sample code for pyspark

pyspark_sample.py

from pyspark import SparkContext
from pyspark.sql import HiveContext
from graphframes.examples import Graphs

sc = SparkContext()
sc.setLogLevel("ERROR")
sqlContext = HiveContext(sc)


g = Graphs(sqlContext).friends()  # Get example graph

print('Run PageRank until convergence to tolerance "tol".')
results = g.pageRank(resetProbability=0.15, tol=0.01)

print()
print('# Display resulting pageranks and final edge weights')
print(results.vertices.select("id", "pagerank").show())
print()
print(results.edges.select("src", "dst", "weight").show())
print()

print('# Run PageRank for a fixed number of iterations.')
results2 = g.pageRank(resetProbability=0.15, maxIter=10)
print(results2)
print()

print('# Run PageRank personalized for vertex "a"')
results3 = g.pageRank(resetProbability=0.15, maxIter=10, sourceId="a")
print(results3)
print()