from pyspark.sql import SparkSession
spark=SparkSession.builder.appName('creditcard_data_processing').getOrCreate()

fn = "SYB62_123_201907_Total.csv"
df=spark.read.csv(fn,header=True,inferSchema=True)
df.sample(False,0.1,seed=250.0).limit(5).select('_c1','Series','Value').show(truncate=False)

+-----------------------------+------------------------------------------------+--------------+
|_c1                          |Series                                          |Value         |
+-----------------------------+------------------------------------------------+--------------+
|Total, all countries or areas|Exports FOB (millions of US dollars)            |5050237.9273  |
|Total, all countries or areas|Exports FOB (millions of US dollars)            |1.5843502717E7|
|Africa                       |Exports FOB (millions of US dollars)            |397465.322    |
|Africa                       |Balance imports/exports (millions of US dollars)|-10892.3263   |
|Eastern Africa               |Exports FOB (millions of US dollars)            |44536.6955    |
+-----------------------------+------------------------------------------------+--------------+