clause_dict = {}
for r in range(RUNS):
print('Run:', r)
x_train, x_test, y_train, y_test = train_test_split(data, labels)
x_train_ids = x_train[:, -1]
x_test_ids = x_test[:, -1]
x_train = x_train[:, :-1]
x_test = x_test[:, :-1]
#print('\nsplits ready:',x_train.shape, x_test.shape)
tm = MultiClassTsetlinMachine(NUM_CLAUSES, T, s)
tm.fit(x_train, y_train, epochs=TRAIN_EPOCHS, incremental=True)
print('\nfit done')
result[r] = 100 * (tm.predict(x_test) == y_test).mean()
feature_vector = np.zeros(NUM_FEATURES * 2)
for cur_cls in CLASSES:
for cur_clause in range(NUM_CLAUSES):
if cur_clause % 2 == 0:
clause_type = 'positive'
else:
clause_type = 'negative'
this_clause = ''
for f in range(0, NUM_FEATURES):
action_plain = tm.ta_action(int(cur_cls), cur_clause, f)
action_negated = tm.ta_action(int(cur_cls), cur_clause,
f + NUM_FEATURES)
feature_vector[f] = action_plain
feature_vector[f + NUM_FEATURES] = action_negated
feature_count_plain[f] += action_plain
# Setup
tm = MultiClassTsetlinMachine(CLAUSES, T, s, weighted_clauses=weighting)
labels_test_indx = np.where(labels_test == 1)
labels_train_indx = np.where(labels_train == 1)
acc = []
acc_train = []
# Training
for i in range(RUNS):
print(i)
start_training = time()
tm.fit(Xtrain, labels_train, epochs=50, incremental=True)
stop_training = time()
start_testing = time()
res_test = tm.predict(Xtest)
res_train = tm.predict(Xtrain)
res_test_indx = np.where(res_test == 1)
res_train_indx = np.where(res_train == 1)
result_test2 = 100 * len(
set(list(res_test_indx[0])).intersection(set(list(
labels_test_indx[0])))) / len(list(labels_test_indx[0]))
result_train2 = 100 * len(
set(list(res_train_indx[0])).intersection(
set(list(labels_train_indx[0])))) / len(list(labels_train_indx[0]))
result_test = 100 * (res_test == labels_test).mean()
result_train = 100 * (res_train == labels_train).mean()
prf_test = precision_recall_fscore_support(res_test,
#Load Testing Data
test_data = np.loadtxt("NoisyXORTestData.txt")
X_test = test_data[:, 0:-1] #last column is class labels
Y_test = test_data[:, -1] #last column is class labels
#Initialize the Tsetlin Machine
tm = MultiClassTsetlinMachine(NUM_CLAUSES,
THRESHOLD,
S,
boost_true_positive_feedback=0)
#Fit TM on training data
tm.fit(X_train, Y_train, epochs=1)
#Predict on test data, compare to ground truth, calculate accuracy0
print("Accuracy:", 100 * (tm.predict(X_test) == Y_test).mean())
print('Type II feedbacks on clauses: ', tm.typeII_feedback_clauses)
#Prediction on some random data
print("Prediction: x1 = 1, x2 = 0, ... -> y = %d" %
(tm.predict(np.array([[1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0]]))))
print("Prediction: x1 = 0, x2 = 1, ... -> y = %d" %
(tm.predict(np.array([[0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0]]))))
print("Prediction: x1 = 0, x2 = 0, ... -> y = %d" %
(tm.predict(np.array([[0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0]]))))
print("Prediction: x1 = 1, x2 = 1, ... -> y = %d" %
(tm.predict(np.array([[1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0]]))))
print("\nLet's try to get clauses....")
NUM_FEATURES = len(X_train[0])
x_train, x_test, y_train, y_test = train_test_split(data, labels)
x_train_ids = x_train[:, -1]
x_test_ids = x_test[:, -1]
x_train = x_train[:, :-1]
x_test = x_test[:, :-1]
NUM_CLAUSES = 20
T = 15
s = 3.9
print('\nsplits ready:', x_train.shape, x_test.shape)
tm = MultiClassTsetlinMachine(NUM_CLAUSES, T, s)
tm.fit(x_train, y_train, epochs=200, incremental=True)
print('\nfit done')
result = 100 * (tm.predict(x_test) == y_test).mean()
print(result)
res = tm.predict(x_test)
for i in range(len(x_test_ids)):
sidx = x_test_ids[i]
print(sents[sidx], res[i])
NUM_CLAUSES = 10
NUM_FEATURES = len(x_train[0])
CLASSES = list(set(y_train))
print('Num Clauses:', NUM_CLAUSES)
print('Num Classes: ', len(CLASSES), ' : ', CLASSES)
print('Num Features: ', NUM_FEATURES)
CLAUSES=250 T=60 s=37 weighting = True training_epoch=5 RUNS=100 X_train, X_test, y_train, y_test = train_test_split(featureset_transformed_X, featureset_transformed_y, test_size=0.30, random_state=42, shuffle=True) tm = MultiClassTsetlinMachine(CLAUSES, T, s, weighted_clauses=weighting,append_negated=False) allacc=[] for i in range(RUNS): tm.fit(X_train, y_train, epochs=training_epoch, incremental=True) res_test=tm.predict(X_test) print(res_test) acc_test = 100*(res_test == y_test).mean() allacc.append(acc_test) #print(type(y_test), type(res_test), len(y_test), len(res_test)) prf_test_macro=precision_recall_fscore_support(list(res_test), list(y_test), average='macro') prf_test_macro=[str(round(p,2)) for p in prf_test_macro[:-1]] prf_test_micro=precision_recall_fscore_support(list(res_test), list(y_test), average='micro') prf_test_micro=[str(round(p,2)) for p in prf_test_micro[:-1]] prf_test_class=precision_recall_fscore_support(list(res_test), list(y_test), average=None)
test_size=0.084,
shuffle=False)
print(x_train.shape)
print(x_test.shape)
print(y_train.shape)
print(y_test.shape)
print('data fitting started..........................')
tm = MultiClassTsetlinMachine(2000, 40, 27, weighted_clauses=False)
print("\nAccuracy over 1000 epochs:\n")
tempAcc = []
for i in range(500):
start_training = time()
tm.fit(x_train, y_train, epochs=1, incremental=True)
stop_training = time()
start_testing = time()
result1 = 100 * (tm.predict(x_test) == y_test).mean()
result2 = 100 * (tm.predict(x_train) == y_train).mean()
stop_testing = time()
tempAcc.append(result1)
print(
"#%d AccuracyTrain: %.2f%% AccuracyTest: %.2f%% Training: %.2fs Testing: %.2fs"
% (i + 1, result2, result1, stop_training - start_training,
stop_testing - start_testing))
finalAccuracy = max(tempAcc)
print('Final Accuracy', finalAccuracy)
CLASSES = list(set(Y_train)) #list of classes
NUM_FEATURES = len(X_train[0]) #number of features
print('Num Clauses:', NUM_CLAUSES)
print('Num Classes: ', len(CLASSES), ' : ', CLASSES)
print('Num Features: ', NUM_FEATURES)
tm = MultiClassTsetlinMachine(NUM_CLAUSES,
THRESHOLD,
S,
boost_true_positive_feedback=0)
tm.fit(X_train, Y_train, epochs=200)
print("Accuracy:", 100 * (tm.predict(X_test) == Y_test))
all_clauses = [[] for i in range(NUM_CLAUSES)]
for cur_cls in CLASSES:
for cur_clause in range(NUM_CLAUSES):
this_clause = ''
for f in range(NUM_FEATURES * 2):
action = tm.ta_action(int(cur_cls), cur_clause, f)
if action == 1:
if this_clause != '':
this_clause += 'AND '
if f < NUM_FEATURES:
this_clause += 'F' + str(f) + ' '
else:
this_clause += '-|F' + str(f - NUM_FEATURES) + ' '
#%%%%%%%%%%%%%%%%%% Initialize Tsetlin Machine %%%%%%%%%%%%%%%%%%%%%%%
tm1 = MultiClassTsetlinMachine(
700, 90 * 100, 15,
weighted_clauses=True) #number of clause= 700, T = 90*100 and s = 15
#tm1.fit(X_train, ytrain, epochs=0)
print("\nTraining Classification Layer...")
print("\nAccuracy over 1000 epochs:\n")
max = 0
for i in range(500):
start_training = time()
tm1.fit(X_train, ytrain, epochs=1, incremental=True)
stop_training = time()
start_testing = time()
result2 = 100 * (tm1.predict(X_train) == ytrain).mean()
result1 = 100 * (tm1.predict(X_test) == ytest).mean()
y_pred = tm1.predict(X_test)
f1 = metrics.f1_score(ytest, y_pred, average='macro')
if result1 > max:
max = result1
pred = tm1.predict(X_test)
ta_state = tm1.get_state()
stop_testing = time()
print(
"#%d AccuracyTrain: %.2f%% AccuracyTest: %.2f%% F1-Score: %.2f%% Training: %.2fs Testing: %.2fs"
% (i + 1, result2, result1, f1 * 100, stop_training - start_training,
stop_testing - start_testing))
#%%%%%%%%%%%%%%%%% To extrat the clause with its literal of particular class %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
tm1.set_state(ta_state)
for r in range(RUNS):
print('Run:', r)
x_train, x_test, y_train, y_test = train_test_split(data, labels)
x_test = x_train[:100].copy() ######
y_test = y_train[:100].copy() ######
x_train_ids = x_train[:, -1]
x_test_ids = x_test[:, -1]
x_train = x_train[:, :-1]
x_test = x_test[:, :-1]
#print('\nsplits ready:',x_train.shape, x_test.shape)
tm = MultiClassTsetlinMachine(NUM_CLAUSES, T, s)
tm.fit(x_train, y_train, epochs=TRAIN_EPOCHS, incremental=True)
print('\nfit done')
res = tm.predict(x_test)
result[r] = 100 * (res == y_test).mean()
X_test_transformed = tm.transform(x_test)
print('here', len(x_test))
for testsample in range(100):
print(testsample)
print(res[testsample], y_test[testsample])
if res[testsample] != y_test[testsample]:
sid = x_test_ids[testsample]
fot.write(str(sid) + '\t')
'''for sentence in sents:
if sentence[0]==sid:
fot.write(' '.join(sentence[1:])+'\n')'''
fot.write(' '.join(sents[sid][1:]) + '\n')
strTransformed = [str(k) for k in X_test_transformed[testsample]]
fot.write(' '.join(strTransformed) + '\n')
EPOCHS = 1
#print('Epoch\tClass\tClause Number\tClause\tFeature\tAction\tType II fb cnt\n')
for ep in range(EPOCHS):
np.random.shuffle(data)
training, test = data[:4000, :], data[4000:, :]
X_train = training[:, 0:2]
Y_train = training[:, -1]
X_test = test[:, 0:2]
Y_test = test[:, -1]
tm.fit(X_train, Y_train, epochs=200)
accur = 100 * (tm.predict(X_test) == Y_test).mean()
#print("Accuracy:", 100*(tm.predict(X_test) == Y_test).mean())
all_clauses = tm.get_all_clauses(CLASSES, NUM_CLAUSES, NUM_FEATURES)
print('all_clauses:')
print('Class\tClause#\tClause\t')
for cur_cls in CLASSES:
for cur_clause in range(NUM_CLAUSES):
print_str = str(cur_cls) + '\t' + str(
cur_clause) + '\t' + all_clauses[cur_clause][int(cur_cls)]
print(print_str)
print(' ')
'''for cur_clause in range(NUM_CLAUSES):
for cur_cls in CLASSES:
for f in range(NUM_FEATURES*2):