HR File Analysis Project

Overview

This project performs exploratory data analysis (EDA) on HR employment data to understand factors influencing job-switching behavior, education levels, experience, and training patterns among job seekers.

Key Research Questions

The analysis addresses the following key questions:

1. Experience & Job Switching - What experience groups are most likely to look for a new job?
2. Education Levels - Which education level is most common among job seekers?
3. Training & Experience - Do candidates with relevant experience have more training hours?
4. Average Experience - What is the average experience (in years) for each education level?
5. Company Type - Which company type has the highest percentage of people waiting to switch jobs?

Project Structure

HR FILE ANALYSIS/
├── hrfile.ipynb        # Main Jupyter notebook with analysis
├── aug_train.csv       # Input data file (HR employment data)
└── README.md           # This file

Technologies Used

• Python 3.x
• pandas - Data manipulation and analysis
• numpy - Numerical computations
• matplotlib - Data visualization
• seaborn - Statistical data visualization

Data Processing

The notebook includes the following data cleaning and preparation steps:

Data Cleaning

• Replaced noisy values in the 'experience' column ('>20' → 21, '<1' → 0)
• Replaced noisy values in the 'last_new_job' column ('>4' → 5, 'never' → 0)
• Converted string columns to numeric data types
• Handled missing values:
  • Experience: Filled with median value
  • Education Level: Filled with mode (most frequent value)
  • Company Type: Filled with 'Unknown'

Data Exploration

• Dataset information and summary statistics
• Unique value analysis
• Null value detection and handling
• Distribution analysis across key demographic groups

Analysis & Visualizations

The notebook includes multiple visualizations:

• Correlation Heatmap - Shows relationships between numeric features
• Job Change by Company Type - Count plot showing switching intentions by company type
• Job Change by Education - Distribution of job-switching behavior across education levels
• Experience Analysis - Trends in training hours and experience

Key Metrics Analyzed

• Training hours by experience level
• Job-switching intention rates
• Education level distribution among job seekers
• Enrollment patterns by company type
• Correlation between numeric variables

How to Use

1. Ensure you have Python and required libraries installed
2. Place the aug_train.csv file in the project directory
3. Open hrfile.ipynb in Jupyter Notebook or JupyterLab
4. Run cells sequentially to execute the analysis
5. Review visualizations and insights generated

Requirements

Install required packages:

pip install pandas numpy matplotlib seaborn

Data Source

The analysis uses aug_train.csv containing HR employment data with features including:

• enrollee_id
• education_level
• experience
• company_type
• training_hours
• target (job switching indicator)
• last_new_job
• gender
• And other employment-related attributes