def main(args):
laplace_number_set = np.linspace(0, 0.2, 2001)
print(laplace_number_set)
laplace_performance = np.zeros(2000)
for number in range(2000):
if (number == 0):
laplace_performance[number] = 0
else:
train_set, train_labels, dev_set, dev_labels = reader.load_dataset(
args.training_dir, args.development_dir, args.stemming)
predicted_labels = nb.naiveBayes(train_set, train_labels, dev_set,
laplace_number_set[number])
accuracy, f1, precision, recall = compute_accuracies(
predicted_labels, dev_set, dev_labels)
laplace_performance[number] = accuracy
best_laplace = np.argmax(laplace_performance)
train_set, train_labels, dev_set, dev_labels = reader.load_dataset(
args.training_dir, args.development_dir, args.stemming)
predicted_labels = nb.naiveBayes(train_set, train_labels, dev_set,
best_laplace)
accuracy, f1, precision, recall = compute_accuracies(
predicted_labels, dev_set, dev_labels)
laplace_performance[number] = accuracy
print("best laplace parameter:", best_laplace)
print("Accuracy:", accuracy)
print("F1-Score:", f1)
print("Precision:", precision)
print("Recall:", recall)
def test_unigram_dev_stem_false_lower_false():
print("Running unigram test..."+'\n')
train_set, train_labels, dev_set, dev_labels = reader.load_dataset(
"data/spam_data/train",
"data/spam_data/dev",
stemming=False,
lower_case=False,
use_tqdm=False
)
predicted_labels = nb.naiveBayes(
train_set, train_labels, dev_set, smoothing_parameter=1.0, pos_prior=0.5)
if len(predicted_labels) != len(dev_labels):
print("The length of the list of predictions is not equivalent to the length of the list of development labels.")
errorDict = {
'name': 'Unigram test on dev set without stemming and without lowercase',
'score': 0,
'max_score': 20,
'visibility': 'visible'
}
return json.dumps(errorDict, indent=1)
(
accuracy,
f1,
precision,
recall,
) = mp2.compute_accuracies(predicted_labels, dev_set, dev_labels)
print("Accuracy:",accuracy)
print("F1-Score:",f1)
print("Precision:",precision)
print("Recall:",recall)
total_score = 0
if accuracy >= 0.81:
total_score += 5
print("+ 5 points for accuracy above " + str(0.81))
else:
print("Accuracy needs to be above " + str(0.81))
if accuracy >= 0.86:
total_score += 5
print("+ 5 points for accuracy above " + str(0.86))
else:
print("Accuracy needs to be above " + str(0.86))
if accuracy >= 0.91:
total_score += 5
print("+ 5 points for accuracy above " + str(0.91))
else:
print("Accuracy needs to be above " + str(0.91))
if accuracy >= 0.95:
total_score += 5
print("+ 5 points for accuracy above " + str(0.95))
else:
print("Accuracy needs to be above " + str(0.95))
resultDict = {
'name': 'Unigram test on dev set without stemming and without lowercase',
'score': total_score,
'max_score': 20,
'visibility': 'visible'
}
return json.dumps(resultDict, indent=1)
def main(args):
train_set, train_labels, dev_set,dev_labels = reader.load_dataset(args.training_dir,args.development_dir,args.stemming)
predicted_labels = nb.naiveBayes(train_set,train_labels, dev_set, args.laplace)
accuracy,f1,precision,recall = compute_accuracies(predicted_labels,dev_set,dev_labels)
print("Accuracy:",accuracy)
print("F1-Score:",f1)
print("Precision:",precision)
print("Recall:",recall)
def main(args):
#Modify stemming and lower case below. Note that our test cases may use both settings of the two parameters
train_set, train_labels, dev_set, dev_labels = reader.load_dataset(args.training_dir,args.development_dir,stemming=False,lower_case=False)
predicted_labels = nb.naiveBayes(train_set, train_labels, dev_set)
accuracy, false_positive, false_negative, true_positive, true_negative = compute_accuracies(predicted_labels,dev_labels)
print("Accuracy:",accuracy)
print("False Positive", false_positive)
print("Fale Negative", false_negative)
print("True Positive", true_positive)
print("True Negative", true_negative)
def all_algo_model(self):
print(" \n----------------------------------\n")
print("\n Decision Tree \n")
print(" \n----------------------------------\n")
#decisionTree().decision_tree_algo()
print(" \n----------------------------------\n")
print("\n Gradient Descent \n")
print(" \n----------------------------------\n")
gradientDescent().gradient_descent_algo()
print(" \n----------------------------------\n")
print("\n K-Nearest Neighbour \n")
print(" \n----------------------------------\n")
#KNNAlgo().KNN__model_algo()
print(" \n----------------------------------\n")
print("\n Linear Regression \n")
print(" \n----------------------------------\n")
linearRegression().linear_regression_algo()
print(" \n----------------------------------\n")
print("\n Naive Bayes \n")
print(" \n----------------------------------\n")
naiveBayes().naive_bayes_algo()
print(" \n----------------------------------\n")
print("\n Support Vector Machine \n")
print(" \n----------------------------------\n")
svmModule().svm_model_algo()
print("\n---------- End ---------------------\n")
def main():
# List of patient objects
patient_list = parse_csv()
# create the ten folds
ten_folds_strat_list = stratify_data(patient_list)
# create the classifer objects
knn = kNN()
naive_bayes = naiveBayes()
# call the 10-fold cross validation
ten_fold_strat_cross_validation(knn, ten_folds_strat_list, 10)
ten_fold_strat_cross_validation(naive_bayes, ten_folds_strat_list)
def main(args):
train_set, train_labels, dev_set, dev_labels = reader.load_dataset(
args.training_dir, args.development_dir, args.stemming)
predicted_labels = nb.naiveBayes(train_set, train_labels, dev_set,
args.laplace)
answer = open('answer.txt', 'w')
test = open('./data/test.jsonl', 'r').readlines()
for i in range(len(test)):
answer.write(json.loads(test[i])['id'])
answer.write(",")
if predicted_labels[i] == 0:
answer.write("SARCASM")
else:
answer.write("NOT_SARCASM")
answer.write("\n")
len_bootstrap = 100
# create bootstrap with random data from data train
list_bootstrap = {}
for i in range(num_bootstrap):
bootstrap = []
for j in range(len_bootstrap):
randomData = dataTrain[np.random.randint(0, len(dataTrain))]
bootstrap.append(randomData)
list_bootstrap[i] = np.copy(bootstrap)
# predict class result from data test with each bootstrap
model_result = {}
for i in range(num_bootstrap):
dataTrain = list_bootstrap[i]
model_result[i] = nb.naiveBayes(dataTrain, dataTest, class_index=2)
# voting all model for final result
final_result = []
for i in range(len(dataTest)):
temp = [model_result[model_idx][i] for model_idx in model_result]
temp = collections.Counter(temp)
result = max(temp.items(), key=operator.itemgetter(1))[0]
final_result.append(result)
print(final_result)
# save result in csv file
data_file = open('Result.csv', 'w', newline='')
with data_file:
writer = csv.writer(data_file)
for row in final_result:
import scipy.io as io
import preprocessor as pre
from naive_bayes import naiveBayes
from logit import logisitcRegression
Numpyfile = io.loadmat('mnist_data.mat')
trX = Numpyfile['trX']
trY = Numpyfile['trY']
tsX = Numpyfile['tsX']
tsY = Numpyfile['tsY']
#extracting features (average value of pixels, standard deviation of pixels)
trxFeatures = pre.extractFeatures(trX)
tsxFeatures = pre.extractFeatures(tsX)
mean_7,mean_8,sd_7,sd_8,accuracy_bayesian_7,accuracy_bayesian_8,accuracy_bayesian_total=naiveBayes(trxFeatures,trY[0],tsxFeatures,tsY[0])
w,accuracy_logit_7,accuracy_logit_8,accuracy_logit_total = logisitcRegression(trxFeatures,trY[0],tsxFeatures,tsY[0])
print("Accuracy for Naive Bayes:")
print("For Digit 7: ",accuracy_bayesian_7*100)
print("For Digit 8: ",accuracy_bayesian_8*100)
print("Overall: ",accuracy_bayesian_total*100)
print("\n")
print("Accuracy for Logistic Regression: ")
print("For Digit 7: ",accuracy_logit_7*100)
print("For Digit 8: ",accuracy_logit_8*100)
print("Overall: ",accuracy_logit_total*100)