test.datacleaner

// Load the sample data
load "sample_data.csv"

// Remove rows with missing values in 'salary' column
remove_rows_missing salary

// Drop specific rows (e.g., 2nd and 5th rows)
drop_row 5

// Remove duplicate rows
remove_duplicates

// Fill missing values in 'salary' column with mean
fill_missing salary with mean

// Normalize 'salary' column to range 0 to 1
normalize salary to_range(0, 1)

// Standardize the 'tax' column
standardize tax

// Logarithm transform the 'experience' column
log_transform experience

// Auto categorize the 'salary' column into 3 clusters
auto_categorize salary n_clusters=3

// Split data into 70% training, 30% testing sets
split_data train=70 , test=30

// Integrate inconsistent data in 'department' column
integrate IT to Finance in department

// Delete outliers in 'salary' column using IQR method
delete_outliers salary with IQR

// Drop specific columns (e.g., 'id' and 'department')
drop_column id

// Encode all columns with one-hot encoding
encode all with one_hot