The dataset in this project scraped from the website of an online car trading company in 2022 and contains more than 50 features that have 13 different brand and 594 models. During the project, various commonly used functions for Data Cleaning, Missing Value Handling and Outliers have been applied and Python libraries such as Numpy, Pandas, Matplotlib, Seaborn, and Scipy has been used in order to reach data integrity so that the data can be open for further analysis and predictive modeling in the Machine Learning Path.
The project is divided into three main parts:
-
Data Cleaning: The part is mostly related with Missing value treatment, Removal of Irrelevant Data, Manual error while typing, Renaming Columns.
-
Missing Value Handling: Dealing with missing values recategorizing discrete categorical data and converting to numeric format (encoding).
-
Handling Outliers of Data: in this part to gaining insights from the data and identify and handle outliers, Removing unrelated features and converting the dataset to numeric format have been performed.
At the end of the project, The tailored dataset is ready for future analysis and predictive modeling in the Machine Learning Path.