Back to normal

data/books.csv

@@ -0,0 +1,23 @@
+id,authorId,title,releaseDate,link
+1,1,Fantastic Beasts and Where to Find Them: The Original Screenplay,11/18/16,http://amzn.to/2kup94P
+2,1,"Harry Potter and the Sorcerer's Stone: The Illustrated Edition (Harry Potter, Book 1)",10/6/15,http://amzn.to/2l2lSwP
+3,1,"The Tales of Beedle the Bard, Standard Edition (Harry Potter)",12/4/08,http://amzn.to/2kYezqr
+4,1,"Harry Potter and the Chamber of Secrets: The Illustrated Edition (Harry Potter, Book 2)",10/4/16,http://amzn.to/2kYhL5n
+5,2,"Informix 12.10 on Mac 10.12 with a dash of Java 8: The Tale of the Apple, the Coffee, and a Great Database",4/23/17,http://amzn.to/2i3mthT
+6,2,"Development Tools in 2006: any Room for a 4GL-style Language?: An independent study by Jean Georges Perrin, IIUG Board Member",12/28/16,http://amzn.to/2vBxOe1
+7,3,Adventures of Huckleberry Finn,5/26/94,http://amzn.to/2wOeOav
+8,3,A Connecticut Yankee in King Arthur's Court,6/17/17,http://amzn.to/2x1NuoD
+10,4,Jacques le Fataliste,3/1/00,http://amzn.to/2uZj2KA
+11,4,Diderot Encyclopedia: The Complete Illustrations 1762-1777,,http://amzn.to/2i2zo3I
+12,,A Woman in Berlin,7/11/06,http://amzn.to/2i472WZ
+13,6,Spring Boot in Action,1/3/16,http://amzn.to/2hCPktW
+14,6,Spring in Action: Covers Spring 4,11/28/14,http://amzn.to/2yJLyCk
+15,7,Soft Skills: The software developer's life manual,12/29/14,http://amzn.to/2zNnSyn
+16,8,Of Mice and Men,,http://amzn.to/2zJjXoc
+17,9,"Java 8 in Action: Lambdas, Streams, and functional-style programming",8/28/14,http://amzn.to/2isdqoL
+18,12,Hamlet,6/8/12,http://amzn.to/2yRbewY
+19,13,Pensées,12/31/1670,http://amzn.to/2jweHOG
+20,14,"Fables choisies, mises en vers par M. de La Fontaine",9/1/1999,http://amzn.to/2yRH10W
+21,15,Discourse on Method and Meditations on First Philosophy,6/15/1999,http://amzn.to/2hwB8zc
+22,12,Twelfth Night,7/1/4,http://amzn.to/2zPYnwo
+23,12,Macbeth,7/1/3,http://amzn.to/2zPYnwo

src/main/java/net/jgp/books/spark/ch01/lab100_csv_to_dataframe/CsvToDataframeApp.java

@@ -0,0 +1,43 @@
+package net.jgp.books.spark.ch01.lab100_csv_to_dataframe;
+
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+/**
+ * CSV ingestion in a dataframe.
+ * 
+ * @author jgp
+ */
+public class CsvToDataframeApp {
+
+  /**
+   * main() is your entry point to the application.
+   * 
+   * @param args
+   */
+  public static void main(String[] args) {
+    CsvToDataframeApp app = new CsvToDataframeApp();
+    app.start();
+  }
+
+  /**
+   * The processing code.
+   */
+  private void start() {
+    // Creates a session on a local master
+    SparkSession spark = SparkSession.builder()
+        .appName("CSV to Dataset")
+        .master("local")
+        .getOrCreate();
+
+    // Reads a CSV file with header, called books.csv, stores it in a
+    // dataframe
+    Dataset<Row> df = spark.read().format("csv")
+        .option("header", "true")
+        .load("data/books.csv");
+
+    // Shows at most 5 rows from the dataframe
+    df.show(5);
+  }
+}

src/main/python/lab100_csv_to_dataframe/csvToDataframeApp.py

@@ -0,0 +1,22 @@
+"""
+CsvToDataframeApp.py - CSV ingestion in a dataframe.
+@author rambabu.posa
+"""
+from pyspark.sql import SparkSession
+import os
+
+current_dir = os.path.dirname(__file__)
+relative_path = "../../../../data/books.csv"
+absolute_file_path = os.path.join(current_dir, relative_path)
+
+# Creates a session on a local master
+session = SparkSession.builder.appName("CSV to Dataset").master("local[*]").getOrCreate()
+
+# Reads a CSV file with header, called books.csv, stores it in a dataframe
+df = session.read.csv(header=True, inferSchema=True, path=absolute_file_path)
+
+# Shows at most 5 rows from the dataframe
+df.show(5)
+
+# Good to stop SparkSession at the end of the application
+session.stop()

src/main/scala/net/jgp/books/spark/ch01/lab100_csv_to_dataframe/CsvToDataframeScalaApp.scala

@@ -0,0 +1,37 @@
+package net.jgp.books.spark.ch01.lab100_csv_to_dataframe
+
+import org.apache.spark.sql.SparkSession
+
+/**
+  * CSV ingestion in a dataframe.
+  *
+  * @author rambabu.posa
+  */
+object CsvToDataframeScalaApp {
+
+  /**
+    * main() is your entry point to the application.
+    *
+    * @param args
+    */
+  def main(args: Array[String]): Unit = {
+
+    // Creates a session on a local master
+    val spark = SparkSession.builder
+                            .appName("CSV to Dataset")
+                            .master("local[*]")
+                            .getOrCreate
+
+    // Reads a CSV file with header, called books.csv, stores it in a dataframe
+    val df = spark.read.format("csv")
+                       .option("header", "true")
+                       .load("data/books.csv")
+
+    // Shows at most 5 rows from the dataframe
+    df.show(5)
+
+    // Good to stop SparkSession at the end of the application
+    spark.stop
+  }
+
+}