Census Income Classfication

Importion of Libraries

Extracting the dataset from the ucml Repository

Overview of the data

Data Cleaning

• Checking the types of categorical vairiable
• Replace "." with "" for income
• Handling Null values
• Checking the Coorelation
• Dropping 'fnlwgt'
• Visualization of Numerical variables
• Visualization of Categorical variables

Feature Engineering

• Label Encoding
• Scaling the Data

Model Training

• Data splitting
• Train the model for Naive Bayes and Random Forest
• Test the model for Naive Bayes and Random Forest

Evaluation

• Compare the Training and Testing Accuracy
• Compare the classififcation Report
• Comapre the Confusion Matrix