31 März 2017

The Training Data Application

There is a training data set with different sports over a period of several years. The data contains beyond other information the sport, the distance, the duration and the difference in altitude per excercise.

I'm interessted in getting a linear function to estimate the duration as a function of the distance per sport. The application allows to select input parameters and then shows a plot of the data and a regression line throuh zero with its standard confidence zone.

The possible input is the sport and a limitation of the difference in altitude to find out, how this difference has an influence on the time per kilometer.

The columns of the training data

##  [1] "Id"            "Date"          "Start"         "Duration"     
##  [5] "Heartrate.Avg" "Heartrate.Max" "KM"            "Distance.Name"
##  [9] "Speed.Avg"     "Speed.Max"     "HM"            "Cad.Avg"      
## [13] "Cad.Max"       "Power.Avg"     "Power.Max"     "Sport"        
## [17] "Zone"          "BORG"          "Material"      "Calories"     
## [21] "Temp.C"        "Weather"       "Wind"          "X"            
## [25] "Year"          "Month"         "Skate.technic"

Plot of all Durations and Distances in the Data Base

Screenshot of the application