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

Added filter parameters to CSV + created names of columns for MSDs + [partly] fixed number of words parameter

Browse Source
This commit is contained in:
Luka
2018-11-13 13:57:49 +01:00
parent a4df732678
commit cbfe3e6025
9 changed files with 502 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

266
src/main/java/util/Export.java
View File

@@ -105,7 +105,8 @@ public class Export {
}
}
headerInfoBlock.put(filter.getCalculateFor().toMetadataString(), String.valueOf(num_frequencies));
headerInfoBlock.put(filter.getCalculateFor().toMetadataString(), String.valueOf(statistics.getUniGramOccurrences()));
// headerInfoBlock.put(filter.getCalculateFor().toMetadataString(), String.valueOf(num_frequencies));
for (CalculateFor otherKey : filter.getMultipleKeys()) {
FILE_HEADER_AL.add(otherKey.toHeaderString());
@@ -132,55 +133,75 @@ public class Export {
FILE_HEADER_AL.add("Relativna pogostost [" + key + "]");
}
}
if (filter.getWriteMsdAtTheEnd()) {
String msd = "";
int maxMsdLength = 0;
for(MultipleHMKeys key : set.iterator().next().getRight().keySet()){
msd = key.getMsd(filter);
if (msd.length() > maxMsdLength){
maxMsdLength = msd.length();
}
}
for(int i = 0; i < maxMsdLength; i++){
FILE_HEADER_AL.add("msd" + String.format("%02d", i + 1));
}
}
FILE_HEADER = new String[ FILE_HEADER_AL.size() ];
FILE_HEADER_AL.toArray(FILE_HEADER);
String fileName = "";
for (Pair<String, Map<MultipleHMKeys, Long>> p : set) {
String title = p.getLeft();
fileName = title.replace(": ", "-");
fileName = fileName.replace(" ", "_").concat(".csv");
for (Pair<String, Map<MultipleHMKeys, Long>> p : set) {
String title = p.getLeft();
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
// statistics.setTimeEnding();
title = statistics.generateResultTitle();
// statistics.
Map<MultipleHMKeys, Long> map = p.getRight();
fileName = title.replace(": ", "-");
fileName = fileName.replace(" ", "_").concat(".csv");
if (map.isEmpty())
continue;
fileName = resultsPath.toString().concat(File.separator).concat(fileName);
Map<MultipleHMKeys, Long> map = p.getRight();
if (map.isEmpty())
continue;
// long total = Util.mapSumFrequencies(map);
OutputStreamWriter fileWriter = null;
CSVPrinter csvFilePrinter = null;
OutputStreamWriter fileWriter = null;
CSVPrinter csvFilePrinter = null;
//Create the CSVFormat object with "\n" as a record delimiter it puts all words in braces
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';').withQuoteMode(QuoteMode.ALL);
//Create the CSVFormat object with "\n" as a record delimiter it puts all words in braces
CSVFormat csvFileFormat = CSVFormat.DEFAULT.withRecordSeparator(NEW_LINE_SEPARATOR).withDelimiter(';').withQuoteMode(QuoteMode.ALL);
try {
//initialize FileWriter object
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
try {
//initialize FileWriter object
fileWriter = new OutputStreamWriter(new FileOutputStream(fileName), StandardCharsets.UTF_8);
//initialize CSVPrinter object
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
//initialize CSVPrinter object
csvFilePrinter = new CSVPrinter(fileWriter, csvFileFormat);
// write info block
printHeaderInfo(csvFilePrinter, headerInfoBlock);
// write info block
printHeaderInfo(csvFilePrinter, headerInfoBlock);
//Create CSV file header
csvFilePrinter.printRecord(FILE_HEADER);
//Create CSV file header
csvFilePrinter.printRecord(FILE_HEADER);
for (Map.Entry<MultipleHMKeys, Long> e : map.entrySet()) {
List dataEntry = new ArrayList<>();
if (!ValidationUtil.isEmpty(filter.getSkipValue()) && filter.getSkipValue() > 0) {
dataEntry.add(e.getKey().getK1());
}
dataEntry.add(eraseSkipgramStars(e.getKey().getK1(), filter));
for (Map.Entry<MultipleHMKeys, Long> e : map.entrySet()) {
List dataEntry = new ArrayList<>();
if (!ValidationUtil.isEmpty(filter.getSkipValue()) && filter.getSkipValue() > 0) {
dataEntry.add(e.getKey().getK1());
}
dataEntry.add(eraseSkipgramStars(e.getKey().getK1(), filter));
if (filter.getCalculateFor().equals(CalculateFor.LEMMA)){
dataEntry.add(eraseSkipgramStars(e.getKey().getK1().toLowerCase(), filter));
}
if (filter.getSuffixLength() != null || filter.getSuffixList() != null || filter.getPrefixLength() != null || filter.getPrefixList() != null) {
if (filter.getSuffixLength() != null || filter.getSuffixList() != null || filter.getPrefixLength() != null || filter.getPrefixList() != null) {
if(filter.getSuffixLength() > 0 || filter.getPrefixLength() > 0) {
if (filter.getPrefixLength() > 0) {
dataEntry.add(((String) dataEntry.get(0)).substring(0, filter.getPrefixLength()));
@@ -217,46 +238,48 @@ public class Export {
dataEntry.add(rsf);
}
}
}
}
int i = 0;
for (CalculateFor otherKey : filter.getMultipleKeys()){
switch(i){
case 0:
if (otherKey.equals(CalculateFor.LEMMA)){
dataEntry.add(eraseSkipgramStars(e.getKey().getK2(), filter));
dataEntry.add(eraseSkipgramStars(e.getKey().getK2().toLowerCase(), filter));
} else {
dataEntry.add(eraseSkipgramStars(e.getKey().getK2(), filter));
}
break;
case 1:
dataEntry.add(eraseSkipgramStars(e.getKey().getK3(), filter));
break;
case 2:
dataEntry.add(eraseSkipgramStars(e.getKey().getK4(), filter));
break;
case 3:
dataEntry.add(eraseSkipgramStars(e.getKey().getK5(), filter));
break;
}
switch(i){
case 0:
if (otherKey.equals(CalculateFor.LEMMA)){
dataEntry.add(eraseSkipgramStars(e.getKey().getK2(), filter));
dataEntry.add(eraseSkipgramStars(e.getKey().getK2().toLowerCase(), filter));
} else {
dataEntry.add(eraseSkipgramStars(e.getKey().getK2(), filter));
}
break;
case 1:
dataEntry.add(eraseSkipgramStars(e.getKey().getK3(), filter));
break;
case 2:
dataEntry.add(eraseSkipgramStars(e.getKey().getK4(), filter));
break;
case 3:
dataEntry.add(eraseSkipgramStars(e.getKey().getK5(), filter));
break;
}
i++;
}
i++;
}
dataEntry.add(e.getValue().toString());
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_frequencies));
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 1000000)/num_frequencies));
for (String key : taxonomyResults.keySet()){
if(!key.equals("Total") && num_taxonomy_frequencies.get(key) > 0) {
AtomicLong frequency = taxonomyResults.get(key).get(e.getKey());
dataEntry.add(frequency.toString());
dataEntry.add(formatNumberAsPercent((double) frequency.get() / num_taxonomy_frequencies.get(key)));
dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / num_taxonomy_frequencies.get(key)));
}
dataEntry.add(e.getValue().toString());
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_frequencies));
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 1000000)/num_frequencies));
for (String key : taxonomyResults.keySet()){
if(!key.equals("Total") && num_taxonomy_frequencies.get(key) > 0) {
AtomicLong frequency = taxonomyResults.get(key).get(e.getKey());
dataEntry.add(frequency.toString());
// dataEntry.add(formatNumberAsPercent((double) frequency.get() / num_taxonomy_frequencies.get(key)));
// dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / num_taxonomy_frequencies.get(key)));
dataEntry.add(formatNumberAsPercent((double) frequency.get() / statistics.getUniGramOccurrences()));
dataEntry.add(String.format("%.2f", ((double) frequency.get() * 1000000) / statistics.getUniGramOccurrences()));
}
}
}
if (filter.getCollocability().size() > 0){
for (Collocability c : filter.getCollocability()) {
@@ -264,67 +287,68 @@ public class Export {
}
}
// Write msd separated per letters at the end of each line in csv
if (filter.getWriteMsdAtTheEnd()) {
String msd = "";
if (filter.getCalculateFor().equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
msd = e.getKey().getK1();
} else if (filter.getMultipleKeys().contains(CalculateFor.MORPHOSYNTACTIC_SPECS)) {
i = 0;
for (CalculateFor otherKey : filter.getMultipleKeys()){
switch(i){
case 0:
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
msd = e.getKey().getK2();
}
break;
case 1:
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
msd = e.getKey().getK3();
}
break;
case 2:
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
msd = e.getKey().getK4();
}
break;
case 3:
if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
msd = e.getKey().getK5();
}
break;
}
// Write msd separated per letters at the end of each line in csv
if (filter.getWriteMsdAtTheEnd()) {
// String msd = "";
//
// if (filter.getCalculateFor().equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// msd = e.getKey().getK1();
// } else if (filter.getMultipleKeys().contains(CalculateFor.MORPHOSYNTACTIC_SPECS)) {
// i = 0;
// for (CalculateFor otherKey : filter.getMultipleKeys()){
// switch(i){
// case 0:
// if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// msd = e.getKey().getK2();
// }
// break;
// case 1:
// if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// msd = e.getKey().getK3();
// }
// break;
// case 2:
// if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// msd = e.getKey().getK4();
// }
// break;
// case 3:
// if (otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// msd = e.getKey().getK5();
// }
// break;
// }
//
// i++;
// }
// }
String msd = e.getKey().getMsd(filter);
String [] charArray = msd.split("(?!^)");
dataEntry.addAll(Arrays.asList(charArray));
}
i++;
}
}
String [] charArray = msd.split("(?!^)");
dataEntry.addAll(Arrays.asList(charArray));
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();
}
}
}
}
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;
return fileName;
}
private static String eraseSkipgramStars(String s, Filter filter){