Class ClassifierTest

history/models.py:242–444

class ClassifierTest(AbstractedTesterClass):

    BUY = 1
    SELL = 0
    HOLD = -1

    type = models.CharField(max_length=30, default='mock', db_index=True)
    symbol = models.CharField(max_length=30, db_index=True)
    name = models.CharField(max_length=100, default='')
    datasetinputs = models.IntegerField()
    granularity = models.IntegerField()
    minutes_back = models.IntegerField(default=0)
    timedelta_back_in_granularity_increments = models.IntegerField(default=0)
    ###############
    time = models.IntegerField(default=0)
    prediction_size = models.IntegerField(default=0)
    score = models.IntegerField(default=0)
    output = models.TextField()
    percent_correct = models.FloatField(null=True)

    def __str__(self):
        return self.name + " on " + str(self.created_on)

    def rerun(self, keep_new_obj=False):
        pass  # todo

    def related_mocks(self):
        days_ago = 2
        return ClassifierTest.objects.filter(created_on__gt=(timezone.now() - datetime.timedelta(days=int(days_ago))),
                                             symbol=self.symbol,
                                             minutes_back=self.minutes_back,
                                             granularity=self.granularity,
                                             datasetinputs=self.datasetinputs,
                                             name=self.name,
                                             type='mock')

    def get_classifier(self, train=True, test=True):

        all_output = ""
        h = .02  # step size in the mesh
        self.names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
                      "Random Forest", "AdaBoost", "Naive Bayes", "Linear Discriminant Analysis",
                      "Quadratic Discriminant Analysis"]
        classifiers = [
            KNeighborsClassifier(3),
            SVC(kernel="linear", C=0.025),
            SVC(gamma=2, C=1),
            DecisionTreeClassifier(max_depth=5),
            RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
            AdaBoostClassifier(),
            GaussianNB(),
            LinearDiscriminantAnalysis(),
            QuadraticDiscriminantAnalysis()]

        for i in range(0, len(self.names)):
            if self.names[i] == self.name:
                clf = classifiers[i]