rsalaza4

# Build seaborn replot
g = sns.relplot(
    data=data,
    x="Replicate",
    y="Value",
    hue="Operator",
    style="Operator",
    col="Part",
    col_wrap=5,
    aspect=0.7

rsalaza4

# Add Replicate column
data["Replicate"] = list(np.arange(1, data["Part"].value_counts()[1]+1))*(int(len(data["Part"])/data["Part"].value_counts()[1]))

# Display top rows
data.head()

rsalaza4

# Import libraries and dependencies
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

# Open Excel file
data = pd.read_excel("msa_2_crossed.xlsx")

rsalaza4

First name: Roberto
Last name: Salazar
Email address: [email protected]
Universities: ['Northwestern University', 'State University of New York at Binghamton']

rsalaza4

# Print results
print(f"First name: {myResume.firstName}")
print(f"Last name: {myResume.lastName}")
print(f"Email address: {myResume.emailAddress}")
print(f"Universities: {myResume.universities}")

rsalaza4

# Instantiate myResume variable
myResume = Resume(text)

# Obtain resume information
myResume.get_first_name()
myResume.get_last_name()
myResume.get_email()
myResume.get_univerisities()

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