Use glm

glm fits a Generalized Linear Model, similar to R’s glm().

Syntax: glm(formula, data, family...)

Parameters:

  • formula: Symbolic description of model to be fitted, for eg: ResponseVariable ~ Predictor1 + Predictor2. Supported operators: ~, +, -, and .
  • data: Any SparkDataFrame
  • family: String, "gaussian" for linear regression or "binomial" for logistic regression
  • lambda: Numeric, Regularization parameter
  • alpha: Numeric, Elastic-net mixing parameter

Output: MLlib PipelineModel

This tutorial shows how to perform linear and logistic regression on the diamonds dataset.

Load diamonds data and split into training and test sets

require(SparkR)

# Read diamonds.csv dataset as SparkDataFrame
diamonds <- read.df("/databricks-datasets/Rdatasets/data-001/csv/ggplot2/diamonds.csv",
                  source = "com.databricks.spark.csv", header="true", inferSchema = "true")
diamonds <- withColumnRenamed(diamonds, "", "rowID")

# Split data into Training set and Test set
trainingData <- sample(diamonds, FALSE, 0.7)
testData <- except(diamonds, trainingData)

# Exclude rowIDs
trainingData <- trainingData[, -1]
testData <- testData[, -1]

print(count(diamonds))
print(count(trainingData))
print(count(testData))
head(trainingData)

Train a linear regression model using glm()

This section shows how to predict a diamond’s price from its features by training a linear regression model using the training data.

There are mix of categorical features (cut - Ideal, Premium, Very Good…) and continuous features (depth, carat). Under the hood, SparkR automatically performs one-hot encoding of such features so that it does not have to be done manually.

# Family = "gaussian" to train a linear regression model
lrModel <- glm(price ~ ., data = trainingData, family = "gaussian")

# Print a summary of the trained model
summary(lrModel)

Use predict() on the test data to see how well the model works on new data.

Syntax: predict(model, newData)

Parameters:

  • model: MLlib model
  • newData: SparkDataFrame, typically your test set

Output: SparkDataFrame

# Generate predictions using the trained model
predictions <- predict(lrModel, newData = testData)

# View predictions against mpg column
display(select(predictions, "price", "prediction"))

Evaluate the model.

errors <- select(predictions, predictions$price, predictions$prediction, alias(predictions$price - predictions$prediction, "error"))
display(errors)

# Calculate RMSE
head(select(errors, alias(sqrt(sum(errors$error^2 , na.rm = TRUE) / nrow(errors)), "RMSE")))

Train a logistic regression model using glm()

This section shows how to create a logistic regression on the same dataset to predict a diamond’s cut based on some of its features.

Logistic regression in MLlib supports only binary classification. To test the algorithm in this example, subset the data to work with only 2 labels.

# Subset data to include rows where diamond cut = "Premium" or diamond cut = "Very Good"
trainingDataSub <- subset(trainingData, trainingData$cut %in% c("Premium", "Very Good"))
testDataSub <- subset(testData, testData$cut %in% c("Premium", "Very Good"))
# Family = "binomial" to train a logistic regression model
logrModel <- glm(cut ~ price + color + clarity + depth, data = trainingDataSub, family = "binomial")

# Print summary of the trained model
summary(logrModel)
# Generate predictions using the trained model
predictionsLogR <- predict(logrModel, newData = testDataSub)

# View predictions against label column
display(select(predictionsLogR, "label", "prediction"))

Evaluate the model.

errorsLogR <- select(predictionsLogR, predictionsLogR$label, predictionsLogR$prediction, alias(abs(predictionsLogR$label - predictionsLogR$prediction), "error"))
display(errorsLogR)