Merge branch 'it19980096' into 'master'

Resume analyser

See merge request !2

package.json → NodeServer/package.json

@@ -11,6 +11,7 @@
   "author": "Namit Nathwani",
   "license": "ISC",
   "dependencies": {
+    "axios": "^1.3.4",
     "bcryptjs": "^2.4.3",
     "cors": "^2.8.5",
     "express": "^4.18.2",

src/config/contants.ts → NodeServer/src/config/contants.ts

@@ -13,3 +13,4 @@ export const DEFAULT_CONTROLS = {
     use: true,
   },
 };
+export const UTILITY_SERVER = "http://127.0.0.1:8000";

src/config/types.ts → NodeServer/src/config/types.ts

@@ -47,6 +47,16 @@ export type AuthType = {
   controls?: ControlsType;
 };
 
+export type ResumeDataType = {
+  skills: string[] | null;
+  degree: string[] | null;
+  designation: string[] | null;
+  experience: string[] | null;
+  company_names: string[] | null;
+  no_of_pages: number;
+  total_experience: number;
+};
+
 export type CandidateType = {
   _id?: string;
   name: string;
@@ -60,6 +70,9 @@ export type CandidateType = {
   dateOfBirth: string;
   jobIds: string[];
   profilePicture: string;
+  state: "INTIAL" | "READY";
+  resume?: string;
+  resumeData?: ResumeDataType;
 };
 
 export type OrganizationType = {
@@ -87,6 +100,41 @@ export type ControlsType = {
   };
 };
 
+export type JobType = {
+  _id: string;
+  title: string;
+  description: string;
+  primarySkills: string[];
+  secondarySkills?: string[];
+  salary: {
+    min: number;
+    max: number;
+    currency: string;
+  };
+  applications: string[];
+  organization: string;
+};
+
+export type ApplicationType = {
+  candidate: string;
+  job: string;
+  status: "Pending" | "Accepted" | "In progress" | "Rejected";
+  interview?: {
+    date: string;
+    time: string;
+    link: string;
+    videoRef?: string;
+  };
+  score: {
+    primary: number;
+    primatyMatch: string[];
+    secondary: number;
+    secondaryMatch: string[];
+    similarity: number;
+    total: number;
+  };
+};
+
 export interface TypedRequest<T extends Query, U> extends Request {
   body: U;
   query: T;

src/index.ts → NodeServer/src/index.ts

@@ -8,11 +8,10 @@ app.use(cors());
 
 // Routes
 const authRoute = require("./routes/auth");
-
-// Environment constants
+const userRoute = require("./routes/user");
+const jobsRoute = require("./routes/jobs");
 
 // Service Initialisation
-
 mongoose.connect(MONGO_URL, {
   useFindAndModify: false,
   useNewUrlParser: true,
@@ -20,13 +19,6 @@ mongoose.connect(MONGO_URL, {
   useCreateIndex: true,
 });
 
-// const db = mongoose.connection;
-
-// db.on("error", (error) => console.log(error, "connection error:"));
-// db.once("open", () => {
-//   console.log("Connected to MongoDB Instance");
-// });
-
 // Express Initialisation
 app.use(express.urlencoded({ extended: true }));
 app.use(express.json());
@@ -35,5 +27,7 @@ app.use(express.urlencoded({ extended: false }));
 
 // Routes
 app.use("/auth", authRoute);
+app.use("/user", userRoute);
+app.use("/jobs", jobsRoute);
 
 app.listen(API_PORT, () => console.log(`Listening on port ${API_PORT}`));

src/middlewares/auth.ts → NodeServer/src/middlewares/auth.ts

 import { Request, Response, NextFunction } from "express";
 import * as jwt from "jsonwebtoken";
 import { JWT_SECRET } from "../config/contants";
+import { TypedRequest, USER_TYPE } from "../config/types";
+import Auth from "../models/Auth";
 
 export const authMiddleware = (
   req: Request,
@@ -21,3 +23,37 @@ export const authMiddleware = (
     }
   }
 };
+
+export const organizationMiddleware = async (
+  req: TypedRequest<{ userId: string }, any>,
+  res: Response,
+  next: NextFunction
+) => {
+  try {
+    const org = await Auth.findOne({ userId: req.query.userId });
+    if (org && org.userType === USER_TYPE.ORGANIZATION) {
+      return next();
+    } else {
+      throw new Error("Organization not found");
+    }
+  } catch (error) {
+    return res.status(400).send(error);
+  }
+};
+
+export const candidateMiddleware = async (
+  req: TypedRequest<{ userId: string }, any>,
+  res: Response,
+  next: NextFunction
+) => {
+  try {
+    const org = await Auth.findOne({ userId: req.query.userId });
+    if (org && org.userType === USER_TYPE.CANDIDATE) {
+      return next();
+    } else {
+      throw new Error("Candidate not found");
+    }
+  } catch (error) {
+    return res.status(400).send(error);
+  }
+};

NodeServer/src/models/Application.ts

+import { Schema, model } from "mongoose";
+import { ApplicationType } from "../config/types";
+
+const applicationSchema = new Schema<ApplicationType>({
+  candidate: { type: Schema.Types.ObjectId, ref: "candidates" },
+  job: { type: Schema.Types.ObjectId, ref: "jobs" },
+  status: { type: String, require: false, default: "Pending" },
+  interview: {
+    type: {
+      date: String,
+      time: String,
+      link: String,
+      videoRef: String,
+    },
+    require: false,
+  },
+  score: {
+    type: {
+      primary: Number,
+      primatyMatch: [String],
+      secondary: Number,
+      secondaryMatch: [String],
+      similarity: Number,
+      total: Number,
+    },
+    require: false,
+  },
+});
+
+const Application = model<ApplicationType>("applications", applicationSchema);
+export default Application;

src/models/Candidate.ts → NodeServer/src/models/Candidate.ts

 import { Schema, model } from "mongoose";
-import { AddressType, CandidateType } from "../config/types";
+import { AddressType, CandidateType, ResumeDataType } from "../config/types";
 
 const AddressSchema = new Schema<AddressType>(
   {
@@ -19,6 +19,18 @@ const ContactsSchema = new Schema<AddressType>(
   },
   { id: false }
 );
+const ResumeDataSchema = new Schema<ResumeDataType>(
+  {
+    skills: { type: [String], require: false },
+    degree: { type: [String], require: false },
+    designation: { type: [String], require: false },
+    experience: { type: [String], require: false },
+    company_names: { type: [String], require: false },
+    no_of_pages: { type: Number, require: false },
+    total_experience: { type: Number, require: false },
+  },
+  { id: false }
+);
 
 const candidateSchema = new Schema<CandidateType>({
   name: String,
@@ -27,6 +39,9 @@ const candidateSchema = new Schema<CandidateType>({
   dateOfBirth: String,
   jobIds: [{ type: Schema.Types.ObjectId, ref: "jobs" }],
   profilePicture: String,
+  state: { type: String, default: "INTIAL" },
+  resume: { type: String, require: false },
+  resumeData: { type: ResumeDataSchema, require: false },
 });
 
 const Candidates = model<CandidateType>("candidates", candidateSchema);

NodeServer/src/models/Job.ts

+import { Schema, model } from "mongoose";
+import { JobType } from "../config/types";
+
+const jobSchema = new Schema<JobType>({
+  title: String,
+  description: String,
+  primarySkills: { type: [String], require: true },
+  secondarySkills: { type: [String], require: false },
+  salary: {
+    min: Number,
+    max: Number,
+    currency: String,
+  },
+  applications: [{ type: Schema.Types.ObjectId, ref: "applications" }],
+  organization: [{ type: Schema.Types.ObjectId, ref: "organizations" }],
+});
+
+const Jobs = model<JobType>("jobs", jobSchema);
+export default Jobs;

src/routes/auth.ts → NodeServer/src/routes/auth.ts

@@ -137,7 +137,7 @@ router.post("/login", async (req: TypedRequest<{}, SignInPayload>, res) => {
     }
 
     const token = await jwt.sign({ userId: auth.userId }, JWT_SECRET, {
-      expiresIn: "2h",
+      expiresIn: "5h",
     });
 
     return res.json({

NodeServer/src/routes/jobs.ts

+import { Router } from "express";
+import {
+  ApplicationType,
+  JobType,
+  TypedRequest,
+  USER_TYPE,
+} from "../config/types";
+import {
+  authMiddleware,
+  candidateMiddleware,
+  organizationMiddleware,
+} from "../middlewares/auth";
+import Application from "../models/Application";
+import Auth from "../models/Auth";
+import Jobs from "../models/Job";
+import ResumeAPI from "../utilities/apis/resume";
+
+const router = Router();
+
+router.get(
+  "/",
+  authMiddleware,
+  async (req: TypedRequest<{ userId: string }, null>, res) => {
+    try {
+      const user = await Auth.findOne({ userId: req.query.userId });
+
+      let jobs;
+
+      if (user.userType === USER_TYPE.CANDIDATE) {
+        jobs = await Jobs.find()
+          .populate({
+            path: "applications",
+            select: ["candidate", "status"],
+          })
+          .populate({ path: "organization" });
+      } else {
+        jobs = await Jobs.find({ organization: req.query.userId }).populate({
+          path: "applications",
+          populate: {
+            path: "candidate",
+            select: [
+              "name",
+              "contacts",
+              "dateOfBirth",
+              "profilePicture",
+              "resume",
+              "resumeData",
+            ],
+          },
+        });
+      }
+
+      return res.json({ jobs, success: true });
+    } catch (error) {
+      return res.json({ error, success: false });
+    }
+  }
+);
+
+router.post(
+  "/",
+  authMiddleware,
+  organizationMiddleware,
+  async (req: TypedRequest<{ userId: string }, JobType>, res) => {
+    try {
+      const newJob = new Jobs({ ...req.body, organization: req.query.userId });
+      const job = await newJob.save();
+      return res.json({ success: true, job });
+    } catch (error) {
+      return res.json({ success: false, error });
+    }
+  }
+);
+
+router.put(
+  "/",
+  authMiddleware,
+  organizationMiddleware,
+  async (req: TypedRequest<{ userId: string }, JobType>, res) => {
+    try {
+      const job = await Jobs.findByIdAndUpdate(req.body._id, {
+        $set: req.body,
+      });
+      return res.json({ success: true, job });
+    } catch (error) {
+      return res.json({ success: false, error });
+    }
+  }
+);
+
+router.delete(
+  "/",
+  authMiddleware,
+  organizationMiddleware,
+  async (req: TypedRequest<{ userId: string }, { jobId: string }>, res) => {
+    try {
+      await Jobs.deleteOne({
+        organization: req.query.userId,
+        _id: req.body.jobId,
+      });
+      return res.json({ success: true });
+    } catch (error) {
+      return res.json({ success: false });
+    }
+  }
+);
+
+router.put(
+  "/apply",
+  authMiddleware,
+  candidateMiddleware,
+  async (
+    req: TypedRequest<
+      { userId: string },
+      { application: ApplicationType; resumeUrl: string }
+    >,
+    res
+  ) => {
+    try {
+      const { application, resumeUrl } = req.body;
+      const job = await Jobs.findById(application.job);
+
+      const data: any = await ResumeAPI.getResumeScores({
+        user_id: req.query.userId,
+        resume_url: resumeUrl,
+        primary_skills: job.primarySkills,
+        secondary_skills: job.secondarySkills,
+        job_desc: job.description,
+      });
+
+      const score: ApplicationType["score"] = {
+        primary: data.primary_score,
+        primatyMatch: data.primary_match,
+        secondary: data.secondary_score,
+        secondaryMatch: data.secondary_match,
+        similarity: data.similarity,
+        total: data.primary_score + data.secondary_score + data.similarity,
+      };
+
+      const newApplication = new Application({ ...application, score });
+      const _application = await newApplication.save();
+      job.applications.push(_application.id);
+      await job.save();
+      return res.json({
+        success: true,
+        applicationId: _application.id,
+      });
+    } catch (error) {
+      return res.json({ success: false, error });
+    }
+  }
+);
+
+module.exports = router;

NodeServer/src/routes/user.ts

+import { Router } from "express";
+import { CandidateType, TypedRequest } from "../config/types";
+import { authMiddleware } from "../middlewares/auth";
+import Candidates from "../models/Candidate";
+import ResumeAPI from "../utilities/apis/resume";
+
+const router = Router();
+
+router.post(
+  "/candidate",
+  authMiddleware,
+  async (req: TypedRequest<{ userId: string }, CandidateType>, res) => {
+    try {
+      const update = req.body;
+      if (req.body?.resume) {
+        const data: any = await ResumeAPI.extractResumeData({
+          user_id: req.query.userId,
+          resume_url: req.body.resume,
+        });
+        update.resumeData = data;
+      }
+      await Candidates.findByIdAndUpdate(req.query.userId, { $set: req.body });
+      return res.status(200).json({ data: req.body });
+    } catch (error) {
+      return res.status(400).send(error);
+    }
+  }
+);
+
+module.exports = router;

NodeServer/src/utilities/apis/resume.ts

+import { ResumeDataType } from "../../config/types";
+import { request } from "../requests";
+
+export default class ResumeAPI {
+  static extractResumeData = (payload: {
+    resume_url: string;
+    user_id: string;
+  }) => request("<BASE_URL>/resume/extract", "POST", payload);
+
+  static getResumeScores = (payload: {
+    resume_url: string;
+    user_id: string;
+    primary_skills: string[];
+    secondary_skills: string[];
+    job_desc: string;
+  }) => request("<BASE_URL>/resume/get-scores", "POST", payload);
+}

src/utilities/keystroke.ts → NodeServer/src/utilities/keystroke.ts

@@ -401,8 +401,15 @@ export const processAttempt = ({
     accepted: false,
   };
 
-  result.accepted =
-    result.standard.inRange.full || result.fullStandard.inRange.full;
+  const standardCheck = controls.standard.use
+    ? result.standard.inRange.full
+    : true;
+
+  const fullStandardCheck = controls.fullStandard.use
+    ? result.fullStandard.inRange.full
+    : true;
+
+  result.accepted = standardCheck || fullStandardCheck;
 
   return result;
 };

NodeServer/src/utilities/requests.ts

+import axios, { AxiosError, AxiosResponse, AxiosRequestConfig } from "axios";
+
+import { UTILITY_SERVER } from "../config/contants";
+
+axios.interceptors.response.use(
+  (response) => response,
+  (error: AxiosError) => {
+    return Promise.reject(error);
+  }
+);
+
+export const request = (
+  url: AxiosRequestConfig["url"],
+  method: AxiosRequestConfig["method"],
+  requestData?: AxiosRequestConfig["data"] | AxiosRequestConfig["params"],
+  contentType?: string
+) =>
+  new Promise(async (resolve, reject) => {
+    const endpoint = url?.replace?.("<BASE_URL>", UTILITY_SERVER);
+
+    const params = method === "GET" ? requestData : null;
+    const data = method === "GET" ? null : requestData;
+
+    const headers = {
+      "Content-Type": contentType || "application/json",
+    };
+
+    axios({
+      url: endpoint,
+      method,
+      data,
+      params,
+      headers,
+      timeout: 30000,
+    })
+      .then(async (response: AxiosResponse) => {
+        resolve(response.data);
+      })
+      .catch(async (error: AxiosError) => {
+        if (error?.response) {
+          return reject(error?.response?.data);
+        }
+        reject(error);
+      });
+  });

yarn.lock → NodeServer/yarn.lock

@@ -276,6 +276,20 @@ astral-regex@^2.0.0:
   resolved "https://registry.npmjs.org/astral-regex/-/astral-regex-2.0.0.tgz"
   integrity sha512-Z7tMw1ytTXt5jqMcOP+OQteU1VuNK9Y02uuJtKQ1Sv69jXQKKg5cibLwGJow8yzZP+eAc18EmLGPal0bp36rvQ==
 
+asynckit@^0.4.0:
+  version "0.4.0"
+  resolved "https://registry.yarnpkg.com/asynckit/-/asynckit-0.4.0.tgz#c79ed97f7f34cb8f2ba1bc9790bcc366474b4b79"
+  integrity sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==
+
+axios@^1.3.4:
+  version "1.3.4"
+  resolved "https://registry.yarnpkg.com/axios/-/axios-1.3.4.tgz#f5760cefd9cfb51fd2481acf88c05f67c4523024"
+  integrity sha512-toYm+Bsyl6VC5wSkfkbbNB6ROv7KY93PEBBL6xyDczaIHasAiv4wPqQ/c4RjoQzipxRD2W5g21cOqQulZ7rHwQ==
+  dependencies:
+    follow-redirects "^1.15.0"
+    form-data "^4.0.0"
+    proxy-from-env "^1.1.0"
+
 balanced-match@^1.0.0:
   version "1.0.2"
   resolved "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz"
@@ -441,6 +455,13 @@ color-name@~1.1.4:
   resolved "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz"
   integrity sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==
 
+combined-stream@^1.0.8:
+  version "1.0.8"
+  resolved "https://registry.yarnpkg.com/combined-stream/-/combined-stream-1.0.8.tgz#c3d45a8b34fd730631a110a8a2520682b31d5a7f"
+  integrity sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==
+  dependencies:
+    delayed-stream "~1.0.0"
+
 complex.js@^2.0.11:
   version "2.1.1"
   resolved "https://registry.npmjs.org/complex.js/-/complex.js-2.1.1.tgz"
@@ -546,6 +567,11 @@ define-properties@^1.1.3, define-properties@^1.1.4:
     has-property-descriptors "^1.0.0"
     object-keys "^1.1.1"
 
+delayed-stream@~1.0.0:
+  version "1.0.0"
+  resolved "https://registry.yarnpkg.com/delayed-stream/-/delayed-stream-1.0.0.tgz#df3ae199acadfb7d440aaae0b29e2272b24ec619"
+  integrity sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==
+
 denque@^1.4.1:
   version "1.5.1"
   resolved "https://registry.npmjs.org/denque/-/denque-1.5.1.tgz"
@@ -934,6 +960,20 @@ flatted@^3.1.0:
   resolved "https://registry.npmjs.org/flatted/-/flatted-3.2.7.tgz"
   integrity sha512-5nqDSxl8nn5BSNxyR3n4I6eDmbolI6WT+QqR547RwxQapgjQBmtktdP+HTBb/a/zLsbzERTONyUB5pefh5TtjQ==
 
+follow-redirects@^1.15.0:
+  version "1.15.2"
+  resolved "https://registry.yarnpkg.com/follow-redirects/-/follow-redirects-1.15.2.tgz#b460864144ba63f2681096f274c4e57026da2c13"
+  integrity sha512-VQLG33o04KaQ8uYi2tVNbdrWp1QWxNNea+nmIB4EVM28v0hmP17z7aG1+wAkNzVq4KeXTq3221ye5qTJP91JwA==
+
+form-data@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/form-data/-/form-data-4.0.0.tgz#93919daeaf361ee529584b9b31664dc12c9fa452"
+  integrity sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==
+  dependencies:
+    asynckit "^0.4.0"
+    combined-stream "^1.0.8"
+    mime-types "^2.1.12"
+
 forwarded@0.2.0:
   version "0.2.0"
   resolved "https://registry.npmjs.org/forwarded/-/forwarded-0.2.0.tgz"
@@ -1410,7 +1450,7 @@ mime-db@1.52.0:
   resolved "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz"
   integrity sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==
 
-mime-types@~2.1.24, mime-types@~2.1.34:
+mime-types@^2.1.12, mime-types@~2.1.24, mime-types@~2.1.34:
   version "2.1.35"
   resolved "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz"
   integrity sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==
@@ -1682,6 +1722,11 @@ proxy-addr@~2.0.7:
     forwarded "0.2.0"
     ipaddr.js "1.9.1"
 
+proxy-from-env@^1.1.0:
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/proxy-from-env/-/proxy-from-env-1.1.0.tgz#e102f16ca355424865755d2c9e8ea4f24d58c3e2"
+  integrity sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==
+
 pstree.remy@^1.1.8:
   version "1.1.8"
   resolved "https://registry.npmjs.org/pstree.remy/-/pstree.remy-1.1.8.tgz"

PythonServer/.gitignore

+__pycache__
+**/__pycache__
\ No newline at end of file

PythonServer/Candidates_score.csv

+filename,name,mobile_number,email,company_names,college_name,experience,skills,experience_age,degree,words,primary_score,primary_match,secondary_score,secondary_match,no_of_pages,document_similarity,document_score,Score
+resumes/Dhaval_Thakkar_Resume.pdf,Dhaval Thakkar,9191729595,thakkar.dhaval.haresh@gmail.com,['UNIFYND TECHNOLOGIES PVT. LTD'],None,"['UNIFYND TECHNOLOGIES PVT. LTD. | Data Scientist', 'Mumbai, MH, India | June 2018 – Present', '• Led the development of a Templatized OCR Engine with GUI to onboard 2000+ retailers from different malls. The', 'microservice deployed is currently operating at an accuracy of 81%', '• Built a Customer Segmentation model to target customers with relevant coupons, rewards, and content resulting', 'in a 3x increase in revenue and 2x increase in coupon utilization', '• Built a Dynamic Coupon Pricing Engine for malls that led to a 5x increase in coupon consumption on the coupon', 'marketplace', '• Built a Pricing Engine and Customer Segmentation Model for a logistics company which saw a 32% reduction in', 'Customer Attrition and a 12% increase in Repeat Purchase Rate', '• Developed an Automated End to End Reporting system to track KPIs performance for 10 malls that saves 60', 'hours of manual labour each month', 'UNIFYND TECHNOLOGIES PVT. LTD. | Intern Data Scientist Mumbai, MH, India | Sept 2017 - June 2018', '• Built a Smart Cryptocurrency trading platform which used social data and historical prices to optimize current', 'portfolio. Boosted overall profit from the portfolio by 30%', '• Worked with Product and Marketing teams to identify the power users of an app which resulted in 43% increase in', 'activity and a 65% increase in revenue from these users', 'ZIFF, INC | Deep Learning Intern', 'Provo, UT, USA | May 2017 – Aug 2017', '• Demonstrated competency in Hyperparameter Optimization, Image Augmentation and Learning Rate decay', 'strategies using the Keras Library', '• Deployed a Multi-Class Image classifier microservice written on Flask as a container on AWS EC2 using Docker']","['Html', 'Data analytics', 'Marketing', 'Segmentation', 'Content', 'Algorithms', 'Numpy', 'Pandas', 'Github', 'R', 'Logistics', 'Css', 'Operating systems', 'Testing', 'Flask', 'Mysql', 'Scrapy', 'Machine learning', 'Security', 'Keras', 'Python', 'Kpis', 'System', 'Docker', 'Reporting', 'Analytics', 'Aws', 'Engineering', 'Anaconda', 'Networking', 'Sql']",5.75,['Bachelor of Engineering'],350,44,"['ocr', 'aws', 'python', 'gcp']",42,"['data', 'ocr', 'science']",1,32,50.0,168.0
+resumes/python-developer-resume-2.pdf,Python Developer,456-7890,ggonzalez@email.com,None,None,"['Python Developer Intern', 'Knewton', 'April 2016 - April 2017', '· Worked alongside another developer to implement RESTful APIs', 'Chicago, IL', 'in Django that enabled internal analytics team to increase', 'reporting speed by 24%', '· Using Selenium, built out a unit testing infrastructure for a client', 'web application that reduced the number of bugs reported by', 'the client by 11% month over month']","['Django', 'Math', 'Oracle', 'Requests', 'Github', 'Api', 'Database', 'Css', 'Design', 'Postgresql', 'Testing', 'Agile', 'Apis', 'Selenium', 'Rest', 'Python', 'Writing', 'System', 'Updates', 'Javascript', 'Reporting', 'Analytics', 'Aws', 'Sql', 'Process']",1.0,"['B.S.', 'M.S.']",223,22,"['python', 'aws']",28,"['science', 'data']",1,20,50.0,120.0
+resumes/software-engineer-resume-1.pdf,New York,456-7890,cmcturland@email.com,None,None,"['Software Engineer', 'Embark', 'January 2015 - current / New York, NY', 'Worked with product managers to re-architect a multi-page web', 'app into a single page web-app, boosting yearly revenue by $1.4M', 'Constructed the logic for a streamlined ad-serving platform that', 'scaled to our 35M users, which improved the page speed by 15%', 'after implementation', 'Tested software for bugs and operating speed, fixing bugs and', 'documenting processes to increase efficiency by 18%', 'Iterated platform for college admissions, collaborating with a group', 'of 4 engineers to create features across the software', 'Software Engineer', 'MarketSmart', 'April 2012 - January 2015 / Washington, DC', 'Built RESTful APIs that served data to the JavaScript front-end', 'based on dynamically chosen user inputs that handled over 500,000', 'concurrent users', 'Built internal tool using NodeJS and Pupeteer.js to automate QA and', 'monitoring of donor-facing web app, which improved CTR by 3%', 'Reviewed code and conducted testing for 3 additional features on', 'donor-facing web app that increased contributions by 12%', 'Software Engineer Intern', 'Marketing Science Company', 'April 2011 - March 2012 / Pittsburgh, PA', 'Partnered with a developer to implement RESTful APIs in Django,', 'enabling analytics team to increase reporting speed by 24%', 'Using Selenium I built out a unit testing infrastructure for a client', 'application that reduced the number of bugs reported by the client', 'by 11% month over month']","['Django', 'Marketing', 'Unix', 'Nosql', 'R', 'Css', 'Postgresql', 'Testing', 'Mysql', 'Sci', 'Apis', 'Selenium', 'Admissions', 'Python', 'Html5', 'Javascript', 'Reporting', 'Analytics', 'C', 'Sql', 'Aws']",3.67,['B.S.'],233,22,"['python', 'aws']",28,"['science', 'data']",1,10,50.0,110.0
+resumes/Santhosh_Narayanan.pdf,SANTHOSH NARAYANAN,417-6755,santhosn@usc.edu,None,None,"['on an EC2 server supported by S3 and RDS.', '\uf0a7  Maintained AWS infrastructure for institute’s annual technical festival website, by hosting the website', 'on an EC2 Ubuntu server.', 'K J Somaiya Inst. of Engg. & I.T – Penetration tester', 'December 2016 – January 2016', '\uf0a7  Conducted penetration testing for institute’s online admission and examination portal.', '\uf0a7  Performed authentication checks, access control checks, per screen checks (XSS, SQL injection.).', '\uf0a7  Delivered error free application, incorporating patches for the respective bugs using ASP.NET']","['Html', 'Jupyter', 'Access', 'Numpy', 'Php', 'Matplotlib', 'Oracle', 'Pandas', 'Computer science', 'Css', 'Purchasing', 'Schedule', 'Scheduling', 'Flask', 'Testing', 'Lan', 'Mysql', 'Scrapy', 'Security', 'Programming', 'Website', 'Keras', 'Python', 'System', 'Wordpress', 'Spyder', 'Technical', 'Ubuntu', 'Javascript', 'Java', 'Aws', 'Engineering', 'Sql', 'Certification']",,None,367,22,"['python', 'aws']",14,['science'],1,7,50.0,93.0

PythonServer/Job_description.txt

+About the job
+
+Borneo.io is building the next-generation ML Powered data privacy platform for hyper-growth companies. The Data Scientist role is at the core of Borneo's engineering. You will be building models, manipulating big data, and working with APIs essential to the Borneo product.
+We are growing fast and expanding our data science family with outstanding minds and diverse personalities.
+
+As a Data Scientist at Borneo, you'll have the opportunity to:
+
+    Work with some of the largest data sets used by some of the leading global technology companies
+    Help build a predictive product and inform features at the ground level.
+    Lead the way in leveraging unstructured data for predictive modeling, anomaly detection, and drive privacy compliance.
+
+Responsibilities:
+
+    Identify, automate data collection processes
+    Dive into complex data sets to analyze trends and identify opportunities for improvement.
+    Build predictive models and machine-learning algorithms
+    Present information using data visualization techniques
+    Propose solutions and strategies to business challenges
+    Have a data-driven decision making approach
+
+Requirements:
+
+    5-8 years of relevant experience, B2B startup experience preferred
+    Proven experience as a Data Scientist or Data Analyst
+    Experience in building ML models and deploying them to production
+    A solid understanding of data science fundamentals, statistical techniques, NLP algorithms
+    Understand research papers and create quick proof of concept relevant to the product
+    Expert in implementing quick prototypes that shows business value
+    Experience with programming languages such as NodeJs /Python/JavaScript: Cloud technologies: AWS/GCP/K8 etc.
+

PythonServer/README.md

+### Create conda python 3.9 env
+
+conda create -n server python=3.9
+
+### PIP Packages
+
+gensim==3.8.1
+texthero==1.1.0
+pyresparser
+
+### CONDA Packages
+
+tqdm
+pdf2image
+pandas
+pytesseract
+"uvicorn[standard]"
+fastapi
+
+### Run server
+
+uvicorn main:app --reload

PythonServer/baseModels/payloads.py

+from typing import List, Union
+from pydantic import BaseModel
+
+class ExtractResume(BaseModel):
+    resume_url: str
+    user_id:str
+
+class ResumeScores(BaseModel):
+    resume_url: str
+    user_id:str
+    primary_skills:List[str] = []
+    secondary_skills:List[str] = []
+    job_desc:str
\ No newline at end of file

PythonServer/main.py

+from fastapi import FastAPI
+
+import routes.resume as resumes
+
+app = FastAPI()
+app.include_router(resumes.router)
+
+@app.get("/")
+def read_root():
+    return {"status": "running"}
\ No newline at end of file

PythonServer/requirements.txt

+tqdm==4.61.2
+pdf2image==1.16.0
+pandas==1.3.0
+pytesseract==0.3.8

PythonServer/resumeSample.py

+
+import pandas as pd
+import os
+
+from scripts.processing import document_processing
+from tqdm import tqdm
+
+import warnings
+warnings.filterwarnings("ignore")
+
+skills = {
+ "primary" : ['Python', 'Machine Learning', 'node.js', 'AWS', 'Kubernetese', 'NLP', 'GCP', 'predective', 'OCR'],
+ "secondary" : ['data', 'science', 'modeling', 'anomaly', 'privacy', 'visualization', 'OCR'],
+}
+
+
+def document_score(df):
+    
+    # Page score
+    df.loc[df['no_of_pages'] == 1, ['page_score']] = 100
+    df.loc[df['no_of_pages'] == 2, ['page_score']] = 60
+    df.loc[(df['no_of_pages'] > 2) |
+           (df['no_of_pages'] == 0), ['page_score']] = 30
+    
+    # Word score
+    df.loc[(df['words'] >= 200) & (df['words'] < 400),
+           ['word_score']] = 100
+    df.loc[(df['words'] >= 400) & (df['words'] < 600),
+           ['word_score']] = 70
+    df.loc[((df['words'] > 0) & (df['words'] < 200))|
+           (df['words'] > 600) | (df['words'].isnull()),
+           ['word_score']] = 40
+    
+    df['document_score'] = (df['page_score'] + df['word_score']) * 0.25
+    
+    df.drop(['word_score', 'page_score'], axis=1, inplace=True)
+    
+    return df
+
+if __name__=='__main__':
+
+    resume_dir = 'resumes/'
+    jd_file = 'Job_description.txt'
+    list_of_resumes = os.listdir(resume_dir)  # list_of_resumes = ['Dhaval_Thakkar_Resume.pdf', 'asdasdasd.pdf']
+    
+    df = pd.DataFrame()
+    for file in tqdm(list_of_resumes):
+        result = document_processing(resume_dir+file, skills, jd_file)
+        candidate = result.skills_match()
+        df = pd.concat([df, candidate], ignore_index=True)
+    
+    df = document_score(df)
+        
+    # Final score
+    df['Score'] = df['primary_score'] + df['secondary_score'] + df['document_score'] + df['document_similarity']
+    
+    df = df.sort_values('Score', ascending=False)
+    df = df.reset_index(drop=True)
+
+    print(df)
+    
+    df.to_csv('Candidates_score.csv', index=False)
\ No newline at end of file

PythonServer/routes/resume.py

+from fastapi import APIRouter
+import os
+from pyresparser import ResumeParser
+import urllib
+from baseModels.payloads import ExtractResume, ResumeScores
+
+from scripts.processing import document_processing
+
+
+router = APIRouter(prefix='/resume')
+
+@router.post("/extract")
+def extract(payload:ExtractResume):
+    filename = 'resumes/'+payload.user_id+'.pdf'
+    urllib.request.urlretrieve(payload.resume_url, filename)
+    pyres_data = ResumeParser(filename).get_extracted_data()
+    os.remove(filename)
+    return pyres_data
+
+@router.post("/get-scores")
+def get_scores(payload:ResumeScores):
+    filename = 'resumes/'+payload.user_id+'.pdf'
+    urllib.request.urlretrieve(payload.resume_url, filename)
+    skills = {"primary":payload.primary_skills, "secondary":payload.secondary_skills}
+
+    result = document_processing(filename, skills, payload.job_desc)
+    candidate = result.skills_match()
+
+    os.remove(filename)
+    return candidate
\ No newline at end of file

PythonServer/scripts/processing.py

+import pandas as pd
+import texthero as hero
+
+from pyresparser.utils import extract_text
+
+from PIL import Image
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# skills = {
+#  "primary" : ['Python', 'Machine Learning', 'node.js', 'AWS', 'Kubernetese', 'NLP', 'GCP', 'predective', 'OCR'],
+#  "secondary" : ['data', 'science', 'modeling', 'anomaly', 'privacy', 'visualization', 'OCR'],
+# }
+
+class document_processing:
+    
+    def __init__(self, resume, skills, job_desc):
+        self.resume = resume
+        self.skills = skills
+        self.job_desc = job_desc
+        
+    def extract_resume(self):
+        filepath = self.resume
+        
+        extension = filepath.split('.')[-1]
+        extension = '.'+extension
+
+        resume_txt = extract_text(filepath, extension=extension)
+        
+        return resume_txt
+         
+    def find_unigram(df, column):
+        
+        unigrams  = (df[column].str.lower()
+                    .str.replace(r'[^a-z\s]', '')
+                    .str.split(expand=True)
+                    .stack()).reset_index(drop=True)
+        
+        unigrams = hero.clean(unigrams)
+        un_df = pd.DataFrame(unigrams, columns = ['text'])
+        
+        return un_df
+    
+    def find_match(self, source, match):
+        
+        # Remove the null values 
+        match.dropna(inplace=True)
+        match.reset_index(drop=True)
+        match.columns = ['text']
+        match['text'] = hero.clean(match['text'])
+        
+        # Find the max val
+        max_val = len(match)  #9
+
+
+        #1. source (main_df) Python, Python, Python, Python 
+        #2. match (primary skill)       
+        # Find the skills that match with the resume
+        df = pd.merge(source, match, on = 'text') 
+        df.drop_duplicates(inplace=True) # Python
+        df.reset_index(drop=True)
+        
+        # Skills matching
+        match_skills = len(df) #5
+        
+        if match_skills == 0:
+            lst_skills = []
+            score = 0
+        elif match_skills > 0:
+            lst_skills = df['text'].tolist()
+            score = int((match_skills / max_val) * 100)
+        
+        return score, lst_skills
+    
+    def fill_data(self, source, target, column):
+   
+        source.loc[0, column] = str(target[column])
+        
+        return source   
+    
+    def resume_cosine_score(self, text):
+        
+        jd_txt = self.job_desc
+        jd_txt = pd.Series(jd_txt)
+        jd_txt = hero.clean(jd_txt)
+        jd_txt = jd_txt[0]
+
+        [[1,24],[24,1]]
+
+        text_list = [text, jd_txt]
+        cv = CountVectorizer()
+        count_matrix = cv.fit_transform(text_list)
+        match_percentage = cosine_similarity(count_matrix)[0][1] * 100
+        match_percentage = round(match_percentage, 2)
+
+        return match_percentage
+        
+    
+    def skills_match(self):
+        
+        skills = self.skills
+        
+        pyres_text = self.extract_resume()
+        self.text = pyres_text
+        
+        ocr_ser = pd.Series(pyres_text)
+        cleaned_words = hero.clean(ocr_ser) 
+        
+        main_df = pd.DataFrame(cleaned_words[0].split(), columns = ['text'])
+        self.clean_data = main_df
+        
+        pri_score, pri_match = self.find_match(main_df, pd.DataFrame(skills['primary']))
+        sec_score, sec_match = self.find_match(main_df, pd.DataFrame(skills['secondary']))
+
+        doc_sim = self.resume_cosine_score(cleaned_words[0])
+        
+        return {'primary_score': pri_score,
+                'primary_match': pri_match,
+                'secondary_score': sec_score,
+                'secondary_match': sec_match,
+                'similarity': int(doc_sim)}