1.安装spark
2.安装anaconda
3.在Jupyter Notebook中使用pyspark
PYSPARK_DRIVER_PYTHON=ipython PYSPARK_DRIVER_PYTHON_OPTS='notebook --allow-root' pyspark --master local[*]
PYSPARK_DRIVER_PYTHON=ipython PYSPARK_DRIVER_PYTHON_OPTS='notebook --allow-root' pyspark --master spark://master:7077 --num-executors 1 --total-executors-cores 3 --executor-memory 512m