Esempio n. 1
0
def parser():
    DarkLogic.init(0)
    db = Database("Test/dbtest.csv")
    dbStates = db.getDatas()
    print("Total number of theorems in database: " + str(len(dbStates)))
    for dbState in dbStates.values():
        thCreated = DarkLogic.makeTheorem(dbState.theoremName(),
                                          dbState.theoremContent())
        assert thCreated, "Theorem name: " + dbState.theoremName() + ", " \
                             "content: " + dbState.theoremContent() + " has not been created"
        dlContent = DarkLogic.toStrTheorem()
        assert dlContent == dbState.theoremContent(), "Bad parsing! content in darklogic is '"\
            + dlContent + "', but original was " + dbState.theoremContent()
Esempio n. 2
0
class NeuralAI(AI):
    MaxNbNode = 100
    NbDiffOperators = 7
    OperatorParams = NbDiffOperators + 2
    NbOperators = 30
    NbTerms = NbOperators
    OpeStateSize = NbOperators + NbDiffOperators
    MaxDepth = 25
    MultExamples = 500
    MaxGameBefLearning = 50
    INIT_LR = 4 * 10 ** -6
    ModelFile = "AI/deepAIModel"
    DbName = "Database/deepaiMemory.csv"

    def __init__(self, maxInstanceIdx, secondTimeout):
        super().__init__(maxInstanceIdx, secondTimeout, name="NeuralAI")
        self._theoremName = ""
        self._theorem = ""
        # get Rule States
        self._trueRuleStates = []
        ruleStates = DarkLogic.getRuleStates()
        for ruleState in ruleStates:
            self._trueRuleStates.append(makeTrueState(ruleState))
        self._inputSize = (len(self._trueRuleStates) + 1) * NeuralAI.NbOperators * 19
        self._storeNodes = []
        self._db = Database(NeuralAI.DbName)
        self._gamesSinceLastLearning = 0
        if file_io.file_exists(NeuralAI.ModelFile):
            print("load DeepAI brain model")
            self._model = keras.models.load_model(NeuralAI.ModelFile)
        else:
            # create model
            print("create new DeepAI brain model")
            self._model = createModel(len(self._trueRuleStates) + 1)
            compileModel(self._model, NeuralAI.INIT_LR)
            self._model.save(NeuralAI.ModelFile)
        self._model = extractTestModel(self._model)
        self._modelMutex = Lock()
        self._elo = 1076  # 1418
        # self._train()

    def getTrueState(self, threadIdx):
        return [makeTrueState(DarkLogic.getState(threadIdx))] + self._trueRuleStates

    """def getTrueState(self):
        return [makeTrueState(DarkLogic.getState())] + self._trueRuleStates"""

    def setTheoremInfo(self):
        self._theoremName = DarkLogic.theoremName()
        self._theorem = DarkLogic.toNormStrTheorem()

    """
    nodeLists: 
    - type is list of list of node
    """

    def evaluate(self, nodes, trueStates):
        # evaluate states
        trueStates = np.array(trueStates)
        self._modelMutex.acquire()
        out = self._model.predict(trueStates, batch_size=len(trueStates), workers=multiprocessing.cpu_count(),
                                  use_multiprocessing=True)
        self._modelMutex.release()
        realOuts = eval(out)
        for node, realOut in zip(nodes, realOuts):
            node.setAIValue(realOut)

    def explore(self, dbNode, threadId):
        self._crtNode.exploreDeep(dbNode.actions(), threadId)

    def _train(self):
        x = []
        y = []
        print("DeepAI is preparing for training...")
        # node.getTrainNodes(x, y)
        dbStates = self._db.getDatas()
        nbExcludedTh = 0
        class_nb = {}
        for cl in range(NeuralAI.MaxDepth + 1):
            class_nb[cl] = 0
        print("Total number of theorems in database: " + str(len(dbStates)))
        dbStateIdx = -1
        remDbStates = list(dbStates.values())
        rand.shuffle(remDbStates)
        # NbMax = 200000
        NbMax = 200000
        if NbMax < len(dbStates):
            NbMaxUnevaluatedThm = NbMax - self._db.nbEvaluatedThm() if NbMax > self._db.nbEvaluatedThm() else 0
            NbMaxEvaluatedThm = NbMax - NbMaxUnevaluatedThm
        else:
            NbMaxUnevaluatedThm = len(dbStates) - self._db.nbEvaluatedThm()
            NbMaxEvaluatedThm = self._db.nbEvaluatedThm()
        print("Must select " + str(NbMaxUnevaluatedThm) + " unevaluated theorems")
        print("Must select " + str(NbMaxEvaluatedThm) + " evaluated theorems")
        NbEvaluated = 0
        NbUnevaluated = 0
        lastEvalPrint = 0
        lastUnevalPrint = 0
        for dbState in remDbStates:
            dbStateIdx += 1
            if NbEvaluated > lastEvalPrint and NbEvaluated % 10000 == 0:
                lastEvalPrint = NbEvaluated
                print(str(NbEvaluated) + " evaluated theorems have been seen")
            if NbUnevaluated > lastUnevalPrint and NbUnevaluated % 10000 == 0:
                lastUnevalPrint = NbUnevaluated
                print(str(NbUnevaluated) + " unevaluated theorems have been seen")
            DarkLogic.makeTheorem(dbState.theoremName(), dbState.theoremContent())
            state = DarkLogic.getState()
            DarkLogic.clearAll()
            if len(state.operators()) > NeuralAI.NbOperators:
                if dbState.isEvaluated() and NbMaxEvaluatedThm == self._db.nbEvaluatedThm():
                    NbMaxUnevaluatedThm += 1
                    NbMaxEvaluatedThm -= 1
                continue
            if dbState.isEvaluated():
                if NbEvaluated == NbMaxEvaluatedThm:
                    continue
                cl = dbState.value() if dbState.value() < NeuralAI.MaxDepth else NeuralAI.MaxDepth
                class_nb[cl] += 1
                l = list(range(len(self._trueRuleStates)))
                rand.shuffle(l)
                x.append([makeTrueState(state), l])
                # y.append(nthColounmOfIdentiy(cl))
                y.append(cl)
                NbEvaluated += 1
                if NbUnevaluated == NbMaxUnevaluatedThm and NbEvaluated == NbMaxEvaluatedThm:
                    break
            else:
                if NbUnevaluated == NbMaxUnevaluatedThm:
                    continue
                l = list(range(len(self._trueRuleStates)))
                rand.shuffle(l)
                x.append([makeTrueState(state), l])
                # y.append(createZeroTab(DeepAI.MaxDepth + 1))
                y.append(-1)
                NbUnevaluated += 1
                if NbUnevaluated == NbMaxUnevaluatedThm and NbEvaluated == NbMaxEvaluatedThm:
                    break

        print("Selected " + str(NbUnevaluated) + " unevaluated theorems")
        print("Selected " + str(NbEvaluated) + " evaluated theorems")

        # if we keep some examples
        if len(x):
            # check class_weight
            class_nb[-1] = 1 / NbUnevaluated
            print("Keep " + str(len(x)) + " examples")
            class_weights = {}
            for val in class_nb:
                nb_cl = class_nb[val]
                if nb_cl >= len(x) - 1:
                    print("[WARNING] Useless to train if almost all examples are from one class! Exit")
                    return
                if nb_cl != 0:
                    class_weights[val] = 1 / nb_cl
                else:
                    class_weights[val] = 0

            # shuffle examples
            print("shuffle " + str(len(x)) + " examples ...")
            randList = list(range(len(x)))
            newX = []
            newY = []
            newValues = []
            for pos in range(len(x)):
                newX.append(x[pos])
                newY.append(y[pos])
            x = newX
            y = newY
            values = newValues

            # prepare for training
            batch_size = 100
            nb_epochs = 1000
            pos = int(0.9 * len(x))
            # x = np.array(x)
            # y = np.array(y)
            values = np.array(values)
            x_train = x[:pos]
            x_test = x[pos:]
            y_train = y[:pos]
            y_test = y[pos:]
            print("training on " + str(len(x_train)) + " examples")
            # earlyStop = keras.callbacks.EarlyStopping(monitor='val_loss', min_delta=0.001, patience=20, verbose=1)
            trainBatches_x = []
            trainBatches_y = []
            testBatches_x = []
            testBatches_y = []
            batch_x = []
            batch_y = []
            # prepare train batches
            for k in range(len(x_train)):
                batch_x.append(x_train[k])
                batch_y.append(y_train[k])
                if len(batch_x) == batch_size:
                    trainBatches_x.append(batch_x)
                    batch_x = []
                    trainBatches_y.append(batch_y)
                    batch_y = []
            if len(batch_x) > 0:
                trainBatches_x.append(batch_x)
                batch_x = []
                trainBatches_y.append(batch_y)
                batch_y = []

            # prepare test batches
            for k in range(len(x_test)):
                batch_x.append(x_test[k])
                batch_y.append(y_test[k])
                if len(batch_x) == batch_size:
                    testBatches_x.append(batch_x)
                    batch_x = []
                    testBatches_y.append(batch_y)
                    batch_y = []
            if len(batch_x) > 0:
                testBatches_x.append(batch_x)
                batch_x = []
                testBatches_y.append(batch_y)
                batch_y = []

            # fit
            lr = NeuralAI.INIT_LR
            minLoss = 10 ** 100
            lastDecLoss = 0  # last epoch since loss has decreased
            # init minValLoss
            print("Validation of current model")
            if file_io.file_exists(NeuralAI.ModelFile):
                # load best model
                print("load last model")
                self._model = keras.models.load_model(NeuralAI.ModelFile)
                compileModel(self._model, lr)
            print("__________________________________________________________________________")
            crtMinValLoss, val_acc = validation(self._model, testBatches_x, testBatches_y,
                                                batch_size, class_weights, self._trueRuleStates, self._inputSize)
            print("VAL_LOSS = " + str(crtMinValLoss))
            print("VAL_ACCURACY = " + str(val_acc))
            minValLoss = 10 ** 100
            lastDecValLoss = 0  # last epoch since loss has decreased

            print("create new model")
            self._model = createModel(len(self._trueRuleStates) + 1)
            compileModel(self._model, lr)
            for epoch in range(nb_epochs):
                print("epoch n°" + str(epoch + 1) + "/" + str(nb_epochs))
                # training...
                loss, accuracy = training(self._model, trainBatches_x, trainBatches_y,
                                          batch_size, class_weights, self._trueRuleStates, self._inputSize)
                print("LOSS = " + str(loss))
                print("ACCURACY = " + str(accuracy))
                if loss < minLoss:
                    print("LOSS decreasing!")
                    minLoss = loss
                    lastDecLoss = 0
                else:
                    print("LOSS increasing!")
                    lastDecLoss += 1

                # validation...
                val_loss, val_accuracy = validation(self._model, testBatches_x, testBatches_y,
                                                    batch_size, class_weights, self._trueRuleStates, self._inputSize)
                print("VAL_LOSS = " + str(val_loss))
                print("VAL_ACCURACY = " + str(val_accuracy))
                if val_loss < minValLoss:
                    print("VAL_LOSS decreasing")
                    minValLoss = val_loss
                    lastDecValLoss = 0
                    if minValLoss < crtMinValLoss:
                        print("Improvement compared to old model!!!")
                        crtMinValLoss = minValLoss
                else:
                    print("VAL_LOSS increasing")
                    lastDecValLoss += 1

                if lastDecLoss == 3:
                    lr = lr / 10
                    print("adapt learning rate: " + str(lr))
                    compileModel(self._model, lr)
                    lastDecLoss = 0
                    minLoss = loss  # keep latest loss for minimal loss
                    print("new current minimal loss: "+str(minLoss))
                if lastDecValLoss == 10:
                    print("Early-stopping!")
                    break

                if val_loss <= crtMinValLoss:
                    print("Save model")
                    self._model.save(NeuralAI.ModelFile)
                print("_______________________________________________________________________________________")
            if file_io.file_exists(NeuralAI.ModelFile):
                # load best model
                print("load best model")
                self._model = keras.models.load_model(NeuralAI.ModelFile)
                self._model = extractTestModel(self._model)
            print("_______________________________________________________________________________________")

    def _storeCrtNode(self):
        self._storeNodes.append(self._crtNode)

    def meditate(self):
        if len(self._storeNodes) > 0:
            self._gamesSinceLastLearning += 1
            DarkLogic.makeTheorem(self._theoremName, self._theorem)
            # update if deepAI found a demonstration
            revNodes = self._storeNodes[::-1]
            if revNodes[0].value() < NeuralAI.MaxDepth:
                val = revNodes[0].value()
                for k in range(1, len(revNodes)):
                    node = revNodes[k]
                    node.setValue(val + k)
            self._db.export(self._storeNodes[0].getDbStates())
            if self._gamesSinceLastLearning == NeuralAI.MaxGameBefLearning:
                self._train()
                self._gamesSinceLastLearning = 0
            self._storeNodes.clear()
            DarkLogic.clearAll()
        super().meditate()

    def getTrainingStates(self, val, x, y):
        trueState = makeTrueState(DarkLogic.getState())
        hasToMult = True
        if val > NeuralAI.MaxDepth:
            val = NeuralAI.MaxDepth + 1
            hasToMult = False
        trueOut = nthColounmOfIdentiy(val)
        # print("shape = "+str(np.shape(trueOut)))
        mult = NeuralAI.MultExamples if hasToMult else 1
        for k in range(mult):
            crtState = [trueState]
            l = list(range(len(self._trueRuleStates)))
            rand.shuffle(l)
            for pos in l:
                crtState.append(self._trueRuleStates[pos])
            x.append(crtState)
            y.append(trueOut)

    def getBestNode(self):
        return self._crtNode.getDeepBestNode()

    def value(self):
        if self._crtNode.isAIValuated():
            return self._crtNode.aiValue()
        return self._crtNode.value()

    def canEvaluate(self, state):
        return len(state.operators()) < NeuralAI.NbOperators and len(state.terms()) < NeuralAI.NbTerms