Package org.apache.mahout.common.iterator

Examples of org.apache.mahout.common.iterator.FileLineIterator

50
51
52
53
54
55
56
  public DataFileIterator(File dataFile) throws IOException {
    if (dataFile == null || dataFile.isDirectory() || !dataFile.exists()) {
      throw new IllegalArgumentException("Bad data file: " + dataFile);
    }
    lineIterator = new FileLineIterator(dataFile);
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
    files = out.listFiles();
    assertEquals("files Size: " + files.length + " is not: " + WORDS.length, files.length, WORDS.length);
    for (File file : files) {
      //should only be one line in the file, and it should be label label
      Iterator<String> it = new FileLineIterator(file);
      String line = it.next().trim();
      assertFalse(it.hasNext());
      String label = "animal" + '\t' + file.getName();
      assertEquals(line + ":::: is not equal to " + label + "::::", line, label);
    }
  }
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
    log.info("Creating FileDataModel for file {}", dataFile);

    this.lastModified = dataFile.lastModified();
    this.lastUpdateFileModified = readLastUpdateFileModified();

    FileLineIterator iterator = new FileLineIterator(dataFile, false);
    String firstLine = iterator.peek();
    while (firstLine.isEmpty() || firstLine.charAt(0) == COMMENT_CHAR) {
      iterator.next();
      firstLine = iterator.peek();
    }
    Closeables.close(iterator, true);

    if (delimiterRegex == null) {
      delimiter = determineDelimiter(firstLine);
View Full Code Here
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
    if (hasPrefValues) {

      if (loadFreshData) {

        FastByIDMap<Collection<Preference>> data = new FastByIDMap<Collection<Preference>>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFile(iterator, data, timestamps, false);

        for (File updateFile : findUpdateFilesAfter(newLastModified)) {
          processFile(new FileLineIterator(updateFile, false), data, timestamps, false);
        }

        return new GenericDataModel(GenericDataModel.toDataMap(data, true), timestamps);

      } else {

        FastByIDMap<PreferenceArray> rawData = ((GenericDataModel) delegate).getRawUserData();

        for (File updateFile : findUpdateFilesAfter(Math.max(oldLastUpdateFileModifieid, newLastModified))) {
          processFile(new FileLineIterator(updateFile, false), rawData, timestamps, true);
        }

        return new GenericDataModel(rawData, timestamps);

      }

    } else {

      if (loadFreshData) {

        FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFileWithoutID(iterator, data, timestamps);

        for (File updateFile : findUpdateFilesAfter(newLastModified)) {
          processFileWithoutID(new FileLineIterator(updateFile, false), data, timestamps);
        }

        return new GenericBooleanPrefDataModel(data, timestamps);

      } else {

        FastByIDMap<FastIDSet> rawData = ((GenericBooleanPrefDataModel) delegate).getRawUserData();

        for (File updateFile : findUpdateFilesAfter(Math.max(oldLastUpdateFileModifieid, newLastModified))) {
          processFileWithoutID(new FileLineIterator(updateFile, false), rawData, timestamps);
        }

        return new GenericBooleanPrefDataModel(rawData, timestamps);

      }
View Full Code Here
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
   * <pre>
   * term DocFreq Index
   * </pre>
   */
  private static String[] loadTermDictionary(InputStream is) throws IOException {
    FileLineIterator it = new FileLineIterator(is);

    int numEntries = Integer.parseInt(it.next());
    String[] result = new String[numEntries];

    while (it.hasNext()) {
      String line = it.next();
      if (line.startsWith("#")) {
        continue;
      }
      String[] tokens = TAB_PATTERN.split(line);
      if (tokens.length < 3) {
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
    if (!dumpFile.exists()) {
      log.error("Input file path {} doesn't exist", dumpFilePath);
      return;
    }

    FileLineIterator it;
    if (dumpFilePath.endsWith(".bz2")) {
      // default compression format from http://download.wikimedia.org
      CompressionCodec codec = new BZip2Codec();
      it = new FileLineIterator(codec.createInputStream(new FileInputStream(dumpFile)));
    } else {
      // assume the user has previously de-compressed the dump file
      it = new FileLineIterator(dumpFile);
    }
    int fileNumber = 0;
    while (it.hasNext()) {
      String thisLine = it.next();
      if (thisLine.trim().startsWith("<page>")) {
        boolean end = false;
        while (!thisLine.trim().startsWith("</page>")) {
          content.append(thisLine).append('\n');
          if (it.hasNext()) {
            thisLine = it.next();
          } else {
            end = true;
            break;
          }
        }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
      FSDataOutputStream outputStream = fs.create(new Path(outputPath, "trainingSet/ratings.tsv"));
      writer = new BufferedWriter(new OutputStreamWriter(outputStream, Charsets.UTF_8));

      int ratingsProcessed = 0;
      for (File movieRatings : new File(trainingDataDir).listFiles()) {
        FileLineIterator lines = null;
        try  {
          lines = new FileLineIterator(movieRatings);
          boolean firstLineRead = false;
          String movieID = null;
          while (lines.hasNext()) {
            String line = lines.next();
            if (firstLineRead) {
              String[] tokens = SEPARATOR.split(line);
              String userID = tokens[0];
              String rating = tokens[1];
              writer.write(userID + TAB + movieID + TAB + rating + NEWLINE);
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
      try {

        averageDiffs.clear();
        allRecommendableItemIDs.clear();
       
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        String firstLine = iterator.peek();
        while (firstLine.isEmpty() || firstLine.charAt(0) == COMMENT_CHAR) {
          iterator.next();
          firstLine = iterator.peek();
        }
        long averageCount = 0L;
        while (iterator.hasNext()) {
          averageCount = processLine(iterator.next(), averageCount);
        }
       
        pruneInconsequentialDiffs();
        updateAllRecommendableItems();
       
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
    log.info("Creating FileDataModel for file {}", dataFile);

    this.lastModified = dataFile.lastModified();
    this.lastUpdateFileModified = readLastUpdateFileModified();

    FileLineIterator iterator = new FileLineIterator(dataFile, false);
    String firstLine = iterator.peek();
    while (firstLine.isEmpty() || firstLine.charAt(0) == COMMENT_CHAR) {
      iterator.next();
      firstLine = iterator.peek();
    }
    Closeables.closeQuietly(iterator);

    delimiter = determineDelimiter(firstLine);
    delimiterPattern = Splitter.on(delimiter);
View Full Code Here
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
    if (hasPrefValues) {

      if (loadFreshData) {

        FastByIDMap<Collection<Preference>> data = new FastByIDMap<Collection<Preference>>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFile(iterator, data, timestamps, false);

        for (File updateFile : findUpdateFilesAfter(newLastModified)) {
          processFile(new FileLineIterator(updateFile, false), data, timestamps, false);
        }

        return new GenericDataModel(GenericDataModel.toDataMap(data, true), timestamps);

      } else {

        FastByIDMap<PreferenceArray> rawData = ((GenericDataModel) delegate).getRawUserData();

        for (File updateFile : findUpdateFilesAfter(Math.max(oldLastUpdateFileModifieid, newLastModified))) {
          processFile(new FileLineIterator(updateFile, false), rawData, timestamps, true);
        }

        return new GenericDataModel(rawData, timestamps);

      }

    } else {

      if (loadFreshData) {

        FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFileWithoutID(iterator, data, timestamps);

        for (File updateFile : findUpdateFilesAfter(newLastModified)) {
          processFileWithoutID(new FileLineIterator(updateFile, false), data, timestamps);
        }

        return new GenericBooleanPrefDataModel(data, timestamps);

      } else {

        FastByIDMap<FastIDSet> rawData = ((GenericBooleanPrefDataModel) delegate).getRawUserData();

        for (File updateFile : findUpdateFilesAfter(Math.max(oldLastUpdateFileModifieid, newLastModified))) {
          processFileWithoutID(new FileLineIterator(updateFile, false), rawData, timestamps);
        }

        return new GenericBooleanPrefDataModel(rawData, timestamps);

      }
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.iterator.FileLineIterator

  • org.apache.mahout.cf.taste.example.jester.JesterDataModel
  • org.apache.mahout.cf.taste.example.kddcup.DataFileIterator
  • org.apache.mahout.cf.taste.hadoop.example.als.netflix.NetflixDatasetConverter
  • org.apache.mahout.cf.taste.impl.model.file.FileDataModel
  • org.apache.mahout.cf.taste.impl.recommender.slopeone.file.FileDiffStorage
  • org.apache.mahout.cf.taste.impl.similarity.file.FileItemItemSimilarityIterator
  • org.apache.mahout.classifier.bayes.BayesFileFormatterTest
  • org.apache.mahout.classifier.bayes.WikipediaXmlSplitter
  • org.apache.mahout.df.data.Data
  • org.apache.mahout.text.wikipedia.WikipediaXmlSplitter
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.