"], data_name)
 
-    #make directory
+    # make directory
     if server == None:
         com = f"mkdir -p {data_dir}"
     else:
         com = f"ssh {server} mkdir -p {data_dir}"
     logger.info(com)
     subprocess.call(com, shell=True)
 
-    #copy new files to data directory
+    # copy new files to data directory
     logger.info("Syncing {}", filename)
     if server == None:
         com = f"rsync -avz {filename} {data_dir}"
     else:
         com = f"rsync -avz {filename} {server}:{data_dir}"
     logger.info(com)
     subprocess.call(com, shell=True)
-    
-def create_neo4j_array_from_array(df,col_name):
-    df[col_name]=df[col_name].astype('str')
-    df[col_name]=df[col_name].str.replace(',',';')
-    df[col_name]=df[col_name].str.strip('[]')
+
+
+def create_neo4j_array_from_array(df, col_name):
+    df[col_name] = df[col_name].astype("str")
+    df[col_name] = df[col_name].str.replace(",", ";")
+    df[col_name] = df[col_name].str.strip("[]")
     return df