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

Added taxonomy presentation in results

Browse Source
This commit is contained in:
Luka
2018-06-29 12:53:29 +02:00
parent d5d06fd7c5
commit 8d7cce6c77
11 changed files with 212 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
src/main/java/util/Export.java
View File

@@ -5,7 +5,11 @@ import static util.Util.*;
import java.io.*;
import java.nio.charset.StandardCharsets;
import java.util.*;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentMap;
import java.util.concurrent.atomic.AtomicLong;
import data.Filter;
import org.apache.commons.csv.CSVFormat;
import org.apache.commons.csv.CSVPrinter;
import org.apache.commons.lang3.tuple.Pair;
@@ -52,17 +56,29 @@ public class Export {
}
}
public static String SetToCSV(Set<Pair<String, Map<String, Long>>> set, File resultsPath, LinkedHashMap<String, String> headerInfoBlock) {
public static String SetToCSV(Set<Pair<String, Map<String, Long>>> set, File resultsPath, LinkedHashMap<String, String> headerInfoBlock,
Map<String, Map<String, AtomicLong>> taxonomyResults) {
//Delimiter used in CSV file
String NEW_LINE_SEPARATOR = "\n";
List<Object> FILE_HEADER_AL = new ArrayList<Object>();
Object[] FILE_HEADER;
//Count frequencies
int num_frequencies = 0;
long num_frequencies = 0;
for (Pair<String, Map<String, Long>> p : set) {
Map<String, Long> map = p.getRight();
for (Map.Entry<String, Long> e : map.entrySet()) {
num_frequencies += e.getValue();
if (map.isEmpty())
continue;
num_frequencies = Util.mapSumFrequencies(map);
}
Map<String, Long> num_taxonomy_frequencies = new ConcurrentHashMap<>();
for (String taxonomyKey : taxonomyResults.keySet()) {
num_taxonomy_frequencies.put(taxonomyKey, (long) 0);
for (AtomicLong value : taxonomyResults.get(taxonomyKey).values()){
long val = num_taxonomy_frequencies.get(taxonomyKey);
val += value.get();
num_taxonomy_frequencies.put(taxonomyKey, val);
}
}
@@ -71,19 +87,36 @@ public class Export {
if (headerInfoBlock.containsKey("Analiza") && headerInfoBlock.get("Analiza").equals("Besede")) {
if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
FILE_HEADER = new Object[]{"Različnica", "Skupna absolutna pogostost", "Delež glede na vse različnice"};
FILE_HEADER_AL.add("Različnica");
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse različnice");
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")) {
headerInfoBlock.put("Skupna vsota vseh lem:", String.valueOf(num_frequencies));
FILE_HEADER = new Object[]{"Lema", "Skupna absolutna pogostost", "Delež glede na vse leme"};
FILE_HEADER_AL.add("Lema");
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse leme");
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("oblikoskladenjska oznaka")) {
headerInfoBlock.put("Skupna vsota vseh oblikoskladenjskih oznak:", String.valueOf(num_frequencies));
FILE_HEADER = new Object[]{"Oblikoskladenjska oznaka", "Skupna absolutna pogostost", "Delež glede na vse oblikoskladenjske oznake"};
FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse oblikoskladenjske oznake");
} else {
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
FILE_HEADER = new Object[]{"Lema", "Skupna pogostost", "Delež glede na leme"};
FILE_HEADER_AL.add("Lema");
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse leme");
}
} else
FILE_HEADER_AL.add("Skupna relativna pogostost");
for (String key : taxonomyResults.keySet()) {
FILE_HEADER_AL.add("Absolutna pogostost [" + key + "]");
FILE_HEADER_AL.add("Delež [" + key + "]");
FILE_HEADER_AL.add("Relativna pogostost [" + key + "]");
}
FILE_HEADER = new String[ FILE_HEADER_AL.size() ];
FILE_HEADER_AL.toArray(FILE_HEADER);
} else {
FILE_HEADER = new Object[]{"word", "frequency", "percent"};
}
String fileName = "";
@@ -99,7 +132,7 @@ public class Export {
if (map.isEmpty())
continue;
long total = Util.mapSumFrequencies(map);
// long total = Util.mapSumFrequencies(map);
OutputStreamWriter fileWriter = null;
CSVPrinter csvFilePrinter = null;
@@ -124,7 +157,16 @@ public class Export {
List dataEntry = new ArrayList<>();
dataEntry.add(e.getKey());
dataEntry.add(e.getValue().toString());
dataEntry.add(formatNumberAsPercent((double) e.getValue() / total));
dataEntry.add(formatNumberAsPercent((double) e.getValue() / num_frequencies));
dataEntry.add(String.format("%.2f", ((double) e.getValue() * 10000)/num_frequencies));
for (String key : taxonomyResults.keySet()){
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() * 10000) / num_taxonomy_frequencies.get(key)));
}
csvFilePrinter.printRecord(dataEntry);
}
} catch (Exception e) {