asw456

//mapper
package com.tistory.devyongsik.hadoop.mapre;
 
import java.io.IOException;
 
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
 

asw456

import java.io.IOException;
import java.nio.ByteBuffer;
import java.util.*;
import org.apache.cassandra.db.IColumn;
import org.apache.cassandra.thrift.*;
import org.apache.cassandra.hadoop.*;
import org.apache.cassandra.utils.ByteBufferUtil;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;

asw456

import theano
from pylearn2.models import mlp
from pylearn2.train_extensions import best_params
from pylearn2.training_algorithms import sgd, learning_rule
from pylearn2.utils import serial
from pylearn2.termination_criteria import MonitorBased
from pylearn2.datasets.dense_design_matrix import DenseDesignMatrix
from sklearn.preprocessing import StandardScaler
import numpy as np
from random import randint

asw456

### MATPLOTLIBRC FORMAT

# This is a sample matplotlib configuration file - you can find a copy
# of it on your system in
# site-packages/matplotlib/mpl-data/matplotlibrc.  If you edit it
# there, please note that it will be overridden in your next install.
# If you want to keep a permanent local copy that will not be
# over-written, place it in HOME/.matplotlib/matplotlibrc (unix/linux
# like systems) and C:\Documents and Settings\yourname\.matplotlib
# (win32 systems).

asw456

import numpy as np
from sklearn.feature_extraction import image
from sklearn.cluster import MiniBatchKMeans
from sklearn import cross_validation, svm, datasets
from sklearn.datasets import fetch_olivetti_faces, fetch_mldata
from matplotlib import pylab as pl

def HIK_kernel(X,Y):
    return np.array([[np.sum(np.minimum(x,y)) for y in Y] for x in X]) 
    

asw456

from scipy.stats import rv_continuous
from scipy.special import gammaln, gammaincinv, gammainc
from numpy import log,exp

class igamma_gen(rv_continuous):
  def _pdf(self, x, a, b):
      return exp(self._logpdf(x,a,b))
  def _logpdf(self, x, a, b):
      return a*log(b) - gammaln(a) -(a+1)*log(x) - b/x
  def _cdf(self, x, a, b):

asw456

Scan scan = new Scan();
scan.setFilter(new MyFilter(appId)); // get only rows for the app with appId
Htable table = new HTable(config, Bytes.UTF8(tableName); // for this table
ResultScanner results = table.getScanner(scan); // apply the scan

asw456

Scan scan = new Scan();
scan.setFilter(new ProxyFilter(new MyFilter(appId)));

asw456

public class ExampleRowKey
{
	long userId;
	String applicationId;
	
	public byte[] getBytes() throws IOException
	{
		ByteArrayOutputStream byteOutput = new ByteArrayOutputStream();
		DataOutputStream data = new DataOutputStream(byteOutput);
		

asw456

********************************
Gist
********************************

Motivation
-----------
The typical mapreduce job creates files with the prefix "part-"..and then the "m" or "r" depending
on whether it is a map or a reduce output, and then the part number.  There are scenarios where we
may want to create separate files based on criteria-data keys and/or values.  Enter the "MultipleOutputs" 
functionality.