List of usage examples for org.apache.hadoop.fs FileSystem open
public FSDataInputStream open(PathHandle fd) throws IOException
From source file:adts.HbaseClient.java
License:Open Source License
public static void main(String[] args) throws IOException { String[] keys = new String[5]; int keywords_counter = 0; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); Path inFile = new Path(args[0]); if (!fs.exists(inFile)) System.out.println("Input file not found"); if (!fs.isFile(inFile)) System.out.println("Input should be a file"); else {/*from ww w .j av a2s . co m*/ FSDataInputStream fsDataInputStream = fs.open(inFile); BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(fsDataInputStream)); String line; while (((line = bufferedReader.readLine()) != null) && (keywords_counter < 5)) { String[] array = line.split("\t"); String keyword = array[0]; System.out.println("Record : " + keyword); keys[keywords_counter] = keyword; keywords_counter++; } bufferedReader.close(); fs.close(); Configuration config = HBaseConfiguration.create(); HTable table = new HTable(config, "index"); Random randomGenerator = new Random(); for (int i = 0; i < 10; i++) { int randomInt = randomGenerator.nextInt(5); System.out.println("Random chosen keyword : " + keys[randomInt]); FilterList list = new FilterList(FilterList.Operator.MUST_PASS_ALL); SingleColumnValueFilter filter_by_name = new SingleColumnValueFilter(Bytes.toBytes("keyword"), Bytes.toBytes(""), CompareOp.EQUAL, Bytes.toBytes(keys[randomInt])); //filter_by_name.setFilterIfMissing(true); list.addFilter(filter_by_name); Scan scan = new Scan(); scan.setFilter(list); //scan.addFamily(Bytes.toBytes("keyword")); ResultScanner scanner = table.getScanner(scan); try { for (Result rr = scanner.next(); rr != null; rr = scanner.next()) { // print out the row we found and the columns we were looking for byte[] cells = rr.getValue(Bytes.toBytes("article"), Bytes.toBytes("")); System.out.println("Keyword " + keys[randomInt] + "belonging to article with md5 : " + Bytes.toString(cells)); } } catch (Exception e) { e.printStackTrace(); } finally { scanner.close(); } } table.close(); } }
From source file:apex.benchmark.RedisHelper.java
License:Apache License
public void fillDB(String fileName) throws IOException { Path filePath = new Path(fileName); Configuration configuration = new Configuration(); FileSystem fs; fs = FileSystem.newInstance(filePath.toUri(), configuration); FSDataInputStream inputStream = fs.open(filePath); BufferedReader bufferedReader; try {//from www.j av a 2s . c o m bufferedReader = new BufferedReader(new InputStreamReader(inputStream)); String line; while ((line = bufferedReader.readLine()) != null) { String[] mapping = line.split("\\s+"); if (mapping.length != 2) { continue; } jedis.sadd("campaigns", mapping[0]); jedis.set(mapping[1], mapping[0]); } } catch (Exception e) { throw e; } }
From source file:application.RecommenderEvaluator.java
License:Open Source License
/** * il metodo evaluate prende in ingresso una collezione di item e media e standard error ad esso associato, * una collezione di user che ha come valore una collezione delle medie degli item per i quali ha espresso un voto, * una stringa che contiene il path ad un file di testo (#user,#item,#vote) per effettuare i test. Il metodo fornisce in output la matrice di confusione cosi' formata * nella cella [0][0] ci sara' il numero di volte in cui il voto e' stato positivo e la previsione e' stata positiva (True Positive) * nella cella [0][1] ci sara' il numero di volte in cui il voto e' stato positivo e la previsione e' stata negativa (False Negative) * nella cella [1][0] ci sara' il numero di volte in cui il voto e' stato negativo e la previsione e' stata positiva (False Positive) * nella cella [1][1] ci sara' il numero di volte in cui il voto e' stato negativo e la previsione e' stata negativa (True Negative) * @param Stato_Item e' una collezione di item con media e standard error a ciascuno di esso associato * @param Stato_User e' una collezione di user con valore una collezione delle medie degli item per i quali l'user ha espresso un voto * @param s e' una stringa che contiene il path ad un file di testo per effettuare i test * @return una matrice di confusione con il numero di TruePositive, FalsePositive, FalseNegative, TrueNegative ottenuti. * @throws IOException// w w w .ja v a 2s . co m */ public void evaluate() { String test_file = GLOBALS.getTEST_FILE_NAME(); String split = GLOBALS.getSPLIT_TOKEN(); try { FileSystem fs = FileSystem.get(conf); BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(new Path(test_file)))); String line; while ((line = br.readLine()) != null) { StringTokenizer st = new StringTokenizer(line, split); int user = Integer.parseInt(st.nextToken()); int item = Integer.parseInt(st.nextToken()); int vote = Integer.parseInt(st.nextToken()); UserProfile UP = USER_STATE.get(user); ItemProfile IP = ITEM_STATE.get(item); if (UP == null || IP == null) { skipped_evaluation++; } else { Boolean prediction = estimatePreference(UP, IP); if (prediction == null) { skipped_evaluation++; continue; } // System.out.println("prediction:"+prediction+", vote:"+vote); if (prediction) { if (vote == 1) { CM[0][0] += 1; } //TP else if (vote == -1) { CM[1][0] += 1; } //FP } else { if (vote == -1) { CM[1][1] += 1; } //TN else if (vote == 1) { CM[0][1] += 1; } //FN } } } br.close(); //STAT // System.out.println("TP: "+CM[0][0]); // System.out.println("FN: "+CM[0][1]); // System.out.println("FP: "+CM[1][0]); // System.out.println("TN: "+CM[1][1]); // System.out.println("SKYPPED: "+skipped_evaluation); } catch (Exception e) { System.out.println("Exception " + e); e.printStackTrace(); System.exit(-1); } }
From source file:ark.util.HadoopUtil.java
License:Apache License
public static BufferedReader getFileReader(String path) { try {//from w w w .ja v a 2 s. co m Path filePath = new Path(path); FileSystem fileSystem = FileSystem.get(new Configuration()); BufferedReader reader = new BufferedReader(new InputStreamReader(fileSystem.open(filePath))); return reader; } catch (Exception e) { return null; } }
From source file:Assignment3_P2_MergeStockAverageCount.StockPriceMergeDriver.java
/** * @param args the command line arguments */// w w w .j a v a2 s . c o m public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); // local file system handle FileSystem local = FileSystem.getLocal(conf); // hdfs file system handle FileSystem hdfs = FileSystem.get(conf); // local input directory Path inputDir = new Path(args[0]); // hdfs i/p directory Path inputDir1 = new Path(args[1]); // local input files in local dir FileStatus[] inputFiles = local.listStatus(inputDir); // o/p stream FSDataOutputStream out = hdfs.create(inputDir1); // open each file and extract contents of file for (int i = 0; i < inputFiles.length; i++) { System.out.println("File name ----------------------------------------------------------------> " + inputFiles[i].getPath().getName()); FSDataInputStream in = local.open(inputFiles[i].getPath()); byte buffer[] = new byte[256]; int bytesRead = 0; // extract all contents of file while ((bytesRead = in.read(buffer)) > 0) { out.write(buffer, 0, bytesRead); } // close input stream in.close(); } Job job = Job.getInstance(conf, "Average Stock Price"); job.setJarByClass(StockPriceMergeDriver.class); job.setMapperClass(StockPriceMerge_Mapper.class); job.setCombinerClass(StockPriceMerge_Reducer.class); job.setReducerClass(StockPriceMerge_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(FloatWritable.class); FileInputFormat.addInputPath(job, new Path(args[1])); // above programs output will be input for mapper FileOutputFormat.setOutputPath(job, new Path(args[2])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:at.illecker.hadoop.rootbeer.examples.matrixmultiplication.cpu.MatrixMultiplicationCpu.java
License:Apache License
static void printOutput(Configuration conf) throws IOException { FileSystem fs = OUTPUT_DIR.getFileSystem(conf); FileStatus[] files = fs.listStatus(OUTPUT_DIR); for (int i = 0; i < files.length; i++) { if (files[i].getLen() > 0) { System.out.println("File " + files[i].getPath()); if (files[i].getPath().getName().endsWith(".log")) { FSDataInputStream in = fs.open(files[i].getPath()); IOUtils.copyBytes(in, System.out, conf, false); in.close();/*w ww. j ava 2 s . co m*/ } } } // fs.delete(FileOutputFormat.getOutputPath(job), true); }
From source file:at.illecker.hadoop.rootbeer.examples.matrixmultiplication.MatrixMultiplicationBenchmark.java
License:Apache License
private void printOutput(Configuration conf) throws IOException { FileSystem fs = FileSystem.get(conf); FileStatus[] files = fs.listStatus(CONF_OUTPUT_DIR); for (int i = 0; i < files.length; i++) { if (files[i].getLen() > 0) { System.out.println("File " + files[i].getPath()); FSDataInputStream in = fs.open(files[i].getPath()); IOUtils.copyBytes(in, System.out, conf, false); in.close();/* w w w. ja v a 2 s . c o m*/ } } // fs.delete(FileOutputFormat.getOutputPath(job), true); }
From source file:at.illecker.hama.hybrid.examples.hellohybrid.HelloHybridBSP.java
License:Apache License
static void printOutput(BSPJob job, Path path) throws IOException { FileSystem fs = path.getFileSystem(job.getConfiguration()); FileStatus[] files = fs.listStatus(path); for (int i = 0; i < files.length; i++) { if (files[i].getLen() > 0) { System.out.println("File " + files[i].getPath()); SequenceFile.Reader reader = null; try { reader = new SequenceFile.Reader(fs, files[i].getPath(), job.getConfiguration()); IntWritable key = new IntWritable(); NullWritable value = NullWritable.get(); while (reader.next(key, value)) { System.out.println("key: '" + key.get() + "' value: '" + value + "'\n"); }//from w ww.ja va2 s . c o m } catch (IOException e) { FSDataInputStream in = fs.open(files[i].getPath()); IOUtils.copyBytes(in, System.out, job.getConfiguration(), false); in.close(); } finally { if (reader != null) { reader.close(); } } } } // fs.delete(FileOutputFormat.getOutputPath(job), true); }
From source file:at.illecker.hama.hybrid.examples.kmeans.KMeansHybridBSP.java
License:Apache License
static void printFile(Configuration conf, FileSystem fs, Path file, Writable key, Writable value) throws IOException { System.out.println("File " + file.toString()); SequenceFile.Reader reader = null; try {/* w w w . j a v a2 s .c o m*/ reader = new SequenceFile.Reader(fs, file, conf); while (reader.next(key, value)) { System.out.println("key: '" + key.toString() + "' value: '" + value.toString() + "'\n"); } } catch (IOException e) { FSDataInputStream in = fs.open(file); IOUtils.copyBytes(in, System.out, conf, false); in.close(); } catch (NullPointerException e) { LOG.error(e); } finally { if (reader != null) { reader.close(); } } }
From source file:at.illecker.hama.hybrid.examples.matrixmultiplication.MatrixMultiplicationHybridBenchmark.java
License:Apache License
static void printOutput(Configuration conf) throws IOException { FileSystem fs = FileSystem.get(conf); FileStatus[] files = fs.listStatus(new Path(OUTPUT_DIR)); for (int i = 0; i < files.length; i++) { if (files[i].getLen() > 0) { System.out.println("File " + files[i].getPath()); FSDataInputStream in = fs.open(files[i].getPath()); IOUtils.copyBytes(in, System.out, conf, false); in.close();//from w w w . ja v a 2 s .c om } } // fs.delete(FileOutputFormat.getOutputPath(job), true); }