lkrsnik/list
1
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

Added translataion fixes + punctuation in export fix

Browse Source
This commit is contained in:
Luka
2019-03-19 14:06:39 +01:00
parent 39624fa4f2
commit 10666b4453
19 changed files with 586 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files

213
src/main/java/util/Export.java
View File

@@ -23,41 +23,41 @@ import data.Enums.WordLevelType;
@SuppressWarnings("unchecked")
public class Export {
public static void SetToJSON(Set<Pair<String, Map<MultipleHMKeys, Long>>> set) {
JSONArray wrapper = new JSONArray();
for (Pair<String, Map<MultipleHMKeys, Long>> p : set) {
JSONArray data_wrapper = new JSONArray();
JSONObject metric = new JSONObject();
String title = p.getLeft();
Map<MultipleHMKeys, Long> map = p.getRight();
if (map.isEmpty())
continue;
long total = Util.mapSumFrequencies(map);
for (Map.Entry<MultipleHMKeys, Long> e : map.entrySet()) {
JSONObject data_entry = new JSONObject();
data_entry.put("word", e.getKey());
data_entry.put("frequency", e.getValue());
data_entry.put("percent", formatNumberAsPercent((double) e.getValue() / total));
data_wrapper.add(data_entry);
}
metric.put("Title", title);
metric.put("data", data_wrapper);
wrapper.add(metric);
}
try (FileWriter file = new FileWriter("statistics.json")) {
file.write(wrapper.toJSONString());
} catch (IOException e) {
e.printStackTrace();
}
}
// public static void SetToJSON(Set<Pair<String, Map<MultipleHMKeys, Long>>> set) {
// JSONArray wrapper = new JSONArray();
//
// for (Pair<String, Map<MultipleHMKeys, Long>> p : set) {
// JSONArray data_wrapper = new JSONArray();
// JSONObject metric = new JSONObject();
//
// String title = p.getLeft();
// Map<MultipleHMKeys, Long> map = p.getRight();
//
// if (map.isEmpty())
// continue;
//
// long total = Util.mapSumFrequencies(map);
//
// for (Map.Entry<MultipleHMKeys, Long> e : map.entrySet()) {
// JSONObject data_entry = new JSONObject();
// data_entry.put("word", e.getKey());
// data_entry.put("frequency", e.getValue());
// data_entry.put("percent", formatNumberAsPercent((double) e.getValue() / total));
//
// data_wrapper.add(data_entry);
// }
//
// metric.put("Title", title);
// metric.put("data", data_wrapper);
// wrapper.add(metric);
// }
//
// try (FileWriter file = new FileWriter("statistics.json")) {
// file.write(wrapper.toJSONString());
// } catch (IOException e) {
// e.printStackTrace();
// }
// }
public static String SetToCSV(Set<Pair<String, Map<MultipleHMKeys, Long>>> set, File resultsPath, LinkedHashMap<String, String> headerInfoBlock,
StatisticsNew statistics, Filter filter) {
@@ -127,12 +127,6 @@ public class Export {
FILE_HEADER_AL.add(I18N.get("exportTable.totalRelativeFrequency"));
if (filter.getCollocability().size() > 0){
for (Collocability c : filter.getCollocability()) {
FILE_HEADER_AL.add(c.toHeaderString());
}
}
for (Taxonomy key : taxonomyResults.keySet()) {
if(!key.equals(statistics.getCorpus().getTotal()) && num_taxonomy_frequencies.containsKey(key) && num_taxonomy_frequencies.get(key).longValue() > 0) {
FILE_HEADER_AL.add(I18N.get("exportTable.absoluteFrequency") + " [" + key.toString() + "]");
@@ -141,6 +135,13 @@ public class Export {
}
}
if (filter.getCollocability().size() > 0){
for (Collocability c : filter.getCollocability()) {
FILE_HEADER_AL.add(c.toHeaderString());
}
}
if (filter.getWriteMsdAtTheEnd()) {
String msd = "";
int maxMsdLength = 0;
@@ -280,14 +281,14 @@ public class Export {
dataEntry.add(e.getValue().toString());
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_selected_taxonomy_frequencies.get(statistics.getCorpus().getTotal())));
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 1000000)/num_taxonomy_frequencies.get(statistics.getCorpus().getTotal()).longValue()));
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_selected_taxonomy_frequencies.get(statistics.getCorpus().getTotal()), statistics.getCorpus().getPunctuation()));
dataEntry.add(formatNumberForExport(((double) e.getValue() * 1000000)/num_taxonomy_frequencies.get(statistics.getCorpus().getTotal()).longValue(), statistics.getCorpus().getPunctuation()));
for (Taxonomy key : taxonomyResults.keySet()){
if(!key.equals(statistics.getCorpus().getTotal()) && num_taxonomy_frequencies.containsKey(key) && num_taxonomy_frequencies.get(key).longValue() > 0) {
AtomicLong frequency = taxonomyResults.get(key).get(e.getKey());
dataEntry.add(frequency.toString());
dataEntry.add(formatNumberAsPercent((double) frequency.get() / num_selected_taxonomy_frequencies.get(key)));
dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / num_taxonomy_frequencies.get(key).longValue()));
dataEntry.add(formatNumberAsPercent((double) frequency.get() / num_selected_taxonomy_frequencies.get(key), statistics.getCorpus().getPunctuation()));
dataEntry.add(formatNumberForExport(((double) frequency.get() * 1000000) / num_taxonomy_frequencies.get(key).longValue(), statistics.getCorpus().getPunctuation()));
// dataEntry.add(formatNumberAsPercent((double) frequency.get() / statistics.getUniGramOccurrences()));
// dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / statistics.getUniGramOccurrences()));
}
@@ -296,7 +297,7 @@ public class Export {
if (filter.getCollocability().size() > 0){
for (Collocability c : filter.getCollocability()) {
dataEntry.add(statistics.getCollocability().get(c).get(e.getKey()));
dataEntry.add(formatNumberForLongExport(statistics.getCollocability().get(c).get(e.getKey()), statistics.getCorpus().getPunctuation()));
}
}
@@ -371,66 +372,66 @@ public class Export {
return s;
}
public static String SetToCSV(String title, Object[][] result, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
//Delimiter used in CSV file
String NEW_LINE_SEPARATOR = "\n";
//CSV file header
Object[] FILE_HEADER = {"word", "frequency", "percent"};
String fileName = "";
fileName = title.replace(": ", "-");
fileName = fileName.replace(" ", "_").concat(".csv");
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
OutputStreamWriter fileWriter = null;
CSVPrinter csvFilePrinter = null;
//Create the CSVFormat object with "\n" as a record delimiter
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';');
try {
//initialize FileWriter object
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
//initialize CSVPrinter object
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
// write info block
printHeaderInfo(csvFilePrinter, headerInfoBlock);
//Create CSV file header
csvFilePrinter.printRecord(FILE_HEADER);
for (Object[] resultEntry : result) {
List dataEntry = new ArrayList<>();
dataEntry.add(resultEntry[0]);
dataEntry.add(resultEntry[1]);
dataEntry.add(formatNumberAsPercent(resultEntry[2]));
csvFilePrinter.printRecord(dataEntry);
}
} catch (Exception e) {
System.out.println("Error in CsvFileWriter!");
e.printStackTrace();
} finally {
try {
if (fileWriter != null) {
fileWriter.flush();
fileWriter.close();
}
if (csvFilePrinter != null) {
csvFilePrinter.close();
}
} catch (IOException e) {
System.out.println("Error while flushing/closing fileWriter/csvPrinter!");
e.printStackTrace();
}
}
return fileName;
}
// public static String SetToCSV(String title, Object[][] result, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
// //Delimiter used in CSV file
// String NEW_LINE_SEPARATOR = "\n";
//
// //CSV file header
// Object[] FILE_HEADER = {"word", "frequency", "percent"};
//
// String fileName = "";
//
// fileName = title.replace(": ", "-");
// fileName = fileName.replace(" ", "_").concat(".csv");
//
// fileName = resultsPath.toString().concat(File.separator).concat(fileName);
//
// OutputStreamWriter fileWriter = null;
// CSVPrinter csvFilePrinter = null;
//
// //Create the CSVFormat object with "\n" as a record delimiter
// CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';');
//
// try {
// //initialize FileWriter object
// fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
//
// //initialize CSVPrinter object
// csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
//
// // write info block
// printHeaderInfo(csvFilePrinter, headerInfoBlock);
//
// //Create CSV file header
// csvFilePrinter.printRecord(FILE_HEADER);
//
// for (Object[] resultEntry : result) {
// List dataEntry = new ArrayList<>();
// dataEntry.add(resultEntry[0]);
// dataEntry.add(resultEntry[1]);
// dataEntry.add(formatNumberAsPercent(resultEntry[2]), statistics.getCorpus().getPunctuation());
// csvFilePrinter.printRecord(dataEntry);
// }
// } catch (Exception e) {
// System.out.println("Error in CsvFileWriter!");
// e.printStackTrace();
// } finally {
// try {
// if (fileWriter != null) {
// fileWriter.flush();
// fileWriter.close();
// }
// if (csvFilePrinter != null) {
// csvFilePrinter.close();
// }
// } catch (IOException e) {
// System.out.println("Error while flushing/closing fileWriter/csvPrinter!");
// e.printStackTrace();
// }
// }
//
// return fileName;
// }
public static String nestedMapToCSV(String title, Map<WordLevelType, Map<String, Map<String, Long>>> result, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
//Delimiter used in CSV file

25
src/main/java/util/Util.java
View File

@@ -54,10 +54,31 @@ public class Util {
return "- invalid input format -";
}
public static String formatNumberAsPercent(Object o) {
return MessageFormat.format("{0,number,#.### %}", o).replace('.', ',');
public static String formatNumberAsPercent(Object o, String punctuation) {
if(punctuation.equals("punctuation.COMMA")) {
return MessageFormat.format("{0,number,#.### %}", o).replace('.', ',');
} else {
return MessageFormat.format("{0,number,#.### %}", o);
}
}
public static String formatNumberForExport(Object o, String punctuation) {
if(punctuation.equals("punctuation.COMMA")) {
return MessageFormat.format("{0,number,#.##}", o).replace('.', ',');
} else {
return MessageFormat.format("{0,number,#.##}", o);
}
}
public static String formatNumberForLongExport(Object o, String punctuation) {
if(punctuation.equals("punctuation.COMMA")) {
return MessageFormat.format("{0,number,#.########}", o).replace('.', ',');
} else {
return MessageFormat.format("{0,number,#.########}", o);
}
}
private static boolean isInstanceOfInteger(Object o) {
Set<Class<?>> types = new HashSet<>();
types.add(Byte.class);