README TEAM 1: DATA ANALYST PROJECT

Work on a dataset of ABC Corporation employees.

Data Analysis Proyect

Carrying out a complex data analysis process consisting of several phases, which will be explained below.

INDEX

• Introduction
• Files
• Requirements
• The process
  • Built with
  • First phase
  • Importations
  • General
  • Second phase
  • Third phase
  • Fourth phase
  • Fifth phase
• Author

INTRODUCTION

Our mission is to identify key factors that influence job satisfaction and ultimately employee retention. To this end, we have carried out a complex data analysis process including: EDA process, data transformation, A/B Testing, visualisations, creation of a MySQL database and ETL process.

FILES

Files required for project review:

• HR RAW EMPLOYEES.csv: contains information about ABC Corporation employees.
• HR RAW DATA CLEAN.csv: CSV file created by us after a thorough cleaning of the data from the initial CSV.
• BBDD_abc_corp_employees.sql: DB created by us from the CSV we generated after data cleansing.

REQUIREMENTS

Make sure you have the following libraries installed in your Python environment:

1. pandas
2. numpy
3. matplotlib
4. seaborn
5. scikit-learn
6. mysql connector
7. scipy stats, chi2_contingency

If you do not have these libraries, you can install them using pip install

THE PROCESS

Built with

Technologies used in the project:

• Operating system: Windows 10 Home
• Development Environment: Jupyter Notebook, Visual Studio Code
• Programming Language: Python
• Libraries specified above
• Version Control: Git, GitHub
• Dependency Management: Pip
• MySQL Workbench

First phase: deep data exploration

Importing libraries and loading data:

Importing and use of pandas to load CSV files into DataFrames.

General exploration

• General deep review and analysis of data using Pandas functions to obtain information about the structure of the data and basic statistics.
• Initial exploration of the data to identify potential problems (null values, duplicate values, outliers, missing data, etc.).
• DataFrame joining

Second phase: data transformation

• Verification of data consistency and correctness.
• Removing unnecesary columns
• Homogenization of titles and values.
• Treatment of negative numbers, outliers, null data and duplicated values.

Third phase: visualization

Study of six real-world questions about the data and their representation through graphs.

Fourth phase: DataBase

Creation of a DB (with clean DF) in MySQL Workbench, editing tables and their corresponding relations/restrictions. Lastly, creation of the DB diagram.

Fifth phase: ETL

Data extraction, transformation and loading (ETL): -automation of the data insertion into the DB and the information transformation process to ensure that information is updated and inserted in a consistent manner.

Author

Made with 💜 by [Belén V N (https://github.com/BelenVN), Gloria L C (https://github.com/GloriaLopezChinarro), Viviana V R (https://github.com/Viviana1988) y Cristina R H (https://github.com/cristinarull14)]

ENJOY IT 🤩