Exploratory Data Analysis
The most vital and inevitable part of any Data Science problem is the EDA- Exploratory Data Analysis. Before working on any data, it is very important to understand the spread of data, its dimension, the datatypes involved, missing values, the relationship between different variables, etc; and this is where EDA becomes important. It helps us to understand the nitty-gritty of the data using both visual and non-visual techniques. The creative part of the EDA is to extract Gold from the data-mine!
However, with great importance comes greater time consumption. This holds true especially in the case of EDA, which consumes about 30% of the whole time required to solve a data science problem. Most of the time, the code for EDA is redundant that checks the data types, data spreading, does univariate and bivariate analysis, calculates the correlation between variables. But What if we could do all of these with just One Line of Code? Voilà!
Dataprep! The one-stop solution for all your EDA needs. With Dataprep you can collect data from common data sources through Connector, Do your exploratory data analysis through EDA, and Clean and standardize data through Clean.However, in the scheme of this blog, we’ll only work on the EDA part. So, Let’s try this library on a real-world dataset. I used the King County Housing dataset from Kaggle…
