Create app.py

app.py

@@ -0,0 +1,406 @@
+##############################
+#### All library imports ##### 
+##############################
+
+
+import streamlit as st # web app 
+import pandas as pd 
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import warnings
+warnings.filterwarnings('ignore')
+
+import nltk
+
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+
+from bs4 import BeautifulSoup
+import re
+from nltk.corpus import stopwords # Import the stop word list
+from wordcloud import WordCloud
+# stopwords.words("english")
+from nltk import word_tokenize 
+from nltk.util import ngrams
+
+import PyPDF2
+import base64 # byte object into a pdf file 
+
+
+
+
+############# Web app streamlit page config ##########
+
+
+st.set_page_config(
+   page_title = 'Resume enhancement by extracting keywords using NLP ',
+   page_icon = '📖',
+   layout = 'wide'
+)
+
+
+st.title(" 📕 Resume enhancement by extracting keywords 📝 ")
+
+st.subheader("📢 using NLP 📢")
+
+
+"""✅ ** Downloading Models and Basic Setup **"""
+
+
+##############
+#### download NLTK models ##############
+##############
+
+nltk.download("popular")
+nltk.download('stopwords')
+
+lemmatizer = WordNetLemmatizer()
+
+
+#########################################
+###### read main resources files ########
+#########################################
+
+
+df=pd.read_csv('Resume_skills.csv')
+
+df=df.drop(columns=['Unnamed: 0'])
+
+
+file1=open('linkedin skill','r')
+skills=[(line.strip()).split(',')[0].lower() for line in file1.readlines()]
+
+
+def sentence_maker(unique_words):
+  sentences=''
+  for i in unique_words:
+    sentences+=''.join(i.strip())+' ' 
+  return sentences
+
+#stop_words = set(nltk.corpus.stopwords.words('english'))
+
+
+
+def extract_skills(input_text):
+  res=[]
+  
+  for i in input_text:
+       
+
+      # generate bigrams and trigrams (such as artificial intelligence)
+      bigrams_trigrams = list(map(' '.join, nltk.everygrams(i, 2, 3)))
+
+      # we create a set to keep the results in.
+      found_skills = set()
+      # we search for each token in our skills database
+      for token in i:
+          if token.lower() in skills:
+              found_skills.add(token)
+      # print('2',found_skills)
+      # we search for each bigram and trigram in our skills database
+      for ngram in bigrams_trigrams:
+          if ngram.lower() in skills:
+              found_skills.add(ngram)
+      res.append(found_skills)
+  print(res)
+  return res
+
+def clean_sentences(df,col_name):
+    reviews = []
+
+    for sent in (df[col_name]):       
+        #remove html content
+        review_text = BeautifulSoup(sent).get_text() 
+        #remove non-alphabetic characters
+        review_text = re.sub("[^a-zA-Z]"," ", review_text)
+        #tokenize the sentences
+        words = word_tokenize(review_text.lower())
+        
+        stops = set(stopwords.words("english"))                     
+        # 5. Remove stop words
+        meaningful_words = [w for w in words if not w in stops]
+
+        reviews.append(meaningful_words)
+
+    return(reviews)
+
+def clean_sentences2(df,col_name):
+    reviews = []
+
+    for sent in (df[col_name]):
+        
+        #remove html content
+        review_text = BeautifulSoup(sent).get_text()
+        
+        #remove non-alphabetic characters
+        review_text = re.sub("[^a-zA-Z]"," ", review_text)
+    
+        #tokenize the sentences
+        words = word_tokenize(review_text.lower())
+        reviews.append(words)
+    return(reviews)
+
+def extract_keywords(res):
+  keywords=set()
+  for i in res:
+    for j in i:
+      keywords.add(j)
+  return(keywords)
+
+
+
+
+
+
+def clean_sentences3(text):
+        reviews = []
+        
+        #remove html content
+        review_text = BeautifulSoup(text).get_text()
+        
+        #remove non-alphabetic characters
+        review_text = re.sub("[^a-zA-Z]"," ", review_text)
+    
+        #tokenize the sentences
+        words = word_tokenize(review_text.lower())
+        
+        stops = set(stopwords.words("english"))                  
+    # 
+        # 5. Remove stop words
+        meaningful_words = [w for w in words if not w in stops]
+    
+        reviews.append(meaningful_words)
+
+        return(reviews)
+
+def decode_txt1(file_name): # for clean text
+  f= open(file_name,"r") 
+  full_text = f.read()
+  clean_text=clean_sentences3(full_text)
+  f.close() 
+  return clean_text
+  # return data
+
+
+
+
+def decode_pdf(filename):
+  # creating a pdf file object 
+  pdfFileObj = open(filename, 'rb') 
+  
+      
+  # creating a pdf reader object 
+  pdfReader1 = PyPDF2.PdfFileReader(pdfFileObj)
+  
+      
+  # printing number of pages in pdf file 
+  num_pages=pdfReader1.numPages 
+  # print(num)
+  text=open('Sample.txt','w')
+  for i in range(num_pages):    
+    # creating a page object 
+    pageObj = pdfReader1.getPage(i) 
+        
+    # extracting text from page 
+    t=(pageObj.extractText())
+    text.write(t) 
+        
+  # closing the pdf file object 
+  pdfFileObj.close()
+  text.close()
+  # print(text) 
+  dec_txt=decode_txt1('Sample.txt')
+   #print(dec_txt)
+  return dec_txt
+
+
+# resume_text
+
+def extract_skills2(input_text):
+  found_skills=[]
+  # input_text=list(input_text)
+  for i in input_text:
+      # print('1',i)
+      # generate bigrams and trigrams (such as artificial intelligence)
+      bigrams_trigrams = list(map(' '.join, nltk.everygrams(i, 2, 3)))
+
+      # we create a set to keep the results in.
+      # found_skills = []
+
+      # we search for each token in our skills database
+      # for token in i:
+      token=i
+      if token.lower() in skills:
+              # print(found_skills)
+              found_skills.append(token)
+      # print('2',found_skills)
+      # we search for each bigram and trigram in our skills database
+      for ngram in bigrams_trigrams:
+          if ngram.lower() in skills:
+              found_skills.append(ngram)
+      # res.append(found_skills)
+  # print(found_skills)
+  return found_skills
+
+
+
+#########################################
+############# Upload your resume ############
+#########################################
+
+uploaded_file = st.file_uploader('Choose your .pdf file', type="pdf")
+
+if uploaded_file is not None:
+    with open("input.pdf", "wb") as f:
+        base64_pdf = base64.b64encode(uploaded_file.read()).decode('utf-8')
+        f.write(base64.b64decode(base64_pdf))
+        f.close()
+    
+    resume_text=decode_pdf("input.pdf") # enter the resume name
+
+        ###################
+    ####### select the category ############
+    ####################
+
+    list_of_cats = [ 'Testing', 'HR', 'DESIGNER', 'INFORMATION-TECHNOLOGY', 'TEACHER', 'ADVOCATE','BUSINESS-DEVELOPMENT', 'HEALTHCARE', 'FITNESS', 'AGRICULTURE','BPO', 'SALES', 'CONSULTANT', 'DIGITAL-MEDIA', 'AUTOMOBILE','CHEF', 'FINANCE', 'APPAREL', 'ENGINEERING', 'ACCOUNTANT','CONSTRUCTION', 'PUBLIC-RELATIONS', 'BANKING', 'ARTS', 'AVIATION','Data Science', 'Advocate', 'Arts', 'Web Designing','Mechanical Engineer', 'Sales', 'Health and fitness','Civil Engineer', 'Java Developer', 'Business Analyst','SAP Developer', 'Automation Testing', 'Electrical Engineering','Operations Manager', 'Python Developer', 'DevOps Engineer','Network Security Engineer', 'PMO', 'Database', 'Hadoop','ETL Developer', 'DotNet Developer', 'Blockchain']
+
+    cat = st.selectbox("Select your desired Category",list_of_cats, index = 0)
+
+
+    #cat = "Testing" #@param ['HR', 'DESIGNER', 'INFORMATION-TECHNOLOGY', 'TEACHER', 'ADVOCATE','BUSINESS-DEVELOPMENT', 'HEALTHCARE', 'FITNESS', 'AGRICULTURE','BPO', 'SALES', 'CONSULTANT', 'DIGITAL-MEDIA', 'AUTOMOBILE','CHEF', 'FINANCE', 'APPAREL', 'ENGINEERING', 'ACCOUNTANT','CONSTRUCTION', 'PUBLIC-RELATIONS', 'BANKING', 'ARTS', 'AVIATION','Data Science', 'Advocate', 'Arts', 'Web Designing','Mechanical Engineer', 'Sales', 'Health and fitness','Civil Engineer', 'Java Developer', 'Business Analyst','SAP Developer', 'Automation Testing', 'Electrical Engineering','Operations Manager', 'Python Developer', 'DevOps Engineer','Network Security Engineer', 'PMO', 'Database', 'Hadoop','ETL Developer', 'DotNet Developer', 'Blockchain', 'Testing'] {allow-input: true}
+    print('You selected:', cat)
+
+    # cat='Data Science' # enter the category to extract
+    sub_df=df[df['Category']==cat]
+
+    sentences1=sentence_maker(sub_df['Resume_skills'])
+
+    """✅ **Extracting Data from PDF **"""
+
+    resume_text2=extract_skills2(resume_text[0])
+    resume_keywords=set(resume_text2)
+    # resume_keywords # keywords for existing resume
+    print(resume_keywords)
+
+
+    wc = WordCloud(width = 500, height = 500,include_numbers=True,collocations=True, background_color ='white',min_font_size = 10).generate(sentence_maker(resume_keywords))
+    plt.figure(figsize=(10,10))
+    plt.imshow(wc, interpolation='bilinear')
+    plt.axis("off")
+    plt.title(' existing Keywords')
+    plt.show()
+
+    # """**sub_unique_words** contains list of category related keywords and existing resume keywords in **resume_keywords**"""
+
+    """✅ Generating ***Similarity Score*** with existing skillset"""
+
+    from cdifflib import CSequenceMatcher
+
+    def get_similarity_score(s1,s2):
+
+        sm= CSequenceMatcher(None,s1,s2)
+        return(str(round(sm.ratio()*100,3))+'%')
+    #return round(sm.ratio()*100,3)
+
+
+    wc_r = WordCloud(width = 500, height = 500,max_words=200,include_numbers=True,collocations=True, 
+        background_color ='white',min_font_size = 10).generate(sentences1)
+    # plt.figure(figsize=(10,10))
+    # plt.imshow(wc_r, interpolation='bilinear')
+    # plt.axis("off")
+    # plt.title('Keywords for : '+cat)
+
+
+
+
+    """✅ **Getting the matching score with database**"""
+
+    sub_unique_words=list(wc_r.words_.keys())
+    resume_keywords=list(resume_keywords)
+
+    bigram = list(map(' '.join,ngrams(sub_unique_words, 1))) 
+    # print(bigram)
+    sub_keywords=set()
+    for bg in bigram:
+        if bg in skills:
+        # print(bg)
+            sub_keywords.add(bg)
+    tokens = nltk.word_tokenize(sentence_maker(sub_unique_words))
+    for i in tokens:
+        sub_keywords.add(i)
+
+    def preprocess(words):
+        res=set()
+        for i in words:
+                #remove html content
+                review_text = BeautifulSoup(i).get_text()
+                
+                #remove non-alphabetic characters
+                review_text = re.sub("[^a-zA-Z]"," ", review_text)
+                #tokenize the sentences
+                words = word_tokenize(review_text.lower())
+                # print(words)
+                for j in words:
+                    res.add(j)
+        # print(res)
+        return res
+
+
+    with st.spinner():
+
+        sub_unique_words_match=list(preprocess(sub_unique_words))
+        resume_keywords=list(preprocess(resume_keywords))
+
+
+        predicted_keywords_match=[i for i in sub_unique_words_match if i not in resume_keywords]
+        pred_keywords=[i for i in sub_keywords if i not in resume_keywords]
+
+        print(pred_keywords)
+
+        ############################
+        #### final word cloud ######
+        ############################
+
+        from collections import Counter
+        word_could_dict=Counter(pred_keywords)
+        wc = WordCloud(width = 500, height = 500,include_numbers=True,collocations=True, 
+            background_color ='white',min_font_size = 10).generate_from_frequencies(word_could_dict)
+        plt.figure(figsize=(10,10))
+        plt.imshow(wc, interpolation='bilinear')
+        plt.axis("off")
+        plt.title(' predicted keywords')
+        #plt.show()
+        wc.to_file('prediction.jpg') # enter file name to save
+
+        st.markdown("# Output")
+
+        col1, col2, col3, col4 = st.columns(4)
+
+        with col2: 
+            st.markdown("### Predicted Keywords WordCloud")
+
+            st.image('prediction.jpg')
+
+
+        ############################
+        #### similarty score  ######
+        ############################
+
+        existing_score = get_similarity_score(sub_unique_words_match,resume_keywords) # get the matching score for resume keywords and category keywords
+        
+        predicted_result_score = get_similarity_score(predicted_keywords_match,sub_unique_words_match)# matching score for predicted keywords and category keywords
+
+        with col1:
+            st.markdown('### Existing Keywords :' )
+
+            st.metric( label = 'Score', value = existing_score)
+
+        with col3:
+            st.markdown(" ")
+
+
+        with col4:
+            st.markdown('### Predicted Keywords :' )
+
+            st.metric( label = 'Score', value = predicted_result_score)