join_eda_bin: Join EDA Binary Classifier Output to Dataset

In PCdLf/e4tools: Tools to Read and Convert Wearables Data

Join EDA Binary Classifier Output to Dataset

Description

This function joins the output of an EDA binary classifier to a dataset based on rounded 5-second intervals. It is designed to merge two data frames: one containing your main data and another containing EDA binary classifier predictions. The function ensures that each record in the main data is matched with the appropriate classifier output by aligning timestamps to the nearest 5-second interval.

Usage

join_eda_bin(data, eda_bin)

Arguments

data	A data frame containing the main dataset with a 'DateTime' column that represents timestamps.
eda_bin	A data frame containing the EDA binary classifier outputs, including an 'id' column that represents timestamps. This data frame is expected to merge with the main data frame based on these timestamps.

Details

The function first uses 'padr::thicken' to extend the main data frame by creating a new column 'DateTime_5_sec', which rounds the 'DateTime' values to 5-second intervals. Then, it performs a left join with the EDA binary classifier data, which has been similarly adjusted using 'lubridate::floor_date' to match these intervals. After the join, unnecessary columns ('DateTime_5_sec' and 'id') are dropped, and the classifier's 'label' column is renamed to 'quality_flag'.

Value

A data frame that combines the main dataset with the EDA binary classifier outputs. The classifier's label is renamed to 'quality_flag'. In cases where a precise match for the 5-second interval is not found in the classifier output, NA values may be introduced in the 'quality_flag' column.

Examples

## Not run: 
  main_data <- data.frame(DateTime = as.POSIXct(...), ...)
  classifier_data <- data.frame(id = as.POSIXct(...), label = ..., ...)
  joined_data <- join_eda_bin(main_data, classifier_data)

## End(Not run)

PCdLf/e4tools documentation built on Nov. 19, 2024, 5:56 p.m.