yaravind

import org.apache.spark.mllib.clustering.BisectingKMeans
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.linalg.Vector

//std_features col is of type vector
scaledFeatures.select($"std_features").printSchema()

val tempFeatureRdd = scaledFeatures.select($"std_features").rdd

import scala.reflect.runtime.universe._

yaravind

from pyspark.sql import SparkSession
from pyspark.sql.functions import *
from pyspark.sql import Row
from pyspark.sql.types import IntegerType

# Create the Spark session
spark = SparkSession.builder \
    .master("local") \
    .config("spark.sql.autoBroadcastJoinThreshold", -1) \
    .config("spark.executor.memory", "500mb") \

yaravind

import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.PipelineStage
import org.apache.spark.ml.Transformer
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.ml.linalg.DenseVector
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.Row

yaravind

package com.diorsding.spark.ml;

import java.util.Arrays;
import java.util.List;

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.ml.Pipeline;
import org.apache.spark.ml.PipelineModel;
import org.apache.spark.ml.PipelineStage;

yaravind

import java.util.Arrays;
import java.util.List;

import org.apache.hadoop.yarn.webapp.hamlet.HamletSpec.P;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.ml.Pipeline;
import org.apache.spark.ml.PipelineModel;
import org.apache.spark.ml.PipelineStage;

yaravind

import org.apache.spark.sql.functions._
import org.apache.spark.sql.SparkSession

object DataFrameWithFileNameApp extends App {
  
  val spark: SparkSession =
    SparkSession
      .builder()
      .appName("DataFrameApp")
      .config("spark.master", "local[*]")

yaravind

# Root logger option
log4j.rootLogger=INFO, stdout

# Redirect log messages to console
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.Target=System.out
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{ISO8601} %-5p %t %c:%L - %m%n

log4j.com.ncr.eda=INFO, stdout

yaravind

:paste

import org.apache.spark.sql.types._
import com.databricks.spark.xml._
import org.apache.spark.sql.functions._
// For implicit conversions like converting RDDs to DataFrames
import spark.implicits._

yaravind

# Custom history configuration
# Run script using:
# chmod u+x better_history.sh
# sudo su
# ./better_history.sh

echo ">>> Starting"
echo ">>> Loading configuration into /etc/bash.bashrc"
echo "HISTTIMEFORMAT='%F %T '" >> /etc/bash.bashrc
echo 'HISTFILESIZE=-1' >> /etc/bash.bashrc

yaravind

[alias]
	co = checkout
	cob = checkout -b
	coo = !git fetch && git checkout
	br = branch
	brd = branch -d
	brD = branch -D
	merged = branch --merged
	dmerged = "git branch --merged | grep -v '\\*' | xargs -n 1 git branch -d"
	st = status