!7

cmodule AutoClassifier > DynConvo {

  srecord Theory(BasicLogicRule statement) {

    new PosNeg<Msg> examples;

    //bool iff; // <=> instead of only =>

    toString { ret str(statement.lhs instanceof MPTrue ? "Every message is " + statement.rhs

      : bidiMode ? statement.lhs + " <=> " + statement.rhs : statement); }

  }

  // propositions about a message. check returns null if unknown

  asclass MsgProp { abstract Bool check(Msg msg); }

  srecord MPTrue() > MsgProp {

    Bool check(Msg msg) { true; }

    toString { ret "always"; }

  }

  record HasLabel(S label) > MsgProp {

    Bool check(Msg msg) { ret msg2label_new.get(msg, label); }

    toString { ret label; }

  }

  record DoesntHaveLabel(S label) > MsgProp {

    Bool check(Msg msg) { ret not(msg2label_new.get(msg, label)); }

    toString { ret "not " + label; }

  }

  record FeatureValueIs(S feature, O value) > MsgProp {

    Bool check(Msg msg) { ret eq(getMsgFeature(msg, feature), value); }

    toString { ret feature + "=" + value; }

  }

  class Label {

    S name;

    *() {}

    *(S *name) {}

    TreeSetWithDuplicates<Theory> bestTheories = new(reverseComparatorFromCalculatedField theoryScore());

    int score() { ret theoryScore(first(bestTheories)); }

    Theory bestTheory() { ret first(bestTheories); }

  }

  switchable double minAdjustedScoreToDisplay = 50;

  switchable bool autoNext = false;

  static bool bidiMode = true; // treat all theories as bidirectional

  L<Msg> msgs; // full dialog

  L<Msg> shownMsgs;

  transient Map<Msg, Map<S, O>> msg2features = AutoMap<>(lambda1 calcMsgFeatures);

  new LinkedHashSet<Theory> theories;

  S analysisText;

  transient JTable theoryTable, labelsTable, trainedExamplesTable, objectsTable;

  transient JTabbedPane tabs;

  transient SingleComponentPanel scpPredictions;

  transient new Map<S, Label> labelsByName;

  new Set<S> allLabels;

  transient new L<IVF1<S>> onNewLabel;

  new DoubleKeyedMap<Msg, S, Bool> msg2label_new;

  transient new Map<S, FeatureExtractor<Msg>> featureExtractors;

  transient Q thinkQ;

  sinterface FeatureEnv<A> {

    A mainObject();

    O getFeature(S name);

  }

  sinterface FeatureExtractor<A> {

    O get(FeatureEnv<A> env);

  }

  start {

    thinkQ = dm_startQ("Thought Queue");

    thinkQ.add(r {

      // legacy + after deletion cleaning

      setField(allLabels := asTreeSet(msg2label_new.bKeys()));

      updateLabelsByName();

      onNewLabel.add(lbl -> change());

      makeTheoriesAboutLabels();

      makeTheoriesAboutFeaturesAndLabels();

      for (S field : fields(Msg))

        featureExtractors.put(field, env -> getOpt(env.mainObject(), field));

      makeTextExtractors("text");

      callFAllOnAll(onNewLabel, allLabels);

      msg2labelUpdated();

      //showRandomMsg();

    });

  }

  void makeTheoriesAboutLabels {

    // For any label X:

    onNewLabel.add(lbl -> {

      // test theory (for every M: M has label X)

      addTheory(new Theory(BasicLogicRule(new MPTrue, new HasLabel(lbl))));

      // test theory (for every M: M doesn't have label X)

      addTheory(new Theory(BasicLogicRule(new MPTrue, new DoesntHaveLabel(lbl))));

    });

  }

  void makeTheoriesAboutFeaturesAndLabels {

    // for every label X:

    onNewLabel.add(lbl -> {

      // For any feature F:

      for (S feature : keys(featureExtractors))

        // for every seen value V of F:

        for (O value : possibleValuesOfFeatureRelatedToLabel(feature, lbl))

          for (O rhs : ll(new HasLabel(lbl), new DoesntHaveLabel(lbl)))

            // test theory (for every M: msg M's feature F has value V => msg has/doesn't have label x))

            addTheory(new Theory(BasicLogicRule(

              new FeatureValueIs(feature, value), rhs)));

    });

  }

  Set possibleValuesOfFeature(S feature) {

    if (isBoolField(Msg, feature))

      ret litset(false, true);

    ret litset();

  }

  Set possibleValuesOfFeatureRelatedToLabel(S feature, S label) {

    Set set = possibleValuesOfFeature(feature);

    fOr (Msg msg : getMsgsRelatedToLabel(label))

      set.add(getMsgFeature(msg, feature));

    ret set;

  }

  // returns AutoMap with no realized entries

  Map<S, O> calcMsgFeatures(Msg msg) {

    new Var<FeatureEnv<Msg>> env;

    AutoMap<S, O> map = new(feature -> featureExtractors.get(feature).get(env!));

    env.set(new FeatureEnv<Msg> {

      Msg mainObject() { ret msg; }

      O getFeature(S feature) { ret map.get(feature); }

    });

    ret map;    

  }

  void showMsgs(L<Msg> l) {

    setField(shownMsgs := l);

    setMsgs(l);

    if (l(shownMsgs) == 1) {

      Msg msg = first(shownMsgs);

      setField(analysisText := joinWithEmptyLines(

        "Trained Labels: " + or2(renderBoolMap(getMsgLabels(msg)), "-"),

        "Features:\n" + formatColonProperties_quoteStringValues(

msg2features.get(msg))

      ));

      setSCPComponent(scpPredictions,

        scrollableStackWithSpacing(map(predictionsForMsg(msg), p ->

          withSideMargin(jLabelWithButtons(iround(p.adjustedConfidence) + "%: " + p.predictedLabel(), 

            "Right", rThread { acceptPrediction(p) },

            "Wrong", rThread { rejectPrediction(p) })))));

    } else setField(analysisText := "");

  }

  void updatePredictions() {

    showMsgs(shownMsgs);

  }

  srecord Prediction(S label, bool plus, double adjustedConfidence) {

    toString {

      ret predictedLabel() + " (confidence: " + iround(adjustedConfidence) + "%)";

    }

    S predictedLabel() {

      ret (plus ? "" : "not ") + label;

    }

  }

  L<Prediction> predictionsForMsg(Msg msg) {

    // positive labels first, then "not"s. sort by score in each group

    new L<Prediction> out;

    for (Label label : values(labelsByName)) {

      Theory t = label.bestTheory(), continue if null;

      Bool lhs = evalTheoryLHS(t, msg), continue if null;

      bool prediction = t.statement.rhs instanceof DoesntHaveLabel ? !lhs : lhs;

      double conf = threeB1BScore(t.examples), adjusted = adjustConfidence(conf);

      //if (adjusted < minAdjustedScoreToDisplay) continue;

      out.add(new Prediction(label.name, prediction, adjusted));

    }

    ret sortedByCalculatedFieldDesc(out, p -> /*pair(p.plus,*/ p.adjustedConfidence/*)*/);

  }

  // go from range 50-100 to 0-100 (might look better)

  double adjustConfidence(double x) {

    ret max(0, (x-50)*2);

  }

  void showRandomMsg {

    showMsgs(randomElementAsList(msgs));

  }

  void showPrevMsg {

    showMsgs(llNonNulls(prevInCyclicList(msgs, first(shownMsgs))));

  }

  void showNextMsg {

    showMsgs(llNonNulls(nextInCyclicList(msgs, first(shownMsgs))));

  }

  void acceptPrediction(Prediction p) {

    if (p != null) sendInput2(p.predictedLabel());

  }

  void rejectPrediction(Prediction p) {

    if (p != null) sendInput2(cloneWithFlippedBoolField plus(p).predictedLabel());

  }

  @Override

  void sendInput2(S s) {

    // treat input as a label

    if (l(shownMsgs) == 1) {

      Msg shown = first(shownMsgs);

      new Matches m;

      if "not ..." {

        S label = cleanLabel(m.rest());

        doubleKeyedMapPutVerbose(+msg2label_new, shown, label, false);

        msg2labelUpdated(label);

        if (autoNext) showRandomMsg();

      } else {

        S label = cleanLabel(s);

        doubleKeyedMapPutVerbose(+msg2label_new, shown, label, true);

        msg2labelUpdated(label);

        if (autoNext) showRandomMsg();

      }

      change();

    }

  }

  Map<S, Bool> getMsgLabels(Msg msg) {

 ret msg2label_new.getA(msg);

 }

  Set<Msg> getMsgsRelatedToLabel(S label) { ret msg2label_new.asForB(label); }

  void msg2labelUpdated(S label) {

    for (Theory t : cloneList(labelByName(label).bestTheories))

      checkTheory(t);

    msg2labelUpdated();

  }

  void msg2labelUpdated() {

    callFAllOnAll(onNewLabel, addAll_returnNew(allLabels, msg2label_new.bKeys()));

    updateTrainedExamplesTable();

  }

  void updateTrainedExamplesTable {

    dataToTable_uneditable(trainedExamplesTable, map(msg2label_new.map1, (msg, map) ->

      litorderedmap(

        "Message" := (msg.fromUser ? "User" : "Bot") + ": " + msg.text,

        "Labels" := renderBoolMap(map))));

  }

  JComponent mainPart() {

    ret jhsplit(jvsplit(

        jCenteredSection("Focused Message", super.mainPart()),

        jhsplit(

          jCenteredSection("Message Analysis", dm_textArea analysisText()),

          jCenteredSection("Predictions", scpPredictions = singleComponentPanel())

        )),

      with(r updateTabs, tabs = jtabs(

        "", with(r updateObjectsTable, withRightAlignedButtons(

          objectsTable = sexyTable(),

          "Import messages...", rThreadEnter importMsgs)),

        "", with(r updateLabelsTable, labelsTable = sexyTable()),

        "", with(r updateTheoryTable, tableWithSearcher2_returnPanel(theoryTable = sexyTable())),

        "", with(r updateTrainedExamplesTable, tableWithSearcher2_returnPanel(trainedExamplesTable = sexyTable()))

      )));

  }

  void updateTabs {

    setTabTitles(tabs,

      firstLetterToUpper(nMessages(msgs)),

      firstLetterToUpper(nLabels(labelsByName)),

      firstLetterToUpper(nTheories(theories)),

      n2(msg2label_new.aKeys(), "Trained Example"));

  }

  void updateTheoryTable {

    L<Theory> sorted = sortedByCalculatedFieldDesc(theories, t ->

      t.examples == null ? null : t.examples.score());

    dataToTable_uneditable(theoryTable, map(sorted, t -> litorderedmap(

      "Score" := renderTheoryScore(t),

      "Theory" := str(t))));

  }

  Map<S, Theory> labelsToBestTheoryMap() {

    Map<S, L<Theory>> map = multiMapToMap(multiMapIndex targetLabelOfTheory(theories));

    ret mapValues(map,

      theories -> highestBy theoryScore(theories));

  }

  void updateObjectsTable enter {

    dataToTable_uneditable_ifHasTable(objectsTable, map(msgs, msg ->

      litorderedmap("Text" := msg.text)

    ));

  }

  void updateLabelsTable enter {

    L<Label> sorted = sortedByCalculatedFieldDesc(values(labelsByName), l -> l.score());

    dataToTable_uneditable_ifHasTable(labelsTable, map(sorted, label -> {

      Cl<Theory> bestTheories = label.bestTheories.tiedForFirst();

      ret litorderedmap(

        "Label" := label.name,

        "Prediction Confidence" := renderTheoryScore(first(bestTheories)),

        "Best Theory" := empty(bestTheories) ? "" :

          (l(bestTheories) > 1 ? "[+" + (l(bestTheories)-1) + "] " : "") +  first(bestTheories));

    }));

  }

  S renderTheoryScore(Theory t) {

    //ret renderPosNegCounts(t.examples);

    ret t == null || t.examples.isEmpty() ? "" : iround(adjustConfidence(threeB1BScore(t.examples))) + "%"

      + " / " + renderPosNegScoreAndCount(t.examples);

  }

  int theoryScore(Theory t) {

    ret t == null ? -100 : t.examples.score();

  }

  void theoriesChanged {

    updateTheoryTable();

    updateLabelsTable();

    updateTabs();

    updatePredictions();

    change();

  }

  visual

    withCenteredButtons(super,

      "<", rInThinkQ(r showPrevMsg),

      "Show random msg", rInThinkQ(r showRandomMsg),

      ">", rInThinkQ(r showNextMsg),

      jPopDownButton_noText(flattenObjectArray(

        "Check theories", rInThinkQ(r checkAllTheories),

        "Clear theories", rInThinkQ(r clearTheories),

        "Update predictions", rInThinkQ(r updatePredictions),

        dm_importAndExportAllDataMenuItems(),

        "Upgrade to v3", rThreadEnter upgradeMe)));

  Runnable rInThinkQ(Runnable r) { ret rInQ(thinkQ, r); }

  void addTheory(Theory theory) {

    if (theories.add(theory)) {

      print("New theory: " + theory);

      addTheoryToCollectors(theory);

      theoriesChanged();

    }

  }

  void clearTheories { theories.clear(); theoriesChanged(); }

  Bool checkMsgProp(O prop, Msg msg) {

    if (prop cast And) ret checkMsgProp(prop.a, msg) && checkMsgProp(prop.b, msg);

    if (prop cast Not) ret not(checkMsgProp(prop.a, msg));

    ret ((MsgProp) prop).check(msg);

  }

  Bool evalTheoryLHS(Theory theory, Msg msg) {

    ret theory == null ? null

      : checkMsgProp(theory.statement.lhs, msg);

  }

  Bool testTheoryOnMsg(Theory theory, Msg msg) {

    Bool lhs = evalTheoryLHS(theory, msg);

    Bool rhs = checkMsgProp(theory.statement.rhs, msg);

    if (lhs == null || rhs == null) null;

    if (bidiMode)

      ret eq(lhs, rhs);

    else

      ret isTrue(rhs) || isFalse(lhs);

  }

  void checkAllTheories {

    for (Theory theory : theories)

      checkTheory_noTrigger(theory);

    theoriesChanged();

  }

  void checkTheory(Theory theory) {

    checkTheory_noTrigger(theory);

    theoriesChanged();

  }

  void checkTheory_noTrigger(Theory theory) {

    new PosNeg<Msg> pn;

    for (Msg msg : msgs)

      pn.add(msg, testTheoryOnMsg(theory, msg));

    if (!eq(theory.examples, pn)) {

      removeTheoryFromCollectors(theory);

      theory.examples = pn;

      addTheoryToCollectors(theory);

      change();

    }

  }

  S cleanLabel(S label) { ret upper(label); }

  S targetLabelOfTheory(Theory theory) {

    O o = theory.statement.rhs;

    if (o cast HasLabel) ret o.label;

    if (o cast DoesntHaveLabel) ret o.label;

    null;

  }

  void addTheoryToCollectors(Theory theory) {

    S lbl = targetLabelOfTheory(theory);

    if (lbl != null)

      labelByName(lbl).bestTheories.add(theory);

  }

  void removeTheoryFromCollectors(Theory theory) {

    S lbl = targetLabelOfTheory(theory);

    if (lbl != null)

      labelByName(lbl).bestTheories.remove(theory);

  }

  Label labelByName(S name) {

    ret getOrCreate(labelsByName, name, () -> new Label(name));

  }

  void updateLabelsByName() {

    for (S lbl : allLabels)

      labelByName(lbl);

    for (Theory t : theories)

      addTheoryToCollectors(t);

  }

  O getMsgFeature(Msg msg, S feature) {

    ret msg2features.get(msg).get(feature);

  }

  void makeTextExtractors(S textFeature) {

    for (WithName<IF1<S, O>> f : textExtractors()) {

      IF1<S, O> theFunction = f!;

      featureExtractors.put(f.name, env -> theFunction.get((S) env.getFeature(textFeature)));

    }

  }

  L<WithName<IF1<S, O>>> textExtractors() {

    new L<WithName<IF1<S, O>>> l;

    l.add(WithName<>("number of words", lambda1 numberOfWords));

    l.add(WithName<>("number of characters", lambda1 l));

    for (char c : characters("\"', .-_"))

      l.add(WithName<>("contains " + quote(c), s -> contains(s, c)));

    /*for (S word : concatAsCISet(lambdaMap words(collect text(msgs))))

      l.add(WithName<>("contains word " + quote(word), s -> containsWord(s, word)));*/

    ret l;

  }

  void importMsgs {

    inputMultiLineText("Messages to import (one per line)", voidfunc(S text) {

      Cl<S> toImport = listMinusSet(asOrderedSet(tlft(text)), collectAsSet text(msgs));

      if (msgs == null) msgs = ll();

      for (S line : toImport)

        msgs.add(new Msg(true, line));

      change();

      infoBox(nMessages(toImport) + " imported");

      updateObjectsTable();

      showRandomMsg();

    });

  }

  void upgradeMe {

    dm_exportStructureToDefaultFile(this);

    dm_changeModuleLibID(this, "#1028058/AutoClassifier");

  }

}