def test_blob_classification_numpy(self):
"""
Tests kNN for classification using
randomly-generated points drawn from
Gaussian-shaped clusters.
Splits data into training and testing
sets.
"""
k = 3
X, y = generate_cluster_samples()
train_X, test_X, train_y, test_y = train_test_split(X, y, stratify=y)
knn = KNN(k)
knn.fit(train_X, train_y)
pred_y = knn.predict_numpy(test_X)
# verify shape of output
self.assertEqual(len(pred_y.shape), 1)
self.assertEqual(pred_y.shape[0], test_X.shape[0])
# with k=1, each point should match itself
accuracy = accuracy_score(test_y, pred_y)
self.assertAlmostEqual(accuracy, 1.0)
def main():
K = [1, 3]
#load CM1
data = pd.read_csv('./lvq_output/seed_137/kc1_lvq3.csv')
X, Y = data.drop(columns=['defects']), data['defects']
# normalize data
#X = normalize_data(X)
# create k-fold splits
kf = KFold(n_splits=10)
# instanciate classifier
for k in K:
clf = KNN(k=k)
print("k equals {}".format(k))
start_time = time.time()
acc = []
for train, test in kf.split(X):
clf.fit(X.iloc[train], Y.iloc[train])
predictions = clf.predict(X.iloc[test])
acc.append((np.sum(predictions == Y.iloc[test]) / len(test)) * 100)
end_time = time.time()
acc = np.array(acc)
print("mean accuracy: {}".format(np.mean(acc)))
print("standard deviation: {}".format(np.std(acc)))
print("time elapsed: {}".format(end_time - start_time))
def test_synthetic_data(self):
"""
Test KNN.predict using some synthetic data
"""
x_train = np.array([[1, 2], [1, 3], [2, 2], [2, 3], [1, 1], [2, 1]])
y_train = np.array([1, 1, 1, -1, -1, -1])
model = KNN(k=3)
model.fit(x_train, y_train)
x_test = np.array([
[1.8, 2.6],
[2.0, 1.8],
[1.5, 2.0],
[1.0, 2.5],
[1.5, 1.0],
[2.0, 1.0],
])
pred = model.predict(x_test)
self.assertTrue(np.array_equal(pred, np.array([1, 1, 1, 1, -1, -1])))
# one labels should change if using 1-nn
model.k = 1
pred2 = model.predict(x_test)
self.assertTrue(np.array_equal(pred2, np.array([-1, 1, 1, 1, -1, -1])))
def test_knn_regression():
while True:
N = np.random.randint(2, 100)
M = np.random.randint(2, 100)
k = np.random.randint(1, N)
ls = np.min([np.random.randint(1, 10), N - 1])
weights = np.random.choice(["uniform", "distance"])
X = np.random.rand(N, M)
X_test = np.random.rand(N, M)
y = np.random.rand(N)
knn = KNN(k=k,
leaf_size=ls,
metric=euclidean,
classifier=False,
weights=weights)
knn.fit(X, y)
preds = knn.predict(X_test)
gold = KNeighborsRegressor(
p=2,
leaf_size=ls,
n_neighbors=k,
weights=weights,
metric="minkowski",
algorithm="ball_tree",
)
gold.fit(X, y)
gold_preds = gold.predict(X_test)
for mine, theirs in zip(preds, gold_preds):
np.testing.assert_almost_equal(mine, theirs)
print("PASSED")
def main():
trainSet = pd.read_csv('datasets/train_set.csv',
converters={'Trajectory': literal_eval})
testSet = pd.read_csv('datasets/test_set_a2.csv',
converters={'Trajectory': literal_eval})
# labels for categories
le = preprocessing.LabelEncoder()
categoryIds = le.fit_transform(trainSet['journeyPatternId'])
allSequences = []
for trainIndex, trainRow in trainSet.iterrows():
allSequences.append(trainRow['Trajectory'])
# initialize KNN classifier
clf = KNN(5, DTW)
crossValidation(clf, allSequences, categoryIds, le)
clf.fit(allSequences, categoryIds)
# predict the categories for the testSet
predIds = clf.predict(testSet['Trajectory'])
predCategs = le.inverse_transform(predIds)
writeInCsv(predCategs)
def foo(k_num=5, distance=distance_metric(p=1)):
_data = [[i[0], i[3]] for i in data]
# Split the data into train and test parts
#train_d, train_l, test_d, test_l = tt_split(_data, label)
train_d, train_l, test_d, test_l = (_data[0:30] + _data[50:80] +
_data[100:130], label[0:30] +
label[50:80] + label[100:130],
_data[30:50] + _data[80:100] +
_data[130:], label[30:50] +
label[80:100] + label[130:])
# Initialize the KNN object
knn = KNN(neighbors_num=k_num, distance=distance)
# Fill the data in KNN
knn.fit(train_d, train_l)
# Take prediction from KNN
result = knn.predict(test_d)
# Print the results on screen as data, real label, predicted label.
#print("%20s - %20s | %20s | %s" %("[Data]", "<Real Label>", "<Predicted Label>", "Truth"))
n = 0
for i, j, r in zip(test_d, test_l, result):
truthness = True if j == r else False
if truthness:
n += 1
#print("%20s - %20s | %20s | %s" %(i, j, r, truthness))
#print("Acc:", n / len(test_d))
return n / len(test_d), n, len(test_d)
class Stacking():
def __init__(self):
pass
def fit(self, X, y):
self.rf = RandomForest(num_trees=15, max_depth=np.inf)
self.rf.fit(X, y)
y_rf = self.rf.predict(X)
self.nb = NaiveBayes()
self.nb.fit(X, y)
y_nb = self.nb.predict(X)
self.knn = KNN(k=3)
self.knn.fit(X, y)
y_knn = self.knn.predict(X)
newX = np.array([y_rf, y_nb, y_knn]).transpose()
model = DecisionTree(max_depth=np.inf,
stump_class=DecisionStumpErrorRate)
self.model = model
model.fit(newX, y)
def predict(self, X):
y_rf = self.rf.predict(X)
y_nb = self.nb.predict(X)
y_knn = self.knn.predict(X)
x_test = np.array([y_rf, y_nb, y_knn]).transpose()
return self.model.predict(x_test)
def test_knn_clf():
while True:
N = np.random.randint(2, 100)
M = np.random.randint(2, 100)
k = np.random.randint(1, N)
n_classes = np.random.randint(10)
ls = np.min([np.random.randint(1, 10), N - 1])
weights = "uniform"
X = np.random.rand(N, M)
X_test = np.random.rand(N, M)
y = np.random.randint(0, n_classes, size=N)
knn = KNN(k=k,
leaf_size=ls,
metric=euclidean,
classifier=True,
weights=weights)
knn.fit(X, y)
preds = knn.predict(X_test)
gold = KNeighborsClassifier(
p=2,
leaf_size=ls,
n_neighbors=k,
weights=weights,
metric="minkowski",
algorithm="ball_tree",
)
gold.fit(X, y)
gold_preds = gold.predict(X_test)
for mine, theirs in zip(preds, gold_preds):
np.testing.assert_almost_equal(mine, theirs)
print("PASSED")
def fit(self, X, y):
# instantiate the input models
rf = RandomForest(num_trees=15)
knn = KNN(k=3)
nb = NaiveBayes(num_classes=2)
# Random Forest fit and predict
rf.create_splits(X)
rf.fit(X, y)
rf_pred = rf.predict(X)
# K-Nearest Neighbors fit and predict
knn.fit(X, y)
knn_pred = knn.predict(X)
# Naive Bayes fit and predict
nb.fit(X, y)
nb_pred = nb.predict(X)
# use predictions from input models as inputs for meta-classifiers
meta_input = np.hstack((rf_pred.reshape(
(rf_pred.size, 1)), knn_pred.reshape(
(knn_pred.size, 1)), nb_pred.reshape((nb_pred.size, 1))))
# use Decision Tree as meta-classifier
dt = DecisionTree(max_depth=np.inf)
dt.fit(meta_input, y)
self.rf = rf
self.knn = knn
self.nb = nb
self.meta_classifier = dt
def eval_model(case):
l, k = case
results = {'precision': [], 'recall': [], 'f1': []}
model = KNN(l, k)
for i in range(folds):
print(l, k, 'cross validation', i)
training, testing = split_data(corpus, i, folds)
print(l, k, 'fit model', i)
model.fit([d.vector for d in training],
[d.label for d in training])
print(l, k, 'predict', i)
preds = [model.predict(d.vector) for d in testing]
labels = [d.label for d in testing]
metrics = model_metrics(labels, preds)
for m, key in zip(metrics, ['precision', 'recall', 'f1']):
results[key].append(m)
print(l, k, mean(results['precision']), mean(results['recall']),
mean(results['f1']))
return results
def knn(corpus, idf):
query = read_folder('./query')
tf_idf(query, idf)
print('fit KNN model')
classifier = KNN(5, 5)
classifier.fit([d.vector for d in corpus], corpus)
start_time = time.time()
for i, d in enumerate(query):
print('Query Doc', i)
print(d.features)
# neighbors = classifier.brute_force(d.vector)
neighbors = classifier.neighbors(d.vector)
print('Query Neighbors', i)
for n in neighbors:
print(n.features)
print('\n')
print('\n')
print("--- %s seconds ---" % (time.time() - start_time))
def knn_validate(data, kernel, metric, k_neighbors, show_plot):
plot = Plot()
matrix_full = [[0, 0], [0, 0]]
y_predict_arr = []
for i in range(len(data)):
data.updateTrainTest(i)
trainDots, trainClass = data.getDotsByMode('train', False)
testDots, testClass = data.getDotsByMode('test', False)
knn = KNN(kernel=kernel, metric=metric, neighbors=k_neighbors)
knn.fit(trainDots, trainClass)
y_predict, distance = knn.predict(testDots)
y_predict_arr.append(y_predict[0])
if show_plot:
tDots = np.array(trainDots)
tCls = np.array(trainClass)
plot.knn(tDots[tCls == 1.0], tDots[tCls == -1.0], distance, testDots[0], y_predict[0])
matrix = get_metrics(y_predict, testClass)
matrix_full[0][0] += matrix[0][0]
matrix_full[0][1] += matrix[0][1]
matrix_full[1][0] += matrix[1][0]
matrix_full[1][1] += matrix[1][1]
return y_predict_arr, get_f_measure(matrix_full), matrix_full
def main():
K = [1, 2, 3, 5, 7, 9, 11, 13, 15]
#load CM1
data = arff.loadarff('./datasets/CM1.arff')
X, Y = build_dataframe(data)
# normalize data
X = normalize_data(X)
# create k-fold splits
kf = KFold(n_splits=10)
# instanciate classifier
for k in K:
clf = KNN(k=k)
print("k equals {}".format(k))
start_time = time.time()
acc = []
for train, test in kf.split(X):
clf.fit(X.iloc[train], Y.iloc[train])
predictions = clf.predict(X.iloc[test])
acc.append((np.sum(predictions == Y.iloc[test]) / len(test)) * 100)
end_time = time.time()
acc = np.array(acc)
print("mean accuracy: {}".format(np.mean(acc)))
print("standard deviation: {}".format(np.std(acc)))
print("time elapsed: {}".format(end_time - start_time))
def test_iris_regression(self):
"""
Tests kNN for regression
"""
k = 1
iris_dataset = load_iris()
knn = KNN(k, "average")
# get petal length as input
# ensure this is 2D
X = iris_dataset.data[:, 2].reshape(-1, 1)
# get petal width as output
y = iris_dataset.data[:, 3]
knn.fit(X, y)
predicted = knn.predict(X)
# verify shape of output
self.assertEqual(len(predicted.shape), 1)
self.assertEqual(predicted.shape[0], iris_dataset.data.shape[0])
# with k=1, each point should match itself
# but with only 1 dimension, some points have
# the same values
mse = mean_squared_error(y, predicted)
self.assertLess(mse, 0.1)
def calc_accuracy_multiclass(train_X,train_y, test_X, test_y,num_folds,K):
knn_classifier = KNN(k=K)
knn_classifier.fit(train_X, train_y)
predict = knn_classifier.predict(test_X)
#rint('predicted ',predict)
#print('real value',test_y)
accuracy = multiclass_accuracy(predict, test_y)
print("Accuracy: %4.2f" % accuracy)
return accuracy
def rerank_results(feedback, similar_images, similar_image_vectors,
query_image_vector):
global feedback_imgs_g, feedback_vals_g, similar_images_g, similar_image_vectors_g
similar_images_g = similar_images
similar_image_vectors_g = similar_image_vectors
# Add DT based relevance feedback function
clf = DecisionTree()
feedback_imgs = list(feedback.keys())
feedback_vals = list(feedback.values())
x_train_old, y_train = get_training_set(feedback_imgs, feedback_vals)
x_train = []
for i in x_train_old:
j = i.tolist()
x_train.append(j)
clf.fit(x_train, y_train)
# x_test = similar_image_vectors_g.values()
x_test = []
for i in similar_image_vectors_g.values():
j = i.tolist()
x_test.append(j)
predictions = clf.predict(x_test)
#relevant images
indices_rel = [i for i, x in enumerate(predictions) if x == 1]
print("Relevant", indices_rel)
x_train_knn_rel = []
rel_len = len(indices_rel)
for i in indices_rel:
x_train_knn_rel.append(x_test[i])
knn = KNN(rel_len)
#knn = KNeighborsClassifier(n_neighbours=rel_len)
knn.fit(x_train_knn_rel)
neighbours_rel = knn.get_neighbours([query_image_vector])
print("Neighbours Rel", neighbours_rel)
#irrelevant images
indices_ir = [i for i, x in enumerate(predictions) if x == -1]
print("Irrelevant", indices_ir)
x_train_knn_ir = []
ir_len = len(indices_ir)
for i in indices_ir:
x_train_knn_ir.append(x_test[i])
knn = KNN(ir_len)
knn.fit(x_train_knn_ir)
neighbours_ir = knn.get_neighbours([query_image_vector])
print("Neighbours IR", neighbours_ir)
ranked_indices = []
ranked_indices.extend(indices_rel)
ranked_indices.extend(indices_ir)
rel_similar_images = [
list(similar_image_vectors_g.keys())[index] for index in ranked_indices
]
return rel_similar_images
def test_fit(self):
"""
Test KNN.fit is actually storing the training data
"""
x_train = np.array([[1, 2], [1, 3], [2, 2], [2, 3], [1, 1], [2, 1]])
y_train = np.array([1, 1, 1, -1, -1, -1])
model = KNN()
model.fit(x_train, y_train)
self.assertTrue(np.array_equal(x_train, model.x_train))
self.assertTrue(np.array_equal(y_train, model.y_train))
def run_knn(data, target_column):
st.sidebar.title('Choose parameters for KNN')
ts = st.sidebar.slider('Training size', min_value=0.0, max_value=1.0, step=0.01, value=0.7)
k = st.sidebar.number_input('k', min_value=1, max_value=int(len(data)*ts), step=1, value=3)
run_status = st.sidebar.button('Run Algorithm')
if run_status:
with st.spinner('Running...'):
x_train, x_test, y_train, y_test = train_test_split(data.drop([target_column], axis=1),
data[target_column],
test_size=1 - ts)
clf = KNN(k=k)
clf.fit(x_train, y_train)
"""
## :dart: Accuracy
"""
st.subheader(accuracy_score(y_test, clf.predict(x_test)))
def cross_validation(corpus, idf):
nb_results = {'precision': [], 'recall': [], 'f1': []}
knn_results = {'precision': [], 'recall': [], 'f1': []}
vocab = sorted(idf.keys())
random.shuffle(corpus)
for i in range(10):
print('cross validation', i)
training, testing = split_data(corpus, i, 10)
nb = NaiveBayes(training, vocab, 0.1)
knn = KNN(5, 5)
knn.fit([d.vector for d in training], [d.label for d in training])
labels = [d.label for d in testing]
nb_preds = [nb.predict(d) for d in testing]
knn_preds = [knn.predict(d.vector) for d in testing]
metrics = model_metrics(labels, nb_preds)
for m, k in zip(metrics, ['precision', 'recall', 'f1']):
nb_results[k].append(m)
metrics = model_metrics(labels, knn_preds)
for m, k in zip(metrics, ['precision', 'recall', 'f1']):
knn_results[k].append(m)
for m in ['precision', 'recall', 'f1']:
print('nb', m)
print(nb_results[m])
print(m, 'nb mean', mean(nb_results[m]))
print('knn', m)
print(knn_results[m])
print(m, 'knn mean', mean(knn_results[m]))
diff = [a - b for a, b in zip(nb_results[m], knn_results[m])]
print(m, 'diff')
print(diff)
t = mean(diff) / (stdev(diff) / len(diff)**0.5)
print(m, 't value:', t)
def test_iris_classification_loop(self):
"""
Tests kNN for classification with loops
"""
k = 1
iris_dataset = load_iris()
knn = KNN(k)
knn.fit(iris_dataset.data, iris_dataset.target)
predicted = knn.predict_loop(iris_dataset.data)
# verify shape of output
self.assertEqual(len(predicted.shape), 1)
self.assertEqual(predicted.shape[0], iris_dataset.data.shape[0])
# with k=1, each point should match itself
accuracy = accuracy_score(iris_dataset.target, predicted)
self.assertAlmostEqual(accuracy, 1.0)
def fit(self, X, y):
N, D = X.shape
rfModel = RandomForestClassifier(n_estimators=50)
nbModel = NaiveBayes(num_classes=2)
knnModel = KNN(3)
knnModel.fit(X, y)
knn_y_pred = knnModel.predict(X).astype(int)
nbModel.fit(X, y)
nb_y_pred = nbModel.predict(X).astype(int)
rfModel.fit(X, y)
rf_y_pred = rfModel.predict(X).astype(int)
Xy_label_combined = np.array(
(knn_y_pred, nb_y_pred, rf_y_pred)).transpose()
self.Xy_label_combined = Xy_label_combined
self.y = y
def cosine():
train_d, train_l, test_d, test_l = tt_split(data, label)
# Initialize the KNN object
knn = KNN(neighbors_num=5, distance=cosine_distance())
# Fill the data in KNN
knn.fit(train_d, train_l)
# Take prediction from KNN
result = knn.predict(test_d)
# Print the results on screen as data, real label, predicted label.
#print("%20s - %20s | %20s | %s" %("[Data]", "<Real Label>", "<Predicted Label>", "Truth"))
n = 0
for i, j, r in zip(test_d, test_l, result):
truthness = True if j == r else False
if truthness:
n += 1
print("%20s - %20s | %20s | %s" % (i, j, r, truthness))
print("Acc:", n / len(test_d))
return n / len(test_d)
def test_predict(self):
knn = KNN(3)
model = knn.fit(self.X, self.y)
md = model.predict(self.X.iloc[4:])
exp_md = pd.DataFrame({
4: ['b', 6],
5: ['b', 6],
6: ['b', 6]
},
index=[0, 1]).T
pdt.assert_frame_equal(exp_md, md)
def test_knn():
df = pd.read_csv(
'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data',
header=None)
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
y = np.random.randint(2, size=100)
x = df.iloc[0:100, [0, 2]].values
print("Testing 2-D Iris data set with only one neighbor...")
neighbor = KNN(k=1)
neighbor.fit(x, y)
neighbor.plot(x, y)
print("Testing Iris data set with 15 neighbor...")
iris = datasets.load_iris()
x = iris.data[:, :2]
y = iris.target
neighbor = KNN(15)
neighbor.fit(x, y)
y_pred = neighbor.predict(x)
neighbor.accuracy(y_pred, y)
neighbor.plot(x, y)
print(
"Adding new point to dataset and testing with full Iris 1-k data set..."
)
neighbor = KNN(1)
neighbor.fit(x, y)
y2 = np.array([1])
y2 = np.append(y, y2)
x2 = np.vstack([x, [5.0, 3.2]])
neighbor.plot(x2, y2)
print("Testing SKLearn's model...")
clf = neighbors.KNeighborsClassifier(1)
clf.fit(x, y)
plot_decision_regions(x2, y2, clf)
def plot_knn():
np.random.seed(12345)
fig, axes = plt.subplots(4, 4)
for i, ax in enumerate(axes.flatten()):
n_in = 1
n_out = 1
d = np.random.randint(1, 5)
n_ex = np.random.randint(5, 500)
std = np.random.randint(0, 1000)
intercept = np.random.rand() * np.random.randint(-300, 300)
X_train, y_train, X_test, y_test, coefs = random_regression_problem(
n_ex, n_in, n_out, d=d, intercept=intercept, std=std, seed=i)
LR = LinearRegression(fit_intercept=True)
LR.fit(X_train, y_train)
y_pred = LR.predict(X_test)
loss = np.mean((y_test.flatten() - y_pred.flatten())**2)
knn_1 = KNN(k=1, classifier=False, leaf_size=10, weights="uniform")
knn_1.fit(X_train, y_train)
y_pred_1 = knn_1.predict(X_test)
loss_1 = np.mean((y_test.flatten() - y_pred_1.flatten())**2)
knn_5 = KNN(k=5, classifier=False, leaf_size=10, weights="uniform")
knn_5.fit(X_train, y_train)
y_pred_5 = knn_5.predict(X_test)
loss_5 = np.mean((y_test.flatten() - y_pred_5.flatten())**2)
knn_10 = KNN(k=10, classifier=False, leaf_size=10, weights="uniform")
knn_10.fit(X_train, y_train)
y_pred_10 = knn_10.predict(X_test)
loss_10 = np.mean((y_test.flatten() - y_pred_10.flatten())**2)
xmin = min(X_test) - 0.1 * (max(X_test) - min(X_test))
xmax = max(X_test) + 0.1 * (max(X_test) - min(X_test))
X_plot = np.linspace(xmin, xmax, 100)
y_plot = LR.predict(X_plot)
y_plot_1 = knn_1.predict(X_plot)
y_plot_5 = knn_5.predict(X_plot)
y_plot_10 = knn_10.predict(X_plot)
ax.scatter(X_test, y_test, alpha=0.5)
ax.plot(X_plot, y_plot, label="OLS", alpha=0.5)
ax.plot(X_plot, y_plot_1, label="KNN (k=1)", alpha=0.5)
ax.plot(X_plot, y_plot_5, label="KNN (k=5)", alpha=0.5)
ax.plot(X_plot, y_plot_10, label="KNN (k=10)", alpha=0.5)
ax.legend()
# ax.set_title(
# "MSE\nLR: {:.2f} KR (poly): {:.2f}\nKR (rbf): {:.2f}".format(
# loss, loss_poly, loss_rbf
# )
# )
ax.xaxis.set_ticklabels([])
ax.yaxis.set_ticklabels([])
plt.tight_layout()
plt.savefig("img/knn_plots.png", dpi=300)
plt.close("all")
def test_query(self):
knn = KNN(3)
model = knn.fit(self.X, self.y)
gen = model.query(self.X.iloc[4:])
dist, md = next(gen)
exp_dist = np.array([
0,
euclidean(self.X.iloc[4], self.X.iloc[6]),
euclidean(self.X.iloc[4], self.X.iloc[5])
])
exp_md = pd.DataFrame([['b', 5], ['b', 7], ['b', 6]], index=[4, 6, 5])
npt.assert_allclose(exp_dist, dist)
pdt.assert_frame_equal(exp_md, md)
def plot(h=.02):
_data = [[i[0], i[3]] for i in data]
# Split the data into train and test parts
##train_d, train_l, test_d, test_l = tt_split(_data, label)
train_d, train_l, test_d, test_l = (_data[0:30] + _data[50:80] +
_data[100:130], label[0:30] +
label[50:80] + label[100:130],
_data[30:50] + _data[80:100] +
_data[130:], label[30:50] +
label[80:100] + label[130:])
# Initialize the KNN object
knn = KNN(neighbors_num=3, distance=cosine_distance())
# Fill the data in KNN
knn.fit(train_d, train_l)
_t = np.array(train_d)
x_min, x_max = _t[:, 0].min() - .2, _t[:, 0].max() + .2
y_min, y_max = _t[:, 1].min() - .2, _t[:, 1].max() + .2
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
Z = np.c_[xx.ravel(), yy.ravel()]
Z = np.array(knn.predict(Z))
Z = Z.reshape(xx.shape)
print(Z)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
# Plot also the training points
plt.scatter(_t[:, 0],
_t[:, 1],
c=train_l,
cmap=cmap_bold,
edgecolor='k',
s=20)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.show()
# https://deeplearningcourses.com/c/data-science-supervised-machine-learning-in-python
# https://www.udemy.com/data-science-supervised-machine-learning-in-python
from knn import KNN
from util import get_xor
import matplotlib.pyplot as plt
if __name__ == '__main__':
X, Y = get_xor()
# display the data
plt.scatter(X[:, 0], X[:, 1], s=100, c=Y, alpha=0.5)
plt.show()
# get the accuracy
model = KNN(3)
model.fit(X, Y)
print "Accuracy:", model.score(X, Y)
# https://deeplearningcourses.com/c/data-science-supervised-machine-learning-in-python
# https://www.udemy.com/data-science-supervised-machine-learning-in-python
from __future__ import print_function, division
from builtins import range, input
# Note: you may need to update your version of future
# sudo pip install -U future
from knn import KNN
from util import get_xor
import matplotlib.pyplot as plt
if __name__ == '__main__':
X, Y = get_xor()
# display the data
plt.scatter(X[:,0], X[:,1], s=100, c=Y, alpha=0.5)
plt.show()
# get the accuracy
model = KNN(3)
model.fit(X, Y)
print("Accuracy:", model.score(X, Y))
import numpy as np from sklearn import datasets from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap from knn import KNN iris = datasets.load_iris() X, y = iris.data, iris.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) clf = KNN(k=3) clf.fit(X_train, y_train) predictions = clf.predict(X_test) accuracy = np.sum(predictions == y_test) / len(y_test) print(accuracy * 100) # my_cmap = ListedColormap(["#FF781F", "#149414", "#52307C"]) # plt.figure() # # Displaying 2 out of 4 features so that we can see in 2D # plt.scatter(X[:, 0], X[:, 1], c=y, cmap=my_cmap, edgecolor='k', s=20) # plt.show()
clf.fit(X, y)
print("Naive Bayes (sklearn) validation error: %.3f" %
(1 - clf.score(X, y)))
elif question == '3':
with open(os.path.join('..', 'data', 'citiesSmall.pkl'), 'rb') as f:
dataset = pickle.load(f)
X = dataset['X']
y = dataset['y']
Xtest = dataset['Xtest']
ytest = dataset['ytest']
for i in [1]:
knn = KNN(i)
knn.fit(X, y)
print("Training")
tr_prediction = knn.predict(X)
knn.getError(tr_prediction, y)
print("Testing")
prediction = knn.predict(Xtest)
knn.getError(prediction, ytest)
utils.plotClassifier(knn, X, y)
neigh = KNeighborsClassifier(n_neighbors=1)
neigh.fit(X, y)
# print(neigh.predict(ytest))
print("Sklearn KNN: {}".format(1 - neigh.score(X, y)))
utils.plotClassifier(neigh, X, y)
elif question == '4':
if elem[2]*av_score[elem[1]-1] > 0 or (elem[2]==0 and av_score[elem[1]-1] <= 0):
accuracy+=1
print "Simple Accuracy:", np.around(100.0*accuracy/len(validationData)), "%"
############# PERSONAL PREF #############
print 20 * "#", "Personal Pref", 20 * "#"
jokeDataNew = jokeData
# replace nan by 0
for i in range(len(jokeData)):
jokeDataNew[i] = [0 if np.isnan(x) else x for x in jokeData[i] ]
for k in [10, 100, 1000]:
print "K Value:", k
knn = KNN(k)
knn.fit(jokeDataNew)
neighbours = knn.neighbours
av_score = []
accuracy = 0
for i in range(100):
average_score = (np.mean([jokeDataNew[ind] for ind in neighbours[i]], 0))
av_score.append(average_score)
for elem in validationData:
if (elem[2]*av_score[elem[0]-1][elem[1]-1] > 0) or (elem[2]==0 and av_score[elem[0]-1][elem[1]-1] < 0):
accuracy+=1
print "Pref Accuracy:", np.around(100.0*accuracy/len(validationData)), "%"
############# LATENT FACTOR ANALYSIS #############
print 20 * "#", "PCA", 20 * "#"