def train_and_val():
training_data = dp.read_data('dataset/splice-Xtrain.dat',
'dataset/splice-Ytrain.dat')
training_set_indices, validation_set_indices = dp.read_training_val_set(
'dataset/train.txt', 'dataset/val.txt')
feature = Features()
features_labels_pair = feature.simple(training_data)
training_set = []
for index in training_set_indices:
training_set.append(features_labels_pair[index])
dp.remove_ambiguous_entry(training_set)
k_nn = KNN(training_set, 19)
confusion_matrix = np.zeros([3, 3])
correct = 0.0
total = 0.0
validation_set = []
for index in validation_set_indices:
validation_set.append(features_labels_pair[index])
dp.remove_ambiguous_entry(validation_set)
for feature_vector, correct_class in validation_set:
prediction = k_nn.predict_diff_bases(feature_vector, k_nn.no_weight)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0, 0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0, 1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0, 2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1, 0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1, 1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1, 2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2, 0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2, 1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2, 2] += 1
#print prediction, correct_class
print confusion_matrix
print correct / total
def train_and_val():
training_data = dp.read_data('dataset/splice-Xtrain.dat', 'dataset/splice-Ytrain.dat')
training_set_indices, validation_set_indices = dp.read_training_val_set('dataset/train.txt', 'dataset/val.txt')
feature = Features()
features_labels_pair = feature.simple(training_data)
training_set = []
for index in training_set_indices:
training_set.append(features_labels_pair[index])
#dp.remove_ambiguous_entry(training_set)
naive_bayes = NaiveBayes(training_set, 4, False)
validation_set = []
for index in validation_set_indices:
validation_set.append(features_labels_pair[index])
dp.remove_ambiguous_entry(validation_set)
confusion_matrix = np.zeros([3,3])
correct = 0.0
total = 0.0
for feature_vector, correct_class in validation_set:
prediction = naive_bayes.predict(feature_vector)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0,0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0,1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0,2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1,0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1,1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1,2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2,0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2,1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2,2] += 1
#print prediction, correct_class
print confusion_matrix
print correct/total
def train_and_val():
training_data = dp.read_data('dataset/splice-Xtrain.dat', 'dataset/splice-Ytrain.dat')
training_set_indices, validation_set_indices = dp.read_training_val_set('dataset/train.txt', 'dataset/val.txt')
feature = Features()
features_labels_pair = feature.amino_acid_count(training_data)
training_set = []
for index in training_set_indices:
training_set.append(features_labels_pair[index])
dp.remove_ambiguous_entry_plus(training_set)
k_nn = KNN(training_set, 23)
confusion_matrix = np.zeros([3,3])
correct = 0.0
total = 0.0
validation_set = []
for index in validation_set_indices:
validation_set.append(features_labels_pair[index])
dp.remove_ambiguous_entry_plus(validation_set)
for feature_vector, correct_class in validation_set:
prediction = k_nn.predict_codon_cosine(feature_vector, k_nn.no_weight)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0,0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0,1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0,2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1,0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1,1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1,2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2,0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2,1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2,2] += 1
#print prediction, correct_class
print confusion_matrix
print correct/total
def train_and_test():
training_data = dp.read_data('dataset/splice-Xtrain.dat',
'dataset/splice-Ytrain.dat')
test_data = dp.read_data('dataset/test40.txt', 'dataset/ytest40.txt')
feature = Features()
dp.remove_ambiguous_entry_plus(training_data)
training_set = feature.amino_acid_count(training_data)
test_set = feature.amino_acid_count(test_data)
k_nearest_neighbors = KNN(training_set, 26)
confusion_matrix = np.zeros([3, 3])
correct = 0.0
total = 0.0
for index in range(len(test_set)):
feature_vector, correct_class = test_set[index]
prediction = k_nearest_neighbors.predict_codon_cosine(
feature_vector, k_nearest_neighbors.no_weight)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0, 0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0, 1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0, 2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1, 0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1, 1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1, 2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2, 0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2, 1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2, 2] += 1
print confusion_matrix
print correct / total
def train_and_test():
training_data = dp.read_data("dataset/splice-Xtrain.dat", "dataset/splice-Ytrain.dat")
test_data = dp.read_data("dataset/test40.txt", "dataset/ytest40.txt")
feature = Features()
dp.remove_ambiguous_entry_plus(training_data)
training_set = feature.amino_acid_count(training_data)
test_set = feature.amino_acid_count(test_data)
k_nearest_neighbors = KNN(training_set, 26)
confusion_matrix = np.zeros([3, 3])
correct = 0.0
total = 0.0
for index in range(len(test_set)):
feature_vector, correct_class = test_set[index]
prediction = k_nearest_neighbors.predict_codon_cosine(feature_vector, k_nearest_neighbors.no_weight)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0, 0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0, 1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0, 2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1, 0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1, 1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1, 2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2, 0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2, 1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2, 2] += 1
print confusion_matrix
print correct / total
def train_and_test():
training_data = dp.read_data('dataset/splice-Xtrain.dat',
'dataset/splice-Ytrain.dat')
test_data = dp.read_data('dataset/test40.txt', 'dataset/ytest40.txt')
feature = Features()
training_set = feature.simple(training_data)
test_set = feature.simple(test_data)
#dp.remove_ambiguous_entry(training_set)
naive_bayes = NaiveBayes(training_set, 4, False)
confusion_matrix = np.zeros([3, 3])
correct = 0.0
total = 0.0
for index in range(len(test_set)):
feature_vector, correct_class = test_set[index]
prediction = naive_bayes.predict(feature_vector)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0, 0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0, 1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0, 2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1, 0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1, 1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1, 2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2, 0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2, 1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2, 2] += 1
print confusion_matrix
print correct / total
def train_and_test():
training_data = dp.read_data("dataset/splice-Xtrain.dat", "dataset/splice-Ytrain.dat")
test_data = dp.read_data("dataset/test40.txt", "dataset/ytest40.txt")
feature = Features()
training_set = feature.simple(training_data)
test_set = feature.simple(test_data)
# dp.remove_ambiguous_entry(training_set)
naive_bayes = NaiveBayes(training_set, 4, False)
confusion_matrix = np.zeros([3, 3])
correct = 0.0
total = 0.0
for index in range(len(test_set)):
feature_vector, correct_class = test_set[index]
prediction = naive_bayes.predict(feature_vector)
total += 1
if prediction == correct_class:
correct += 1
if prediction == 0 and correct_class == 0:
confusion_matrix[0, 0] += 1
if prediction == 0 and correct_class == 1:
confusion_matrix[0, 1] += 1
if prediction == 0 and correct_class == 2:
confusion_matrix[0, 2] += 1
if prediction == 1 and correct_class == 0:
confusion_matrix[1, 0] += 1
if prediction == 1 and correct_class == 1:
confusion_matrix[1, 1] += 1
if prediction == 1 and correct_class == 2:
confusion_matrix[1, 2] += 1
if prediction == 2 and correct_class == 0:
confusion_matrix[2, 0] += 1
if prediction == 2 and correct_class == 1:
confusion_matrix[2, 1] += 1
if prediction == 2 and correct_class == 2:
confusion_matrix[2, 2] += 1
print confusion_matrix
print correct / total