# Use the Spark CSV datasource with options specifying:
# - First line of file is a header
# - Automatically infer the schema of the data
data = spark.read.format("csv") 
  .option("header", "true") 
  .option("inferSchema", "true") 
  .load("/databricks-datasets/samples/population-vs-price/data_geo.csv")

data.cache() # Cache data for faster reuse