Exploratory Data Analysis with Python
Here, we are going to show you how we can use Python for a task, in my opinion the most important in projects involving data analysis, Exploratory Data Analysis !
Exploratory Data Analysis
Is an approach to analyzing data to summarize the main characteristics of the data, gain a better understanding of the dataset, discover relationships between different variables and extract variables. important. EDA, is an important step in any Data Analysis or Data Science project.
Main objective of the EDA
The main purpose of EDA is to detect any errors or discrepancies, as well as understand different patterns in the data. It allows analysts to better understand the data before making any assumptions and also discover relationships between variables. EDA results help companies get to know their customers, grow their business and make better decisions.
The example
Our example dataset is Sales from a Used Car Dealership.
If you want to download the data source ( Download )
Description of Columns
data.set
- Training or test datatotal.cost
- Total cost of the vehiclelot.sale.days
- Sales time in daysoverage
- Sale after 90 daysmileage
- mileagevehicle.type
- Vehicle type (economy, family.medium, family.large...)domestic.import
- Manufacture, domestic or importedvehicle.age
- Vehicle agevehicle.age.group
- Vehicle age groupcolor.set
- Colormakex
- Brandstate
- Car Status (region)make.model
- Model
The code
To make it easier and more practical, I will make the code available on Google Colab , feel free to download and carry out your tests and studies.
In the code above, there is a very detailed walkthrough of some of the main day-to-day commands and the best, with examples.