#!/usr/bin/python import json import time import pymysql.cursors import pymysql from datetime import date from sklearn.feature_extraction.text import CountVectorizer from sklearn.metrics.pairwise import cosine_similarity today = date.today() db = pymysql.connect (host="cldy-hub-db-prod-do-user-1524670-0.a.db.ondigitalocean.com", user="doadmin", passwd="jmbly6e4obtma5z0", db="defaultdb", port=25060, charset='utf8mb4', cursorclass=pymysql.cursors.DictCursor) with db.cursor() as cursor: sql = "SELECT `id`, `details` from jobs where id = '5932'" cursor.execute(sql) records = cursor.fetchall() for record in records: job_description = record['details'] sql = "SELECT `id`, `email`, `resume_details` from resumes where person_id = '3919'" cursor.execute(sql) records = cursor.fetchall() for record in records: resume = record['resume_details'] ''' MODEL 1 text = [resume, job_description] cv = CountVectorizer() count_matrix = cv.fit_transform(text) #Print the similarity scores print("\nSimilarity Scores:") print(cosine_similarity(count_matrix)) #get the match percentage matchPercentage = cosine_similarity(count_matrix)[0][1] * 100 matchPercentage = round(matchPercentage, 2) # round to two decimal print("Your resume matches about "+ str(matchPercentage)+ "% of the job description.") ''' # https://github.com/visheshwar/Resume_recomendation-/blob/master/codes/search.py import glob import os import warnings # import textract import requests from flask import (Flask, json, Blueprint, jsonify, redirect, render_template, request, url_for) from gensim.summarization import summarize from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer from sklearn.neighbors import NearestNeighbors #from werkzeug import secure_filename from autocorrect import spell warnings.filterwarnings(action='ignore', category=UserWarning, module='gensim') import re, string, unicodedata import nltk import contractions import inflect from bs4 import BeautifulSoup from nltk import word_tokenize, sent_tokenize from nltk.corpus import stopwords from nltk.stem import LancasterStemmer, WordNetLemmatizer nltk.download('punkt') nltk.download('stopwords') def remove_non_ascii(words): """Remove non-ASCII characters from list of tokenized words""" new_words = [] for word in words: new_word = unicodedata.normalize('NFKD', word).encode('ascii', 'ignore').decode('utf-8', 'ignore') new_words.append(new_word) return new_words def to_lowercase(words): """Convert all characters to lowercase from list of tokenized words""" new_words = [] for word in words: new_word = word.lower() new_words.append(new_word) return new_words def remove_punctuation(words): """Remove punctuation from list of tokenized words""" new_words = [] for word in words: new_word = re.sub(r'[^\w\s]', '', word) if new_word != '': new_words.append(new_word) return new_words def replace_numbers(words): """Replace all interger occurrences in list of tokenized words with textual representation""" p = inflect.engine() new_words = [] for word in words: if word.isdigit(): new_word = p.number_to_words(word) new_words.append(new_word) else: new_words.append(word) return new_words def remove_stopwords(words): """Remove stop words from list of tokenized words""" new_words = [] for word in words: # print(word) if word not in stopwords.words('english'): new_words.append(word) return new_words def stem_words(words): """Stem words in list of tokenized words""" stemmer = LancasterStemmer() stems = [] for word in words: stem = stemmer.stem(word) stems.append(stem) return stems def lemmatize_verbs(words): """Lemmatize verbs in list of tokenized words""" lemmatizer = WordNetLemmatizer() lemmas = [] for word in words: lemma = lemmatizer.lemmatize(word, pos='v') lemmas.append(lemma) return lemmas def normalize(words): words = remove_non_ascii(words) words = to_lowercase(words) words = remove_punctuation(words) # words = replace_numbers(words) words = remove_stopwords(words) words = stem_words(words) words = lemmatize_verbs(words) return words def lcs(X, Y): try: mat = [] for i in range(0,len(X)): row = [] for j in range(0,len(Y)): if X[i] == Y[j]: if i == 0 or j == 0: row.append(1) else: val = 1 + int( mat[i-1][j-1] ) row.append(val) else: row.append(0) mat.append(row) new_mat = [] for r in mat: r.sort() r.reverse() new_mat.append(r) lcs = 0 for r in new_mat: if lcs < r[0]: lcs = r[0] return lcs except: return -9999 def spellCorrect(string): words = string.split(" ") correctWords = [] for i in words: correctWords.append(spell(i)) return " ".join(correctWords) def semanticSearch(searchString, searchSentencesList): result = None #searchString = spellCorrect(searchString) bestScore = 0 for i in searchSentencesList: score = lcs(searchString, i) print(score , i[0:100]) print("") temp = [score] Final_Array.extend(temp) if score > bestScore: bestScore = score result = i return result Final_Array = [] with db.cursor() as cursor: sql = "SELECT `id`, `details` from jobs where id = '5932'" cursor.execute(sql) records = cursor.fetchall() for record in records: job_description = record['details'] jobfile = nltk.word_tokenize(job_description) jobfile = normalize(job_description) jobfile = ' '.join(map(str, job_description)) sql = "SELECT `id`, `email`, `resume_details` from resumes where person_id = '3919'" cursor.execute(sql) records = cursor.fetchall() for record in records: resume = record['resume_details'] resumefile = nltk.word_tokenize(resume) resumefile = normalize(resume) resumefile = ' '.join(map(str, resume)) skill_match = skill_keyword_match(jobfile) #skill_match.extract_jobs_keywords() #resume_skills = skill_match.extract_resume_keywords(config.SAMPLE_RESUME_PDF) #top_job_matches = skill_match.cal_similarity(resume_skills.index, location) #top_job_matches.to_csv(config.RECOMMENDED_JOBS_FILE+location+'.csv', index=False) print('File of recommended jobs saved')