conda create -n pyspark2.4 python=3.7
activate pyspark2.4
pip install py4j
pip install psutil

系統(tǒng)變量添加
HADOOP_HOME
E:\bigdata\ENV\hadoop-3.0.0
 
SPARK_HOME
E:\bigdata\ENV\spark-2.4.4-bin-without-hadoop
 
PYSPARK_PYTHON
C:\Users\zakza\anaconda3\envs\pyspark2.4\python.exe
 
PATH添加
%HADOOP_HOME%\bin
%SPARK_HOME%\bin

FOR /F %%i IN ('hadoop classpath') DO @set SPARK_DIST_CLASSPATH=%%i

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
 
# Set everything to be logged to the console
log4j.rootCategory=WARN, console
log4j.appender.console=org.apache.log4j.ConsoleAppender
log4j.appender.console.target=System.err
log4j.appender.console.layout=org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
 
# Set the default spark-shell log level to WARN. When running the spark-shell, the
# log level for this class is used to overwrite the root logger's log level, so that
# the user can have different defaults for the shell and regular Spark apps.
log4j.logger.org.apache.spark.repl.Main=WARN
 
# Settings to quiet third party logs that are too verbose
log4j.logger.org.spark_project.jetty=WARN
log4j.logger.org.spark_project.jetty.util.component.AbstractLifeCycle=ERROR
log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
log4j.logger.org.apache.parquet=ERROR
log4j.logger.parquet=ERROR
 
# SPARK-9183: Settings to avoid annoying messages when looking up nonexistent UDFs in SparkSQL with Hive support
log4j.logger.org.apache.hadoop.hive.metastore.RetryingHMSHandler=FATAL
log4j.logger.org.apache.hadoop.hive.ql.exec.FunctionRegistry=ERROR

hello hadoop
hadoop spark python
flink storm spark
master slave
first
second thrid
kafka scikit-learn
flume
hive spark-streaming
hbase

from pyspark import SparkContext
 
if __name__ == '__main__':
    sc = SparkContext('local', 'WordCount')
    textFile = sc.textFile("wc.txt")
    wordCount = textFile.flatMap(lambda line: line.split(" ")).map(lambda word: (word, 1)).reduceByKey(
        lambda a, b: a + b)
    wordCount.foreach(print)