public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String cur_file =
((FileSplit) context.getInputSplit()).getPath().getParent().getParent().getName();
String train_file = context.getConfiguration().get("train_file");
if (cur_file.equals(train_file)) {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
myKey.set(word);
myVal.set(f_id);
context.write(myKey, myVal);
} else {
StringTokenizer st = new StringTokenizer(value.toString());
String word = st.nextToken();
String f_id = st.nextToken();
StringBuilder builder = new StringBuilder(dlt);
while (st.hasMoreTokens()) {
String filename = st.nextToken();
String tf_idf = st.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myKey.set(word);
myVal.set(builder.toString());
context.write(myKey, myVal);
}
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
Text word = new Text();
StringTokenizer s = new StringTokenizer(value.toString());
while (s.hasMoreTokens()) {
word.set(s.nextToken());
context.write(word, one);
}
}
public static List<Double> GetPoint(String s) {
StringTokenizer tokenizer = new StringTokenizer(s);
List<Double> p = new ArrayList<Double>(58);
while (tokenizer.hasMoreTokens()) {
p.add(Double.parseDouble(tokenizer.nextToken()));
}
return p;
}
public static List<InetSocketAddress> readAddresses(Path path, Configuration conf)
throws IOException {
final List<InetSocketAddress> addrs = new ArrayList<InetSocketAddress>();
for (final String line : readConfig(path, conf)) {
final StringTokenizer tokens = new StringTokenizer(line);
if (tokens.hasMoreTokens()) {
final String host = tokens.nextToken();
if (tokens.hasMoreTokens()) {
final String port = tokens.nextToken();
addrs.add(new InetSocketAddress(host, Integer.parseInt(port)));
}
}
}
return addrs;
}
/** Implements the map-method of the Mapper-interface */
@Override
public void map(
LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
String token = tokenizer.nextToken();
if (token.length() > 3) {
word.set(token);
output.collect(word, one);
}
}
}
public List<String> resolve(List<String> names) {
List<String> m = new ArrayList<String>(names.size());
if (names.isEmpty()) {
return m;
}
if (scriptName == null) {
for (int i = 0; i < names.size(); i++) {
m.add(NetworkTopology.DEFAULT_RACK);
}
return m;
}
String output = runResolveCommand(names);
if (output != null) {
StringTokenizer allSwitchInfo = new StringTokenizer(output);
while (allSwitchInfo.hasMoreTokens()) {
String switchInfo = allSwitchInfo.nextToken();
m.add(switchInfo);
}
if (m.size() != names.size()) {
// invalid number of entries returned by the script
LOG.warn(
"Script "
+ scriptName
+ " returned "
+ Integer.toString(m.size())
+ " values when "
+ Integer.toString(names.size())
+ " were expected.");
return null;
}
} else {
// an error occurred. return null to signify this.
// (exn was already logged in runResolveCommand)
return null;
}
return m;
}
public void map(
LongWritable key,
Text value,
OutputCollector<IntWritable, DoubleWritable> output,
Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int rowIdx = 0;
double xValue = 0;
if (tokenizer.hasMoreTokens()) {
rowIdx = Integer.parseInt(tokenizer.nextToken());
xValue = Double.parseDouble(tokenizer.nextToken());
}
double xResult = (resVec[rowIdx] - (sumVec[rowIdx] * xValue)) / diaVec[rowIdx];
output.collect(new IntWritable(rowIdx), new DoubleWritable(xResult));
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
Path matFile = new Path(args[0]);
FSDataInputStream matData = fs.open(matFile);
BufferedReader br = new BufferedReader(new InputStreamReader(matData));
int i = 0;
String line;
while ((line = br.readLine()) != null) {
StringTokenizer tokenizer = new StringTokenizer(line);
String iRow = tokenizer.nextToken();
String iCol = tokenizer.nextToken();
if (Integer.parseInt(iRow) == Integer.parseInt(iCol)) {
i++;
}
}
br.close();
int dimention = i;
conf.setInt("DIMENTION", dimention);
Path xFile = new Path("preX/Result");
FSDataOutputStream xData = fs.create(xFile);
BufferedWriter iniX = new BufferedWriter(new OutputStreamWriter(xData));
for (int j = 0; j < dimention; j++) {
iniX.write(String.valueOf(j) + " 0");
iniX.newLine();
}
iniX.close();
URI matVec = new URI(args[0]);
DistributedCache.addCacheFile(matVec, conf);
int iteration = 0;
do {
ToolRunner.run(conf, new Jacobi(), args);
} while (iteration++ < max_iter && (!stopIteration(conf)));
}
public void configure(JobConf conf) {
try {
Path vInput;
FileSystem fs;
URI[] fvector;
nsize = conf.getInt("DIMENTION", 0);
sumVec = new double[nsize];
resVec = new double[nsize];
diaVec = new double[nsize];
Arrays.fill(sumVec, 0);
Arrays.fill(resVec, 0);
Arrays.fill(diaVec, 0);
fvector = DistributedCache.getCacheFiles(conf);
vInput = new Path(fvector[0].getPath());
fs = FileSystem.get(URI.create("hdfs://node17.cs.rochester.edu:9000"), conf);
FSDataInputStream fdis = fs.open(vInput);
String line;
while ((line = fdis.readLine()) != null) {
StringTokenizer tokenizer = new StringTokenizer(line);
int rowIdx = Integer.parseInt(tokenizer.nextToken());
int colIdx = Integer.parseInt(tokenizer.nextToken());
double matVar = Double.parseDouble(tokenizer.nextToken());
if (rowIdx == colIdx) {
diaVec[rowIdx] = matVar;
} else if (colIdx == nsize) {
resVec[rowIdx] = matVar;
} else {
sumVec[rowIdx] += matVar;
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
protected void setup(Context context) throws IOException, InterruptedException {
FileSystem fs = FileSystem.get(context.getConfiguration());
Path cFile = new Path(context.getConfiguration().get("CFILE"));
DataInputStream d = new DataInputStream(fs.open(cFile));
BufferedReader reader = new BufferedReader(new InputStreamReader(d));
String line;
while ((line = reader.readLine()) != null) {
StringTokenizer tokenizer = new StringTokenizer(line.toString());
if (tokenizer.hasMoreTokens()) {
List<Double> centroid = new ArrayList<Double>(58);
while (tokenizer.hasMoreTokens()) {
centroid.add(Double.parseDouble(tokenizer.nextToken()));
}
centroids.add(centroid);
}
}
k = centroids.size();
}
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
String[] pair = new String[2];
int count = 0;
for (Text txt : values) {
pair[count] = txt.toString();
count++;
}
// word exists in training
if (count == 2) {
StringTokenizer st_one, st_two;
if (pair[0].contains(dlt)) {
st_one = new StringTokenizer(pair[1]);
st_two = new StringTokenizer(pair[0]);
} else {
st_one = new StringTokenizer(pair[0]);
st_two = new StringTokenizer(pair[1]);
}
// outputting the data
String f_id = st_one.nextToken();
StringBuilder builder = new StringBuilder(dlt);
builder.append(f_id);
builder.append(dlt);
while (st_two.hasMoreTokens()) {
String filename = st_two.nextToken();
String tf_idf = st_two.nextToken();
builder.append(filename);
builder.append(dlt);
builder.append(tf_idf);
builder.append("\t");
}
myVal.set(builder.toString());
context.write(key, myVal);
}
}
