data pre-processing module updated

Ontology_Based_Information_System/CSV Translator/csv_convertor.py

@@ -3,23 +3,19 @@ import re
 import pandas as pd
 
 if __name__ == '__main__':
-    df = pd.read_csv('C:\\Users\\LENOVO\\Music\\New folder\\Ontology generation\\petmd.csv')
+    df = pd.read_csv('petmd.csv')
 
     df_col = df.columns
 
     data_dict = {
         'Disease': [],
         'DiseaseDescription': [],
-        'DiseaseCause': [],
         'DiseaseCauseDescription': [],
-        'DiseaseDiagnose': [],
         'DiseaseDiagnoseDescription': [],
-        'DiseasePrevention': [],
         'DiseasePreventionDescription': [],
-        'DiseaseSymptoms': [],
-        'DiseaseSymptomsDescription': [],
-        'DiseaseTreatment': [],
+        'DiseaseSymptomDescription': [],
         'DiseaseTreatmentDescription': [],
+        'DiseaseInfection': []
     }
 
     disease = ''
@@ -63,13 +59,11 @@ if __name__ == '__main__':
             topic = row[1][df_col[1]]
             description = row[1][df_col[2]]
             if regexp.search(str(topic)):
-                data_dict['DiseaseCause'].append(str(disease).strip().replace(" ", "") + 'Cause')
                 data_dict['DiseaseCauseDescription'].append(str(description))
                 temp = 1
                 break
 
         if temp == 0:
-            data_dict['DiseaseCause'].append('')
             data_dict['DiseaseCauseDescription'].append('')
 
         temp = 0
@@ -78,13 +72,11 @@ if __name__ == '__main__':
             topic = row[1][df_col[1]]
             description = row[1][df_col[2]]
             if regexp.search(str(topic)):
-                data_dict['DiseaseDiagnose'].append(str(disease).strip().replace(" ", "") + 'Diagnose')
                 data_dict['DiseaseDiagnoseDescription'].append(str(description))
                 temp = 1
                 break
 
         if temp == 0:
-            data_dict['DiseaseDiagnose'].append('')
             data_dict['DiseaseDiagnoseDescription'].append('')
 
         temp = 0
@@ -93,13 +85,11 @@ if __name__ == '__main__':
             topic = row[1][df_col[1]]
             description = row[1][df_col[2]]
             if regexp.search(str(topic)):
-                data_dict['DiseasePrevention'].append(str(disease).strip().replace(" ", "") + 'Prevention')
                 data_dict['DiseasePreventionDescription'].append(str(description))
                 temp = 1
                 break
 
         if temp == 0:
-            data_dict['DiseasePrevention'].append('')
             data_dict['DiseasePreventionDescription'].append('')
 
         temp = 0
@@ -108,14 +98,12 @@ if __name__ == '__main__':
             topic = row[1][df_col[1]]
             description = row[1][df_col[2]]
             if regexp.search(str(topic)):
-                data_dict['DiseaseSymptoms'].append(str(disease).strip().replace(" ", "") + 'Symptoms')
-                data_dict['DiseaseSymptomsDescription'].append(str(description))
+                data_dict['DiseaseSymptomDescription'].append(str(description))
                 temp = 1
                 break
 
         if temp == 0:
-            data_dict['DiseaseSymptoms'].append('')
-            data_dict['DiseaseSymptomsDescription'].append('')
+            data_dict['DiseaseSymptomDescription'].append('')
 
         temp = 0
         for row in grouped_rows.iterrows():
@@ -123,13 +111,47 @@ if __name__ == '__main__':
             topic = row[1][df_col[1]]
             description = row[1][df_col[2]]
             if regexp.search(str(topic)):
-                data_dict['DiseaseTreatment'].append(str(disease).strip().replace(" ", "") + 'Treatment')
                 data_dict['DiseaseTreatmentDescription'].append(str(description))
                 temp = 1
                 break
 
         if temp == 0:
-            data_dict['DiseaseTreatment'].append('')
             data_dict['DiseaseTreatmentDescription'].append('')
 
-    pd.DataFrame(data_dict).to_csv('dogDisease.csv', index=False)
+        temp = 0
+        for row in grouped_rows.iterrows():
+            description = row[1][df_col[2]]
+            regexp = re.compile(r'Allerg|allerg')
+            if regexp.search(str(description)):
+                data_dict['DiseaseInfection'].append('Allergic')
+                temp = 1
+                break
+
+            regexp = re.compile(r'Bacter|bacter')
+            if regexp.search(str(description)):
+                data_dict['DiseaseInfection'].append('Bacterial')
+                temp = 1
+                break
+
+            regexp = re.compile(r'Flea|flea')
+            if regexp.search(str(description)):
+                data_dict['DiseaseInfection'].append('Fleas')
+                temp = 1
+                break
+
+            regexp = re.compile(r'Fung|fung')
+            if regexp.search(str(description)):
+                data_dict['DiseaseInfection'].append('Fungal')
+                temp = 1
+                break
+
+            regexp = re.compile(r'Virus|virus')
+            if regexp.search(str(description)):
+                data_dict['DiseaseInfection'].append('Viral')
+                temp = 1
+                break
+
+        if temp == 0:
+            data_dict['DiseaseInfection'].append('')
+
+    pd.DataFrame(data_dict).drop_duplicates().to_csv('dogDisease.csv', index=False)