def run_with_sample() -> None:
total_point = 0.0
number_test = 100
for i in range(0, number_test):
data = get_train_data()
samples: List[FrameOrSeries] = []
data[0], sample = get_sample_data(data[0], 25) # type: FrameOrSeries
samples.append(sample)
data[1], sample = get_sample_data(data[1], 25) # type: FrameOrSeries
samples.append(sample)
knn.clear()
knn.fit(data[0].values.tolist(), data[1].values.tolist())
point = 0
total = 0
for k in range(0, len(samples)):
for s in samples[k].values:
if knn.predict(s.tolist(), k=3) == k:
point += 1
total += 1
print('point: ' + str(point))
print('total: ' + str(total))
total_point += float(point / total * 100)
print(point / total * 100)
print('total_point: ' + str(total_point / number_test))
def test__predict_with_tans_fun(self):
X = array([[2, 4], [6, 8]])
Y = array(['a','b'])
knn = KNN(trans_fun = KNN.STD_TRANS)
knn.fit(X,Y)
self.assertEqual(knn.predict(array([4,5]), 1), 'a')
self.assertEqual(knn.predict(array([5,6]), 1), 'b')
def test__predict_with_tans_fun(self):
X = array([[2, 4], [6, 8]])
Y = array(['a', 'b'])
knn = KNN(trans_fun=KNN.STD_TRANS)
knn.fit(X, Y)
self.assertEqual(knn.predict(array([4, 5]), 1), 'a')
self.assertEqual(knn.predict(array([5, 6]), 1), 'b')
def run() -> None:
test_data = get_test_data()
data = get_train_data()
knn.clear()
knn.fit(data[0].values.tolist(), data[1].values.tolist())
test_list: list = test_data.values.tolist()
results = []
for i in test_list: # type: list
id = i[:1][0]
del i[0]
results.append([int(id), knn.predict(i)])
write_to_csv(results)
def gridsearchKNN2(parametros, xTrain, yTrain, Xval, yVal):
f1Metric = []
par = []
for params in ParameterGrid(parametros):
knn = KNeighborsClassifier(n_neighbors=params['n_neighbors'],
metric=params['metric'])
knn.fit(xTrain, yTrain)
pred = knn.predict(Xval)
f1 = metrics.f1_score(yVal, pred, average='weighted')
print(f1)
f1Metric.append(f1)
par.append(params)
return par[f1Metric.index(max(f1Metric))]
y = dataset['y']
Xtest = dataset['Xtest']
ytest = dataset['ytest']
# part 1: implement knn.predict
# part 2: print training and test errors for k=1,3,10 (use utils.classification_error)
# part 3: plot classification boundaries for k=1 (use utils.plot_2dclassifier)
model = None
predict = None
yhat = None
Yhat = None
tr_err = 0
te_err = 0
for k in [1, 3, 10]:
model = knn.fit(X, y, k)
predict = model['predict']
yhat = predict(model, X)
Yhat = predict(model, Xtest)
tr_err = utils.classification_error(y, yhat)
te_err = utils.classification_error(ytest, Yhat)
print("Training error for k =", k, "is =", tr_err)
print("Testing error for k =", k, "is =", te_err)
utils.plot_2dclassifier(knn.fit(X, y, 1), Xtest, ytest)
plt.show()
if question == '1.2':
dataset = utils.load_dataset('citiesBig1')
X = dataset['X']
y = dataset['y']
import EEG_feature_extraction
import EEG_load
# main - train&test
#dataset = EEG_load.load_data("s16",20)
dataset = EEG_feature_extraction.generate_feature_data("s16", 20)
X = dataset['X_train']
y = dataset['Y_train']
Xtest = dataset['X_test']
ytest = dataset['Y_test']
k = [1, 3, 10]
for i in range(3):
model = knn.fit(X, y, k[i])
y_pred = knn.predict(model, X)
train_error = np.mean(y_pred.flatten() != y)
print("The current training error is: %r" % train_error)
y_pred = knn.predict(model, Xtest)
test_error = np.mean(y_pred.flatten() != ytest)
print("The current test error is: %r" % test_error)
# part 3: plot classification boundaries for k=1 (use utils.plot_2dclassifier)
model1 = knn.fit(X, y, k[2])
utils.plot_2dclassifier(model1, X, y)
#plt.show()
# save figure
fname = "../s16-c20-mean.png"
'1.1', '1.2', '2.1', '2.2', '3.1', '3.2', '3.3',
'4.1', '4.2', '4.3'
])
io_args = parser.parse_args()
question = io_args.question
if question == '1.1':
dataset = utils.load_dataset('citiesSmall')
X = dataset['X']
y = dataset['y']
Xtest = dataset['Xtest']
ytest = dataset['ytest']
#model = knn.fit(X,y,3)
#model = knn.fit(X,y,1)
model = knn.fit(X, y, 10)
y_pred_tr = knn.predict(model, X)
y_pred_te = knn.predict(model, Xtest)
trerror = utils.classification_error(y_pred_tr, y)
teerror = utils.classification_error(y_pred_te, ytest)
print(trerror)
print(teerror)
utils.plot_2dclassifier(model, Xtest, ytest)
# part 1: implement knn.predict
# part 2: print training and test errors for k=1,3,10 (use utils.classification_error)
# part 3: plot classification boundaries for k=1 (use utils.plot_2dclassifier)
print(feat_vec.shape)
feat_vec = np.concatenate((feat_vec[:, :1], add / np.mean(add)), axis=1)
accuracy = 0
for i in range(0, 100):
np.random.shuffle(feat_vec)
sli = 0.8 * len(feat_vec)
X = np.split(feat_vec, [int(sli)], axis=0)
y_train = np.transpose(X[0][:, :1])[0]
X_train = X[0][:, 1:]
y_test = np.transpose(X[1][:, :1])[0]
X_test = X[1][:, 1:]
knn = neighbors.KNeighborsClassifier(n_neighbors=4,
weights='distance',
metric='manhattan')
knn.fit(X_train, y_train)
test = knn.predict(X_test)
acc = test == y_test
accuracy += acc.sum() / len(acc)
print(accuracy / 100)
