ComeçarComece de graça

Modeling with categorical inputs

For this exercise, you will fit a linear model to the flowers data, to predict Flowers as a function of Time and Intensity.

The model formula fmla that you created in the previous exercise is still available, as is the model matrix mmat.

Este exercício faz parte do curso

Supervised Learning in R: Regression

Ver curso

Instruções do exercício

  • Use fmla and lm to train a linear model that predicts Flowers from Intensity and Time. Assign the model to the variable flower_model.
  • Use summary() to remind yourself of the structure of mmat.
  • Use summary() to examine the flower_model. Do the variables match what you saw in mmat?
  • Use flower_model to predict the number of flowers. Add the predictions to flowers as the column predictions.
  • Fill in the blanks to plot predictions vs. actual flowers (predictions on the x-axis).

Exercício interativo prático

Experimente este exercício completando este código de exemplo.

# flowers is available
str(flowers)

# fmla is available
fmla

# Fit a model to predict Flowers from Intensity and Time : flower_model
flower_model <- ___

# Use summary on mmat to remind yourself of its structure
___

# Use summary to examine flower_model 
___

# Predict the number of flowers on each plant
flowers$predictions <- ___

# Plot predictions vs actual flowers (predictions on x-axis)
ggplot(___, aes(x = ___, y = ___)) + 
  geom_point() +
  geom_abline(color = "blue")
Editar e executar o código