dilipbobby

from pyspark import SparkContext, SparkConf
from pyspark.sql import SQLContext

conf = SparkConf()
conf.setMaster("local[4]")
conf.setAppName("Spark Cassandra")
conf.set("spark.cassandra.connection.host","127.0.0.1")

sc = SparkContext(conf=conf)
sqlContext = SQLContext(sc)

dilipbobby

print("hello")

dilipbobby

import json
import numpy as np
import keras
import keras.preprocessing.text as kpt
from keras.preprocessing.text import Tokenizer
from keras.models import model_from_json

# we're still going to use a Tokenizer here, but we don't need to fit it
tokenizer = Tokenizer(num_words=3000)
# for human-friendly printing

dilipbobby

print("hello")

dilipbobby

public class MySplit {

    public static String[] mySplit(String text, String delimiter) {
        java.util.List<String> parts = new java.util.ArrayList<String>();

        text += delimiter;

        for (int i = text.indexOf(delimiter), j=0; i != -1;) {
            String temp = text.substring(j,i);
            if(temp.trim().length() != 0) {

dilipbobby

import com.datumbox.framework.common.Configuration;
import com.datumbox.framework.common.dataobjects.Dataframe;
import com.datumbox.framework.common.dataobjects.Record;
import com.datumbox.framework.core.machinelearning.classification.SoftMaxRegression;
import com.datumbox.framework.core.machinelearning.topicmodeling.LatentDirichletAllocation;
import com.datumbox.framework.core.utilities.text.extractors.UniqueWordSequenceExtractor;

import java.io.UncheckedIOException;