Struct DataOperations 

pub struct DataOperations;

Implementations

impl DataOperations

pub fn drop_column( df: DataFrame, column_name: &str, ) -> Result<DataFrame, Box<dyn Error>>

Drop a single column from the DataFrame

Arguments

• df - The DataFrame to operate on
• column_name - The name of the column to drop

Returns

• Result<DataFrame, Box<dyn Error>> - A new DataFrame with the column removed

pub fn drop_columns( df: DataFrame, column_names: &[&str], ) -> Result<DataFrame, Box<dyn Error>>

Drop multiple columns from the DataFrame

Arguments

• df - The DataFrame to operate on
• column_names - A slice of column names to drop

Returns

• Result<DataFrame, Box<dyn Error>> - A new DataFrame with the columns removed

pub fn drop_rows( df: DataFrame, indexes: &[usize], ) -> Result<DataFrame, Box<dyn Error>>

Drop rows by their indexes from the DataFrame

Arguments

• df - The DataFrame to operate on
• ìndexes` - indexes to drop

Returns

• Result<DataFrame, Box<dyn Error>>

pub fn detect_duplicate_columns( df: &DataFrame, ) -> Result<Vec<(String, Vec<String>)>, Box<dyn Error>>

Detect duplicate columns

Arguments

• df - The DataFrame to analyze

Returns

• Result<Vec<(String, Vec<String>)>, Box<dyn Error>> - A vector of tuples where

• the first element is the original column name
• the second element is a vector of duplicate column names that have the same data

pub fn count_duplicate_rows( df: &DataFrame, ) -> Result<(usize, Vec<usize>), Box<dyn Error>>

Count duplicate rows in the DataFrame

Arguments

• df - The DataFrame to analyze

Returns

• Result<(usize, Vec<usize>), Box<dyn Error>> - A tuple where
  • the first element is the count of duplicate rows
  • the second element is a vector of indexes of duplicate rows