changes

SkillExtract.py

@@ -77,7 +77,7 @@ class SkillExtractorDetails:
             except Exception as error:
                 test = 1
         return job_roles 
-    def SkillExtract(db_params,skill_extractor,JdID):
+    def SkillExtract(db_params,skill_extractor,JdID, IsJD):
         print("Extracting Skills for the JD...")
         # Connect to the PostgreSQL database
         conn = psycopg2.connect(**db_params)
@@ -87,9 +87,12 @@ class SkillExtractorDetails:
         # Retrieve "id" and "description" columns from the table
         #query = sql.SQL("select jdmasterid,jobdescription from JDMaster where isskillsextracted in (0)")
         query = "select jdmasterid,jobdescription,filename from JDMaster where isskillsextracted = 0 and jdmasterid ="+ jd_id 
-
+        CVquery = "select masterid,description,filename from CourseMaster where isskillsextracted = 0 and masterid ="+ jd_id
         # Use Pandas to read the data into a DataFrame
-        df = pd.read_sql_query(query, conn)
+        if(IsJD):
+            df = pd.read_sql_query(query, conn)
+        else:
+            df = pd.read_sql_query(query, conn)    
 
         # Print the DataFrame (for demonstration purposes)
         #print(df)
@@ -103,18 +106,22 @@ class SkillExtractorDetails:
         OldSkillCount = 0
         NewSkillCount = 0
         if(len(df.index) > 0):
-            print("Total JDs for Extractraction : " + str(len(df.index)))
+            print("Total IDs for Extractraction : " + str(len(df.index)))
         for index, row in df.iterrows():
             # Access individual columns using column names
-            id_value = row['jdmasterid']
+            if(IsJD):
+                id_value = row['jdmasterid']
+                description_value = row['jobdescription']
+            else:
+                id_value = row['masterid']
+                description_value = row['description']
+
             filename_jd = row['filename']
             OldSkillCount = 0
             NewSkillCount = 0
             skill_score = 0.0
             print("Extracting Skills For ", filename_jd + " , Id : " + str(id_value) + " , Index " + str(index + 1))
 
-            description_value = row['jobdescription']
-            #print(description_value)
             
             annotations = skill_extractor.annotate(description_value)
             matches = annotations['results']['full_matches']+annotations['results']['ngram_scored']
@@ -145,18 +152,33 @@ class SkillExtractorDetails:
                             #print("Skill Already in SkillMaster")
                             OldSkillCount = OldSkillCount + 1
                             isOld = "Yes"
-                            query = "SELECT skillid FROM jdSkilldetails WHERE skillid IN (%s) and jdMasterid in (%s)"
+                            if(IsJD):
+                                query = "SELECT skillid FROM jdSkilldetails WHERE skillid IN (%s) and jdMasterid in (%s)"
+                            else:
+                                query = "SELECT skillid FROM CourseSkilldetails WHERE skillid IN (%s) and Masterid in (%s)"    
                             params = (row_as_int[0],id_value,)  
                             cursor.execute(query, params)
                             if cursor.rowcount > 0: 
                                 weightage = -1.0  
                                 #print("Skill Already in SkillMaster and JDSkillDetails")
                             else:  
-                                Skillid = row_as_int[0]
-                                jdMasterid = id_value   
-                                insert_query = sql.SQL("""INSERT INTO jdSkilldetails (Skillid, jdMasterid) VALUES (%s, %s)""")
-                                cursor.execute(insert_query, (Skillid, jdMasterid))
-                                conn.commit()
+                                if(IsJD):
+                                    Skillid = row_as_int[0]
+                                    jdMasterid = id_value   
+                                    insert_query = sql.SQL("""INSERT INTO jdSkilldetails (Skillid, jdMasterid) VALUES (%s, %s)""")
+                                    cursor.execute(insert_query, (Skillid, jdMasterid))
+                                    conn.commit()
+                                else:
+                                    query = "Select max(skilldetailsid) from courseskilldetails"                
+                                    df = pd.read_sql_query(query, conn)
+                                    CourseID = df.iat[0,0] + 1
+
+                                    Skillid = row_as_int[0]
+                                    jdMasterid = id_value   
+                                    insert_query = sql.SQL("""INSERT INTO Courseskilldetails (skilldetailsid, Skillid, Masterid) VALUES (%s, %s, %s)""")
+                                    cursor.execute(insert_query, (CourseID, Skillid, jdMasterid))
+                                    conn.commit()
+
                                 #print("Skill Already in SkillMaster and Inserted in JDSkillDetails")	
                                 #print(row_as_int)
                     else:    
@@ -175,23 +197,37 @@ class SkillExtractorDetails:
                         generated_skill_id = cursor.fetchone()[0]
                         Skillid = generated_skill_id
                         jdMasterid = id_value
-                        insert_query = sql.SQL("""INSERT INTO jdSkilldetails (Skillid, jdMasterid) VALUES (%s, %s)""")
-                        cursor.execute(insert_query, (Skillid, jdMasterid))
-                        conn.commit()
+                        if(IsJD):
+                            insert_query = sql.SQL("""INSERT INTO jdSkilldetails (Skillid, jdMasterid) VALUES (%s, %s)""")
+                            cursor.execute(insert_query, (Skillid, jdMasterid))
+                            conn.commit()
+                        else:
+                            query = "Select max(skilldetailsid) from courseskilldetails"                
+                            df = pd.read_sql_query(query, conn)
+                            CourseID = df.iat[0,0] + 1
+
+                            insert_query = sql.SQL("""INSERT INTO CourseSkilldetails (skilldetailsid,Skillid, Masterid) VALUES (%s, %s, %s)""")
+                            cursor.execute(insert_query, (CourseID,Skillid, jdMasterid))
+                            conn.commit()    
                         print("Skill Identified : ", skill_name)
                         #print("Skill inserted in SkillMaster and Inserted in JDSkillDetails")
-            SkillExtractorDetails.extractWords(description_value,id_value,db_params)
-            query = "update public.jdmaster set isskillsextracted = 1 where jdmasterid = (%s)"
+
+            
+            if(IsJD):
+                SkillExtractorDetails.extractWords(description_value,id_value,db_params)
+                query = "update public.jdmaster set isskillsextracted = 1 where jdmasterid = (%s)"
+            else:
+                query = "update public.coursemaster set isskillsextracted = 1 where masterid = (%s)"
             
             params = (id_value,)  
             cursor.execute(query, params)
             conn.commit()
             print("Skills Updated for Skills Extraction for file ", filename_jd)
             print("Total Skills : ", len(skills_list))
-            return SkillExtractorDetails.latestSkillDetails(id_value,db_params)
-    def latestSkillDetails(jid,db_params):
+            return SkillExtractorDetails.latestSkillDetails(id_value,db_params,IsJD)
+    def latestSkillDetails(jid,db_params,IsJD):
         data = ""
-        data = SkillExtractorDetails.display_skills(jid,db_params)
+        data = SkillExtractorDetails.display_skills(jid,db_params,IsJD)
         #    jid = df.iat[0,0]
         return data
     def tuple_to_int(tup):
@@ -201,7 +237,7 @@ class SkillExtractorDetails:
             return tup[0] * (10 ** (len(tup) - 1)) + SkillExtractorDetails.tuple_to_int(tup[1:])
 
 
-    def skill_check(dbQuery,db_params):
+    def skill_check(dbQuery,db_params,IsJD):
         conn = psycopg2.connect(**db_params)
         cursor = conn.cursor()
         df = pd.read_sql_query(dbQuery, conn)
@@ -213,19 +249,24 @@ class SkillExtractorDetails:
         
         Required_Skills = Required_Skills[2:] 
         return Required_Skills
-    def display_skills(id, db_params):
+    def display_skills(id, db_params,IsJD):
         jd=str(id)
-        query = "select skillname from SkillDetails  where id = "+ jd +" and skillscore > 99 and skilltype = 'Hard Skill'"
-        RequiredSkills_Hard  = SkillExtractorDetails.skill_check(query,db_params)
+        tableName = 'CVSkillDetails'
+        if(IsJD):
+            tableName = 'SkillDetails'
+        
+
+        query = "select skillname from " + tableName +"  where id = "+ jd +" and skillscore > 99 and skilltype = 'Hard Skill'"    
+        RequiredSkills_Hard  = SkillExtractorDetails.skill_check(query,db_params,IsJD)
 
-        query = "select skillname from SkillDetails  where id = "+ jd +" and skillscore > 50 and skilltype = 'Soft Skill'"  
-        RequiredSkills_Soft  = SkillExtractorDetails.skill_check(query,db_params)
+        query = "select skillname from " + tableName +"  where id = "+ jd +" and skillscore > 50 and skilltype = 'Soft Skill'"  
+        RequiredSkills_Soft  = SkillExtractorDetails.skill_check(query,db_params,IsJD)
 
-        query = "select skillname from SkillDetails  where id = "+ jd +" and skillscore < 50 and skilltype = 'Soft Skill'"  
-        RequiredSkills_G1  = SkillExtractorDetails.skill_check(query,db_params)
+        query = "select skillname from " + tableName +"  where id = "+ jd +" and skillscore < 50 and skilltype = 'Soft Skill'"  
+        RequiredSkills_G1  = SkillExtractorDetails.skill_check(query,db_params,IsJD)
 
-        query = "select skillname from SkillDetails  where id = "+ jd +" and skillscore < 99 and skilltype = 'Hard Skill'"  
-        RequiredSkills_G2  = SkillExtractorDetails.skill_check(query,db_params)
+        query = "select skillname from " + tableName +"  where id = "+ jd +" and skillscore < 99 and skilltype = 'Hard Skill'"  
+        RequiredSkills_G2  = SkillExtractorDetails.skill_check(query,db_params,IsJD)
 
         print('')
         print("Required Skills      : " + RequiredSkills_Hard)

app.py

@@ -50,7 +50,7 @@ def parse_csv(df):
 def UploadJobDescription(file: bytes =  File(...), FileName: str = "sample.pdf"):   
     text= ExtractContentFromFile.ExtractDataFromFile(FileName,file)
     returnID = UploadOpenFile.uploadFile(text,FileName,db_params,True)
-    returnSkills = SkillExtractorDetails.SkillExtract(db_params,skill_extractor,returnID)     
+    returnSkills = SkillExtractorDetails.SkillExtract(db_params,skill_extractor,returnID,True)     
     details = returnSkills.split('@')
     data = {'Data':['Required Skills', 'Soft Skills', 'Good to have Skills'], 'Values':[details[0], details[1], details[2]]}
     df = pd.DataFrame(data)