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

Beautified code and added Normalized word functionality on OneWords

Browse Source
This commit is contained in:
Luka 2018-08-10 11:08:01 +02:00
parent 9b5fa4616b
commit e140a9538b
12 changed files with 194 additions and 162 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/main/java/alg/XML_processing.java
View File

@ -892,7 +892,7 @@ public class XML_processing {
if (filter.getAl() == AnalysisLevel.STRING_LEVEL) {
// ngram level: if not 0 must be less than or equal to number of words in this sentence.
if (filter.getNgramValue() > 0 && filter.getNgramValue() > sentence.size()) {
return null;
return new ArrayList<>();
}
// if we're calculating values for letters, omit words that are shorter than string length

9
src/main/java/alg/ngram/Ngrams.java
View File

@ -56,7 +56,8 @@ public class Ngrams {
// String test = key;
// }
// key = (!key.equals("") && key.charAt(key.length()-1) == ',') ? key.substring(0, key.length() - 1) : key;
if (stats.getFilter().getNotePunctuations())
key = (!key.equals("") && key.charAt(key.length()-1) == ',') ? key.substring(0, key.length() - 1) : key;
MultipleHMKeys multipleKeys;
@ -165,6 +166,12 @@ public class Ngrams {
// .collect(Collectors.toList()));
// .substring(0, 1)
return StringUtils.join(candidate, " ");
case NORMALIZED_WORD:
candidate.addAll(ngramCandidate
.stream()
.map(Word::getNormalizedWord)
.collect(Collectors.toList()));
return StringUtils.join(candidate, " ");
}
return StringUtils.join(candidate, " ");

50
src/main/java/data/CalculateFor.java
View File

@ -2,6 +2,7 @@ package data;
public enum CalculateFor {
WORD("različnica"),
NORMALIZED_WORD("normalizirana različnica"),
LEMMA("lema"),
MORPHOSYNTACTIC_SPECS("oblikoskladenjska oznaka"),
MORPHOSYNTACTIC_PROPERTY("oblikoskladenjska lastnost"),
@ -37,7 +38,56 @@ public enum CalculateFor {
if (WORD_TYPE.toString().equals(cf)) {
return WORD_TYPE;
}
if (NORMALIZED_WORD.toString().equals(cf)) {
return NORMALIZED_WORD;
}
}
return null;
}
public String toHeaderString() {
switch(this){
case WORD:
return "Različnica";
case NORMALIZED_WORD:
return "Normalizirana različnica";
case LEMMA:
return "Lema";
case MORPHOSYNTACTIC_SPECS:
return "Oblikoskladenjska oznaka";
case MORPHOSYNTACTIC_PROPERTY:
return "Oblikoskladenjska lastnost";
case WORD_TYPE:
return "Besedna vrsta";
case DIST_WORDS:
return "Različnica";
case DIST_LEMMAS:
return "Lema";
default:
return null;
}
}
public String toPercentString() {
switch(this){
case WORD:
return "Delež glede na vse različnice";
case NORMALIZED_WORD:
return "Delež glede na vse normalizirane različnice";
case LEMMA:
return "Delež glede na vse leme";
case MORPHOSYNTACTIC_SPECS:
return "Delež glede na vse oblikoskladenjske oznake";
case MORPHOSYNTACTIC_PROPERTY:
return "Delež glede na vse oblikoskladenjske lastnosti";
case WORD_TYPE:
return "Delež glede na vse besedne vrste";
case DIST_WORDS:
return "Delež glede na vse različnice";
case DIST_LEMMAS:
return "Delež glede na vse leme";
default:
return null;
}
}
}

8
src/main/java/data/MultipleHMKeys.java
View File

@ -7,10 +7,10 @@ Created for when words are sorted by multiple keys, i.e. not just lemmas but lem
*/
public interface MultipleHMKeys {
String getK1();
String getK2();
String getK3();
String getK4();
String getK5();
default String getK2(){ return null; }
default String getK3(){ return null; }
default String getK4(){ return null; }
default String getK5(){ return null; }
@Override
int hashCode();

16
src/main/java/data/MultipleHMKeys1.java
View File

@ -16,22 +16,6 @@ public final class MultipleHMKeys1 implements MultipleHMKeys {
return k1;
}
public String getK2() {
return null;
}
public String getK3() {
return null;
}
public String getK4() {
return null;
}
public String getK5() {
return null;
}
@Override
public int hashCode() {
return k1.hashCode();

12
src/main/java/data/MultipleHMKeys2.java
View File

@ -21,18 +21,6 @@ public final class MultipleHMKeys2 implements MultipleHMKeys {
return k2;
}
public String getK3() {
return null;
}
public String getK4() {
return null;
}
public String getK5() {
return null;
}
@Override
public int hashCode() {
return Objects.hash(k1, k2);

8
src/main/java/data/MultipleHMKeys3.java
View File

@ -26,14 +26,6 @@ public final class MultipleHMKeys3 implements MultipleHMKeys {
return k3;
}
public String getK4() {
return null;
}
public String getK5() {
return null;
}
@Override
public int hashCode() {
return Objects.hash(k1, k2, k3);

4
src/main/java/data/MultipleHMKeys4.java
View File

@ -31,10 +31,6 @@ public final class MultipleHMKeys4 implements MultipleHMKeys {
return k4;
}
public String getK5() {
return null;
}
@Override
public int hashCode() {
return Objects.hash(k1, k2, k3, k4);

55
src/main/java/gui/OneWordAnalysisTab.java
View File

@ -87,8 +87,11 @@ public class OneWordAnalysisTab {
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS = FXCollections.observableArrayList("lema", "različnica", "oblikoskladenjska oznaka");
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_LETTERS = FXCollections.observableArrayList("lema", "različnica");
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS_ORTH = FXCollections.observableArrayList("različnica");
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS_GOS = FXCollections.observableArrayList("lema", "različnica", "oblikoskladenjska oznaka", "normalizirana različnica");
private static final ObservableList<String> alsoVisualizeItemsLemma = FXCollections.observableArrayList("besedna vrsta", "oblikoskladenjska oznaka");
private static final ObservableList<String> alsoVisualizeItemsDifferential = FXCollections.observableArrayList("lema", "besedna vrsta", "oblikoskladenjska oznaka");
private static final ObservableList<String> alsoVisualizeItemsWord = FXCollections.observableArrayList("lema", "besedna vrsta", "oblikoskladenjska oznaka");
private static final ObservableList<String> alsoVisualizeItemsWordGos = FXCollections.observableArrayList("lema", "besedna vrsta", "oblikoskladenjska oznaka", "normalizirana različnica");
private static final ObservableList<String> alsoVisualizeItemsNormalizedWord = FXCollections.observableArrayList("lema", "besedna vrsta", "oblikoskladenjska oznaka", "različnica");
private static final ObservableList<String> alsoVisualizeItemsEmpty = FXCollections.observableArrayList();
// TODO: pass observables for taxonomy based on header scan
@ -103,37 +106,28 @@ public class OneWordAnalysisTab {
// calculateForCB
calculateForCB.valueProperty().addListener((observable, oldValue, newValue) -> {
calculateFor = CalculateFor.factory(newValue);
alsoVisualizeCCB.getItems().removeAll();
if(newValue.equals("lema")){
alsoVisualizeCCB.getItems().removeAll();
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsLemma);
alsoVisualizeCCB.getCheckModel().getCheckedItems().addListener((ListChangeListener<String>) c -> {
alsoVisualize = new ArrayList<>();
ObservableList<String> checkedItems = alsoVisualizeCCB.getCheckModel().getCheckedItems();
alsoVisualize.addAll(checkedItems);
logger.info(String.format("Selected also visualize items: %s", StringUtils.join(checkedItems, ",")));
});
alsoVisualizeCCB.getCheckModel().clearChecks();
} else if(newValue.equals("različnica")){
alsoVisualizeCCB.getItems().removeAll();
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsDifferential);
alsoVisualizeCCB.getCheckModel().getCheckedItems().addListener((ListChangeListener<String>) c -> {
alsoVisualize = new ArrayList<>();
ObservableList<String> checkedItems = alsoVisualizeCCB.getCheckModel().getCheckedItems();
alsoVisualize.addAll(checkedItems);
logger.info(String.format("Selected also visualize items: %s", StringUtils.join(checkedItems, ",")));
});
alsoVisualizeCCB.getCheckModel().clearChecks();
} else {
alsoVisualizeCCB.getItems().removeAll();
} else if(newValue.equals("različnica")) {
if (corpus.getCorpusType() == CorpusType.GOS)
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsWordGos);
else
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsWord);
} else if(newValue.equals("normalizirana različnica")) {
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsNormalizedWord);
}else {
alsoVisualizeCCB.getItems().setAll(alsoVisualizeItemsEmpty);
alsoVisualizeCCB.getCheckModel().getCheckedItems().addListener((ListChangeListener<String>) c -> {
alsoVisualize = new ArrayList<>();
ObservableList<String> checkedItems = alsoVisualizeCCB.getCheckModel().getCheckedItems();
alsoVisualize.addAll(checkedItems);
logger.info(String.format("Selected also visualize items: %s", StringUtils.join(checkedItems, ",")));
});
alsoVisualizeCCB.getCheckModel().clearChecks();
}
alsoVisualizeCCB.getCheckModel().getCheckedItems().addListener((ListChangeListener<String>) c -> {
alsoVisualize = new ArrayList<>();
ObservableList<String> checkedItems = alsoVisualizeCCB.getCheckModel().getCheckedItems();
alsoVisualize.addAll(checkedItems);
logger.info(String.format("Selected also visualize items: %s", StringUtils.join(checkedItems, ",")));
});
alsoVisualizeCCB.getCheckModel().clearChecks();
logger.info("calculateForCB:", calculateFor.toString());
});
@ -343,7 +337,10 @@ public class OneWordAnalysisTab {
logger.info("mode: ", mode.toString());
if (mode == MODE.WORD) {
calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_WORDS);
if (corpus.getCorpusType() == CorpusType.GOS)
calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_WORDS_GOS);
else
calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_WORDS);
} else if (mode == MODE.LETTER) {
calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_LETTERS);

5
src/main/java/gui/StringAnalysisTabNew2.java
View File

@ -108,6 +108,7 @@ public class StringAnalysisTabNew2 {
private HostServices hostService;
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS = FXCollections.observableArrayList("lema", "različnica", "oblikoskladenjska oznaka");
// private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS_GOS = FXCollections.observableArrayList("lema", "različnica", "oblikoskladenjska oznaka", "normalizirana različnica");
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_LETTERS = FXCollections.observableArrayList("lema", "različnica");
private static final ObservableList<String> N_GRAM_COMPUTE_FOR_WORDS_ORTH = FXCollections.observableArrayList("različnica");
@ -420,7 +421,11 @@ public class StringAnalysisTabNew2 {
if (mode == MODE.WORD) {
paneWords.setVisible(true);
paneLetters.setVisible(false);
// if (corpus.getCorpusType() == CorpusType.GOS)
// calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_WORDS_GOS);
// else
calculateForCB.getItems().setAll(N_GRAM_COMPUTE_FOR_WORDS);
} else if (mode == MODE.LETTER) {
paneWords.setVisible(false);
paneLetters.setVisible(true);

140
src/main/java/util/Export.java
View File

@ -87,83 +87,93 @@ public class Export {
//CSV file header
if (headerInfoBlock.containsKey("Analiza") && (headerInfoBlock.get("Analiza").equals("Besede") || headerInfoBlock.get("Analiza").equals("Besedni nizi"))) {
if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
if (headerInfoBlock.get("Analiza").equals("Besede")){
FILE_HEADER_AL.add("Različnica");
} else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
FILE_HEADER_AL.add("Različnice");
}
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")) {
headerInfoBlock.put("Skupna vsota vseh lem:", String.valueOf(num_frequencies));
if (headerInfoBlock.get("Analiza").equals("Besede")){
FILE_HEADER_AL.add("Lema");
FILE_HEADER_AL.add("Lema male črke");
} else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
FILE_HEADER_AL.add("Leme");
FILE_HEADER_AL.add("Leme male črke");
}
} else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("oblikoskladenjska oznaka")) {
headerInfoBlock.put("Skupna vsota vseh oblikoskladenjskih oznak:", String.valueOf(num_frequencies));
if (headerInfoBlock.get("Analiza").equals("Besede")){
FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
} else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
FILE_HEADER_AL.add("Oblikoskladenjska oznake");
}
} else {
headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
FILE_HEADER_AL.add("Lema");
FILE_HEADER_AL.add("Lema male črke");
}
FILE_HEADER_AL.add(filter.getCalculateFor().toHeaderString());
if (filter.getCalculateFor().equals(CalculateFor.LEMMA))
FILE_HEADER_AL.add("Lema male črke");
// if (headerInfoBlock.containsKey("Analiza") && (headerInfoBlock.get("Analiza").equals("Besede") || headerInfoBlock.get("Analiza").equals("Besedni nizi"))) {
// if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
// headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
// if (headerInfoBlock.get("Analiza").equals("Besede")){
// FILE_HEADER_AL.add("Različnica");
// } else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
// FILE_HEADER_AL.add("Različnice");
// }
// } else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")) {
// headerInfoBlock.put("Skupna vsota vseh lem:", String.valueOf(num_frequencies));
// if (headerInfoBlock.get("Analiza").equals("Besede")){
// FILE_HEADER_AL.add("Lema");
// FILE_HEADER_AL.add("Lema male črke");
// } else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
// FILE_HEADER_AL.add("Leme");
// FILE_HEADER_AL.add("Leme male črke");
// }
// } else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("oblikoskladenjska oznaka")) {
// headerInfoBlock.put("Skupna vsota vseh oblikoskladenjskih oznak:", String.valueOf(num_frequencies));
// if (headerInfoBlock.get("Analiza").equals("Besede")){
// FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
// } else if (headerInfoBlock.get("Analiza").equals("Besedni nizi")) {
// FILE_HEADER_AL.add("Oblikoskladenjska oznake");
// }
// } else {
// headerInfoBlock.put("Skupna vsota vseh različnic:", String.valueOf(num_frequencies));
// FILE_HEADER_AL.add("Lema");
// FILE_HEADER_AL.add("Lema male črke");
// }
// for (Map<MultipleHMKeys, AtomicLong> value : taxonomyResults.values()) {
for (CalculateFor otherKey : filter.getMultipleKeys()){
if(otherKey.equals(CalculateFor.LEMMA)){
FILE_HEADER_AL.add("Lema");
FILE_HEADER_AL.add("Lema male črke");
}
if(otherKey.equals(CalculateFor.WORD_TYPE)){
FILE_HEADER_AL.add("Besedna vrsta");
}
if(otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
}
}
for (CalculateFor otherKey : filter.getMultipleKeys()) {
FILE_HEADER_AL.add(otherKey.toHeaderString());
if (otherKey.equals(CalculateFor.LEMMA))
FILE_HEADER_AL.add("Lema male črke");
}
// if(otherKey.equals(CalculateFor.LEMMA)){
// FILE_HEADER_AL.add("Lema");
// FILE_HEADER_AL.add("Lema male črke");
// }
// if(otherKey.equals(CalculateFor.WORD_TYPE)){
// FILE_HEADER_AL.add("Besedna vrsta");
// }
// if(otherKey.equals(CalculateFor.MORPHOSYNTACTIC_SPECS)){
// FILE_HEADER_AL.add("Oblikoskladenjska oznaka");
// }
// if(otherKey.equals(CalculateFor.NORMALIZED_WORD)){
// FILE_HEADER_AL.add("Normalizirana različnica");
// }
// }
// break;
// }
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add(filter.getCalculateFor().toPercentString());
if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("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")) {
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")) {
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse oblikoskladenjske oznake");
} else {
FILE_HEADER_AL.add("Skupna absolutna pogostost");
FILE_HEADER_AL.add("Delež glede na vse leme");
// if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("različnica")) {
// FILE_HEADER_AL.add("Delež glede na vse različnice");
// } else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("lema")) {
// FILE_HEADER_AL.add("Delež glede na vse leme");
// } else if (headerInfoBlock.containsKey("Izračunaj za:") && headerInfoBlock.get("Izračunaj za:").equals("oblikoskladenjska oznaka")) {
// FILE_HEADER_AL.add("Delež glede na vse oblikoskladenjske oznake");
// } else {
// FILE_HEADER_AL.add("Delež glede na vse leme");
// }
FILE_HEADER_AL.add("Skupna relativna pogostost");
for (String key : taxonomyResults.keySet()) {
if(!key.equals("Total")) {
FILE_HEADER_AL.add("Absolutna pogostost [" + key + "]");
FILE_HEADER_AL.add("Delež [" + key + "]");
FILE_HEADER_AL.add("Relativna pogostost [" + key + "]");
}
FILE_HEADER_AL.add("Skupna relativna pogostost");
for (String key : taxonomyResults.keySet()) {
if(!key.equals("Total")) {
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"};
}
FILE_HEADER = new String[ FILE_HEADER_AL.size() ];
FILE_HEADER_AL.toArray(FILE_HEADER);
// } else {
// FILE_HEADER = new Object[]{"word", "frequency", "percent"};
// }
String fileName = "";

47
src/main/resources/gui/StringAnalysisTabNew2.fxml
View File

@ -15,7 +15,28 @@
<AnchorPane fx:id="stringAnalysisTabPaneNew2" prefHeight="600.0" prefWidth="800.0" xmlns="http://javafx.com/javafx/8.0.121" xmlns:fx="http://javafx.com/fxml/1" fx:controller="gui.StringAnalysisTabNew2">
<Pane>
<Label layoutX="10.0" layoutY="60.0" prefHeight="25.0" text="N-gram nivo" />
<Pane fx:id="paneWords">
<children>
<Label layoutX="10.0" layoutY="100.0" prefHeight="25.0" text="Preskok besed" />
<ComboBox fx:id="skipValueCB" layoutX="185.0" layoutY="100.0" prefWidth="180.0" promptText="izberi" visibleRowCount="5">
<items>
<FXCollections fx:factory="observableArrayList">
<String fx:value="0" />
<String fx:value="1" />
<String fx:value="2" />
<String fx:value="3" />
<String fx:value="4" />
<String fx:value="5" />
<String fx:value="6" />
<String fx:value="7" />
</FXCollections>
</items>
</ComboBox>
</children>
</Pane>
<!-- for some reason following two ComboBoxes have to be below paneWords -->
<ComboBox fx:id="ngramValueCB" layoutX="185.0" layoutY="60.0" prefHeight="25.0" prefWidth="180.0" promptText="izberi" visibleRowCount="5">
<items>
<FXCollections fx:factory="observableArrayList">
@ -40,27 +61,6 @@
</items>
</ComboBox>
<Pane fx:id="paneWords">
<children>
<Label layoutX="10.0" layoutY="100.0" prefHeight="25.0" text="Preskok besed" />
<ComboBox fx:id="skipValueCB" layoutX="185.0" layoutY="100.0" prefWidth="180.0" promptText="izberi" visibleRowCount="5">
<items>
<FXCollections fx:factory="observableArrayList">
<String fx:value="0" />
<String fx:value="1" />
<String fx:value="2" />
<String fx:value="3" />
<String fx:value="4" />
<String fx:value="5" />
<String fx:value="6" />
<String fx:value="7" />
</FXCollections>
</items>
</ComboBox>
</children>
</Pane>
<Label layoutX="10.0" layoutY="140.0" prefHeight="25.0" text="Upoštevaj ločila" />
<CheckBox fx:id="notePunctuationsChB" layoutX="263.0" layoutY="145.0" selected="true" />
@ -82,6 +82,9 @@
<Button fx:id="computeNgramsB" layoutX="10.0" layoutY="440.0" mnemonicParsing="false" prefHeight="25.0" prefWidth="250.0" text="Izračunaj" />
<Label layoutX="10.0" layoutY="60.0" prefHeight="25.0" text="N-gram nivo" />
</Pane>
<Pane layoutX="400.0" prefHeight="480.0" prefWidth="380.0">
<Label fx:id="solarFilters" layoutX="10.0" layoutY="60.0" text="Izbrani filtri:" />