In this analysis, I will demonstrate how to explore the cars dataset using Python. I will first load the dataset and then process the data. I will also visualize the dataset and then finally apply ttest to explore the relationship between variables. When the final dataset is prepared, the same dataset can be used to develop various models.
Briefly:
- I converted some variables from chr format into numbers. To do so, I first removed dollar and punction from the data and then changed the data type.
- I replaced missing variable with the set median.
- I identified outliers and then remove some of them. I also prepared some codes for data normalization procedure.
- I created three graphs about the dataset.
- I created three hypothesis testing models and used ttest to compare groups' means.
- I also created boxplots to show the ttest results in context.
To see the file, please click this link.