Resume Screening with Python

Companies often receive thousands of resumes for each job posting and employ dedicated screening officers to screen qualified candidates. In this article, I will introduce you to a machine learning project on Resume Screening with Python programming language.

What is Resume Screening?

Hiring the right talent is a challenge for all businesses. This challenge is magnified by the high volume of applicants if the business is labour-intensive, growing, and facing high attrition rates.

Also, Read – 100+ Machine Learning Projects Solved and Explained.

An example of such a business is that IT departments are short of growing markets. In a typical service organization, professionals with a variety of technical skills and business domain expertise are hired and assigned to projects to resolve customer issues. This task of selecting the best talent among many others is known as Resume Screening.

Typically, large companies do not have enough time to open each CV, so they use machine learning algorithms for the Resume Screening task.

Machine Learning Project on Resume Screening with Python

In this section, I will take you through a Machine Learning project on Resume Screening with Python programming language. I will start this task by importing the necessary Python libraries and the dataset:

Now let’s have a quick look at the categories of resumes present in the dataset:

print ("Displaying the distinct categories of resume -")
print (resumeDataSet['Category'].unique())

Displaying the distinct categories of resume -
['Data Science' 'HR' 'Advocate' 'Arts' 'Web Designing'
 'Mechanical Engineer' 'Sales' 'Health and fitness' 'Civil Engineer'
 'Java Developer' 'Business Analyst' 'SAP Developer' 'Automation Testing'
 'Electrical Engineering' 'Operations Manager' 'Python Developer'
 'DevOps Engineer' 'Network Security Engineer' 'PMO' 'Database' 'Hadoop'
 'ETL Developer' 'DotNet Developer' 'Blockchain' 'Testing']

Now let’s have a look at the distinct categories of resume and the number of records belonging to each category:

print ("Displaying the distinct categories of resume and the number of records belonging to each category -")
print (resumeDataSet['Category'].value_counts())

Displaying the distinct categories of resume and the number of records belonging to each category -
Java Developer               84
Testing                      70
DevOps Engineer              55
Python Developer             48
Web Designing                45
HR                           44
Hadoop                       42
Mechanical Engineer          40
Sales                        40
ETL Developer                40
Blockchain                   40
Operations Manager           40
Data Science                 40
Arts                         36
Database                     33
Electrical Engineering       30
Health and fitness           30
PMO                          30
DotNet Developer             28
Business Analyst             28
Automation Testing           26
Network Security Engineer    25
SAP Developer                24
Civil Engineer               24
Advocate                     20
Name: Category, dtype: int64

Now let’s visualize the number of categories in the dataset:

import seaborn as sns
plt.figure(figsize=(15,15))
plt.xticks(rotation=90)
sns.countplot(y="Category", data=resumeDataSet)

Now let’s visualize the distribution of categories:

Now I will create a helper function to remove the URLs, hashtags, mentions, special letters, and punctuations:

Now as we have cleared the dataset, the next task is to have a look at the Wordcloud. A Wordcloud represents the most numbers of words larger and vice versa:

[('Details', 484), ('Exprience', 446), ('months', 376), ('company', 330), ('description', 310), ('1', 290), ('year', 232), ('January', 216), ('Less', 204), ('Data', 200), ('data', 192), ('Skill', 166), ('Maharashtra', 166), ('6', 164), ('Python', 156), ('Science', 154), ('I', 146), ('Education', 142), ('College', 140), ('The', 126), ('project', 126), ('like', 126), ('Project', 124), ('Learning', 116), ('India', 114), ('Machine', 112), ('University', 112), ('Web', 106), ('using', 104), ('monthsCompany', 102), ('B', 98), ('C', 98), ('SQL', 96), ('time', 92), ('learning', 90), ('Mumbai', 90), ('Pune', 90), ('Arts', 90), ('A', 84), ('application', 84), ('Engineering', 78), ('24', 76), ('various', 76), ('Software', 76), ('Responsibilities', 76), ('Nagpur', 76), ('development', 74), ('Management', 74), ('projects', 74), ('Technologies', 72)]

Now I will convert these words into categorical values:

Training Machine Learning Model for Resume Screening

Now the next step in the process is to train a model for the task of Resume Screening. Here I will use the one vs the rest classifier; KNeighborsClassifier. For this task, I will first split the data into training and test sets:

Now let’s train the model and print the classification report:

Accuracy of KNeighbors Classifier on training set: 0.99
Accuracy of KNeighbors Classifier on test set: 0.99

 Classification report for classifier OneVsRestClassifier(estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=None, n_neighbors=5, p=2,
           weights='uniform'),
          n_jobs=None):
              precision    recall  f1-score   support

           0       1.00      1.00      1.00         3
           1       1.00      1.00      1.00         3
           2       1.00      0.80      0.89         5
           3       1.00      1.00      1.00         9
           4       1.00      1.00      1.00         6
           5       0.83      1.00      0.91         5
           6       1.00      1.00      1.00         9
           7       1.00      1.00      1.00         7
           8       1.00      0.91      0.95        11
           9       1.00      1.00      1.00         9
          10       1.00      1.00      1.00         8
          11       0.90      1.00      0.95         9
          12       1.00      1.00      1.00         5
          13       1.00      1.00      1.00         9
          14       1.00      1.00      1.00         7
          15       1.00      1.00      1.00        19
          16       1.00      1.00      1.00         3
          17       1.00      1.00      1.00         4
          18       1.00      1.00      1.00         5
          19       1.00      1.00      1.00         6
          20       1.00      1.00      1.00        11
          21       1.00      1.00      1.00         4
          22       1.00      1.00      1.00        13
          23       1.00      1.00      1.00        15
          24       1.00      1.00      1.00         8

   micro avg       0.99      0.99      0.99       193
   macro avg       0.99      0.99      0.99       193
weighted avg       0.99      0.99      0.99       193

So this is how we can train a Machine Learning model for the task of Resume Screening. I hope you liked this article on Resume Screening with Python programming language. Feel free to ask your valuable questions in the comments section below.