Description Usage Arguments Details Value Examples
This function builds a feature matrix for a specific subset of features, e.g. labs/visits/observations/drug exposures. Returns a feature matrix with all features from all patients included.
1 | convertFeatVecPortion(featuresType, key, labIndic)
|
featuresType |
A set of patient data in the form of a list of data frames. Each data frame contains a pid to label the patient, the names of the features that the patient had present, and the frequency counts of these features in his/her record |
key |
String descriptor of type of feature (e.g. "obs:" or "visit:"). This will be used to label the feature |
labIndic=0 |
Whether this is for a lab feature. If so, must be converted from factor to numeric. Default is 0=no conversion required; 1=conversion required. |
This function takes a list of patient data frames as input. Each patient's data frame contains the features that this patient has present in his/her record. This function flattens this information into the combined feature matrix, with all features (of a certain type - e.g. labs or visits) from all patients included. Clearly, many patients will not have data for many features; their feature counts for any feature that was not present in their record will be set as 0.
An data frame of (pts) x (features of input type)
1 2 3 4 5 6 7 8 9 10 | ## Not run:
FV_converted<-convertFeatVecPortion(featuresType, 'obs:')
#OR
FV_converted<-convertFeatVecPortion(featuresType, 'labs:', labIndic=1)
## End(Not run)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.