Regression model evaluation metrics. More...
Include dependency graph for dmlfw_model_accuracy_score.h:
This graph shows which files directly or indirectly include this file:
Go to the source code of this file.
Functions | |
| double | dmlfw_get_r2_score (dmlfw_column_vec_double *target_values_vector, dmlfw_column_vec_double *predicted_values_vector) |
| Computes the R2 (coefficient of determination) score for regression. | |
Detailed Description
Regression model evaluation metrics.
- Version
- 1.0
- Date
- 2025-09-25
This header provides functions to evaluate the accuracy of regression models using numerical metrics such as the R2 score (coefficient of determination).
Error Handling:
Functions validate inputs, check vector sizes, allocate necessary temporaries, and set errors on failure. After calling, check dmlfw_error() and use dmlfw_get_error_string() and dmlfw_get_debug_string() for diagnostics.
Ownership:
Input vectors are owned by the caller; temporary allocations are freed internally. Returned scores are scalars.
Function Documentation
◆ dmlfw_get_r2_score()
| double dmlfw_get_r2_score | ( | dmlfw_column_vec_double * | target_values_vector, |
| dmlfw_column_vec_double * | predicted_values_vector | ||
| ) |
Computes the R2 (coefficient of determination) score for regression.
The R2 score is calculated as:
![\[
R^2 = 1 - \frac{\sum_i (y_i - \hat{y}_i)^2}{\sum_i (y_i - \bar{y})^2}
\]](form_0_dark.png)
- Parameters
-
target_values_vector [in] Pointer to true target value vector (non-NULL). predicted_values_vector [in] Pointer to predicted value vector (non-NULL).
- Returns
- R2 score as double. Returns 0.0 and sets an appropriate error if inputs are invalid or computation fails.
- Note
- Input vectors must be the same size.
- Caller retains ownership of input vectors.
Usage:
dmlfw_column_vec_double *target = ...; // Initialized true values
dmlfw_column_vec_double *predicted = ...;// Initialized predictions
double r2 = dmlfw_get_r2_score(target, predicted);
if (dmlfw_error()) {
char err[512], dbg[512];
dmlfw_get_error_string(err, sizeof(err));
dmlfw_get_debug_string(dbg, sizeof(dbg));
printf("Error computing R2 score: %s\nDebug info: %s\n", err, dbg);
}
printf("R2 score: %lf\n", r2);
void dmlfw_get_error_string(char *error_string, uint32_t size)
Copies the last error message into the provided character buffer.
void dmlfw_get_debug_string(char *debug_string, uint32_t size)
Copies detailed debug information about the last error into the provided character buffer.
double dmlfw_get_r2_score(dmlfw_column_vec_double *target_values_vector, dmlfw_column_vec_double *predicted_values_vector)
Computes the R2 (coefficient of determination) score for regression.
struct __dmlfw_column_vec_double dmlfw_column_vec_double
Opaque structure representing a column vector of doubles.
Definition dmlfw_vec_double.h:83
- Examples
- example_dmlfw_model_accuracy_score.c.
