Merge 39a95e63d9ae7451c902949deb2fc44936127c15 into d851c500afb094614c654e262fd9d44f05b05bd8

Cleanup comments and formatting

README.md

@@ -1,9 +1,5 @@
 # rustframe
 
-<!-- # <img align="center" alt="Rustframe" src=".github/rustframe_logo.png" height="50px" /> rustframe -->
-
-<!-- though the centre tag doesn't work as it would normally, it achieves the desired effect -->
-
 📚 [Docs](https://magnus167.github.io/rustframe/) | 🐙 [GitHub](https://github.com/Magnus167/rustframe) | 🌐 [Gitea mirror](https://gitea.nulltech.uk/Magnus167/rustframe) | 🦀 [Crates.io](https://crates.io/crates/rustframe) | 🔖 [docs.rs](https://docs.rs/rustframe/latest/rustframe/)
 
 <!-- [![Last commit](https://img.shields.io/endpoint?url=https://magnus167.github.io/rustframe/rustframe/last-commit-date.json)](https://github.com/Magnus167/rustframe) -->
@@ -131,10 +127,6 @@ let mc: Matrix<f64> = Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]);
 let md: Matrix<f64> = Matrix::from_cols(vec![vec![5.0, 6.0], vec![7.0, 8.0]]);
 let mul_result: Matrix<f64> = mc.matrix_mul(&md);
 // Expected:
-// 1*5 + 3*6 = 5 + 18 = 23
-// 2*5 + 4*6 = 10 + 24 = 34
-// 1*7 + 3*8 = 7 + 24 = 31
-// 2*7 + 4*8 = 14 + 32 = 46
 assert_eq!(mul_result.data(), &[23.0, 34.0, 31.0, 46.0]);
 
 // Dot product (alias for matrix_mul for FloatMatrix)
@@ -143,14 +135,7 @@ assert_eq!(dot_result, mul_result);
 
 // Transpose
 let original_matrix: Matrix<f64> = Matrix::from_cols(vec![vec![1.0, 2.0, 3.0], vec![4.0, 5.0, 6.0]]);
-// Original:
-// 1 4
-// 2 5
-// 3 6
 let transposed_matrix: Matrix<f64> = original_matrix.transpose();
-// Transposed:
-// 1 2 3
-// 4 5 6
 assert_eq!(transposed_matrix.rows(), 2);
 assert_eq!(transposed_matrix.cols(), 3);
 assert_eq!(transposed_matrix.data(), &[1.0, 4.0, 2.0, 5.0, 3.0, 6.0]);
@@ -159,10 +144,6 @@ assert_eq!(transposed_matrix.data(), &[1.0, 4.0, 2.0, 5.0, 3.0, 6.0]);
 let matrix = Matrix::from_cols(vec![vec![1.0, 2.0, 3.0], vec![4.0, 5.0, 6.0]]);
 // Map function to double each value
 let mapped_matrix = matrix.map(|x| x * 2.0);
-// Expected data after mapping
-// 2 8
-// 4 10
-// 6 12
 assert_eq!(mapped_matrix.data(), &[2.0, 4.0, 6.0, 8.0, 10.0, 12.0]);
 
 // Zip
@@ -170,12 +151,136 @@ let a = Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]); // 2x2 matrix
 let b = Matrix::from_cols(vec![vec![5.0, 6.0], vec![7.0, 8.0]]); // 2x2 matrix
                                                                    // Zip function to add corresponding elements
 let zipped_matrix = a.zip(&b, |x, y| x + y);
-// Expected data after zipping
-// 6 10
-// 8 12
 assert_eq!(zipped_matrix.data(), &[6.0, 8.0, 10.0, 12.0]);
 ```
 
+---
+
+## DataFrame Usage Example
+
+```rust
+use chrono::NaiveDate;
+use rustframe::dataframe::DataFrame;
+use rustframe::utils::{BDateFreq, BDatesList};
+use std::any::TypeId;
+use std::collections::HashMap;
+
+// Helper for NaiveDate
+fn d(y: i32, m: u32, d: u32) -> NaiveDate {
+    NaiveDate::from_ymd_opt(y, m, d).unwrap()
+}
+
+// Create a new DataFrame
+let mut df = DataFrame::new();
+
+// Add columns of different types
+df.add_column("col_int1", vec![1, 2, 3, 4, 5]);
+df.add_column("col_float1", vec![1.1, 2.2, 3.3, 4.4, 5.5]);
+df.add_column(
+    "col_string",
+    vec![
+        "apple".to_string(),
+        "banana".to_string(),
+        "cherry".to_string(),
+        "date".to_string(),
+        "elderberry".to_string(),
+    ],
+);
+df.add_column("col_bool", vec![true, false, true, false, true]);
+// df.add_column("col_date", vec![d(2023,1,1), d(2023,1,2), d(2023,1,3), d(2023,1,4), d(2023,1,5)]);
+df.add_column(
+    "col_date",
+    BDatesList::from_n_periods("2023-01-01".to_string(), BDateFreq::Daily, 5)
+        .unwrap()
+        .list()
+        .unwrap(),
+);
+
+println!("DataFrame after initial column additions:\n{}", df);
+
+// Demonstrate frame re-use when adding columns of existing types
+let initial_frames_count = df.num_internal_frames();
+println!(
+    "\nInitial number of internal frames: {}",
+    initial_frames_count
+);
+
+df.add_column("col_int2", vec![6, 7, 8, 9, 10]);
+df.add_column("col_float2", vec![6.6, 7.7, 8.8, 9.9, 10.0]);
+
+let frames_after_reuse = df.num_internal_frames();
+println!(
+    "Number of internal frames after adding more columns of existing types: {}",
+    frames_after_reuse
+);
+assert_eq!(initial_frames_count, frames_after_reuse); // Should be equal, demonstrating re-use
+
+println!(
+    "\nDataFrame after adding more columns of existing types:\n{}",
+    df
+);
+
+// Get number of rows and columns
+println!("Rows: {}", df.rows()); // Output: Rows: 5
+println!("Columns: {}", df.cols()); // Output: Columns: 5
+
+// Get column names
+println!("Column names: {:?}", df.get_column_names());
+// Output: Column names: ["col_int", "col_float", "col_string", "col_bool", "col_date"]
+
+// Get a specific column by name and type
+let int_col = df.get_column::<i32>("col_int1").unwrap();
+// Output: Integer column: [1, 2, 3, 4, 5]
+println!("Integer column (col_int1): {:?}", int_col);
+
+let int_col2 = df.get_column::<i32>("col_int2").unwrap();
+// Output: Integer column: [6, 7, 8, 9, 10]
+println!("Integer column (col_int2): {:?}", int_col2);
+
+let float_col = df.get_column::<f64>("col_float1").unwrap();
+// Output: Float column: [1.1, 2.2, 3.3, 4.4, 5.5]
+println!("Float column (col_float1): {:?}", float_col);
+
+// Attempt to get a column with incorrect type (returns None)
+let wrong_type_col = df.get_column::<bool>("col_int1");
+// Output: Wrong type column: None
+println!("Wrong type column: {:?}", wrong_type_col);
+
+// Get a row by index
+let row_0 = df.get_row(0).unwrap();
+println!("Row 0: {:?}", row_0);
+// Output: Row 0: {"col_int1": "1", "col_float1": "1.1", "col_string": "apple", "col_bool": "true", "col_date": "2023-01-01", "col_int2": "6", "col_float2": "6.6"}
+
+let row_2 = df.get_row(2).unwrap();
+println!("Row 2: {:?}", row_2);
+// Output: Row 2: {"col_int1": "3", "col_float1": "3.3", "col_string": "cherry", "col_bool": "true", "col_date": "2023-01-03", "col_int2": "8", "col_float2": "8.8"}
+
+// Attempt to get an out-of-bounds row (returns None)
+let row_out_of_bounds = df.get_row(10);
+// Output: Row out of bounds: None
+println!("Row out of bounds: {:?}", row_out_of_bounds);
+
+// Drop a column
+df.drop_column("col_bool");
+println!("\nDataFrame after dropping 'col_bool':\n{}", df);
+
+println!("Columns after drop: {}", df.cols());
+println!("Column names after drop: {:?}", df.get_column_names());
+
+// Drop another column, ensuring the underlying Frame is removed if empty
+df.drop_column("col_float1");
+println!("\nDataFrame after dropping 'col_float1':\n{}", df);
+
+println!("Columns after second drop: {}", df.cols());
+println!(
+    "Column names after second drop: {:?}",
+    df.get_column_names()
+);
+
+// Attempt to drop a non-existent column (will panic)
+// df.drop_column("non_existent_col"); // Uncomment to see panic
+```
+
 ### More examples
 
 See the [examples](./examples/) directory for some demonstrations of Rustframe's syntax and functionality.

examples/game_of_life.rs

@@ -3,7 +3,7 @@
 //! It demonstrates matrix operations like shifting, counting neighbors, and applying game rules.
 //! The game runs in a loop, updating the board state and printing it to the console.
 //! To modify the behaviour of the example, please change the constants at the top of this file.
-//! By default,
+
 
 use rustframe::matrix::{BoolMatrix, BoolOps, IntMatrix, Matrix};
 use rustframe::random::{rng, Rng};
@@ -21,8 +21,6 @@ fn main() {
     let debug_mode = args.contains(&"--debug".to_string());
     let print_mode = if debug_mode { false } else { PRINT_BOARD };
 
-    // Initialize the game board.
-    // This demonstrates `BoolMatrix::from_vec`.
     let mut current_board =
         BoolMatrix::from_vec(vec![false; BOARD_SIZE * BOARD_SIZE], BOARD_SIZE, BOARD_SIZE);
 
@@ -31,15 +29,11 @@ fn main() {
     add_simulated_activity(&mut current_board, BOARD_SIZE);
 
     let mut generation_count: u32 = 0;
-    // `previous_board_state` will store a clone of the board.
-    // This demonstrates `Matrix::clone()` and later `PartialEq` for `Matrix`.
     let mut previous_board_state: Option<BoolMatrix> = None;
     let mut board_hashes = Vec::new();
-    // let mut print_board_bool = true;
     let mut print_bool_int = 0;
 
     loop {
-        // if print_board_bool {
         if print_bool_int % SKIP_FRAMES == 0 {
             print_board(&current_board, generation_count, print_mode);
 
@@ -47,7 +41,6 @@ fn main() {
         } else {
             print_bool_int += 1;
         }
-        // `current_board.count()` demonstrates a method from `BoolOps`.
         board_hashes.push(hash_board(&current_board, primes.clone()));
         if detect_stable_state(&current_board, &previous_board_state) {
             println!(
@@ -68,10 +61,8 @@ fn main() {
             add_simulated_activity(&mut current_board, BOARD_SIZE);
         }
 
-        // `current_board.clone()` demonstrates `Clone` for `Matrix`.
         previous_board_state = Some(current_board.clone());
 
-        // This is the core call to your game logic.
         let next_board = game_of_life_next_frame(&current_board);
         current_board = next_board;
 
@@ -106,7 +97,6 @@ fn print_board(board: &BoolMatrix, generation_count: u32, print_mode: bool) {
         print_str.push_str("| ");
         for c in 0..board.cols() {
             if board[(r, c)] {
-                // Using Index trait for Matrix<bool>
                 print_str.push_str("██");
             } else {
                 print_str.push_str("  ");
@@ -188,74 +178,38 @@ pub fn game_of_life_next_frame(current_game: &BoolMatrix) -> BoolMatrix {
     if rows == 0 && cols == 0 {
         return BoolMatrix::from_vec(vec![], 0, 0); // Return an empty BoolMatrix
     }
-    // Assuming valid non-empty dimensions (e.g., 25x25) as per typical GOL.
-    // Your Matrix::from_vec would panic for other invalid 0-dim cases.
-
     // Define the 8 neighbor offsets (row_delta, col_delta)
     let neighbor_offsets: [(isize, isize); 8] = [
         (-1, -1),
         (-1, 0),
-        (-1, 1), // Top row (NW, N, NE)
+        (-1, 1),
         (0, -1),
-        (0, 1), // Middle row (W, E)
+        (0, 1),
         (1, -1),
         (1, 0),
-        (1, 1), // Bottom row (SW, S, SE)
+        (1, 1),
     ];
 
-    // 1. Initialize `neighbor_counts` with the first shifted layer.
-    //    This demonstrates creating an IntMatrix from a function and using it as a base.
     let (first_dr, first_dc) = neighbor_offsets[0];
     let mut neighbor_counts = get_shifted_neighbor_layer(current_game, first_dr, first_dc);
 
-    // 2. Add the remaining 7 neighbor layers.
-    //    This demonstrates element-wise addition of matrices (`Matrix + Matrix`).
     for i in 1..neighbor_offsets.len() {
         let (dr, dc) = neighbor_offsets[i];
         let next_neighbor_layer = get_shifted_neighbor_layer(current_game, dr, dc);
-        // `neighbor_counts` (owned IntMatrix) + `next_neighbor_layer` (owned IntMatrix)
-        // uses `impl Add for Matrix`, consumes both, returns new owned `IntMatrix`.
         neighbor_counts = neighbor_counts + next_neighbor_layer;
     }
 
-    // 3. Apply Game of Life rules using element-wise operations.
-
-    // Rule: Survival or Birth based on neighbor counts.
-    // A cell is alive in the next generation if:
-    //   (it's currently alive AND has 2 or 3 neighbors) OR
-    //   (it's currently dead AND has exactly 3 neighbors)
-
-    // `neighbor_counts.eq_elem(scalar)`:
-    //   Demonstrates element-wise comparison of a Matrix with a scalar (broadcast).
-    //   Returns an owned `BoolMatrix`.
     let has_2_neighbors = neighbor_counts.eq_elem(2);
-    let has_3_neighbors = neighbor_counts.eq_elem(3); // This will be reused
+    let has_3_neighbors = neighbor_counts.eq_elem(3);
 
-    // `has_2_neighbors | has_3_neighbors`:
-    //   Demonstrates element-wise OR (`Matrix<bool> | Matrix<bool>`).
-    //   Consumes both operands, returns an owned `BoolMatrix`.
-    let has_2_or_3_neighbors = has_2_neighbors | has_3_neighbors.clone(); // Clone has_3_neighbors as it's used again
+    let has_2_or_3_neighbors = has_2_neighbors | has_3_neighbors.clone();
 
-    // `current_game & &has_2_or_3_neighbors`:
-    //   `current_game` is `&BoolMatrix`. `has_2_or_3_neighbors` is owned.
-    //   Demonstrates element-wise AND (`&Matrix<bool> & &Matrix<bool>`).
-    //   Borrows both operands, returns an owned `BoolMatrix`.
     let survives = current_game & &has_2_or_3_neighbors;
 
-    // `!current_game`:
-    //   Demonstrates element-wise NOT (`!&Matrix<bool>`).
-    //   Borrows operand, returns an owned `BoolMatrix`.
     let is_dead = !current_game;
 
-    // `is_dead & &has_3_neighbors`:
-    //   `is_dead` is owned. `has_3_neighbors` is owned.
-    //   Demonstrates element-wise AND (`Matrix<bool> & &Matrix<bool>`).
-    //   Consumes `is_dead`, borrows `has_3_neighbors`, returns an owned `BoolMatrix`.
     let births = is_dead & &has_3_neighbors;
 
-    // `survives | births`:
-    //   Demonstrates element-wise OR (`Matrix<bool> | Matrix<bool>`).
-    //   Consumes both operands, returns an owned `BoolMatrix`.
     let next_frame_game = survives | births;
 
     next_frame_game

examples/logistic_regression.rs

@@ -16,7 +16,7 @@ fn student_passing_example() {
 
     // Hours studied for each student
     let hours = vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0];
-    // 0 = fail, 1 = pass
+    // Label: 0 denotes failure and 1 denotes success
     let passed = vec![0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0];
 
     let x = Matrix::from_vec(hours.clone(), hours.len(), 1);

examples/stats_overview.rs

@@ -6,9 +6,9 @@ use rustframe::matrix::{Axis, Matrix};
 /// Demonstrates some of the statistics utilities in Rustframe.
 ///
 /// The example is split into three parts:
-///   1. Basic descriptive statistics on a small data set.
-///   2. Covariance and correlation calculations.
-///   3. Simple inferential tests (t-test and chi-square).
+///   - Basic descriptive statistics on a small data set
+///   - Covariance and correlation calculations
+///   - Simple inferential tests (t-test and chi-square)
 fn main() {
     descriptive_demo();
     println!("\n-----\n");

src/compute/models/pca.rs

@@ -44,11 +44,7 @@ mod tests {
 
     #[test]
     fn test_pca_basic() {
-        // Simple 2D data, points along y=x line
-        // Data:
-        // 1.0, 1.0
-        // 2.0, 2.0
-        // 3.0, 3.0
+        // Simple 2D data with points along the y = x line
         let data = Matrix::from_rows_vec(vec![1.0, 1.0, 2.0, 2.0, 3.0, 3.0], 3, 2);
         let (_n_samples, _n_features) = data.shape();
 
@@ -71,15 +67,7 @@ mod tests {
         assert!((pca.components.get(0, 0) - 1.0).abs() < EPSILON);
         assert!((pca.components.get(0, 1) - 1.0).abs() < EPSILON);
 
-        // Test transform
-        // Centered data:
-        // -1.0, -1.0
-        //  0.0,  0.0
-        //  1.0,  1.0
-        // Projected: (centered_data * components.transpose())
-        // (-1.0 * 1.0 + -1.0 * 1.0) = -2.0
-        // ( 0.0 * 1.0 +  0.0 * 1.0) =  0.0
-        // ( 1.0 * 1.0 +  1.0 * 1.0) =  2.0
+        // Test transform: centered data projects to [-2.0, 0.0, 2.0]
         let transformed_data = pca.transform(&data);
         assert_eq!(transformed_data.rows(), 3);
         assert_eq!(transformed_data.cols(), 1);

src/compute/stats/correlation.rs

@@ -137,10 +137,7 @@ mod tests {
 
     #[test]
     fn test_covariance_scalar_same_matrix() {
-        // M =
-        // 1,2
-        // 3,4
-        // mean = 2.5
+        // Matrix with rows [1, 2] and [3, 4]; mean is 2.5
         let data = vec![1.0, 2.0, 3.0, 4.0];
         let m = Matrix::from_vec(data.clone(), 2, 2);
 
@@ -152,10 +149,7 @@ mod tests {
 
     #[test]
     fn test_covariance_scalar_diff_matrix() {
-        // x =
-        // 1,2
-        // 3,4
-        // y = 2*x
+        // Matrix x has rows [1, 2] and [3, 4]; y is two times x
         let x = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
         let y = Matrix::from_vec(vec![2.0, 4.0, 6.0, 8.0], 2, 2);
 
@@ -167,10 +161,7 @@ mod tests {
 
     #[test]
     fn test_covariance_vertical() {
-        // M =
-        // 1,2
-        // 3,4
-        // cols are [1,3] and [2,4], each var=1, cov=1
+        // Matrix with rows [1, 2] and [3, 4]; columns are [1,3] and [2,4], each var=1, cov=1
         let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
         let cov_mat = covariance_vertical(&m);
 
@@ -184,10 +175,7 @@ mod tests {
 
     #[test]
     fn test_covariance_horizontal() {
-        // M =
-        // 1,2
-        // 3,4
-        // rows are [1,2] and [3,4], each var=0.25, cov=0.25
+        // Matrix with rows [1,2] and [3,4], each var=0.25, cov=0.25
         let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
         let cov_mat = covariance_horizontal(&m);
 
@@ -201,10 +189,7 @@ mod tests {
 
     #[test]
     fn test_covariance_matrix_vertical() {
-        // Test with a simple 2x2 matrix
-        // M =
-        // 1, 2
-        // 3, 4
+        // Test with a simple 2x2 matrix with rows [1, 2] and [3, 4]
         // Expected covariance matrix (vertical, i.e., between columns):
         // Col1: [1, 3], mean = 2
         // Col2: [2, 4], mean = 3
@@ -212,9 +197,7 @@ mod tests {
         // Cov(Col2, Col2) = ((2-3)^2 + (4-3)^2) / (2-1) = (1+1)/1 = 2
         // Cov(Col1, Col2) = ((1-2)*(2-3) + (3-2)*(4-3)) / (2-1) = ((-1)*(-1) + (1)*(1))/1 = (1+1)/1 = 2
         // Cov(Col2, Col1) = 2
-        // Expected:
-        // 2, 2
-        // 2, 2
+        // Expected matrix filled with 2
         let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
         let cov_mat = covariance_matrix(&m, Axis::Col);
 
@@ -226,10 +209,7 @@ mod tests {
 
     #[test]
     fn test_covariance_matrix_horizontal() {
-        // Test with a simple 2x2 matrix
-        // M =
-        // 1, 2
-        // 3, 4
+        // Test with a simple 2x2 matrix with rows [1, 2] and [3, 4]
         // Expected covariance matrix (horizontal, i.e., between rows):
         // Row1: [1, 2], mean = 1.5
         // Row2: [3, 4], mean = 3.5
@@ -237,9 +217,7 @@ mod tests {
         // Cov(Row2, Row2) = ((3-3.5)^2 + (4-3.5)^2) / (2-1) = (0.25+0.25)/1 = 0.5
         // Cov(Row1, Row2) = ((1-1.5)*(3-3.5) + (2-1.5)*(4-3.5)) / (2-1) = ((-0.5)*(-0.5) + (0.5)*(0.5))/1 = (0.25+0.25)/1 = 0.5
         // Cov(Row2, Row1) = 0.5
-        // Expected:
-        // 0.5, -0.5
-        // -0.5, 0.5
+        // Expected matrix: [[0.5, -0.5], [-0.5, 0.5]]
         let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
         let cov_mat = covariance_matrix(&m, Axis::Row);
 

src/compute/stats/descriptive.rs

@@ -350,11 +350,7 @@ mod tests {
         let data: Vec<f64> = (1..=24).map(|x| x as f64).collect();
         let x = Matrix::from_vec(data, 4, 6);
 
-        // columns:
-        //  1,  5,  9, 13, 17, 21
-        //  2,  6, 10, 14, 18, 22
-        //  3,  7, 11, 15, 19, 23
-        //  4,  8, 12, 16, 20, 24
+        // columns contain sequences increasing by four starting at 1 through 4
 
         let er0 = vec![1., 5., 9., 13., 17., 21.];
         let er50 = vec![3., 7., 11., 15., 19., 23.];

src/dataframe/df.rs

@@ -0,0 +1,659 @@
+use crate::frame::{Frame, RowIndex};
+use std::any::{Any, TypeId};
+use std::collections::HashMap;
+use std::fmt; // Import TypeId
+
+const DEFAULT_DISPLAY_ROWS: usize = 5;
+const DEFAULT_DISPLAY_COLS: usize = 10;
+
+// Trait to enable type-agnostic operations on Frame objects within DataFrame
+pub trait SubFrame: Send + Sync + fmt::Debug + Any {
+    fn rows(&self) -> usize;
+    fn get_value_as_string(&self, physical_row_idx: usize, col_name: &str) -> String;
+    fn clone_box(&self) -> Box<dyn SubFrame>;
+    fn delete_column_from_frame(&mut self, col_name: &str);
+    fn get_frame_cols(&self) -> usize; // Add a method to get the number of columns in the underlying frame
+
+    // Methods for downcasting to concrete types
+    fn as_any(&self) -> &dyn Any;
+    fn as_any_mut(&mut self) -> &mut dyn Any;
+}
+
+// Implement SubFrame for any Frame<T> that meets the requirements
+impl<T> SubFrame for Frame<T>
+where
+    T: Clone + PartialEq + fmt::Display + fmt::Debug + 'static + Send + Sync + Any,
+{
+    fn rows(&self) -> usize {
+        self.rows()
+    }
+
+    fn get_value_as_string(&self, physical_row_idx: usize, col_name: &str) -> String {
+        self.get_row(physical_row_idx).get(col_name).to_string()
+    }
+
+    fn clone_box(&self) -> Box<dyn SubFrame> {
+        Box::new(self.clone())
+    }
+
+    fn delete_column_from_frame(&mut self, col_name: &str) {
+        self.delete_column(col_name);
+    }
+
+    fn get_frame_cols(&self) -> usize {
+        self.cols()
+    }
+
+    fn as_any(&self) -> &dyn Any {
+        self
+    }
+
+    fn as_any_mut(&mut self) -> &mut dyn Any {
+        self
+    }
+}
+
+pub struct DataFrame {
+    frames_by_type: HashMap<TypeId, Box<dyn SubFrame>>, // Maps TypeId to the Frame holding columns of that type
+    column_to_type: HashMap<String, TypeId>,            // Maps column name to its TypeId
+    column_names: Vec<String>,
+    index: RowIndex,
+}
+
+impl DataFrame {
+    pub fn new() -> Self {
+        DataFrame {
+            frames_by_type: HashMap::new(),
+            column_to_type: HashMap::new(),
+            column_names: Vec::new(),
+            index: RowIndex::Range(0..0), // Initialize with an empty range index
+        }
+    }
+
+    /// Returns the number of rows in the DataFrame.
+    pub fn rows(&self) -> usize {
+        self.index.len()
+    }
+
+    /// Returns the number of columns in the DataFrame.
+    pub fn cols(&self) -> usize {
+        self.column_names.len()
+    }
+
+    /// Returns a reference to the vector of column names.
+    pub fn get_column_names(&self) -> &Vec<String> {
+        &self.column_names
+    }
+
+    /// Returns the number of internal Frame objects (one per unique data type).
+    pub fn num_internal_frames(&self) -> usize {
+        self.frames_by_type.len()
+    }
+
+    /// Returns a reference to a column of a specific type, if it exists.
+    pub fn get_column<T>(&self, col_name: &str) -> Option<&[T]>
+    where
+        T: Clone + PartialEq + fmt::Display + fmt::Debug + 'static + Send + Sync + Any,
+    {
+        let expected_type_id = TypeId::of::<T>();
+        if let Some(actual_type_id) = self.column_to_type.get(col_name) {
+            if *actual_type_id == expected_type_id {
+                if let Some(sub_frame_box) = self.frames_by_type.get(actual_type_id) {
+                    if let Some(frame) = sub_frame_box.as_any().downcast_ref::<Frame<T>>() {
+                        return Some(frame.column(col_name));
+                    }
+                }
+            }
+        }
+        None
+    }
+
+    /// Returns a HashMap representing a row, mapping column names to their string values.
+    pub fn get_row(&self, row_idx: usize) -> Option<HashMap<String, String>> {
+        if row_idx >= self.rows() {
+            return None;
+        }
+
+        let mut row_data = HashMap::new();
+        for col_name in &self.column_names {
+            if let Some(type_id) = self.column_to_type.get(col_name) {
+                if let Some(sub_frame_box) = self.frames_by_type.get(type_id) {
+                    let value = sub_frame_box.get_value_as_string(row_idx, col_name);
+                    row_data.insert(col_name.clone(), value);
+                }
+            }
+        }
+        Some(row_data)
+    }
+
+    pub fn add_column<T>(&mut self, col_name: &str, data: Vec<T>)
+    where
+        T: Clone + PartialEq + fmt::Display + fmt::Debug + 'static + Send + Sync + Any,
+    {
+        let type_id = TypeId::of::<T>();
+        let col_name_string = col_name.to_string();
+
+        // Check for duplicate column name across the entire DataFrame
+        if self.column_to_type.contains_key(&col_name_string) {
+            panic!(
+                "DataFrame::add_column: duplicate column name: '{}'",
+                col_name_string
+            );
+        }
+
+        // If this is the first column being added, set the DataFrame's index
+        if self.column_names.is_empty() {
+            self.index = RowIndex::Range(0..data.len());
+        } else {
+            // Ensure new column has the same number of rows as existing columns
+            if data.len() != self.index.len() {
+                panic!(
+                    "DataFrame::add_column: new column '{}' has {} rows, but existing columns have {} rows",
+                    col_name_string,
+                    data.len(),
+                    self.index.len()
+                );
+            }
+        }
+
+        // Check if a Frame of this type already exists
+        if let Some(sub_frame_box) = self.frames_by_type.get_mut(&type_id) {
+            // Downcast to the concrete Frame<T> and add the column
+            if let Some(frame) = sub_frame_box.as_any_mut().downcast_mut::<Frame<T>>() {
+                frame.add_column(col_name_string.clone(), data);
+            } else {
+                // This should ideally not happen if TypeId matches, but good for safety
+                panic!(
+                    "Type mismatch when downcasting existing SubFrame for TypeId {:?}",
+                    type_id
+                );
+            }
+        } else {
+            // No Frame of this type exists, create a new one
+            // The Frame::new constructor expects a Matrix and column names.
+            // We create a Matrix from a single column vector.
+            let new_frame = Frame::new(
+                crate::matrix::Matrix::from_cols(vec![data]),
+                vec![col_name_string.clone()],
+                Some(self.index.clone()), // Pass the DataFrame's index to the new Frame
+            );
+            self.frames_by_type.insert(type_id, Box::new(new_frame));
+        }
+
+        // Update column mappings and names
+        self.column_to_type.insert(col_name_string.clone(), type_id);
+        self.column_names.push(col_name_string);
+    }
+
+    /// Drops a column from the DataFrame.
+    /// Panics if the column does not exist.
+    pub fn drop_column(&mut self, col_name: &str) {
+        let col_name_string = col_name.to_string();
+
+        // 1. Get the TypeId associated with the column
+        let type_id = self
+            .column_to_type
+            .remove(&col_name_string)
+            .unwrap_or_else(|| {
+                panic!(
+                    "DataFrame::drop_column: column '{}' not found",
+                    col_name_string
+                );
+            });
+
+        // 2. Remove the column name from the ordered list
+        self.column_names.retain(|name| name != &col_name_string);
+
+        // 3. Find the Frame object and delete the column from it
+        if let Some(sub_frame_box) = self.frames_by_type.get_mut(&type_id) {
+            sub_frame_box.delete_column_from_frame(&col_name_string);
+
+            // 4. If the Frame object for this type becomes empty, remove it from frames_by_type
+            if sub_frame_box.get_frame_cols() == 0 {
+                self.frames_by_type.remove(&type_id);
+            }
+        } else {
+            // This should not happen if column_to_type was consistent
+            panic!(
+                "DataFrame::drop_column: internal error, no frame found for type_id {:?}",
+                type_id
+            );
+        }
+    }
+}
+
+impl fmt::Display for DataFrame {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        // Display column headers
+        for col_name in self.column_names.iter().take(DEFAULT_DISPLAY_COLS) {
+            write!(f, "{:<15}", col_name)?;
+        }
+        if self.column_names.len() > DEFAULT_DISPLAY_COLS {
+            write!(f, "...")?;
+        }
+        writeln!(f)?;
+
+        // Display data rows
+        let mut displayed_rows = 0;
+        for i in 0..self.index.len() {
+            if displayed_rows >= DEFAULT_DISPLAY_ROWS {
+                writeln!(f, "...")?;
+                break;
+            }
+            for col_name in self.column_names.iter().take(DEFAULT_DISPLAY_COLS) {
+                if let Some(type_id) = self.column_to_type.get(col_name) {
+                    if let Some(sub_frame_box) = self.frames_by_type.get(type_id) {
+                        write!(f, "{:<15}", sub_frame_box.get_value_as_string(i, col_name))?;
+                    } else {
+                        // This case indicates an inconsistency: column_to_type has an entry,
+                        // but frames_by_type doesn't have the corresponding Frame.
+                        write!(f, "{:<15}", "[ERROR]")?;
+                    }
+                } else {
+                    // This case indicates an inconsistency: column_names has an entry,
+                    // but column_to_type doesn't have the corresponding column.
+                    write!(f, "{:<15}", "[ERROR]")?;
+                }
+            }
+            if self.column_names.len() > DEFAULT_DISPLAY_COLS {
+                write!(f, "...")?;
+            }
+            writeln!(f)?;
+            displayed_rows += 1;
+        }
+        Ok(())
+    }
+}
+
+impl fmt::Debug for DataFrame {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_struct("DataFrame")
+            .field("column_names", &self.column_names)
+            .field("index", &self.index)
+            .field("column_to_type", &self.column_to_type)
+            .field("frames_by_type", &self.frames_by_type)
+            .finish()
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////////////////////////
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::frame::Frame;
+    use crate::matrix::Matrix;
+
+    #[test]
+    fn test_dataframe_new() {
+        let df = DataFrame::new();
+        assert_eq!(df.rows(), 0);
+        assert_eq!(df.cols(), 0);
+        assert!(df.get_column_names().is_empty());
+        assert!(df.frames_by_type.is_empty());
+        assert!(df.column_to_type.is_empty());
+    }
+
+    #[test]
+    fn test_dataframe_add_column_initial() {
+        let mut df = DataFrame::new();
+        let data = vec![1, 2, 3];
+        df.add_column("col_int", data.clone());
+
+        assert_eq!(df.rows(), 3);
+        assert_eq!(df.cols(), 1);
+        assert_eq!(df.get_column_names(), &vec!["col_int".to_string()]);
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert_eq!(df.column_to_type.get("col_int"), Some(&TypeId::of::<i32>()));
+
+        // Verify the underlying frame
+        let sub_frame_box = df.frames_by_type.get(&TypeId::of::<i32>()).unwrap();
+        let frame = sub_frame_box.as_any().downcast_ref::<Frame<i32>>().unwrap();
+        assert_eq!(frame.rows(), 3);
+        assert_eq!(frame.cols(), 1);
+        assert_eq!(frame.columns(), &vec!["col_int".to_string()]);
+    }
+
+    #[test]
+    fn test_dataframe_add_column_same_type() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int1", vec![1, 2, 3]);
+        df.add_column("col_int2", vec![4, 5, 6]);
+
+        assert_eq!(df.rows(), 3);
+        assert_eq!(df.cols(), 2);
+        assert_eq!(
+            df.get_column_names(),
+            &vec!["col_int1".to_string(), "col_int2".to_string()]
+        );
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert_eq!(
+            df.column_to_type.get("col_int1"),
+            Some(&TypeId::of::<i32>())
+        );
+        assert_eq!(
+            df.column_to_type.get("col_int2"),
+            Some(&TypeId::of::<i32>())
+        );
+
+        // Verify the underlying frame
+        let sub_frame_box = df.frames_by_type.get(&TypeId::of::<i32>()).unwrap();
+        let frame = sub_frame_box.as_any().downcast_ref::<Frame<i32>>().unwrap();
+        assert_eq!(frame.rows(), 3);
+        assert_eq!(frame.cols(), 2);
+        assert_eq!(
+            frame.columns(),
+            &vec!["col_int1".to_string(), "col_int2".to_string()]
+        );
+    }
+
+    #[test]
+    fn test_dataframe_add_column_different_type() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+        df.add_column(
+            "col_string",
+            vec!["a".to_string(), "b".to_string(), "c".to_string()],
+        );
+
+        assert_eq!(df.rows(), 3);
+        assert_eq!(df.cols(), 3);
+        assert_eq!(
+            df.get_column_names(),
+            &vec![
+                "col_int".to_string(),
+                "col_float".to_string(),
+                "col_string".to_string()
+            ]
+        );
+
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<String>()));
+
+        assert_eq!(df.column_to_type.get("col_int"), Some(&TypeId::of::<i32>()));
+        assert_eq!(
+            df.column_to_type.get("col_float"),
+            Some(&TypeId::of::<f64>())
+        );
+        assert_eq!(
+            df.column_to_type.get("col_string"),
+            Some(&TypeId::of::<String>())
+        );
+
+        // Verify underlying frames
+        let int_frame = df
+            .frames_by_type
+            .get(&TypeId::of::<i32>())
+            .unwrap()
+            .as_any()
+            .downcast_ref::<Frame<i32>>()
+            .unwrap();
+        assert_eq!(int_frame.columns(), &vec!["col_int".to_string()]);
+
+        let float_frame = df
+            .frames_by_type
+            .get(&TypeId::of::<f64>())
+            .unwrap()
+            .as_any()
+            .downcast_ref::<Frame<f64>>()
+            .unwrap();
+        assert_eq!(float_frame.columns(), &vec!["col_float".to_string()]);
+
+        let string_frame = df
+            .frames_by_type
+            .get(&TypeId::of::<String>())
+            .unwrap()
+            .as_any()
+            .downcast_ref::<Frame<String>>()
+            .unwrap();
+        assert_eq!(string_frame.columns(), &vec!["col_string".to_string()]);
+    }
+
+    #[test]
+    fn test_dataframe_get_column() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+        df.add_column(
+            "col_string",
+            vec!["a".to_string(), "b".to_string(), "c".to_string()],
+        );
+
+        // Test getting existing columns with correct type
+        assert_eq!(
+            df.get_column::<i32>("col_int").unwrap(),
+            vec![1, 2, 3].as_slice()
+        );
+        assert_eq!(
+            df.get_column::<f64>("col_float").unwrap(),
+            vec![1.1, 2.2, 3.3].as_slice()
+        );
+        assert_eq!(
+            df.get_column::<String>("col_string").unwrap(),
+            vec!["a".to_string(), "b".to_string(), "c".to_string()].as_slice()
+        );
+
+        // Test getting non-existent column
+        assert_eq!(df.get_column::<i32>("non_existent"), None);
+
+        // Test getting existing column with incorrect type
+        assert_eq!(df.get_column::<f64>("col_int"), None);
+        assert_eq!(df.get_column::<i32>("col_float"), None);
+    }
+
+    #[test]
+    fn test_dataframe_get_row() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+        df.add_column(
+            "col_string",
+            vec!["a".to_string(), "b".to_string(), "c".to_string()],
+        );
+
+        // Test getting an existing row
+        let row0 = df.get_row(0).unwrap();
+        assert_eq!(row0.get("col_int"), Some(&"1".to_string()));
+        assert_eq!(row0.get("col_float"), Some(&"1.1".to_string()));
+        assert_eq!(row0.get("col_string"), Some(&"a".to_string()));
+
+        let row1 = df.get_row(1).unwrap();
+        assert_eq!(row1.get("col_int"), Some(&"2".to_string()));
+        assert_eq!(row1.get("col_float"), Some(&"2.2".to_string()));
+        assert_eq!(row1.get("col_string"), Some(&"b".to_string()));
+
+        // Test getting an out-of-bounds row
+        assert_eq!(df.get_row(3), None);
+    }
+
+    #[test]
+    #[should_panic(expected = "DataFrame::add_column: duplicate column name: 'col_int'")]
+    fn test_dataframe_add_column_duplicate_name() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_int", vec![4, 5, 6]);
+    }
+
+    #[test]
+    #[should_panic(
+        expected = "DataFrame::add_column: new column 'col_int2' has 2 rows, but existing columns have 3 rows"
+    )]
+    fn test_dataframe_add_column_mismatched_rows() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int1", vec![1, 2, 3]);
+        df.add_column("col_int2", vec![4, 5]);
+    }
+
+    #[test]
+    fn test_dataframe_display() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3, 4, 5, 6]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3, 4.4, 5.5, 6.6]);
+        df.add_column(
+            "col_string",
+            vec![
+                "a".to_string(),
+                "b".to_string(),
+                "c".to_string(),
+                "d".to_string(),
+                "e".to_string(),
+                "f".to_string(),
+            ],
+        );
+
+        let expected_output = "\
+col_int        col_float      col_string     
+1              1.1            a              
+2              2.2            b              
+3              3.3            c              
+4              4.4            d              
+5              5.5            e              
+...
+";
+        assert_eq!(format!("{}", df), expected_output);
+    }
+
+    #[test]
+    fn test_dataframe_debug() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+
+        let debug_output = format!("{:?}", df);
+        assert!(debug_output.contains("DataFrame {"));
+        assert!(debug_output.contains("column_names: [\"col_int\", \"col_float\"]"));
+        assert!(debug_output.contains("index: Range(0..3)"));
+        assert!(debug_output.contains("column_to_type: {"));
+        assert!(debug_output.contains("frames_by_type: {"));
+    }
+
+    #[test]
+    fn test_dataframe_drop_column_single_type() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int1", vec![1, 2, 3]);
+        df.add_column("col_int2", vec![4, 5, 6]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+
+        assert_eq!(df.cols(), 3);
+        assert_eq!(
+            df.get_column_names(),
+            &vec![
+                "col_int1".to_string(),
+                "col_int2".to_string(),
+                "col_float".to_string()
+            ]
+        );
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+
+        df.drop_column("col_int1");
+
+        assert_eq!(df.cols(), 2);
+        assert_eq!(
+            df.get_column_names(),
+            &vec!["col_int2".to_string(), "col_float".to_string()]
+        );
+        assert!(df.column_to_type.get("col_int1").is_none());
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>())); // Frame<i32> should still exist
+        let int_frame = df
+            .frames_by_type
+            .get(&TypeId::of::<i32>())
+            .unwrap()
+            .as_any()
+            .downcast_ref::<Frame<i32>>()
+            .unwrap();
+        assert_eq!(int_frame.columns(), &vec!["col_int2".to_string()]);
+
+        df.drop_column("col_int2");
+
+        assert_eq!(df.cols(), 1);
+        assert_eq!(df.get_column_names(), &vec!["col_float".to_string()]);
+        assert!(df.column_to_type.get("col_int2").is_none());
+        assert!(!df.frames_by_type.contains_key(&TypeId::of::<i32>())); // Frame<i32> should be removed
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+    }
+
+    #[test]
+    fn test_dataframe_drop_column_mixed_types() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.add_column("col_float", vec![1.1, 2.2, 3.3]);
+        df.add_column(
+            "col_string",
+            vec!["a".to_string(), "b".to_string(), "c".to_string()],
+        );
+
+        assert_eq!(df.cols(), 3);
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<String>()));
+
+        df.drop_column("col_float");
+
+        assert_eq!(df.cols(), 2);
+        assert_eq!(
+            df.get_column_names(),
+            &vec!["col_int".to_string(), "col_string".to_string()]
+        );
+        assert!(df.column_to_type.get("col_float").is_none());
+        assert!(!df.frames_by_type.contains_key(&TypeId::of::<f64>())); // Frame<f64> should be removed
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<String>()));
+
+        df.drop_column("col_int");
+        df.drop_column("col_string");
+
+        assert_eq!(df.cols(), 0);
+        assert!(df.get_column_names().is_empty());
+        assert!(df.frames_by_type.is_empty());
+        assert!(df.column_to_type.is_empty());
+    }
+
+    #[test]
+    #[should_panic(expected = "DataFrame::drop_column: column 'non_existent' not found")]
+    fn test_dataframe_drop_column_non_existent() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int", vec![1, 2, 3]);
+        df.drop_column("non_existent");
+    }
+
+    #[test]
+    fn test_dataframe_add_column_reuses_existing_frame() {
+        let mut df = DataFrame::new();
+        df.add_column("col_int1", vec![1, 2, 3]);
+        df.add_column("col_float1", vec![1.1, 2.2, 3.3]);
+
+        // Initially, there should be two frames (one for i32, one for f64)
+        assert_eq!(df.frames_by_type.len(), 2);
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+
+        // Add another integer column
+        df.add_column("col_int2", vec![4, 5, 6]);
+
+        // The number of frames should still be 2, as the existing i32 frame should be reused
+        assert_eq!(df.frames_by_type.len(), 2);
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+
+        // Verify the i32 frame now contains both integer columns
+        let int_frame = df.frames_by_type.get(&TypeId::of::<i32>()).unwrap().as_any().downcast_ref::<Frame<i32>>().unwrap();
+        assert_eq!(int_frame.columns(), &vec!["col_int1".to_string(), "col_int2".to_string()]);
+        assert_eq!(int_frame.cols(), 2);
+
+        // Add another float column
+        df.add_column("col_float2", vec![4.4, 5.5, 6.6]);
+
+        // The number of frames should still be 2, as the existing f64 frame should be reused
+        assert_eq!(df.frames_by_type.len(), 2);
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<i32>()));
+        assert!(df.frames_by_type.contains_key(&TypeId::of::<f64>()));
+
+        // Verify the f64 frame now contains both float columns
+        let float_frame = df.frames_by_type.get(&TypeId::of::<f64>()).unwrap().as_any().downcast_ref::<Frame<f64>>().unwrap();
+        assert_eq!(float_frame.columns(), &vec!["col_float1".to_string(), "col_float2".to_string()]);
+        assert_eq!(float_frame.cols(), 2);
+    }
+}

src/dataframe/mod.rs

@@ -0,0 +1,4 @@
+//! This module provides the DataFrame structure for handling tabular data with mixed types.
+pub mod df;
+
+pub use df::{DataFrame, SubFrame};

src/frame/base.rs

@@ -316,7 +316,7 @@ impl<T: Clone + PartialEq> Frame<T> {
         )
     }
 
-    /// Returns an immutable slice of the specified column's data.
+    /// Returns an immutable slice of the specified column's data by name.
     /// Panics if the column name is not found.
     pub fn column(&self, name: &str) -> &[T] {
         let idx = self
@@ -325,7 +325,13 @@ impl<T: Clone + PartialEq> Frame<T> {
         self.matrix.column(idx)
     }
 
-    /// Returns a mutable slice of the specified column's data.
+    /// Returns an immutable slice of the specified column's data by its physical index.
+    /// Panics if the index is out of bounds.
+    pub fn column_by_physical_idx(&self, idx: usize) -> &[T] {
+        self.matrix.column(idx)
+    }
+
+    /// Returns a mutable slice of the specified column's data by name.
     /// Panics if the column name is not found.
     pub fn column_mut(&mut self, name: &str) -> &mut [T] {
         let idx = self
@@ -334,6 +340,12 @@ impl<T: Clone + PartialEq> Frame<T> {
         self.matrix.column_mut(idx)
     }
 
+    /// Returns a mutable slice of the specified column's data by its physical index.
+    /// Panics if the index is out of bounds.
+    pub fn column_mut_by_physical_idx(&mut self, idx: usize) -> &mut [T] {
+        self.matrix.column_mut(idx)
+    }
+
     // Row access methods
 
     /// Returns an immutable view of the row for the given integer key.

src/lib.rs

@@ -1,5 +1,8 @@
 #![doc = include_str!("../README.md")]
 
+/// Documentation for the [`crate::dataframe`] module.
+pub mod dataframe;
+
 /// Documentation for the [`crate::matrix`] module.
 pub mod matrix;
 

src/matrix/mat.rs

@@ -1028,9 +1028,7 @@ mod tests {
 
     #[test]
     fn test_from_rows_vec() {
-        // Representing:
-        // 1 2 3
-        // 4 5 6
+        // Matrix with rows [1, 2, 3] and [4, 5, 6]
         let rows_data = vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0];
         let matrix = Matrix::from_rows_vec(rows_data, 2, 3);
 
@@ -1042,19 +1040,14 @@ mod tests {
 
     // Helper function to create a basic Matrix for testing
     fn static_test_matrix() -> Matrix<i32> {
-        // Column-major data:
-        // 1 4 7
-        // 2 5 8
-        // 3 6 9
+        // Column-major data representing a 3x3 matrix of sequential integers
         let data = vec![1, 2, 3, 4, 5, 6, 7, 8, 9];
         Matrix::from_vec(data, 3, 3)
     }
 
     // Another helper for a different size
     fn static_test_matrix_2x4() -> Matrix<i32> {
-        // Column-major data:
-        // 1 3 5 7
-        // 2 4 6 8
+        // Column-major data representing a 2x4 matrix of sequential integers
         let data = vec![1, 2, 3, 4, 5, 6, 7, 8];
         Matrix::from_vec(data, 2, 4)
     }
@@ -1132,10 +1125,7 @@ mod tests {
 
     #[test]
     fn test_from_cols_basic() {
-        // Representing:
-        // 1 4 7
-        // 2 5 8
-        // 3 6 9
+        // Matrix with columns forming a 3x3 sequence
         let cols_data = vec![vec![1, 2, 3], vec![4, 5, 6], vec![7, 8, 9]];
         let matrix = Matrix::from_cols(cols_data);
 
@@ -1512,8 +1502,7 @@ mod tests {
 
         // Delete the first row
         matrix.delete_row(0);
-        // Should be:
-        // 3 6 9
+        // Resulting data should be [3, 6, 9]
         assert_eq!(matrix.rows(), 1);
         assert_eq!(matrix.cols(), 3);
         assert_eq!(matrix.data(), &[3, 6, 9]);

src/matrix/seriesops.rs

@@ -215,20 +215,13 @@ mod tests {
 
     // Helper function to create a FloatMatrix for SeriesOps testing
     fn create_float_test_matrix() -> FloatMatrix {
-        // 3x3 matrix (column-major) with some NaNs
-        // 1.0  4.0  7.0
-        // 2.0  NaN  8.0
-        // 3.0  6.0  NaN
+        // 3x3 column-major matrix containing a few NaN values
         let data = vec![1.0, 2.0, 3.0, 4.0, f64::NAN, 6.0, 7.0, 8.0, f64::NAN];
         FloatMatrix::from_vec(data, 3, 3)
     }
 
     fn create_float_test_matrix_4x4() -> FloatMatrix {
-        // 4x4 matrix (column-major) with some NaNs
-        // 1.0  5.0  9.0  13.0
-        // 2.0  NaN  10.0 NaN
-        // 3.0  6.0  NaN  14.0
-        // NaN  7.0  11.0 NaN
+        // 4x4 column-major matrix with NaNs inserted at positions where index % 5 == 0
         // first make array with 16 elements
         FloatMatrix::from_vec(
             (0..16)