Udemy – Exploratory Data Analysis in Data Science

The idea of this course is that before you start building ML models, first understand what the dataset actually contains. Exploratory Data Analysis is meant to uncover structure, patterns, relationships, anomalies, and assumptions in the data.

EDA steps are:

• Know your data => Clean it => Explore each variable => Find relationships => Detect anomalies/ Outliers => Extract meaningful insights => Useful in feature engineering and machine learning
• Learn EDA with Python libraries – Pandas, NumPy, SciPy, Matplotlib and Seaborn

Learn about statistical measures like Measures of central tendency, Measures of spread and Measures of distortion. Learn approach to plot data distributions for continuous and discrete form of data it includes Normal Distribution, Std Normal Distribution, Uniform Distribution, Poisson and Binomial distribution.