Changes for Add and remove skills

app.py

@@ -7,6 +7,7 @@ import pandas as pd
 from datetime import date
 import numpy as np
 import spacy
+import re
 from sentence_transformers import SentenceTransformer, util
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
@@ -192,7 +193,7 @@ def SkillExtract():
                     conn.commit()
                     print("Skill Identified : ", skill_name)
                     #print("Skill inserted in SkillMaster and Inserted in JDSkillDetails")
-
+        extractWords(description_value,id_value)
         query = "update public.jdmaster set isskillsextracted = 1 where jdmasterid = (%s)"
         
         params = (id_value,)  
@@ -200,6 +201,106 @@ def SkillExtract():
         conn.commit()
         print("Skills Updated for Skills Extraction for file ", filename_jd)
         print("Total Skills : ", len(skills_list))
+
+def GetSkillId(skillname,jdmasterid):    
+    #Fetching skill id from skillmaster
+    conn = psycopg2.connect(**db_params)
+    cursor = conn.cursor()
+    query = "select skillid from skillmaster where upper(skilldetails) = (%s)"
+    params = (skillname.upper(),)  
+    cursor.execute(query, params)
+    generated_skill_id = cursor.fetchone()[0]
+    #jdmasterid = 912
+    #print(generated_skill_id)
+    #checking if skill id already in skilldetails
+    query = "SELECT skillid FROM jdSkilldetails WHERE skillid IN (%s) and jdMasterid in (%s)"
+    params = (generated_skill_id,jdmasterid,)  
+    cursor.execute(query, params)
+    if cursor.rowcount > 0: 
+        #print("Already")
+        query =''
+    else:
+        #print("Updating in DB")
+        insert_query = sql.SQL("""INSERT INTO jdSkilldetails (Skillid, jdMasterid) VALUES (%s, %s)""")
+        cursor.execute(insert_query, (generated_skill_id, jdmasterid))
+        conn.commit()
+
+    cursor.close()
+    # Close the connection
+    conn.close()   
+    return generated_skill_id
+
+def getNewSkills():
+    query = "select skillid,skilldetails,skilltype,skill_score from skillmaster where weightage = -2"
+    conn = psycopg2.connect(**db_params)
+    cursor = conn.cursor()
+    df_skill_master = pd.read_sql_query(query, conn)
+    df_skill_master['skilldetails'] = df_skill_master['skilldetails'].str.upper()
+    cursor.close()
+    # Close the connection
+    conn.close()
+
+    #print(df_skill_master)
+    return df_skill_master
+def skill_Validate(df, skill):
+    skill = skill.upper()
+    if (len(skill.split()) < 2 and len(skill) < 3) or len(skill.split())==1:
+        df['skill_present'] = df['skilldetails'].apply(lambda x: re.match(rf'^{skill}$', x))
+        if any(df['skill_present']):
+            #print("Valid Skill")
+            return 1
+        else:
+            #print("Not a Skill")
+            return 0
+    elif df['skilldetails'].str.contains(skill.upper()).any():
+        #print("Valid Skill")
+        return 1
+    else:
+        # print("Not a Skill")
+        return 0 
+def extractWords(job_description,JdMasterid):
+    job_roles = []
+    job_description = job_description.replace(')',' ')
+    delimiters = ",", " ", " , ", ";","\n","/","\\"
+    regex_pattern = '|'.join(map(re.escape, delimiters))
+    df = getNewSkills()
+    data = re.split(regex_pattern, job_description)
+    #data = job_description.split(',')
+    for ds in data:
+        #print(ds)
+        try:
+            if(skill_Validate(df,ds.strip())):                
+                job_roles.append(ds) 
+                GetSkillId(ds.strip(),JdMasterid)
+                print("Skills Identified* : " + ds)   
+        except Exception as error:
+            test = 1
+    return job_roles  
+
+def extract_job_role(job_description):
+    # Process the job description text
+    doc = nlp(job_description)
+    df = getNewSkills()
+    # Define keywords related to job roles
+    job_role_keywords = ["role", "responsibilities", "duties", "position", "job title", "experience", "skills", "location", "tecnologies", "soft skills"]
+    #job_role_keywords = ["location"]
+    
+    # Initialize an empty list to store extracted job roles
+    job_roles = []
+    
+    # Iterate through the sentences in the document
+    for sent in doc.sents:
+        # Check if any of the job role keywords are present in the sentence
+        if any(keyword in sent.text.lower() for keyword in job_role_keywords):
+            # Extract noun phrases that represent job roles
+            for chunk in sent.noun_chunks:
+                print("NLP-" + chunk.text)
+                if(skill_Validate(df,chunk.text)):
+                    job_roles.append(chunk.text)
+                    print("Skills Identified* : " + chunk.text)
+                
+    # Return the extracted job roles
+    return job_roles
         
 def SkillExtraction(file):
     annotations = skill_extractor.annotate(file)
@@ -322,7 +423,12 @@ def Last20JD():
    conn = psycopg2.connect(**db_params)   
    df = pd.read_sql_query(dbQuery, conn)
    st.dataframe(df,use_container_width = True, hide_index = True)         
-
+def Executequery(dbquery):
+    conn = psycopg2.connect(**db_params)
+    cursor_obj = conn.cursor()    
+    cursor_obj.execute(dbquery)
+    cursor_obj.close()
+    conn.close() 
 def uploadFile(text,filePath):
     hostname = socket.gethostname()
 ## getting the IP address using socket.gethostbyname() method
@@ -341,13 +447,69 @@ def uploadFile(text,filePath):
     print(ip_address)
     print("File Uploaded...")
 
+def RemoveSkills(data):
+    conn = psycopg2.connect(**db_params)
+    cursor = conn.cursor()  
+    skill_rm = data.split(':')[1]
+    print("Removing Skills " +  skill_rm)
+    query = "update skillmaster set weightage = 0 where skilldetails = (%s)"        
+    params = (skill_rm,)  
+    cursor.execute(query, params)
+    conn.commit()
+    cursor.close()
+    conn.close() 
+def insert_skill(skills):
+    details = skills.split(',')
+    skill_details = details[0]
+    skill_type = details [1]
+    skill_score1 = details[2]
+    weightage = -2
+    is_active = True
+    conn = psycopg2.connect(**db_params)
+    cursor = conn.cursor()
+    print("Adding Skill " + skill_details)
+    query = "SELECT skillid FROM skillmaster WHERE skillDetails IN (%s)"
+    params = (skill_details,)  # Replace 'Test' with your actual variable or user input
+    cursor.execute(query, params)
+    if cursor.rowcount == 0:    
+
+        insert_query = sql.SQL("""INSERT INTO SkillMaster (SkillDetails, SkillType, Weightage, IsActive, skill_score) 
+                    VALUES (%s, %s, %s, %s, %s) RETURNING SkillID""")
+        cursor.execute(insert_query, (skill_details, skill_type, weightage, is_active, skill_score1))
+        conn.commit()
+    else:
+        print("Skill Already in DB")    
+     # Close the cursor and connection
+    cursor.close()
+    # Close the connection
+    conn.close()
+def AddSkills(data):
+    skill_add = data.split(':')[1]
+    insert_skill(skill_add)    
 def AppFlow(text,fName,query, IsUpload):
    profile=""
+   if(len(query) > 8):
+        profile = query[0:7] 
+        print(profile)
+   if("@Remove" in profile):
+        
+        RemoveSkills(query)
+        st.success('Skills removed')
+        return
+   elif("@Add" in profile):
+        AddSkills(query) 
+        st.success('Skills added')
+        return        
    if(IsUpload == False and len(query) > 10):
         text = query
         IsUpload = True
         query = ''
-        fName = 'Open Text' 
+        fName = 'Open Text'
+   elif(IsUpload == False and len(query) > 10):
+        text = query
+        IsUpload = True
+        query = ''
+        fName = 'Open Text'
    with st.spinner('Processing...'):
         if(query.upper() == 'SKILLS'):
             LatestExtractedSkills()
@@ -355,6 +517,9 @@ def AppFlow(text,fName,query, IsUpload):
         elif(query.upper() == 'JD'):            
             Last20JD()
             st.success('Recently uploaded JDs')
+        elif(query.upper() == 'JD'):            
+            Last20JD()
+            st.success('Recently uploaded JDs')
         else:     
             if(IsUpload and query == ''):                
                 uploadFile(str(text),fName)
@@ -370,7 +535,26 @@ def AppFlow(text,fName,query, IsUpload):
                 st.write(details[2] +  " " + details[3])
 
                 st.success('Profile Tagging - ' + profile)
-
+def extract_Newjob_role(job_description):
+    # Process the job description text
+    doc = nlp(job_description)
+    
+    # Define keywords related to job roles
+    job_role_keywords = ["role", "responsibilities", "duties", "position", "job title"]
+    
+    # Initialize an empty list to store extracted job roles
+    job_roles = []
+    
+    # Iterate through the sentences in the document
+    for sent in doc.sents:
+        # Check if any of the job role keywords are present in the sentence
+        if any(keyword in sent.text.lower() for keyword in job_role_keywords):
+            # Extract noun phrases that represent job roles
+            for chunk in sent.noun_chunks:
+                job_roles.append(chunk.text)
+    
+    # Return the extracted job roles
+    return job_roles
 def submit (uploaded_resume, query):
     text = ""
     fName = ""