run_performance: Apply calculate performance metrics for model evaluation

In choonghyunryu/alookr: Model Classifier for Binary Classification

Apply calculate performance metrics for model evaluation

Description

Apply calculate performance metrics for binary classification model evaluation.

Usage

run_performance(model, actual = NULL)

Arguments

model	A model_df. results of predicted model that created by run_predict().
actual	factor. A data of target variable to evaluate the model. It supports factor that has binary class.

Details

run_performance() is performed in parallel when calculating the performance evaluation index. However, it is not supported in MS-Windows operating system and RStudio environment.

Value

model_df. results of predicted model. model_df is composed of tbl_df and contains the following variables.:

• step : character. The current stage in the model fit process. The result of calling run_performance() is returned as "3.Performanced".

• model_id : character. Type of fit model.

• target : character. Name of target variable.

• positive : character. Level of positive class of binary classification.

• fitted_model : list. Fitted model object.

• predicted : list. Predicted value by individual model. Each value has a predict_class class object.

• performance : list. Calculate metrics by individual model. Each value has a numeric vector.

The performance metrics calculated are as follows.:

• ZeroOneLoss : Normalized Zero-One Loss(Classification Error Loss).

• Accuracy : Accuracy.

• Precision : Precision.

• Recall : Recall.

• Sensitivity : Sensitivity.

• Specificity : Specificity.

• F1_Score : F1 Score.

• Fbeta_Score : F-Beta Score.

• LogLoss : Log loss / Cross-Entropy Loss.

• AUC : Area Under the Receiver Operating Characteristic Curve (ROC AUC).

• Gini : Gini Coefficient.

• PRAUC : Area Under the Precision-Recall Curve (PR AUC).

• LiftAUC : Area Under the Lift Chart.

• GainAUC : Area Under the Gain Chart.

• KS_Stat : Kolmogorov-Smirnov Statistic.

Examples

library(dplyr)

# Divide the train data set and the test data set.
sb <- rpart::kyphosis %>%
  split_by(Kyphosis)

# Extract the train data set from original data set.
train <- sb %>%
  extract_set(set = "train")

# Extract the test data set from original data set.
test <- sb %>%
  extract_set(set = "test")

# Sampling for unbalanced data set using SMOTE(synthetic minority over-sampling technique).
train <- sb %>%
  sampling_target(seed = 1234L, method = "ubSMOTE")

# Cleaning the set.
train <- train %>%
  cleanse

# Run the model fitting.
result <- run_models(.data = train, target = "Kyphosis", positive = "present")
result

# Predict the model. (Case 1)
pred <- run_predict(result, test)
pred

# Calculate performace metrics. (Case 1)
perf <- run_performance(pred)
perf
perf$performance

# Predict the model. (Case 2)
pred <- run_predict(result, test[, -1])
pred

# Calculate performace metrics. (Case 2)
perf <- run_performance(pred, pull(test[, 1]))
perf
perf$performance

# Convert to matrix for compare performace.
sapply(perf$performance, "c")

choonghyunryu/alookr documentation built on Feb. 28, 2024, 3:04 a.m.