adding defined tables

analysis/dataset_definition_core.py

@@ -67,6 +67,4 @@
 
 
 dataset.sex = patients.sex
-dataset.dob = patients.date_of_birth
-
-
+dataset.dob = patients.date_of_birth

analysis/report.py

@@ -8,19 +8,29 @@
 os.makedirs(output_dir, exist_ok=True)
 
 # Load the data
-data = pd.read_csv("output/full_dataset.csv.gz")
+data = pd.read_csv("output/full_dataset_test.csv.gz")
 
 # Melt the ADHD events data
 adhd_events = data.melt(
-    id_vars=['patient_id', 'sex'],
+    id_vars=['patient_id', 'sex','dob'],
     value_vars=[f'num_adhd_events_{year}' for year in range(2016, 2024)],
     var_name='year',
     value_name='num_adhd_events'
 )
 
 #Computing ADHD disgnosis 
 
+#First this is the total
 adhd_total_sex_table = data.groupby(['sex']).count()
-adhd_total_sex_table = adhd_total_sex_table.drop(['patient_id'],axis=1)
+adhd_total_sex_table = adhd_total_sex_table.drop(['patient_id','dob'],axis=1)
 
-adhd_dia_sex_table = data.
+#Second the the number of adhd dia
+#Need to binaries the dia
+adhd_dia_sex_table = data.copy()
+col_years = [f'num_adhd_events_{year}' for year in range(2016, 2024)]
+adhd_dia_sex_table[col_years] = adhd_dia_sex_table[col_years] > 0
+adhd_dia_sex_table = adhd_dia_sex_table.groupby(['sex']).sum()
+adhd_dia_sex_table = adhd_dia_sex_table.drop(['patient_id','dob'],axis=1)
+
+#Caulcate the prelavence
+prevelnce = adhd_dia_sex_table/adhd_total_sex_table