🧙🏻‍♂️ Resume Wizard
Ardian the Great
October 04th, 2023
Resume Ranking & Clustering Tool
Introduction
Background
In today’s job market, finding the right candidates is tough. Companies need skilled professionals, and they need them fast. But here’s the problem: going through resumes one by one takes forever, and it’s not always effective. Glassdoor found that, on average, each of their corporate job postings attracts approximately 250 resumes.
To speed things up, many companies use something called an Applicant Tracking System (ATS). It’s like a robot that reads resumes and looks for specific words. It’s good at some things, but not everything.
ATS has a flaw. It only likes resumes that look a certain way. If your resume doesn’t fit the mold, it might get ignored. That’s not fair to talented people who don’t have traditional resumes.
My project is different. Instead of parsing resumes, I look at what’s inside. I check how well a resume matches what a company wants. It’s like finding a puzzle piece that fits, no matter its shape.
I want to make hiring smarter and faster. With my project, companies can find the best candidates, even if their resumes are a bit different. It’s a bridge between robots and real people, making hiring better for everyone. We believe this will help companies succeed in today’s competitive job market.
Problem Statement
In the fast-paced world of job recruitment, finding the right candidates can be a tough challenge. Companies often use Applicant Tracking Systems (ATS) to help them sort through resumes. But here’s the problem: ATS systems use parsing techniques that have limitations. They are not adept at handling resumes that deviate from the standard mold, potentially causing them to overlook promising candidates.
The issue at the heart of this problem is that ATS filters out resumes that don’t precisely match its predefined criteria. However, in doing so, it can inadvertently discard resumes that hold hidden potential—those belonging to talented individuals whose profiles don’t conform to the conventional format. This situation is akin to searching for a needle in a haystack and unintentionally discarding valuable pieces of straw.
This problem of resume parsing and its consequences are further explored in the paper titled “The Dark Side of Applicant Tracking Systems: How Unfairness and Bias Undermine Diversity and Inclusion in Hiring,” authored by Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner (2016). The paper sheds light on how ATS can unwittingly introduce unfairness and bias into the hiring process, thus undermining efforts to promote diversity and inclusion in recruitment.
Our approach offers a distinctive solution. Instead of outrightly filtering out resumes, we propose ranking them based on their alignment with what companies are seeking. This approach ensures that we don’t miss the hidden gems among the applicants. What sets us apart is that we bypass parsing techniques like those employed by ATS. Instead, we employ text similarity analysis, avoiding the parsing-related pitfalls that ATS systems encounter. Our overarching goal is to enhance recruitment efficiency, accuracy, and flexibility. By prioritizing resumes based on their content, we offer companies a more intelligent and inclusive method for identifying the most suitable candidates for their needs.
Project Idea
The project aims to develop an innovative Resume Ranking & Clustering Tool that leverages Natural Language Processing (NLP) techniques to revolutionize the recruitment process. Instead of relying on traditional Applicant Tracking Systems (ATS) with their limitations, this tool will rank all resumes based on the intersection between the desired candidate qualifications and the content of resumes. The primary goal is to make the recruitment process more efficient, fair, inclusive, and flexible.
Key Features:
Matching Criteria Based Ranking: Implement pure Natural Language Processing to rank all the resumes based on how much the resume matches the desired criteria.
Matching Criteria Based Clustering: Implement K-means Clustering algorithm to clusters all the resumes based on the matching criteria into the desired number of segments.
User-Friendly Interface: Create an intuitive and user-friendly web interface where recruiters can easily upload resumes and enter the desired criteria. The ranked results will be displayed in a clear and accessible format.
Flexible objective and descriptive Criteria: Allow users to input specific job criteria, including skills, platforms, experience, education, and other qualifications. The tool will adapt the ranking accordingly.
No Parsing Limitations: Emphasize that the tool does not rely on parsing techniques, eliminating the common parsing problems associated with ATS.
Value Proposition:
Improved Recruitment Efficiency: Traditional ATS systems often struggle with parsing errors and rigid filtering, leading to missed opportunities. By ranking resumes based on matching criteria, Resume Wizard ensures recruiters quickly identify the most relevant candidates without any chance of losing high potential candidate due to parsing errors.
Inclusivity: ATS systems can inadvertently exclude candidates with non-standard resume formats or unique experiences. Resume Wizard ensures that every candidate has a fair chance to be considered, regardless of resume style.
Flexibility: Recruiters can fine-tune their criteria to adapt to changing hiring needs without the need to update the tool (Resume Wizard) itself like how it should with ATS, making the tool suitable for various job roles and industries. This flexibility eliminates the rigidity of ATS systems.
Conclusion:
Resume Wizard offers a transformative approach to CV/resume selection, directly addressing the limitations of traditional ATS systems. It empowers businesses to efficiently identify and select the best-suited candidates based on resume content, ultimately enhancing the quality of hires and streamlining the recruitment process while overcoming the weaknesses of ATS.
Work Flow
Data Preprocessing:
- Collecting Data: Gather a large number of resumes in form of PDF from applicants.
- Converting PDFs to Raw Text: Convert all PDF files into raw texts.
- Creating a Data frame: Create a data frame with two columns, the resume PDF file name and the extracted raw resume text.
Text Preprocessing:
- Text Corpus Creation: Transform the input text into a text corpus.
- Lowercasing: Convert all text to lowercase.
- Removing Stop-Words: Eliminate common stop-words from the text.
- Punctuation Removal: Strip away punctuation marks.
- Removing Extra Spaces: Cleanse the text by removing extra spaces.
Resume Ranking:
- Tokenizing the Ideal Criteria: The cleaned ideal criteria are split into individual words.
- Scoring Resumes: For each resume, the function calculates the word count of matched words between the resume and the ideal criteria.
- Ranking Resumes: Resumes are ranked based on their word count scores, with resumes containing more matched words receiving higher rankings.
- Generating Ranked Resume Data Frame: The function generates a data frame that includes the resume names, the matched words in each resume (as a string), and a ratio indicating the proportion of matched words relative to the total words in the ideal criteria.
Resume Clustering:
- Turns the matching criteria into columns: The matching criteria are split into individual words and turned into columns.
- Apply K-means Clustering: With matching criteria as features, the resumes are clustered into the desired number of segments
- Extract common words: The common words of each segment is extracted for segment information.
Output
The output of this project is a Shiny Apps based Web App that can be used by anyone with PDF format resumes.
Business Impact
The implementation of Resume Wizard have a significant positive impact on businesses and their recruitment processes. Here are the key areas where Resume Wizard can make a difference:
1. Enhanced Recruitment Efficiency
Traditional recruitment processes, especially when reliant on ATS, can be time-consuming and prone to missing potential candidates. ATS systems often encounter difficulties in parsing resumes with non-standard structures or complex formatting. These parsing errors can result in the exclusion of potentially qualified candidates, leading to inefficiencies in the recruitment process. By employing a text-based ranking approach, Resume Wizard eliminates parsing problems, streamlining the candidate selection process. This increased efficiency means that recruiters can quickly identify the most qualified candidates without being bogged down by parsing errors or rigid filtering.
2. Diverse and Inclusive Hiring
One of the limitations of ATS is that it often excludes candidates with non-standard resume formats or unique experiences. This lack of inclusivity can hinder diversity and result in the unintentional exclusion of talented individuals. Resume Wizard, by focusing on content and similarity rather than rigid filtering, ensures inclusivity in the hiring process. It accommodates candidates with diverse resume styles and experiences, enabling recruiters to discover talented individuals who might have been overlooked by traditional systems. This approach contributes to a more diverse and inclusive workforce, fostering innovation and representation.
3. Adaptability to Changing Needs
Traditional ATS systems rely on predefined criteria and rigid keyword filtering, which may inadvertently exclude candidates who use different terms or phrasing. This lack of flexibility can be a hindrance, particularly in fast-paced industries where skill demands can change rapidly. In contrast, Resume Wizard provides businesses with the agility to adapt to evolving hiring needs. Recruiters can customize job criteria, including skills, experience, education, and other qualifications, making the tool suitable for various job roles and industries. This adaptability ensures that no qualified candidate is overlooked, even as recruitment requirements change over time.
4. Cost Savings
Manual resume screening and the limitations of ATS can lead to increased recruitment costs. Traditional ATS systems often require substantial human intervention to address parsing errors and filter out candidates. By improving the selection process through text-based ranking and clustering, Resume Wizard reduces the time and resources required for recruitment. It enables HR teams to focus their efforts on strategic aspects of the hiring process, such as interviews and candidate engagement, leading to significant cost savings in the long run.
5. Data-Driven Decision-Making
Resume Wizard provides recruiters with data-driven insights into candidate rankings, empowering organizations to make more informed and objective hiring decisions. In contrast, traditional ATS systems may lack the data-driven capabilities necessary for precise candidate evaluation. This data-driven approach enhances recruitment strategies, leading to better hires and improved workforce performance. Recruiters can leverage analytics to gain valuable insights into candidate suitability and tailor their hiring processes accordingly.
In summary, the Resume Wizard offers a holistic approach to the recruitment process, addressing the limitations of traditional ATS systems. It eliminates parsing problems, ensures inclusivity, provides adaptability, reduces costs, and supports data-driven decision-making. By adopting Resume Wizard, companies can elevate their recruitment procedures, securing a competitive advantage in the talent acquisition arena and ensuring they access the most qualified candidates.
Technical Preparation
Used Libraries
Text Cleaner Function
The clean_text() function will be used to clean text
data.
Function Input:
- text: Basically a raw text.
- as.corpus: If TRUE, function will return text in the form of corpus.
- Other conditional statements: These are conditional statements of what transformations to be done on the text.
Function Workflow:
- Transforming the input text into a text corpus
- Converting all text to lowercase
- Removing stop-words
- Removing punctuation marks
- Applying text stemming to reduce words to their base forms
- Eliminating extra spaces
- Returning the cleaned text corpus
Function Output:
The output is a cleaned text in the form of character or corpus based on the as.corpus argument.
clean_text <- function(text, as.corpus = T, lower = T, re.english_stopwords = T, re.bahasa_stopwords = T, re.punctuation = T, re.whitespace = T){
list_stop_words_indo <- readLines("stopwords_indo.txt", warn = FALSE, encoding = "UTF-8")
text_corpus <- text %>% VectorSource() %>% VCorpus()
if (lower){
text_corpus <- tm_map(x = text_corpus,
FUN = content_transformer(tolower))
}
if (re.english_stopwords){
text_corpus <- tm_map(x = text_corpus,
FUN = removeWords,
stopwords(kind = "en"))
}
if (re.bahasa_stopwords){
text_corpus <- tm_map(x = text_corpus,
FUN = removeWords,
list_stop_words_indo)
}
if (re.punctuation){
text_corpus <- tm_map(x = text_corpus,
FUN = removePunctuation)
}
if (re.whitespace){
text_corpus <- tm_map(x = text_corpus,
FUN = stripWhitespace)
}
if (as.corpus){
return(text_corpus)
}
else(
return(sapply(text_corpus, as.character))
)
}Folder to Table Converter Function
The folder_to_table() function serves the purpose of
transforming a folder of PDF documents into a structured table,
represented as a data frame. The resulting table comprises two columns:
file_name, which contains the PDF file names, and
text, which contains the cleaned raw text extracted from those
PDFs. This function simplifies the process of working with PDF data and
is especially useful for tasks like text analysis or data
pre-processing.
Function Input:
- folder_path: This parameter specifies the path to the folder containing the PDF files to be processed. It should be provided as a character string.
Function Workflow:
- PDF to Text Conversion: The function employs an internal process to convert each PDF document within the specified folder into plain text. This process involves extracting text from each page of the PDF and combining it into a single text block.
- File Name Extraction: For each PDF file, the function extracts the file name without the file extension. This extracted file name is used as the file_name value in the resulting table.
- Data Frame Creation: The extracted file names and their corresponding text contents are organized into a data table with two columns: file_name and text.
Function Output:
The output of the folder_to_table() function is a data
frame structured as follows:
- file_name: This column contains the PDF file names, representing each document.
- text: This column contains the cleaned raw text content extracted from the PDF documents.
folder_to_table <- function(folder_path) {
# Function to convert PDF to text
convert_pdf_to_text <- function(pdf_path) {
pdf_text_content <- pdf_text(pdf_path)
extracted_text <- list()
for (page in seq_along(pdf_text_content)) {
text <- pdf_text_content[[page]]
extracted_text[[page]] <- text
}
all_text <- paste(extracted_text, collapse = "\n")
}
# Function to get file name
get_file_name <- function(file_path) {
file_path_sans_ext(basename(file_path))
}
# Get PDF files from the specified folder
pdf_files <- list.files(folder_path, pattern = ".pdf", full.names = TRUE)
# Convert PDFs to text
pdf_texts <- lapply(pdf_files, convert_pdf_to_text)
# Create a data table with file names and extracted text
table_data <- data.table(
file_name = paste(sapply(pdf_files, get_file_name), ".pdf", sep = ""),
text = unlist(pdf_texts)
)
return(table_data)
}Resume Ranking Function
The rank_resume() function is designed to rank resumes
based on their similarity to desired criteria. This function takes two
inputs: the ideal criteria and a data frame containing resumes. It then
produces a ranked list of resumes, with those most closely matching the
criteria receiving higher ranks.
Function Input:
- ideal_criteria: This is the set of criteria or keywords that define the ideal candidate. It serves as a reference for ranking resumes.
- resume_df: This data frame should contain the resumes to be ranked, with each resume represented as text in the text column.
- for.clustering: If TRUE, function will only return the Matching_Word and put file_name as row names.
Function Workflow:
- Cleaning the Ideal Criteria and Resumes: Both the ideal_criteria and the resume text are pre-processed to remove noise, such as stop words and punctuation.
- Tokenizing Ideal Criteria: The cleaned ideal criteria are then tokenized into individual words.
- Calculating Word Count and Matched Ideal Words: For each resume, the function calculates the word count of matched words between the resume and the ideal criteria. Additionally, it identifies the specific words that match.
- Scoring Resumes Based on Matched Word Count: Resumes are scored based on the count of matched words, with higher counts resulting in higher scores.
- Sorting Resumes by Score: Resumes are sorted in descending order of their scores, with the most relevant resumes ranked at the top.
- Returning Ranked Resumes as a Data Frame: The function returns the ranked resumes as a data frame, in form that is based on for.clustering argument.
Function Output:
The output of the rank_resume() function is a data frame
that includes the following columns:
- Resume: The names or identifiers of the resumes.
- Matched_Words: A string containing the words that matched between the resume and the ideal criteria, separated by spaces.
- Matched_Ideal: A ratio indicating the proportion of matched words relative to the total words in the ideal criteria.
rank_resume <- function(ideal_criteria, resume_df, for.clustering = F) {
# Clean the ideal criteria and resume text
clean_ideal_criteria <- clean_text(ideal_criteria, FALSE)
resume_df$text <- clean_text(resume_df$text, FALSE)
# Tokenize the cleaned ideal criteria into unique words
unlist_ideal_criteria <- unlist(str_split(clean_ideal_criteria, " ")) %>% unique()
# Check if the resume data frame is empty
if (nrow(resume_df) == 0) {
stop("There's no PDF/resume.")
}
# Calculate word count, matched ideal words, and rank resumes
ranking_df <- resume_df %>%
mutate(
Word_Count = map_int(tolower(text), ~ length(intersect(unlist_ideal_criteria, unlist(str_split(., "\\W+"))))),
Matching_Words = map_chr(tolower(text), ~ paste(intersect(unlist_ideal_criteria, unlist(str_split(., "\\W+"))), collapse = " ")),
Matching_Percentage = round(Word_Count / length(unlist_ideal_criteria), 2)
) %>%
arrange(desc(Word_Count)) %>%
mutate(Rank = row_number()) %>%
select(-Word_Count) %>%
column_to_rownames(var = "Rank") # Set "Rank" as row names
if (for.clustering == T){
rownames(ranking_df) <- ranking_df$file_name
return(ranking_df %>% select(Matching_Words))
}
return(ranking_df)
}Words as Columns Converter Function
The words_as_columns() function is made to transform the
matching criteria into column per word.
Function Input:
- ranking_df: The ranked resumes with the matching criteria.
Function Workflow:
- The function creates the document term matrix of the matching criteria.
- The created document term matrix is then turned into a data frame.
- The row names of the data frame is replaced with the resume file names.
Function Output:
The output of the words_as_columns() function is a data
with matching criteria as columns and resume file names as row
names.
words_as_columns <- function(ranking_df){
# Create the document term matrix of the matching words
dtm <- DocumentTermMatrix(ranking_df$Matching_Words)
# Convert document term matrix into a data frame
df <- dtm %>%
as.matrix() %>%
as.data.frame()
# Replace the row names with the resume file names
rownames(df) <- rownames(ranking_df)
return(df)
}Resume Clustering Function
The cluster_resume() function is made to cluster the
ranked resumes based on the matching criteria
Function Input:
- ranking_df: The ranked resumes with the matching criteria.
- k: The number of clusters/segments.
Function Workflow:
- The function applies
words_as_columns()function on the ranking_df. - The data frame is then applied K-means clustering with k centers.
Function Output:
The output of the cluster_resume() function is a k-means
cluster model of the resumes.
Cluster Words Extractor Function
The get_cluster_words() function is made to extract the
word
Function Input:
- cluster: The k-means cluster model from
cluster_resume()function. - ranking_df: The ranked resumes with the matching criteria.
Function Workflow:
- The function creates an empty array to for the words.
- The function loops through the cluster segments to extract the words and then stores it in the array.
Function Output:
The output of the get_clusters_words() function is a
list of words from each cluster.
get_clusters_words <- function(clusters, ranking_df){
# Create an empty array for cluster words
words_list <- c()
# Store each cluster's words inside the array
for (center in 1:nrow(clusters$centers)){
cluster_assignments <- clusters$cluster
cluster_index <- which(cluster_assignments == center)
cluster_data <- ranking_df[cluster_index, ]
cluster_words <- paste(cluster_data, collapse = " ")
words_list[center] <- cluster_words
}
return (words_list)
}Word Cloud Function
The get_wordcloud() function is a powerful tool designed
to create a word cloud that highlights words matched between a resume
and the provided ideal criteria. This function takes two inputs: the
matching words and is particularly useful for visualizing the alignment
between a resume and desired criteria.
Function Input:
- matching_words: This is a string containing words that match between a resume and the ideal criteria.
Function Workflow:
- Word List Creation: The input string is split into individual words, creating a list of words.
- Counting Occurrences: The function counts the occurrences of each word in the list and creates a data frame with the words and their respective counts.
- Word Cloud Visualization: Using the word counts, the function generates a word cloud with specified settings, allowing for customization of text color, word scaling, order preservation, and the maximum number of words to display.
Function Output:
The output is a word cloud plot of the input text/words
get_wordcloud <- function(matching_words, colors = T){
# Split the input string into individual words
words_list <- unlist(str_split(matching_words, " "))
# Create a data frame of matching words and count their occurrences.
words <- data.frame(word = words_list) %>%
count(word, sort = TRUE)
color <- "black"
if (colors == T){
color <- brewer.pal(8, "Blues")
}
# Generate a word cloud with specified settings, scaling word size by frequency (n)
words %>%
with(
wordcloud(
words = word, # Words to be included in the word cloud.
colors = color, # Custom color palette
random.order = FALSE, # Preserve the order of words.
min.freq = 0,
scale = c(3, 1),
max.words = 100, # Maximum number of words to display.
freq = n # Scale word size based on frequency (n values)
)
)
}Technical Test
clean_text() Testing
raw_text <- "This is a sample text for testing the text cleaner function. It contains various elements such as numbers like 12345, punctuation marks (.,;:!?), and common English stopwords like 'the,' 'and,' 'is,' and 'in.' Additionally, it includes some mixed-case words like 'WordS,' 'CLEaner,' and 'FunctioN.' The text also has some special characters and symbols: @username, #hashtag, $price, %percentage, and &ersand. We should test if the text cleaner can handle these different elements effectively and produce clean and normalized text output."
clean_text(raw_text, F)## 1
## " sample text testing text cleaner function contains various elements numbers like 12345 punctuation marks common english stopwords like additionally includes mixedcase words like words cleaner function text also special characters symbols username hashtag price percentage ampersand test text cleaner can handle different elements effectively produce clean normalized text output"folder_to_table() Testing
To test this function, I will use a collection of designer profession resumes that I obtained from Kaggle by this link: https://www.kaggle.com/datasets/snehaanbhawal/resume-dataset
Resume vs Extracted Text Comparison
Extracted Text
## [1] "PRODUCT DESIGNER\nProfessional Summary\n4-5 years engineering experience and 1-2 years working experience. Able to work independently and under pressure, detail oriented, excellent\nproblem solver, Innovator. Efficient Mechanical Engineer leveraging a strong technical background in bringing products from the laboratory to\nmass-manufacturing. Mechanical Engineer with [Number] + years of training in varied industries, including manufacturing and high-tech\nenvironments. Creative manufacturing engineer. Lead team member on process redesign for [Describe product] . Design engineer who has worked\non [Number] new products, including the [Product name] recognized for industry excellence.\nSkills\n CAD\n Complex problem solving\n Stress analysis training\n Component functions and\n testing requirements Engine components, pumps, and fuel systems knowledgeFEA toolsAutoCAD proficientTeam\n Technical direction and leadershipManufacturing systems integrationManufacturing systems integration\n product strategies\n Works well in diverse team\n environment\n Strong decision maker\n\nWork History\nProduct designer 10/2014 to Current\nCompany Name – City , State\n The team wants to develop a portable, easily shipped, cost effective hardware that can send and receive digital content directly from\n satellites.\n Personally involve with prototype designing and 3D modeling.\n Cooperating with a startup called Outernet (https://www.outernet.is/en/), a for-profit media company that already has two satellites covering\n North America, Europe, and the Middle East and has recently started broadcasting free Internet content.\n Assisting drafters in developing the structural design of products using drafting tools or computer-assisted design (CAD) or drafting\n equipment and software.\n Completing project mechanical design while providing technical solutions feedback.\nproduct design 09/2014 to Current\nCompany Name – City , State\n Two engineers and designers to collaborate together to create new innovative wearable pieces for a fashion show competition.\n Will access new Makerspce, which includes a 3D printer, will be given a $500 budget to create their wearable piece.\nRESEARCH EcoPRT Research Assistant 01/2014 to 05/2014\nCompany Name – City , State\n The goal is to develop an economical, automated transit system.\n It will focus on the hands on design and development of a small manned autonomous vehicle.\n www.ecoprt.com).\n The key in the design is to understand the impact weight has on the overall cost and performance, and the incorporation of automated\n control.\n Aspects of the development will possibly include\nproduct design 01/2014 to 05/2014\nCompany Name – City , State\n VOLUNTEER The purpose of this project is to design and fabricate a cable management system for a public-access electric\n EXPERIENCE vehicle charging station.\n This system will dispense and retract 20 feet of cable for operation and provide secured storage for the cable when not in use.\n The prototype will be subjected to the following constraints\nTeam member 10/2013 to 04/2014\nCompany Name – City , State\n Attending scheduled control and mechanical teams' training classes.\n EXPERIENCE · Learned shop safety, vehicle glider equations, drive cycle modeling, and Simulation.\n Learned the powertrain architecture and components of the 2013 Chevrolet Malibu.\n Learned vehicle dynamics.\n And practiced model simulation by using MATLAB Simulink.\n Mechanical Engineering Components design project (material design.\nmaterial design 10/2013 to 04/2014\n\nCompany Name – City , State\n Designed fillet welds connections and bolts for the plate girder, which holds the pipe with horizontal and vertical force loads.\n Calculated the related shear or bending stresses for the welds and bolts to determine the right materials and sizes of welds (thickness) and\n bolts.\nEddy Current DYNO Research Assistant 09/2013 to 05/2014\nCompany Name – City , State\n Built the engine stander for our engine and Eddy current dynamometer.\n Currently installing the Eddy current dynamometer with graduate students.\n Future possibility of experimenting with torque, horsepower, RPM, EGR (Exhaust Gas Recirculation) and temperature measurements of the\n Kubota Diesel Engine after installation.\n Possibility of learning the engine tuning.\nResearch Assistant 06/2013 to 08/2013\nCompany Name – City , State\n Graphed sketches and figures for professor's Thermodynamics eBook.\n Learned how to use Smartdraw.\n Performed literature reviews on ongoing research topics and eBook materials.\n Added video links and real-world images to the eBook.\nProgram Assistant 05/2013 to 06/2013\nCompany Name – City , State\n Assisting Dr.\n Eischen, the director of the Hangzhou Engineering Study Abroad Program at Zhejiang University, during his program this coming summer.\n Helping with tasks such as translating, program activities, running errands, classes, transportation, and culture immersion.\n2323 04/2013 to 10/2013\nCompany Name – City , State\n Designed Airplane Landing Gear by modeling with a mass-spring-damper SDOF system and designing the spring k and damper C that\n limits the given amplitude.\n Part 2\nwew 10/2012 to 04/2013\nCompany Name – City , State\n Utilized MATLAB for statistical analysis of an elastic band rocket.\n Learned how to make experimental designs, statistical processes, statistics simulations, and graphical displays of data on computer\n workstations.\n Used statistical methods including point and interval estimation of population parameters and curve and surface fitting (regression analysis).\n Graphic Communications Project (3D design.\nrer 10/2012 to 04/2013\nCompany Name – City , State\n Utilized SolidWorks to design a tape floss container.\n Developed the ability to use SolidWorks within the context of a concurrent design process to understand how everyday objects are\n designed and created.\n Emphasis placed on decision-making processes involving creating geometry and the development of modeling strategies that incorporate the\n intentions of the designer.\nre 02/2009 to 04/2009\nCompany Name – City , State\n Visited construction sites with senior engineers.\n Kept record of site investigations.\n Dealt with paperwork with senior engineers and answered phone calls.\n Helped install residential wiring in new construction sites.\n Investigated electrical problems and developed the ability to read electrical diagrams and wire electrical panels.\nEducation\nMaster of science : Mechanical engineering Robotic & Manufacture Current Columbia University in the City of New York - City , State\n Sep -2015 Dec Mechanical engineering Robotic & Manufacture\n\n Coursework in Advanced Mechanical Engineering\n Coursework in Drafting, Computer-Aided Design (CAD) and Computer-Aided Manufacturing (CAM)\nBachelor of science : Mechanical Engineering 1 2010 North Carolina State University, Raleigh (NCSU) - City , State\nGPA: Magna Cum Laude GPA: 3.5 GPA: 3.63/4.0 Mechanical Engineering Magna Cum Laude GPA: 3.5 GPA: 3.63/4.0\nNorth Carolina State University -\nGPA: Magna Cum Laude Magna Cum Laude\nAccomplishments\n Listed in the dean's list for three semesters during Junior and Senior Year · Chosen to be on the cover of NC State freshman admissions\n booklet · In the process of receiving the Professional Development Certificate · NCSU Chinese basketball team player.\n Math and physics club member · Control and Mechanical Team member of NCSU EcoCAR2 · Took the global training class at NC\n State University · CUSA member (Chinese undergraduate student association).\nSkills\n3D, 3D modeling, AutoCAD, broadcasting, budget, C, cable, Chinese, com, hardware, content, controller, data analysis, Dec, decision-making,\ndesigning, product design, English, fashion, focus, Fortran, frame, Graphic, Lathe, Linux, director, Maple, materials, MATLAB, mechanical,\nMechanical Engineering, access, Mill, modeling, navigation, printer, processes, profit, speaking, Python, Quantitative analysis, reading, read,\nresearch, safety, Simulation, sketching, SolidWorks, statistical analysis, Statistics, phone, translating, transportation, video, Welding, wiring, written\n"Works Perfectly!
rank_resume() Testing
“I will intentionally use the skills listed on resume 10751444.pdf. If resume 10751444.pdf is ranked 1st, it means the function is working well!”
ideal_designer <- "3D modeling, AutoCAD, broadcasting, budget, C, cable, Chinese, com, hardware, content, controller, data analysis, Dec, decision-making,\ndesigning, product design, English, fashion, focus, Fortran, frame, Graphic, Lathe, Linux, director, Maple, materials, MATLAB, mechanical,\nMechanical Engineering, access, Mill, modeling, navigation, printer, processes, profit, speaking, Python, Quantitative analysis, reading, read,\nresearch, safety, Simulation, sketching, SolidWorks, statistical analysis, Statistics, phone, translating, transportation, video, Welding, wiring, written\n"
rank_resume(ideal_designer, designers)Nice.
rank_resume()function works well!
rank_resume() Testing (2)
This time, I will intentionally use the criteria possessed by resume 10748989.pdf. If resume 10748989.pdf ranks 1st, it means the function is working well!
But first, let’s take a look at resume 10748989.pdf!
Now let’s rank the resumes. The resume 10748989.pdf should ranks 1st and have 1.00 matching percentage!
ideal_designer <- "Building codes knowledge Complex problem solving Strong analytical ability Excellent attention to detail Commercial interior design Working drawings and procedures Space planning methodology Sketching Rendering Digital drafting 3D rendering software Proficient in SketchUp"
rank_resume(ideal_designer, designers)Perfect.
rank_resume()function works well!
words_as_columns() Testing
Perfect.
words_as_columns()function works well!
cluster_resume() Testing
I will test this function with 3 segments
## K-means clustering with 3 clusters of sizes 34, 59, 14
##
## Cluster means:
## ability analytical attention building codes commercial complex
## 1 0.70588235 0.14705882 0.23529412 0.3529412 0.08823529 0.23529412 0.3235294
## 2 0.08474576 0.03389831 0.08474576 0.1864407 0.00000000 0.06779661 0.1355932
## 3 0.35714286 0.00000000 0.14285714 0.5714286 0.28571429 0.35714286 0.1428571
## design detail digital drafting drawings excellent interior
## 1 0.9117647 0.3235294 0.2941176 0.26470588 0.3529412 0.5588235 0.08823529
## 2 0.8644068 0.1186441 0.2542373 0.08474576 0.2203390 0.1186441 0.13559322
## 3 1.0000000 0.1428571 0.0000000 0.50000000 0.2857143 0.2857143 1.00000000
## knowledge methodology planning problem procedures proficient rendering
## 1 0.7058824 0.05882353 0.5294118 0.44117647 0.2647059 0.3529412 0.14705882
## 2 0.2711864 0.08474576 0.1016949 0.08474576 0.2372881 0.1186441 0.03389831
## 3 0.2857143 0.00000000 0.9285714 0.14285714 0.1428571 0.5000000 0.28571429
## sketching sketchup software solving space strong working
## 1 0.23529412 0.02941176 0.5588235 0.26470588 0.11764706 0.7647059 0.6764706
## 2 0.08474576 0.03389831 0.3728814 0.06779661 0.05084746 0.1355932 0.3728814
## 3 0.00000000 0.07142857 0.2857143 0.07142857 0.92857143 0.3571429 0.4285714
##
## Clustering vector:
## 10748989.pdf 11155153.pdf 26496059.pdf 10751444.pdf 12547982.pdf 26676567.pdf
## 1 1 1 1 3 1
## 22496394.pdf 25023614.pdf 28326441.pdf 30968749.pdf 37058472.pdf 37263609.pdf
## 1 3 3 1 3 1
## 67645662.pdf 18795567.pdf 38565119.pdf 41506705.pdf 13014900.pdf 15425154.pdf
## 1 1 3 1 1 1
## 16288901.pdf 18198627.pdf 19195747.pdf 20748926.pdf 24655918.pdf 28663949.pdf
## 3 1 3 1 3 3
## 94417768.pdf 11807040.pdf 11919526.pdf 20390397.pdf 24285142.pdf 26622051.pdf
## 1 1 1 1 1 2
## 30965258.pdf 37664296.pdf 68240723.pdf 22675694.pdf 25422388.pdf 26924514.pdf
## 1 1 1 1 1 1
## 34317538.pdf 35990852.pdf 39776400.pdf 42384185.pdf 44145704.pdf 44185767.pdf
## 2 2 2 1 1 2
## 67582956.pdf 13774329.pdf 13998435.pdf 15471999.pdf 17555081.pdf 20986595.pdf
## 2 2 3 1 1 1
## 24455357.pdf 24583187.pdf 26503829.pdf 26790545.pdf 26942552.pdf 29524570.pdf
## 1 3 1 2 3 2
## 37695494.pdf 38744475.pdf 39252859.pdf 51018476.pdf 76010167.pdf 85101052.pdf
## 2 3 2 2 1 2
## 13518263.pdf 17199951.pdf 18979238.pdf 21283733.pdf 21916744.pdf 23951429.pdf
## 3 2 2 2 2 2
## 34511655.pdf 34657584.pdf 51681660.pdf 12415691.pdf 14528265.pdf 20932019.pdf
## 2 2 2 2 2 2
## 22506245.pdf 25061645.pdf 26046064.pdf 27529455.pdf 90066849.pdf 93301686.pdf
## 2 2 2 2 2 2
## 11722421.pdf 11958994.pdf 13557622.pdf 14724186.pdf 14743911.pdf 19164410.pdf
## 2 2 2 2 2 2
## 22567495.pdf 27497542.pdf 29865476.pdf 34349255.pdf 54201930.pdf 12674307.pdf
## 2 2 2 2 2 2
## 14014749.pdf 18835363.pdf 32532982.pdf 34051710.pdf 36269672.pdf 62312955.pdf
## 2 2 2 2 2 2
## 81011612.pdf 10466583.pdf 18460045.pdf 25949631.pdf 29147100.pdf 32954522.pdf
## 2 2 2 2 2 2
## 78149576.pdf 15936656.pdf 21705160.pdf 39434376.pdf 91153752.pdf
## 2 2 2 2 2
##
## Within cluster sum of squares by cluster:
## [1] 167.85294 175.32203 52.92857
## (between_SS / total_SS = 15.8 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"Perfect.
cluster_resume()works perfectly
get_clusters_words()
Testing
Raw words
## [1] "building codes knowledge complex problem solving strong analytical ability excellent attention detail commercial interior design working drawings procedures space planning methodology sketching rendering digital drafting 3d software proficient sketchup knowledge complex strong ability detail commercial design working drawings procedures planning digital drafting 3d proficient building codes knowledge strong ability excellent attention detail commercial design working rendering digital 3d proficient complex problem solving strong ability excellent detail design working sketching digital drafting 3d software building knowledge problem solving strong excellent attention design working planning sketching rendering drafting software building knowledge complex problem solving strong excellent design drawings planning drafting 3d software knowledge complex strong analytical ability excellent commercial design drawings planning drafting 3d software building complex problem ability attention detail interior design working drawings procedures 3d codes knowledge problem analytical ability excellent design drawings procedures space drafting software problem solving ability detail design working planning rendering digital 3d software knowledge strong analytical ability commercial design working drawings drafting 3d software knowledge complex strong ability excellent design working drawings space proficient building knowledge ability attention detail design planning digital software proficient knowledge solving ability design working procedures space digital 3d proficient building knowledge problem strong commercial working procedures planning software proficient complex problem solving strong design drawings sketching drafting 3d proficient strong ability excellent design working procedures planning digital software knowledge problem strong ability excellent design procedures planning software knowledge complex problem strong excellent design drawings software proficient knowledge problem excellent design planning digital 3d software proficient knowledge strong ability excellent interior design working planning digital building complex ability commercial design working planning sketching software building strong ability attention detail design working drawings sketching knowledge strong ability excellent design planning software proficient knowledge complex strong attention detail design working drawings building knowledge strong analytical ability design working procedures knowledge problem strong design planning methodology rendering 3d knowledge strong excellent attention detail design working software problem solving strong ability excellent detail working building strong ability design working planning software knowledge strong ability excellent commercial working planning knowledge ability excellent design sketching software proficient knowledge problem solving strong design working sketching building strong ability excellent design working planning"
## [2] "building complex detail design working drawings 3d software proficient commercial design procedures planning methodology digital 3d software attention interior design working procedures methodology digital software strong interior design working drawings drafting 3d software building complex problem design working space methodology software complex analytical excellent commercial design drawings 3d software design working drawings procedures planning digital drafting building ability design working procedures digital software complex strong design working digital software proficient complex attention detail design sketching 3d proficient knowledge attention detail design working digital 3d excellent attention detail design drawings drafting software building knowledge design working drawings methodology software building complex interior design drawings software building knowledge analytical design working digital knowledge strong design procedures methodology proficient excellent design working space sketching software problem solving detail design drawings procedures interior design working space digital software knowledge interior working planning digital 3d building working sketching drafting proficient sketchup problem solving strong procedures software knowledge commercial design 3d sketchup complex design drawings 3d software knowledge excellent design procedures digital knowledge attention design working digital knowledge strong design 3d software knowledge design working procedures software building knowledge design planning software knowledge ability design procedures 3d detail design drawings software knowledge strong working procedures building design rendering 3d interior design sketching rendering ability design working procedures excellent detail design drawings complex design procedures software knowledge design digital proficient problem solving ability procedures building interior design drawings design working planning digital interior design planning knowledge design software strong design proficient design drawings drafting building design working problem solving excellent design sketching digital strong 3d software excellent design ability design commercial working design digital knowledge design design working design design design design"
## [3] "building codes knowledge strong detail commercial interior design working procedures space planning software proficient building knowledge problem solving ability excellent attention interior design working space planning drafting strong ability excellent attention detail interior design working space planning drafting proficient sketchup building strong interior design drawings procedures space planning rendering drafting 3d proficient building codes problem commercial interior design working drawings space planning proficient strong ability excellent interior design drawings space planning drafting proficient building codes complex commercial interior design space planning rendering drafting building complex ability excellent interior design planning rendering 3d software knowledge interior design working drawings space planning rendering drafting 3d interior design space planning drafting 3d proficient building codes commercial interior design space software knowledge ability interior design space planning software building commercial interior design working space planning strong interior design space planning proficient"Perfect.
get_clusters_strings()function works well!
get_wordcloud() Testing
ideal_designer <- "Photoshop, Illustrator, Blender, SketchUp, Canva, Graphic Design, UI/UX Design, Typography"
rank <- rank_resume(ideal_designer, designers)
rank[1, "Matching_Words"]## [1] "photoshop illustrator graphic design typography"
Cool!
get_WordCloud()works perfectly
Shiny Web-App
Overview
This is just a temporary overview, the web app is not yet completed and is not functioning as it should.
Input Example
User Work Flow
- The user uploads resumes in PDF format.
- The user enters the desired criteria.
- The web app generates a ranking in the form of a chart and a table.
- The user can type a specific resume file name in the PDF viewer.
- When a resume file name is entered in the PDF viewer, the user will see the resume’s most appearing words and also the resume file itself.
Limitations & Notes
- The resumes input must be in PDF format.
- Only text will be extracted, which means images will be ignored.
- There are no restrictions on the type of text input. HOWEVER, please note that stop-words (words such as: “yang”; “adalah”; “tidak”; “saya”; “is”; “am”; “no”; “yes”; etc) will be eliminated during the text processing process.
- There is no limitation on the number of input words. HOWEVER, please note that duplicated words will be eliminated during text processing.