ezhulenev

object ServerSparkContext {

  private[this] lazy val _sqlContext = {
    val conf = new SparkConf()
      .setAppName("....")
    val sc = new SparkContext(conf)

    // TODO: Bug in Spark: http://stackoverflow.com/questions/30323212
    val ctx = new HiveContext(sc)
    ctx.setConf("spark.sql.hive.convertMetastoreParquet", "false")

andershammar

%pyspark

import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
import StringIO

def show(p):
    img = StringIO.StringIO()
    p.savefig(img, format='svg')

tomhopper

#' When plotting multiple data series that share a common x axis but different y axes,
#' we can just plot each graph separately. This suffers from the drawback that the shared axis will typically
#' not align across graphs due to different plot margins.
#' One easy solution is to reshape2::melt() the data and use ggplot2's facet_grid() mapping. However, there is
#' no way to label individual y axes.
#' facet_grid() and facet_wrap() were designed to plot small multiples, where both x- and y-axis ranges are
#' shared acros all plots in the facetting. While the facet_ calls allow us to use different scales with
#' the \code{scales = "free"} argument, they should not be used this way.
#' A more robust approach is to the grid package grid.draw(), rbind() and ggplotGrob() to create a grid of 
#' individual plots where the plot axes are properly aligned within the grid.