update scripts for DB generation with new repos (+ blacked)

Models/AVC/generate_avcdataset.py

@@ -44,7 +44,7 @@ population.rename(columns={"index": "id"}, inplace=True)
 
 ###### Assign an AVC status
 
-pAVC, pTA = pickle.load(open("AVCGenerator/ptavc.pkl", "rb"))
+pAVC, pTA = pickle.load(open("Models/AVC/ptavc.pkl", "rb"))
 pAVC["sex"] = (pAVC["gender"] == "F").astype("int") + 1
 
 # transform the age into intervals matching the ones of pTAVC
@@ -59,7 +59,7 @@ population = pd.merge(
 )[["id", "age", "sex", "dpt", "code", "RR", "city_name", "p"]]
 
 
-population["avc"] = population["p"] > np.random.rand(len(population["p"])) 
+population["avc"] = population["p"] > np.random.rand(len(population["p"]))
 population["type"] = np.random.choice(
     pTA["type"], p=pTA["p"], size=len(population["p"])
 )
@@ -72,7 +72,7 @@ population.loc[population.avc == True, "date_avc"] = [
 ]
 
 
-mortality_laws = pickle.load(open("AVCGenerator/mortality_weibull_params.pkl", "rb"))
+mortality_laws = pickle.load(open("Models/AVC/mortality_weibull_params.pkl", "rb"))
 # mortality_laws[['age','sex','type','k','lambda']]
 mortality_laws.set_index(["age", "sex", "type"], inplace=True)  # ,'k','lambda']]
 
@@ -139,10 +139,10 @@ simulator.run()
 
 # create a context with the default nomenclature DB
 # context =  OpenDataFactoryContext("datarep/snds_nomenclature.db", datarep="../datarep")
-#generate the patients 
+# generate the patients
 factory = PatientFactory(simulator.context, simulator.GPs)
-attribute_map={'sex':'sex', 'age':'age', 'dc_date':"deathdate", 'dc_cause':'type'}
-patients=factory.load(population, attribute_map)
+attribute_map = {"sex": "sex", "age": "age", "dc_date": "deathdate", "dc_cause": "type"}
+patients = factory.load(population, attribute_map)
 
 
 ##########################################
@@ -218,7 +218,10 @@ def generate_drugs(x):
     loc_drugs["patient"] = np.random.choice(indices, size=len(loc_drugs))
 
     # random dates
-    loc_drugs['date']=[np.datetime64("2022-01-01") + np.timedelta64(e, "D") for e in np.random.randint(size=len(loc_drugs), low=0, high=365)]
+    loc_drugs["date"] = [
+        np.datetime64("2022-01-01") + np.timedelta64(e, "D")
+        for e in np.random.randint(size=len(loc_drugs), low=0, high=365)
+    ]
     return loc_drugs
 
 
@@ -247,7 +250,10 @@ simu = {
         "data": hosps,
         "attributes": {"pid": "id", "cim": "type", "date": "date_avc"},
     },
-    "drugs": {"data": drugs, "attributes": {"pid": "patient", "cip": "CIP13", 'date':'date'}},
+    "drugs": {
+        "data": drugs,
+        "attributes": {"pid": "patient", "cip": "CIP13", "date": "date"},
+    },
 }
 
 simulator.load(simu)
@@ -275,5 +281,5 @@ for p in simulator.patients:
     injector.injection(p)
 
 dbgen = simDB()
-dbgen.output_db_name = "AVCGenerator/snds_testgen.db"
+dbgen.output_db_name = "Models/AVC/snds_testgen.db"
 dbgen.generate(simulator, rootschemas="schema-snds/schemas")

Models/AVC/generate_eins.py

@@ -44,7 +44,7 @@ population.rename(columns={"index": "id"}, inplace=True)
 
 ###### Assign an AVC status
 
-pAVC, pTA = pickle.load(open("AVCGenerator/ptavc.pkl", "rb"))
+pAVC, pTA = pickle.load(open("Models/AVC/ptavc.pkl", "rb"))
 pAVC["sex"] = (pAVC["gender"] == "F").astype("int") + 1
 
 # transform the age into intervals matching the ones of pTAVC
@@ -59,7 +59,7 @@ population = pd.merge(
 )[["id", "age", "sex", "dpt", "code", "RR", "city_name", "p"]]
 
 
-population["avc"] = population["p"] > np.random.rand(len(population["p"])) 
+population["avc"] = population["p"] > np.random.rand(len(population["p"]))
 population["type"] = np.random.choice(
     pTA["type"], p=pTA["p"], size=len(population["p"])
 )
@@ -72,8 +72,8 @@ population.loc[population.avc == True, "date_avc"] = [
 ]
 
 ########################
-#uniform generation of genepi population (with strokes)
-population["genepi"] = np.random.rand(len(population))<(1000/taille_pop)
+# uniform generation of genepi population (with strokes)
+population["genepi"] = np.random.rand(len(population)) < (1000 / taille_pop)
 nbgenepi = len(population.loc[population.genepi == True])
 population.loc[population.genepi == True, "date_genepi"] = [
     np.datetime64("2022-01-01") + np.timedelta64(e, "D")
@@ -82,7 +82,7 @@ population.loc[population.genepi == True, "date_genepi"] = [
 ########################
 
 
-mortality_laws = pickle.load(open("AVCGenerator/mortality_weibull_params.pkl", "rb"))
+mortality_laws = pickle.load(open("Models/AVC/mortality_weibull_params.pkl", "rb"))
 # mortality_laws[['age','sex','type','k','lambda']]
 mortality_laws.set_index(["age", "sex", "type"], inplace=True)  # ,'k','lambda']]
 
@@ -149,10 +149,10 @@ simulator.run()
 
 # create a context with the default nomenclature DB
 # context =  OpenDataFactoryContext("datarep/snds_nomenclature.db", datarep="../datarep")
-#generate the patients 
+# generate the patients
 factory = PatientFactory(simulator.context, simulator.GPs)
-attribute_map={'sex':'sex', 'age':'age', 'dc_date':"deathdate", 'dc_cause':'type'}
-patients=factory.load(population, attribute_map)
+attribute_map = {"sex": "sex", "age": "age", "dc_date": "deathdate", "dc_cause": "type"}
+patients = factory.load(population, attribute_map)
 
 
 ##########################################
@@ -213,7 +213,10 @@ def generate_drugs(x):
     loc_drugs["patient"] = np.random.choice(indices, size=len(loc_drugs))
 
     # random dates
-    loc_drugs['date']=[np.datetime64("2022-01-01") + np.timedelta64(e, "D") for e in np.random.randint(size=len(loc_drugs), low=0, high=365)]
+    loc_drugs["date"] = [
+        np.datetime64("2022-01-01") + np.timedelta64(e, "D")
+        for e in np.random.randint(size=len(loc_drugs), low=0, high=365)
+    ]
     return loc_drugs
 
 
@@ -223,10 +226,10 @@ drugs = pd.concat(res.to_list())
 hosps = population[["id", "type", "date_avc"]].dropna()
 
 # Add hospitalisation for epileptic patients
-hosps_genepi=population[["id", "date_genepi"]].dropna()
-hosps_genepi['type']=np.random.choice(["G40", "G41"], size=len(hosps_genepi))
-hosps_genepi=hosps_genepi.rename( columns={'date_genepi': 'date_avc'} )
-hosps=pd.concat([hosps, hosps_genepi])
+hosps_genepi = population[["id", "date_genepi"]].dropna()
+hosps_genepi["type"] = np.random.choice(["G40", "G41"], size=len(hosps_genepi))
+hosps_genepi = hosps_genepi.rename(columns={"date_genepi": "date_avc"})
+hosps = pd.concat([hosps, hosps_genepi])
 
 #################################################################
 ################################################################
@@ -247,7 +250,10 @@ simu = {
         "data": hosps,
         "attributes": {"pid": "id", "cim": "type", "date": "date_avc"},
     },
-    "drugs": {"data": drugs, "attributes": {"pid": "patient", "cip": "CIP13", 'date':'date'}},
+    "drugs": {
+        "data": drugs,
+        "attributes": {"pid": "patient", "cip": "CIP13", "date": "date"},
+    },
 }
 
 simulator.load(simu)
@@ -277,5 +283,5 @@ for p in simulator.patients:
     injector_genepi.injection(p)
 
 dbgen = simDB()
-dbgen.output_db_name = "AVCGenerator/snds_testgen.db"
+dbgen.output_db_name = "Models/AVC/snds_testgen.db"
 dbgen.generate(simulator, rootschemas="schema-snds/schemas")

Models/VICAN/Simu_VICAN.py

@@ -155,5 +155,5 @@ for P in [P1, P2, P3, P4, P5, P6, P7, P8, P9, P10]:
         p.injection(patient)
 
 dbgen = simDB()
-dbgen.output_db_name = "Marie/snds_testgen.db"
+dbgen.output_db_name = "Models/VICAN/snds_testgen.db"
 dbgen.generate(simulator, rootschemas="schema-snds/schemas")