def naive_bayes_classify(self):
nb = NaiveBayesClassifier()
nb.train(self.X_train, self.y_train)
predictions = nb.predict(self.X_test)
accuracy = str(self.main.accuracy(self.y_test, predictions))
accuracy = accuracy[0:4]
self.naive_bayes_acc_label.setText(accuracy)
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 classifyPoems(filename):
try:
with open('CSVs/'+filename, 'r') as fp:
print('opened ' + filename )
global cl
cl = NaiveBayesClassifier(fp, format="csv")
print(cl)
except IOError:
print('\nFile not found for Naive-Bayes Classifier')
def started():
if __name__ == '__main__':
print("Ok let's go!")
# Where to find data
datasource_info = [('newyorktimes', 'data/nyt_discussions.json'),
('motherjones', 'data/motherjones_discussions.json'),
('breitbart', 'data/breitbart_discussions.json')]
# Load the dataset into memory
json_text = load_json_files(datasource_info, verbose=True)
dataset = build_dataset(json_text, featurize_text, verbose=True)
# Split our data into train and test
train_dataset, test_dataset = split_dataset(dataset, fraction_train=0.8)
# Train our classifier
nb_classifier = NaiveBayesClassifier()
nb_classifier.train(train_dataset)
# Evaluate our classifier, for each class
performance_string = 'Class {klass} performance: f1={f1:.{digits}}, precision={precision:.{digits}}, recall={recall:.{digits}}'
for klass in sorted(nb_classifier.class_counter): # sort just for nicer output
f1, precision, recall = evaluate_classifier(nb_classifier, klass,
test_dataset)
print(performance_string.format(klass=klass, f1=f1, precision=precision, recall=recall, digits=3))
else:
print("Ok let's go!")
# Where to find data
datasource_info = [('newyorktimes', 'data/nyt_discussions.json'),
('motherjones', 'data/motherjones_discussions.json'),
('breitbart', 'data/breitbart_discussions.json')]
# Load the dataset into memory
json_text = load_json_files(datasource_info, verbose=True)
dataset = build_dataset(json_text, featurize_text, verbose=True)
# Split our data into train and test
train_dataset, test_dataset = split_dataset(dataset, fraction_train=0.8)
# Train our classifier
nb_classifier = NaiveBayesClassifier()
nb_classifier.train(train_dataset)
# Evaluate our classifier, for each class
performance_string = 'Class {klass} performance: f1={f1:.{digits}}, precision={precision:.{digits}}, recall={recall:.{digits}}'
for klass in sorted(nb_classifier.class_counter): # sort just for nicer output
f1, precision, recall = evaluate_classifier(nb_classifier, klass,
test_dataset)
print(performance_string.format(klass=klass, f1=f1, precision=precision, recall=recall, digits=3))
def classify_custom_input(self, custom_input_vector):
nb = NaiveBayesClassifier()
nb.train(self.X_train, self.y_train)
prediction = nb.predict([custom_input_vector])
self.custom_text_nb_label.setText(str(prediction[0]))
knn = KNNClassifier()
prediction = knn.predict_classification(self.X_train, self.y_train,
[custom_input_vector])
self.custom_text_knn_label.setText(str(prediction[0]))
rf = SklearnRandomForest()
prediction = rf.random_forest(self.X_train, self.y_train,
[custom_input_vector])
self.custom_text_dt_label.setText(str(prediction[0]))
dt = SklearnDecisionTree()
prediction = dt.decision_tree(self.X_train, self.y_train,
[custom_input_vector])
self.custom_text_rf_label.setText(str(prediction[0]))
print("Ok let's go!")
# Where to find data
datasource_info = [('newyorktimes', 'data/nyt_discussions.json'),
('motherjones', 'data/motherjones_discussions.json'),
('breitbart', 'data/breitbart_discussions.json')]
# Load the dataset into memory
json_text = load_json_files(datasource_info, verbose=True)
dataset = build_dataset(json_text, featurize_text, verbose=True)
# Split our data into train and test
train_dataset, test_dataset = split_dataset(dataset, fraction_train=0.8)
# Train our classifier
nb_classifier = NaiveBayesClassifier()
nb_classifier.train(train_dataset)
#pdb.set_trace()
# Evaluate our classifier, for each class
performance_string = 'Class {klass} performance: f1={f1:.{digits}}, precision={precision:.{digits}}, recall={recall:.{digits}}'
for klass in sorted(
nb_classifier.class_counter): # sort just for nicer output
f1, precision, recall = evaluate_classifier(nb_classifier, klass,
test_dataset)
print(
performance_string.format(klass=klass,
f1=f1,
precision=precision,