1.从github上下载graphframes包,或者从链接下载:https://download.csdn.net/download/weixin_42247685/10591772
2.解压后将graphframes-master\python下的graphframes文件夹拷贝到python/Lib/site-packages文件下。
3.在python中输入import graphframes ,查看是否正常。
示例代码:
from graphframes import * from pyspark.sql import SparkSession import os import graphframes #下面这段必须有,否则报错, os.environ["PYSPARK_SUBMIT_ARGS"] = ( "--packages graphframes:graphframes:0.5.0-spark2.1-s_2.11 pyspark-shell" ) sqlContext = SparkSession.builder.appName("Python Spark SQL basic example").config("spark.some.config.option", "some-value").getOrCreate() v = sqlContext.createDataFrame([ ("a", "Alice", 34), ("b", "Bob", 36), ("c", "Charlie", 30), ], ["id", "name", "age"]) # Create an Edge DataFrame with "src" and "dst" columns e = sqlContext.createDataFrame([ ("a", "b", "friend"), ("b", "c", "follow"), ("c", "b", "follow"), ], ["src", "dst", "relationship"]) # Create a GraphFrame g = GraphFrame(v, e) # Query: Get in-degree of each vertex. g.inDegrees.show() # Query: Count the number of "follow" connections in the graph. g.edges.filter("relationship = 'follow'").count() # Run PageRank algorithm, and show results. results = g.pageRank(resetProbability=0.01, maxIter=20) results.vertices.select("id", "pagerank").show()