EDA is nothing but exlporing the data by using some means to infer rational insights to gain better understanding of the data. Data Science usually involves myriad number of techniques for EDA , in this post we will discuss most commonly used techniques.
Pandas is a great library for Data Science. It provides high level abstraction implementation for analysing the data. Click this link for its documentation : https://pandas.pydata.org/pandas-docs/stable/
Seaborn is another important package for visualizing the data, it provides one line python functions to plot the data similiar to MatPlotLib in MATLab except Matplotlib is not useful in some cases for visualizing where seaborn compensates this lack. Seaborn has great visualising tools like Violinplots for making better inference from the data.
Violin plots give you 25th, 50th(Median), 75th quartile of the data plus it gives you Probability Density Function(Khan academy gives you awesome explanation of what it is!)
Numpy is Numerical Python library for doing high level math computations involving complex data structures like matrices
Your welcome to add any EDA techniques to this repo.