Kidney_dataset_analysis

The process i underwent when working on this model:

preparing data for analysis and modelling

• loading the data,
• dropping unncessary columns,
• extracting categorical and numerical data from the entire kidney dataset.
• imputing errors in the data

analysing data using seaborn and plotly (EDA)

• filling missing data with random samples

feature encoding - label encoding technique

• selecting best feature using SelectKBest method and chi2 techniques
• selecting important features

predicted using XGBClassifier algorithmn achieved an accuracy of 0.97 (97%)

contributors

• Antony Gitau