import findspark
findspark.init()

from pyspark.sql import SparkSession

# Connect to Remote Spark Deployment
# spark = SparkSession \
#     .builder.master('spark://master-node:7077') \
#     .appName("read-csv") \
#     .getOrCreate()

spark = SparkSession \
    .builder \
    .appName("read-csv") \
    .getOrCreate()
    
df = spark.read.option("header",True).csv('./csv-file.csv')

type(df)
df.printSchema()
# df.show(10,False)
df.dtypes