Added pairRdd/filter/*.py

Author: Pedro Bernardo

pairRdd/filter/AirportsNotInUsaProblem.py

@@ -0,0 +1,20 @@
+from pyspark import SparkContext
+
+if __name__ == "__main__":
+
+    '''
+    Create a Spark program to read the airport data from in/airports.text;
+    generate a pair RDD with airport name being the key and country name being the value.
+    Then remove all the airports which are located in United States and output the pair RDD to out/airports_not_in_usa_pair_rdd.text
+
+    Each row of the input file contains the following columns:
+    Airport ID, Name of airport, Main city served by airport, Country where airport is located,
+    IATA/FAA code, ICAO Code, Latitude, Longitude, Altitude, Timezone, DST, Timezone in Olson format
+
+    Sample output:
+
+    ("Kamloops", "Canada")
+    ("Wewak Intl", "Papua New Guinea")
+    ...
+
+    '''

pairRdd/filter/AirportsNotInUsaSolution.py

@@ -0,0 +1,16 @@
+from pyspark import SparkContext
+from commons.Utils import Utils
+
+if __name__ == "__main__":
+
+    sc = SparkContext("local", "airports")
+    sc.setLogLevel("ERROR")
+
+    airportsRDD = sc.textFile("in/airports.text")
+
+    airportPairRDD = airportsRDD.map(lambda line: \
+        (Utils.COMMA_DELIMITER.split(line)[1],
+         Utils.COMMA_DELIMITER.split(line)[3]))
+    airportsNotInUSA = airportPairRDD.filter(lambda keyValue: keyValue[1] != "\"United States\"")
+
+    airportsNotInUSA.saveAsTextFile("out/airports_not_in_usa_pair_rdd.text")