Struct DataOperations 

pub struct DataOperations;

Data operations for spreadsheet manipulation

Implementations

impl DataOperations

pub fn new() -> Self

impl DataOperations

pub fn sort_by_column( &self, data: &mut Vec<Vec<String>>, column: usize, order: SortOrder, ) -> Result<()>

Sort rows by a specific column (public for backward compatibility)

impl DataOperations

pub fn filter_rows( &self, data: &[Vec<String>], column: usize, operator: &str, value: &str, ) -> Result<Vec<Vec<String>>>

Filter rows by a condition on a column (legacy method for compatibility)

pub fn evaluate_filter_condition( &self, cell_value: &str, operator: &str, value: &str, ) -> Result<bool>

Evaluate a filter condition (legacy method for compatibility)

pub fn replace( &self, data: &mut Vec<Vec<String>>, column: usize, find: &str, replace_with: &str, ) -> usize

Replace values in a column

pub fn find_replace( &self, data: &mut Vec<Vec<String>>, find: &str, replace_with: &str, _column: Option<usize>, ) -> Result<usize>

Find and replace across all columns

pub fn deduplicate(&self, data: &[Vec<String>]) -> Vec<Vec<String>>

Remove duplicate rows (returns new vec)

pub fn deduplicate_mut(&self, data: &mut Vec<Vec<String>>) -> usize

Remove duplicate rows in place

pub fn transpose(&self, data: &[Vec<String>]) -> Vec<Vec<String>>

Transpose data (rows to columns)

pub fn to_markdown(&self, data: &[Vec<String>]) -> String

Format data as markdown table

pub fn insert_row( &self, data: &mut Vec<Vec<String>>, index: usize, row: Vec<String>, )

Insert a row at a specific index

pub fn delete_row( &self, data: &mut Vec<Vec<String>>, index: usize, ) -> Option<Vec<String>>

Delete a row at a specific index

pub fn insert_column( &self, data: &mut Vec<Vec<String>>, index: usize, values: Vec<String>, )

Insert a column at a specific index

pub fn delete_column(&self, data: &mut Vec<Vec<String>>, index: usize)

Delete a column at a specific index

impl DataOperations

pub fn select_columns( &self, data: &[Vec<String>], columns: &[usize], ) -> Vec<Vec<String>>

Select specific columns by index

pub fn select_columns_by_name( &self, data: &[Vec<String>], names: &[&str], ) -> Result<Vec<Vec<String>>>

Select columns by name (first row is header)

pub fn head(&self, data: &[Vec<String>], n: usize) -> Vec<Vec<String>>

Get first n rows (head)

pub fn tail(&self, data: &[Vec<String>], n: usize) -> Vec<Vec<String>>

Get last n rows (tail)

pub fn sample( &self, data: &[Vec<String>], n: usize, seed: Option<u64>, ) -> Vec<Vec<String>>

Sample random rows

pub fn drop_columns( &self, data: &[Vec<String>], columns: &[usize], ) -> Vec<Vec<String>>

Drop columns by index

pub fn rename_columns( &self, data: &mut Vec<Vec<String>>, renames: &[(&str, &str)], ) -> Result<()>

Rename columns (first row is header)

pub fn fillna(&self, data: &mut Vec<Vec<String>>, value: &str)

Fill missing/empty values

pub fn dropna(&self, data: &[Vec<String>]) -> Vec<Vec<String>>

Drop rows with any empty values

pub fn concat(&self, datasets: &[Vec<Vec<String>>]) -> Vec<Vec<String>>

Concatenate multiple datasets vertically

pub fn join( &self, left: &[Vec<String>], right: &[Vec<String>], left_col: usize, right_col: usize, how: JoinType, ) -> Result<Vec<Vec<String>>>

Join two datasets on a column

pub fn groupby( &self, data: &[Vec<String>], group_col: usize, aggregations: &[(usize, AggFunc)], ) -> Result<Vec<Vec<String>>>

Group by column with aggregations

pub fn melt( &self, data: &[Vec<String>], id_vars: &[usize], value_vars: &[usize], ) -> Result<Vec<Vec<String>>>

Unpivot wide → long: repeat id_vars for each value_vars column; add variable and value.

If value_vars is empty, uses every column index not listed in id_vars.

impl DataOperations

pub fn describe(&self, data: &[Vec<String>]) -> Result<Vec<Vec<String>>>

Describe/summary statistics for all numeric columns

pub fn value_counts( &self, data: &[Vec<String>], column: usize, ) -> Vec<Vec<String>>

Count unique values in a column

pub fn pivot( &self, data: &[Vec<String>], index_col: usize, columns_col: usize, values_col: usize, agg: AggFunc, ) -> Result<Vec<Vec<String>>>

Pivot table

pub fn crosstab( &self, data: &[Vec<String>], row_col: usize, col_col: usize, ) -> Result<Vec<Vec<String>>>

Frequency crosstab: counts of (row_col, col_col) pairs (two categorical columns).

First row is the header: row dimension name, then distinct values from col_col. First column lists distinct values from row_col; cell (r, c) is the count.

pub fn correlation( &self, data: &[Vec<String>], columns: &[usize], ) -> Result<Vec<Vec<String>>>

Correlation matrix

pub fn dtypes(&self, data: &[Vec<String>]) -> Vec<Vec<String>>

Infer column types

pub fn unique(&self, data: &[Vec<String>], column: usize) -> Vec<Vec<String>>

Get unique values in a column

pub fn nunique(&self, data: &[Vec<String>], column: usize) -> usize

Count unique values in a column

pub fn info(&self, data: &[Vec<String>]) -> Vec<Vec<String>>

Get info about the dataset

impl DataOperations

pub fn query( &self, data: &[Vec<String>], where_clause: &str, ) -> Result<Vec<Vec<String>>>

Query with SQL-like WHERE clause

pub fn mutate( &self, data: &mut Vec<Vec<String>>, new_col_name: &str, formula: &str, ) -> Result<()>

Add computed column using formula

pub fn astype( &self, data: &mut Vec<Vec<String>>, column: usize, dtype: &str, ) -> Result<usize>

Cast column to specified type

pub fn sort_by_columns( &self, data: &mut Vec<Vec<String>>, columns: &[(usize, SortOrder)], ) -> Result<()>

Sort by multiple columns

pub fn apply_column<F>( &self, data: &mut Vec<Vec<String>>, column: usize, f: F, ) -> Result<()>

where F: Fn(&str) -> String,

Apply a function to each cell in a column

pub fn clip( &self, data: &mut Vec<Vec<String>>, column: usize, min: Option<f64>, max: Option<f64>, ) -> Result<usize>

Clip values to a range

pub fn normalize( &self, data: &mut Vec<Vec<String>>, column: usize, ) -> Result<()>

Normalize column values (0-1 range)

pub fn zscore(&self, data: &mut Vec<Vec<String>>, column: usize) -> Result<()>

Standardize numeric column to z-scores using population mean and standard deviation.

Non-numeric cells are left unchanged. If the column has fewer than two numeric values or the standard deviation is zero, cells are unchanged.

pub fn rolling_mean_column( &self, data: &mut Vec<Vec<String>>, value_col: usize, window: usize, new_col_name: &str, ) -> Result<()>

Append a column with rolling mean of value_col over the last window data rows (inclusive). Header is row 0; partial windows at the start use available rows (min_periods = 1).

pub fn rolling_sum_column( &self, data: &mut Vec<Vec<String>>, value_col: usize, window: usize, new_col_name: &str, ) -> Result<()>

Append a column with rolling sum of value_col over the last window data rows (inclusive).

pub fn parse_date( &self, data: &mut Vec<Vec<String>>, column: usize, from_format: &str, to_format: &str, ) -> Result<usize>

Parse and reformat date column

pub fn regex_filter( &self, data: &[Vec<String>], column: usize, pattern: &str, ) -> Result<Vec<Vec<String>>>

Filter rows by regex pattern

pub fn regex_replace( &self, data: &mut Vec<Vec<String>>, column: usize, pattern: &str, replacement: &str, ) -> Result<usize>

Replace values using regex pattern

pub fn extract_date_part( &self, data: &mut Vec<Vec<String>>, column: usize, part: &str, new_col_name: &str, date_format: &str, ) -> Result<()>

Extract date parts (year, month, day, weekday)

Trait Implementations

impl FilterOperator for DataOperations

fn filter( &self, data: &[Vec<String>], column: usize, condition: FilterCondition, ) -> Result<Vec<Vec<String>>>

impl SortOperator for DataOperations

fn sort( &self, data: &mut Vec<Vec<String>>, column: usize, ascending: bool, ) -> Result<()>

impl TransformOperator for DataOperations

fn transform( &self, data: &mut Vec<Vec<String>>, operation: TransformOperation, ) -> Result<()>

impl DataOperator for DataOperations