def test_knn(self):
from classifiers import KNNClassifier
if type(self.k) == int:
k = "%s" % self.k
else:
k = "-".join([str(i) for i in self.k])
print("KNNClassifier")
print("---" * 45)
print("Train num = %s" % self.train_num)
print("Test num = %s" % self.test_num)
print("K = %s" % k)
knn = KNNClassifier(self.train_data, self.train_labels, k=self.k, best_words=self.best_words)
classify_labels = []
print("KNNClassifiers is testing ...")
for data in self.test_data:
classify_labels.append(knn.classify(data))
print("KNNClassifiers tests over.")
filepath = "f_runout/KNN-%s-train-%d-test-%d-f-%d-k-%s-%s.xls" % \
(self.type,
self.train_num, self.test_num,
self.feature_num, k,
datetime.datetime.now().strftime(
"%Y-%m-%d-%H-%M-%S"))
self.write(filepath, classify_labels)
def classify(data, classifier, num_classes, train_labels, train_features,
test_labels, test_features):
"""
Function used by FoldRunner to execute classification based on the current classifier
:param data: the configuration dictionary
:param classifier: current classifier (from the classifiers list in the configuration file)
:param num_classes: the number of distinct labels (binary or multiclass classification)
:param train_labels: the labels of all train instances
:param train_features: the features of all train instances
:param test_labels: the labels of all test instances
:param test_features: the features of all test instances
:return: the confusion matrix of the classification
"""
if classifier == "NN_keras":
return nnk.classify(data, num_classes, train_labels, train_features,
test_labels, test_features)
elif classifier == "NN_scikit-learn":
return nns.classify(train_labels, train_features, test_labels,
test_features)
elif classifier == "KNN":
return knn.classify(data, train_labels, train_features, test_labels,
test_features)
elif classifier == "NaiveBayes":
return nb.classify(train_labels, train_features, test_labels,
test_features)
elif classifier == "RandomForest":
return rf.classify(train_labels, train_features, test_labels,
test_features)
elif classifier == "LogisticRegression":
return lr.classify(train_labels, train_features, test_labels,
test_features)
def test_knn(self):
from classifiers import KNNClassifier
if type(self.k) == int:
k = "%s" % self.k
else:
k = "-".join([str(i) for i in self.k])
print("KNNClassifier")
print("---" * 45)
print("Train num = %s" % self.train_num)
print("Test num = %s" % self.test_num)
print("K = %s" % k)
# print self.train_data
print (self.train_labels)
print (len(self.train_data))
print (self.train_data[0])
knn = KNNClassifier(self.train_data, self.train_labels, k=self.k, best_words=self.best_words)
classify_labels = []
print("KNNClassifiers is testing ...")
for data in self.test_data:
classify_labels.append(knn.classify(data))
print("KNNClassifiers tests over.")
filepath = "f_runout/KNN-%s-train-%d-test-%d-f-%d-k-%s-%s.xls" % \
(self.type,
self.train_num, self.test_num,
self.feature_num, k,
datetime.datetime.now().strftime(
"%Y-%m-%d-%H-%M-%S"))
self.write(filepath, classify_labels)