# model = models.Word2Vec.load("model6.word2vec")
# dictionary = load_doc_hashes("temp_mapper.txt")
# dim = len(model[model.vocab.keys()[0]])
# d = np.zeros(shape=(10000,100))
questions = load_thread(16,os.getcwd())
qs = Questions(questions)
with open("correct_questions_content.pickle","wb") as f:
pickle.dump(qs,f)
if __name__ == "__muin__":
with open("pickle/questions_content.pickle") as f:
questions = pickle.load(f)
(M,b) = train(questions.q.values(),[])
doc_model = Doc_Model(M,b)
with open("doc_model_content.pickle","wb") as f:
pickle.dump(doc_model,f)
# new_questions = merge_dicts(questions.q)
# qs = Questions(new_questions)
# with open("new_questions_content.pickle","wb") as f:
# pickle.dump(qs,f)
if __name__ == "__main__":
rel = [line for line in open("rel4.txt")]
hash = [line for line in open("hashes2.txt")]
qid = [line for line in open("metadata2.txt")]
dictionary = load_doc_hashes("doc_mapper.txt")
model = models.Doc2Vec.load("model1.doc2vec")
questions = load_questions(model,rel,hash,qid,dictionary)
'Triceps skin fold thickness (mm)',
'2-Hour serum insulin (mu U/ml)',
'Body mass index (weight in kg/(height in m)^2)',
'Diabetes pedigree function',
'Age (years)',
'Class variable (0: no diabetes, 1: diabetes)']
# Load data and perform train test split.
print('[INFO] Loading data.')
data = load_data(file_name, columns)
X_train, X_test, y_train, y_test = train_test_split(data, frac=0.8, seed=5)
# Logistic Model
print('\n[INFO] Training logistic regression model.')
logreg = LogReg(args.lr_logreg, args.epochs, len(X_train[0]))
bias_logreg, weights_logreg = logreg.train(X_train, y_train)
y_logistic = [round(logreg.predict(example)) for example in X_test]
# Perceptron Model
print('[INFO] Training Perceptron model.')
perceptron = Perceptron(args.lr_perceptron, args.epochs, len(X_train[0]))
bias_perceptron, weights_perceptron = perceptron.train(X_train, y_train)
y_perceptron = [round(perceptron.predict(example)) for example in X_test]
# Compare accuracies
accuracy_logistic = get_accuracy(y_logistic, y_test)
accuracy_perceptron = get_accuracy(y_perceptron, y_test)
print('\n[INFO] Logistic Regression Accuracy: {:0.3f}'.format(
accuracy_logistic))
print('[INFO] Perceptron Accuracy: {:0.3f}'.format(accuracy_perceptron))
'Diastolic blood pressure (mm Hg)', 'Triceps skin fold thickness (mm)',
'2-Hour serum insulin (mu U/ml)',
'Body mass index (weight in kg/(height in m)^2)',
'Diabetes pedigree function', 'Age (years)',
'Class variable (0: no diabetes, 1: diabetes)'
]
# Load data and perform train test split.
print('[INFO] Loading data.')
data = load_data(file_name, columns)
X_train, X_test, y_train, y_test = train_test_split(data, frac=0.8, seed=5)
# Logistic Model
print('\n[INFO] Training logistic regression model.')
logreg = LogReg(args.lr_logreg, args.epochs, len(X_train[0]))
bias_logreg, weights_logreg = logreg.train(X_train, y_train, args.decay)
y_logistic = [round(logreg.predict(example)) for example in X_test]
# Perceptron Model
print('[INFO] Training Perceptron model.')
perceptron = Perceptron(args.lr_perceptron, args.epochs, len(X_train[0]))
bias_perceptron, weights_perceptron = perceptron.train(
X_train, y_train, args.decay)
y_perceptron = [round(perceptron.predict(example)) for example in X_test]
# Compare accuracies
accuracy_logistic = get_accuracy(y_logistic, y_test)
accuracy_perceptron = get_accuracy(y_perceptron, y_test)
print('\n[INFO] Logistic Regression Accuracy: {:0.3f}'.format(
accuracy_logistic))
print('[INFO] Perceptron Accuracy: {:0.3f}'.format(accuracy_perceptron))
from model_simple import model
from config_simple import *
import logreg
if __name__ == "__main__":
logreg.train(model, dim_embed=dim_embed, class_num=class_num, learning_rate=learning_rate)
else:
# io.mmread("R_new.mtx")
# model = models.Word2Vec.load("model6.word2vec")
# dictionary = load_doc_hashes("temp_mapper.txt")
# dim = len(model[model.vocab.keys()[0]])
# d = np.zeros(shape=(10000,100))
questions = load_thread(16, os.getcwd())
qs = Questions(questions)
with open("correct_questions_content.pickle", "wb") as f:
pickle.dump(qs, f)
if __name__ == "__muin__":
with open("pickle/questions_content.pickle") as f:
questions = pickle.load(f)
(M, b) = train(questions.q.values(), [])
doc_model = Doc_Model(M, b)
with open("doc_model_content.pickle", "wb") as f:
pickle.dump(doc_model, f)
# new_questions = merge_dicts(questions.q)
# qs = Questions(new_questions)
# with open("new_questions_content.pickle","wb") as f:
# pickle.dump(qs,f)
if __name__ == "__main__":
rel = [line for line in open("rel4.txt")]
hash = [line for line in open("hashes2.txt")]
qid = [line for line in open("metadata2.txt")]
dictionary = load_doc_hashes("doc_mapper.txt")
model = models.Doc2Vec.load("model1.doc2vec")
questions = load_questions(model, rel, hash, qid, dictionary)
from sklearn.linear_model import LogisticRegression
import dataset_mnist
import logreg
'''
Apply logistic regression with sklearn
'''
def train_sclearn(X_train, y_train, X_test, y_test):
clf = LogisticRegression(fit_intercept=True, C=1e15)
print('Training with sklearn:')
clf.fit(X_train, y_train)
print('Train set accuracy: ' + str(clf.score(X_train, y_train)))
print('Test set accuracy: ' + str(clf.score(X_test, y_test)))
if __name__ == '__main__':
X_train, y_train, X_test, y_test = dataset_mnist.load_mnist_bin()
#train_sclearn(X_train, y_train, X_test, y_test)
logreg.train(X_train,
y_train,
X_test,
y_test,
30,
0.001,
use_intercept=True,
batch_size=-1)