Exploratory Data Analysis on Haberman's Cancer Survival Dataset

• Domain: Healthcare
• Type of problem: Binary Classification Objective: The objective is to use EDA on the independent features to understand their distribution w.r.t target feature to define general conditions that can distinguish between a patient who survived and who didn't. Approach:

1. Analyzed High Level Stats of the Dataset.
2. Performed Univariate Analysis to observe distribution of data - (Plots - Count, Hist, Box, Violin, PDF & CDF)
3. Performed Bivariate Analysis to observe behaviour of a feature w.r.t other - (Plots - Scatter, Pair, Contour)
4. Summary and Conclusion.