rsalaza4

class Resume:
    def __init__(self, text):
        
        self.text = text
        self.firstName = ""
        self.lastName = ""
        self.emailAddress = ""
        self.universities = []
        
    def get_first_name(self):

rsalaza4

# Define multiple universities names patterns
sub_patterns = [
    
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]* [A-Z][a-z]* at [A-Z][a-z]* [A-Z][a-z]*',
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]* [A-Z][a-z]* at [A-Z][a-z]*',
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]* at [A-Z][a-z]* [A-Z][a-z]*',
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]* at [A-Z][a-z]*',
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]* [A-Z][a-z]*',
                '[A-Z][a-z]* [A-Z][a-z]* [A-Z][a-z]* University of [A-Z][a-z]*',
    

rsalaza4

def get_email(self):
  
  # Find all strings that follow emails conventions
  match = re.search(r'[\w.+-]+@[\w-]+\.[\w.-]+', self.text)
  
  # Assign word to email address
  self.emailAddress = match.group(0)

rsalaza4

def get_last_name(self):
  
  # Split resume text and store up to the first 10 words one position after the index of the string where the first name was found
  firstWords = self.text.split()[self.text.split().index(self.firstName)+1:10]
  
  # Loop through the first 10 words
  for word in firstWords:
    
    # Validate that the word is not a digit and
    # Validate that the character is an uppercase letter and

rsalaza4

def get_first_name(self):
  
  # Split resume text and store first 10 words
  firstWords = self.text.split()[:10]
  
  # Loop through the first 10 words
  for word in firstWords:
    
    # Validate that the word is not a digit and
    # Validate that the character is an uppercase letter and

rsalaza4

class Resume:
    def __init__(self, text):
        
        self.text = text
        self.firstName = ""
        self.lastName = ""
        self.emailAddress = ""
        self.universities = []

rsalaza4

'    Roberto Salazar  99 Birch Canoe Ct, The Woodlands, TX 77375   (607) 422-0469 | [email protected] | linkedin.com/in/roberto-salazar-reyna    PROFESSIONAL EXPERIENCE     SimWell                                                                                                                                                                                                                                  Houston, TX    Simulation Consultant                                                                                                        October 2020 – Present  •  Built and developed simulation models in AnyLogic based on client needs  •  Supported simulation modeling team projects across a variety of industries  •  Analyzed simulation results through visualization dashboards in Power BI and Tableau  •  Produced functional design specifications according to customer needs based on The SimWell Simulation Methodology    Northwestern University                                                             

rsalaza4

# Import libraries and dependencies
import re
import fitz
import PyPDF2

# Open resume PDF file
with fitz.open('Roberto_Salazar_Resume.pdf') as doc:

    # Declare text string variable
    text = ""

rsalaza4

# Remove warning messages
import warnings
warnings.filterwarnings("ignore")

# Import libraries and dependencies
import os
import pandas as pd

# Define 'merge_files' function
def merge_files(folder_path, excel_output=True, csv_output=True):

rsalaza4

# Set matplotlib style
plt.style.use('ggplot')

# Plot linechart
plt.figure(figsize=(20,7))
plt.plot(employees_df, "--o", c= "grey")
plt.xlabel("Date")
plt.ylabel("Count of Active Employees")
plt.title("Employees Growth Over Time")
plt.xticks(employees_df.index, rotation=90)