CoOL_0_working_example {CoOL}

CoOL working example with sex, drug A, and drug B

Description

To reproduce the CoOL working example with sex, drug A, and drug B.

Usage

CoOL_0_working_example(n)

Arguments

n

number of observations for the synthetic data.

Value

A data frame with the columns Y, sex, drug_a, drug_b and rows equal to n.

References

Rieckmann, Dworzynski, Arras, Lapuschkin, Samek, Arah, Rod, Ekstrom. 2022. Causes of outcome learning: A causal inference-inspired machine learning approach to disentangling common combinations of potential causes of a health outcome. International Journal of Epidemiology <https://doi.org/10.1093/ije/dyac078>

Examples

	while (FALSE) {
 library(CoOL)
 set.seed(1)
 data <- CoOL_0_working_example(n=10000)
 outcome_data <- data[,1]
 exposure_data <- data[,-1]
 exposure_data <- CoOL_0_binary_encode_exposure_data(exposure_data)
 model <- CoOL_1_initiate_neural_network(inputs=ncol(exposure_data),
 output = outcome_data,hidden=5)
 model <- CoOL_2_train_neural_network(lr = 1e-4,X_train=exposure_data,
 Y_train=outcome_data,X_test=exposure_data, Y_test=outcome_data,
 model=model, epochs=1000,patience = 200, input_parameter_reg = 1e-3
 ) # Train the non-negative model (The model can be retrained)
 model <- CoOL_2_train_neural_network(lr = 1e-5,X_train=exposure_data,
 Y_train=outcome_data,X_test=exposure_data, Y_test=outcome_data, model=model,
 epochs=1000,patience = 100, input_parameter_reg = 1e-3)
 # Train the non-negative model (The model can be retrained)
 model <- CoOL_2_train_neural_network(lr = 1e-6,X_train=exposure_data,
 Y_train=outcome_data,X_test=exposure_data, Y_test=outcome_data, model=model,
 epochs=1000,patience = 50, input_parameter_reg = 1e-3
 ) # Train the non-negative model (The model can be retrained)
 plot(model$train_performance,type='l',yaxs='i',ylab="Mean squared error",
 xlab="Epochs",main="A) Performance during training\n\n",
 ylim=quantile(model$train_performance,c(0,.975))) # Model performance
 CoOL_3_plot_neural_network(model,names(exposure_data),5/max(model[[1]]),
 title = "B) Model connection weights\nand intercepts") # Model visualization
 CoOL_4_AUC(outcome_data,exposure_data,model,
 title = "C) Receiver operating\ncharacteristic curve") # AUC
 risk_contributions <- CoOL_5_layerwise_relevance_propagation(exposure_data,model
 ) # Risk contributions
 CoOL_6_number_of_sub_groups(risk_contributions = risk_contributions,
 low_number = 1, high_number = 5)
 CoOL_6_dendrogram(risk_contributions,number_of_subgroups = 3,
 title = "D) Dendrogram with 3 sub-groups") # Dendrogram
 sub_groups <- CoOL_6_sub_groups(risk_contributions,number_of_subgroups = 3
 ) # Assign sub-groups
 CoOL_6_calibration_plot(exposure_data = exposure_data,
 outcome_data = outcome_data, model = model, sub_groups = sub_groups)
 CoOL_7_prevalence_and_mean_risk_plot(risk_contributions,sub_groups,
 title = "E) Prevalence and mean risk of sub-groups") # Prevalence and mean risk plot
 results <- CoOL_8_mean_risk_contributions_by_sub_group(risk_contributions,
 sub_groups,outcome_data = outcome_data,exposure_data = exposure_data,
 model=model,exclude_below = 0.01) #  Mean risk contributions by sub-groups
	CoOL_9_visualised_mean_risk_contributions(results = results,  sub_groups = sub_groups)
	CoOL_9_visualised_mean_risk_contributions_legend(results = results)
	}