It estimates a group of metrics characterizing the prediction performance for a continuous (regression) or categorical (classification) predicted-observed dataset. By default, it calculates all available metrics for either regression or classification.
Usage
metrics_summary(
data = NULL,
obs,
pred,
type = NULL,
metrics_list = NULL,
orientation = "PO",
pos_level = 2,
na.rm = TRUE
)Arguments
- data
argument to call an existing data frame containing the data (optional).
- obs
vector with observed values (numeric).
- pred
vector with predicted values (numeric).
- type
argument of class string specifying the type of model. For continuous variables use type = 'regression'. For categorical variables use type = 'classification'.
- metrics_list
vector or list of specific selected metrics. Default is = NULL, which will estimate all metrics available for either regression or classification.
- orientation
argument of class string specifying the axis orientation to estimate slope(B1) and intercept(B0). It only applies when type = "regression". "PO" is for predicted vs observed, and "OP" for observed vs predicted. Default is orientation = "PO".
- pos_level
(for classification only). Integer, for binary cases, indicating the order (1|2) of the level corresponding to the positive. Generally, the positive level is the second (2) since following an alpha-numeric order, the most common pairs are
(Negative | Positive),(0 | 1),(FALSE | TRUE). Default : 2.- na.rm
Logic argument to remove rows with missing values (NA). Default is na.rm = TRUE.
Details
The user can choose to calculate a single metric, or to calculate all metrics at once.
This function creates a data.frame with all (or selected) metrics in the metrica-package.
If looking for specific metrics, the user can pass a list of desired metrics using the
argument “metrics_list” (e.g. metrics_list = c("R2","MAE", "RMSE", "RSR", "NSE", "KGE")).
For the entire list of available metrics with formula,
see online-documentation
Examples
# \donttest{
# Continuous variable (regression)
X <- rnorm(n = 100, mean = 0, sd = 10)
Y <- rnorm(n = 100, mean = 0, sd = 10)
regression_case <- data.frame(obs = X, pred = Y)
# Get a metrics summary for a regression problem
metrics_summary(regression_case, obs = X, pred = Y, type = "regression")
#> Metric Score
#> 1 B0 2.261092e+00
#> 2 B1 9.823083e-01
#> 3 r 3.057903e-02
#> 4 R2 9.350771e-04
#> 5 Xa 9.720574e-01
#> 6 CCC 2.972457e-02
#> 7 MAE 1.094530e+01
#> 8 RMAE -1.017724e+01
#> 9 MAPE -2.233993e+01
#> 10 SMAPE 1.497724e+02
#> 11 RAE 1.452330e+00
#> 12 RSE 1.961015e+00
#> 13 MBE -2.280119e+00
#> 14 PBE 2.120118e+02
#> 15 PAB 2.863901e+00
#> 16 PPB 1.596094e-02
#> 17 MSE 1.815336e+02
#> 18 RMSE 1.347344e+01
#> 19 RRMSE -1.252798e+01
#> 20 RSR 1.455467e-01
#> 21 iqRMSE 1.061780e+00
#> 22 MLA 5.227917e+00
#> 23 MLP 1.763057e+02
#> 24 RMLA 5.227917e+00
#> 25 RMLP 1.763057e+02
#> 26 SB 5.198943e+00
#> 27 SDSD 2.897447e-02
#> 28 LCS 1.763057e+02
#> 29 PLA 2.879862e+00
#> 30 PLP 9.712014e+01
#> 31 Ue 9.712014e+01
#> 32 Uc 1.596094e-02
#> 33 Ub 2.863901e+00
#> 34 NSE -9.610150e-01
#> 35 E1 -4.523297e-01
#> 36 Erel 7.188393e-01
#> 37 KGE -1.992940e+00
#> 38 d 4.208294e-01
#> 39 d1 2.782443e-01
#> 40 d1r 2.738352e-01
#> 41 RAC 5.080269e-01
#> 42 AC -8.388534e-01
#> 43 lambda 2.972457e-02
#> 44 dcorr 1.374032e-01
#> 45 MIC 1.911684e-01
# Categorical variable (classification)
binomial_case <- data.frame(labels = sample(c("True","False"), 100,
replace = TRUE), predictions = sample(c("True","False"), 100, replace = TRUE))
#' # Get a metrics summary for a regression problem
metrics_summary(binomial_case, obs = labels, pred = predictions,
type = "classification")
#> Metric Score
#> 1 accuracy 0.48000000
#> 2 error_rate 0.52000000
#> 3 precision 0.45098039
#> 4 recall 0.48936170
#> 5 specificity 0.47169811
#> 6 balacc 0.48052991
#> 7 fscore 0.46938776
#> 8 agf 0.49147938
#> 9 gmean 0.48044874
#> 10 khat -0.03875350
#> 11 mcc -0.03887781
#> 12 fmi 0.46977924
#> 13 bmi -0.03894018
#> 14 csi 0.30263158
#> 15 deltap -0.03881553
#> 16 posLr 0.92629179
#> 17 negLr 1.08255319
#> 18 dor 0.85565476
#> 19 npv 0.51020408
#> 20 FPR 0.52830189
#> 21 FNR 0.51063830
#> 22 FDR 0.54901961
#> 23 FOR 0.48979592
#> 24 preval 0.47000000
#> 25 preval_t 0.49540479
#> 26 AUC_roc 0.47035256
#> 27 p4 0.47956631
# }