def predict(self, x, y):
# since dimension issue x*W.T will be the right way to describe
# so the assign of W will change the original dimension setting(take transpose, but mean the same)
self.h1 = f.sigmoid((self.x).dot(self.w1))
self.h2 = f.sigmoid((self.h1).dot(self.w2))
self.res = f.sigmoid((self.h2).dot(self.w3))
self.pred_y = np.where(self.res >= 0.5, 1, 0)
self.acc = (self.y.shape[0] -
abs(self.y - self.pred_y).sum()) / self.y.shape[0] * 100.0
def predict(network, x):
W1, W2, W3 = network["W1"], network["W2"], network["W3"]
b1, b2, b3 = network["b1"], network["b2"], network["b3"]
a1 = np.dot(x, W1) + b1
z1 = func.sigmoid(a1)
a2 = np.dot(z1, W2) + b2
z2 = func.sigmoid(a2)
a3 = np.dot(z2, W3) + b3
y = func.softmax(a3)
return y
def predict(w, b, X):
'''
Predict whether the label is 0 or 1 using learned logistic regression parameters (w, b)
Arguments:
w -- weights, a numpy array of size (num_px * num_px * 3, 1)
b -- bias, a scalar
X -- data of size (num_px * num_px * 3, number of examples)
Returns:
Y_prediction -- a numpy array (vector) containing all predictions (0/1) for the examples in X
'''
m = X.shape[1]
Y_prediction = np.zeros((1, m))
w = w.reshape(X.shape[0], 1)
# Compute vector "A" predicting the probabilities of a cat being present in the picture
### START CODE HERE ### (≈ 1 line of code)
A = sigmoid(np.dot(w.T, X) + b)
### END CODE HERE ###
for i in range(A.shape[1]):
# Convert probabilities a[0,i] to actual predictions p[0,i]
### START CODE HERE ### (≈ 4 lines of code)
Y_prediction[0, i] = 1 if A[0, i] > 0.5 else 0
### END CODE HERE ###
assert(Y_prediction.shape == (1, m))
return Y_prediction
def fit(self, x, y, learning_rate=0.01, epochs: int = 10, L2=0.1):
# 如果y只有一列，给他reshape一下，如果shape是(m,)容易出错，改为(m,1)
if y.ndim == 1:
y = y.reshape(-1, 1)
# 初始化w,目标函数，损失函数，求导，正则项，更新w
# w是一个列向量。
m = len(y)
np.random.seed(42)
self.w = np.random.random((x.shape[1], 1))
# 采用平方误差
y_pred = np.zeros(y.shape)
grad = 0
b = 0
for i in range(epochs):
for j in range(m):
y_pred[j] = sigmoid(np.dot(x[j, :], self.w))
temp = (1 - y_pred[j]) * y_pred[j] * x[j, :] * y[j] + (
1 - y[j]) * y_pred[j] * x[j, :]
grad = temp.reshape(-1, 1) + grad
b = b + y[j] - y_pred[j]
regular = L2 / m * self.w
grad = grad.reshape(-1, 1)
grad = grad / m + regular
b = b / m
self.w = self.w - learning_rate * grad
self.w[0] = b
err = loss(y, y_pred, w)
print(f"loss:{err}，grad{grad.T},,,a")
return self.w
def predict(self, x):
W1, W2 = self.params["W1"], self.params["W2"]
b1, b2 = self.params["b1"], self.params["b2"]
a1 = np.dot(x, W1) + b1
z1 = func.sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = func.softmax(a2)
return y
def fit(self, x, y, learning_rate=0.01, epochs: int = 10, L2=0.1):
# 如果y只有一列，给他reshape一下，如果shape是(m,)容易出错，改为(m,1)
if y.ndim == 1:
y = y.reshape(-1, 1)
# 初始化w,目标函数，损失函数，求导，正则项，更新w
# w是一个列向量。
m = len(y)
np.random.seed(42)
self.w = np.random.random((x.shape[1], 1))
# 采用平方误差
for i in range(epochs):
target = np.clip(sigmoid(np.dot(x, self.w)), 1e-5, 1 - 1e-5)
grad = np.dot(x.T, target - target**2 * y) / m + self.w * L2
loss = -(np.dot(y.T, np.log(target)) +
np.dot(1 - y.T, np.log(1 - target))) / m
self.w = self.w - learning_rate * grad
self.w[0] = np.sum(y - target) / m
print(f"loss:{loss}，grad{grad.T}")
return self.w
def propagate(w, b, X, Y):
"""
Implement the cost function and its gradient for the propagation explained above
Arguments:
w -- weights, a numpy array of size (num_px * num_px * 3, 1)
b -- bias, a scalar
X -- data of size (num_px * num_px * 3, number of examples)
Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)
Return:
cost -- negative log-likelihood cost for logistic regression
dw -- gradient of the loss with respect to w, thus same shape as w
db -- gradient of the loss with respect to b, thus same shape as b
Tips:
- Write your code step by step for the propagation
"""
m = X.shape[1]
# FORWARD PROPAGATION (FROM X TO COST)
### START CODE HERE ### (≈ 2 lines of code)
A = sigmoid(np.dot(w.T, X) + b) # compute activation
cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A))) # compute cost
### END CODE HERE ###
# BACKWARD PROPAGATION (TO FIND GRAD)
### START CODE HERE ### (≈ 2 lines of code)
dw = (1 / m) * np.dot(X, (A - Y).T)
db = (1 / m) * np.sum(A - Y)
### END CODE HERE ###
assert(dw.shape == w.shape)
assert(db.dtype == float)
cost = np.squeeze(cost)
assert(cost.shape == ())
grads = {"dw": dw,
"db": db}
return grads, cost
def gradient(self, x, t):
W1, W2 = self.params["W1"], self.params["W2"]
b1, b2 = self.params["b1"], self.params["b2"]
grads = {}
batch_num = x.shape[0]
a1 = np.dot(x, W1) + b1
z1 = func.sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = func.softmax(a2)
dy = (y - t) / batch_num
grads['W2'] = np.dot(z1.T, dy)
grads['b2'] = np.sum(dy, axis=0)
dz1 = np.dot(dy, W2.T)
da1 = func.sigmoid_grad(a1) * dz1
grads['W1'] = np.dot(x.T, da1)
grads['b1'] = np.sum(da1, axis=0)
return grads
def main():
# simple arguments check
if len(sys.argv) != 6:
print("wrong number of arguments")
sys.exit(0)
# passing args
learning_rate = sys.argv[1]
num_hidden_units = sys.argv[2]
num_epoches = sys.argv[3]
training_set_path = sys.argv[4]
test_set_path = sys.argv[5]
# load data
training_set, test_set = func.load_data(training_set_path, test_set_path)
# find index of num and category features
num_feature_index_list, cate_feature_index_list = func.classify_features(training_set, test_set)
# getting traning set matrices
training_set_num_feature_matrix, training_set_cate_feature_matrix, training_set_label_matrix = func.get_matrices(training_set, num_feature_index_list, cate_feature_index_list)
test_set_num_feature_matrix, test_set_cate_feature_matrix, test_set_label_matrix = func.get_matrices(test_set, num_feature_index_list, cate_feature_index_list)
# get the total number of training and test instances
total_num_training = training_set_num_feature_matrix.shape[0]
total_num_test = test_set_num_feature_matrix.shape[0]
# fill up the feature status list
# [num, cate]
feature_status = [0,0]
if training_set_num_feature_matrix.size != 0 :
feature_status[0] = 1
if training_set_label_matrix.size != 0 :
feature_status[1] = 1
# standardize num features
normed_training_set_num_feature_matrix = np.zeros((total_num_training,0))
normed_test_set_num_feature_matrix = np.zeros((total_num_test,0))
if feature_status[0] == 1:
normed_training_set_num_feature_matrix, normed_test_set_num_feature_matrix = func.standardize(training_set_num_feature_matrix, test_set_num_feature_matrix)
# combine the feature matrix, reorder
combined_index_list = num_feature_index_list + cate_feature_index_list
sorted_index_list = np.argsort(combined_index_list)
combined_training_set_feature_matrix = np.hstack((normed_training_set_num_feature_matrix,training_set_cate_feature_matrix))
combined_test_set_feature_matrix = np.hstack((normed_test_set_num_feature_matrix,test_set_cate_feature_matrix))
ordered_training_set_feature_matrix = combined_training_set_feature_matrix[:,sorted_index_list]
ordered_test_set_feature_matrix = combined_test_set_feature_matrix[:,sorted_index_list]
# one-hot
num_to_skip = 0
for idx,original_idx in enumerate(cate_feature_index_list):
variant_list = training_set["metadata"]["features"][:-1][original_idx][1]
cur_training_col = training_set_cate_feature_matrix[:,idx]
cur_test_col = test_set_cate_feature_matrix[:,idx]
for jdx, variant in enumerate(variant_list):
cur_training_col[cur_training_col == variant] = jdx
cur_test_col[cur_test_col == variant] = jdx
cur_training_col = cur_training_col.astype(int)
cur_test_col = cur_test_col.astype(int)
expanded_training_cols = np.zeros((total_num_training,len(variant_list)))
expanded_training_cols[np.arange(total_num_training),cur_training_col.flatten()] = 1
expanded_test_cols = np.zeros((total_num_test,len(variant_list)))
expanded_test_cols[np.arange(total_num_test),cur_test_col.flatten()] = 1
ordered_training_set_feature_matrix = np.delete(ordered_training_set_feature_matrix,original_idx + num_to_skip,axis=1)
ordered_training_set_feature_matrix = np.insert(ordered_training_set_feature_matrix,[original_idx + num_to_skip],expanded_training_cols,axis=1)
ordered_test_set_feature_matrix = np.delete(ordered_test_set_feature_matrix,original_idx + num_to_skip,axis=1)
ordered_test_set_feature_matrix = np.insert(ordered_test_set_feature_matrix,[original_idx + num_to_skip],expanded_test_cols,axis=1)
num_to_skip += (len(variant_list) - 1)
# append bias entry
ordered_training_set_feature_matrix = np.insert(ordered_training_set_feature_matrix,0,1,axis=1).astype(float)
ordered_test_set_feature_matrix = np.insert(ordered_test_set_feature_matrix,0,1,axis=1).astype(float)
# initialize weight
w_i_h = np.random.uniform(low=-0.01, high=0.01, size=(int(num_hidden_units), ordered_training_set_feature_matrix.shape[1]))
w_h_o = np.random.uniform(low=-0.01, high=0.01, size=(1, int(num_hidden_units) + 1))
# nn SGD
class_list = training_set["metadata"]["features"][-1][1]
for epoch in range(int(num_epoches)):
num_corr = 0
num_incorr = 0
sum_E = 0
for idx in range(total_num_training):
# index indicate hidden unit, 1d
net_i_h = np.dot(ordered_training_set_feature_matrix[idx,:],np.transpose(w_i_h))
h = func.sigmoid(net_i_h)
# adding bias entry
h_o = np.insert(h,0,1).astype(float)
net_h_o = np.dot(w_h_o, h_o)
o = func.sigmoid(net_h_o)
y = training_set_label_matrix[idx,0]
if class_list.index(y) == 0:
y = 0
else:
y = 1
E = -y * np.log(o) - (1 - y) * np.log(1 - o)
sum_E += E
d_o = y - o
d_h = h_o*(1 - h_o)*d_o*w_h_o
update_h_o = float(learning_rate)*d_o*h_o
update_i_h = float(learning_rate)*d_h[:,1]*ordered_training_set_feature_matrix[idx,:]
for curcol in range(2,d_h.shape[1]):
temp = float(learning_rate)*d_h[:,curcol]*ordered_training_set_feature_matrix[idx,:]
update_i_h = np.vstack((update_i_h,temp))
w_i_h += update_i_h
w_h_o += update_h_o
pred = 0
if o > 0.5:
pred = 1
else:
pred = 0
if pred == y:
num_corr +=1
else:
num_incorr +=1
print(str(epoch+1)+ " {:.12f}".format(sum_E[0])+ " " + str(num_corr) + " " + str(num_incorr))
# prediction on test set
num_corr = 0
num_incorr = 0
# true positive
tp = 0
# predicted positive
pp = 0
for idx in range(total_num_test):
# index indicate hidden unit, 1d
net_i_h = np.dot(ordered_test_set_feature_matrix[idx,:],np.transpose(w_i_h))
h = func.sigmoid(net_i_h)
# adding bias entry
h_o = np.insert(h,0,1).astype(float)
net_h_o = np.dot(w_h_o, h_o)
o = func.sigmoid(net_h_o)
y = test_set_label_matrix[idx,0]
if class_list.index(y) == 0:
y = 0
else:
y = 1
pred = 0
if o > 0.5:
pred = 1
pp += 1
else:
pred = 0
if pred == y:
num_corr +=1
if pred == 1:
tp += 1
else:
num_incorr +=1
print("{:.12f} ".format(o[0]) + str(pred) + " " + str(y))
print(str(num_corr) + " " + str(num_incorr))
actual_pos = np.sum(test_set_label_matrix == class_list[1])
recall = tp/actual_pos
precision = tp/pp
F1 = 2*precision*recall/(precision + recall)
print("{:.12f}".format(F1))
#print(trainDataArray[d,:])
currData = np.append(currData, trainDataArray[d, :])
#print(currData)
currData = currData[:, None]
#print(repr(devWeight1Array_GD))
#print(repr(currData))
hiddenLayerInput = np.dot(devWeight1Array_GD, currData)
#print(repr(hiddenLayerInput))
hiddenLayerOutput = vectSigmoid(hiddenLayerInput)
hiddenLayerOutput = np.insert(hiddenLayerOutput, 0, 1)
hiddenLayerOutput = hiddenLayerOutput[:, None]
#print(repr(hiddenLayerOutput))
#print(repr(devWeight2Array_GD))
finalLayerInput = np.dot(devWeight2Array_GD, hiddenLayerOutput)
#print(finalLayerInput)
finalLayerOutput = sigmoid(finalLayerInput)
#print(finalLayerOutput)
# calculate error signal of output neuron
errorOutputNeuron = -finalLayerOutput*(1-finalLayerOutput)* \
(trainKeyArray[d]-finalLayerOutput)
#print(finalLayerOutput)
#print(trainKeyArray[d])
#print(errorOutputNeuron)
errorHiddenLayer = np.zeros([1, 4])
for i in range(4):
#print(i)
if i == 0:
continue
else:
def main():
# simple arguments check
if len(sys.argv) != 5:
print("wrong number of arguments")
sys.exit(0)
# passing args
learning_rate = sys.argv[1]
max_epoch = sys.argv[2]
training_set_path = sys.argv[3]
test_set_path = sys.argv[4]
# load data
training_set, test_set = func.load_data(training_set_path, test_set_path)
# find index of num and category features
num_feature_index_list, cate_feature_index_list = func.classify_features(
training_set, test_set)
# getting traning set matrices
training_set_num_feature_matrix, training_set_cate_feature_matrix, training_set_label_matrix = func.get_matrices(
training_set, num_feature_index_list, cate_feature_index_list)
test_set_num_feature_matrix, test_set_cate_feature_matrix, test_set_label_matrix = func.get_matrices(
test_set, num_feature_index_list, cate_feature_index_list)
# get the total number of training and test instances
total_num_training = training_set_num_feature_matrix.shape[0]
total_num_test = test_set_num_feature_matrix.shape[0]
# fill up the feature status list
# [num, cate]
feature_status = [0, 0]
if training_set_num_feature_matrix.size != 0:
feature_status[0] = 1
if training_set_label_matrix.size != 0:
feature_status[1] = 1
# standardize num features
normed_training_set_num_feature_matrix = np.zeros((total_num_training, 0))
normed_test_set_num_feature_matrix = np.zeros((total_num_test, 0))
if feature_status[0] == 1:
normed_training_set_num_feature_matrix, normed_test_set_num_feature_matrix = func.standardize(
training_set_num_feature_matrix, test_set_num_feature_matrix)
# combine the feature matrix, reorder
combined_index_list = num_feature_index_list + cate_feature_index_list
sorted_index_list = np.argsort(combined_index_list)
combined_training_set_feature_matrix = np.hstack(
(normed_training_set_num_feature_matrix,
training_set_cate_feature_matrix))
combined_test_set_feature_matrix = np.hstack(
(normed_test_set_num_feature_matrix, test_set_cate_feature_matrix))
ordered_training_set_feature_matrix = combined_training_set_feature_matrix[:,
sorted_index_list]
ordered_test_set_feature_matrix = combined_test_set_feature_matrix[:,
sorted_index_list]
# one-hot
num_to_skip = 0
for idx, original_idx in enumerate(cate_feature_index_list):
variant_list = training_set["metadata"]["features"][:-1][original_idx][
1]
cur_training_col = training_set_cate_feature_matrix[:, idx]
cur_test_col = test_set_cate_feature_matrix[:, idx]
for jdx, variant in enumerate(variant_list):
cur_training_col[cur_training_col == variant] = jdx
cur_test_col[cur_test_col == variant] = jdx
cur_training_col = cur_training_col.astype(int)
cur_test_col = cur_test_col.astype(int)
expanded_training_cols = np.zeros(
(total_num_training, len(variant_list)))
expanded_training_cols[np.arange(total_num_training),
cur_training_col.flatten()] = 1
expanded_test_cols = np.zeros((total_num_test, len(variant_list)))
expanded_test_cols[np.arange(total_num_test),
cur_test_col.flatten()] = 1
ordered_training_set_feature_matrix = np.delete(
ordered_training_set_feature_matrix,
original_idx + num_to_skip,
axis=1)
ordered_training_set_feature_matrix = np.insert(
ordered_training_set_feature_matrix, [original_idx + num_to_skip],
expanded_training_cols,
axis=1)
ordered_test_set_feature_matrix = np.delete(
ordered_test_set_feature_matrix,
original_idx + num_to_skip,
axis=1)
ordered_test_set_feature_matrix = np.insert(
ordered_test_set_feature_matrix, [original_idx + num_to_skip],
expanded_test_cols,
axis=1)
num_to_skip += (len(variant_list) - 1)
# append bias entry
ordered_training_set_feature_matrix = np.insert(
ordered_training_set_feature_matrix, 0, 1, axis=1).astype(float)
ordered_test_set_feature_matrix = np.insert(
ordered_test_set_feature_matrix, 0, 1, axis=1).astype(float)
# SGD
F1_training = []
F1_test = []
class_list = training_set["metadata"]["features"][-1][1]
for num_epoches in range(1, int(max_epoch) + 1):
# initialize weight
w = np.random.uniform(
low=-0.01,
high=0.01,
size=(1, ordered_training_set_feature_matrix.shape[1]))
for epoch in range(num_epoches):
for idx in range(total_num_training):
net = np.dot(w, ordered_training_set_feature_matrix[idx, :])
o = func.sigmoid(net)
y = training_set_label_matrix[idx, 0]
if class_list.index(y) == 0:
y = 0
else:
y = 1
E = -y * np.log(o) - (1 - y) * np.log(1 - o)
grad = (o - y) * ordered_training_set_feature_matrix[idx, :]
update = -float(learning_rate) * grad
w += update
# prediction on test set
num_corr = 0
num_incorr = 0
# true positive
tp = 0
# predicted positive
pp = 0
for idx in range(total_num_test):
net = np.dot(w, ordered_test_set_feature_matrix[idx, :])
o = func.sigmoid(net)
y = test_set_label_matrix[idx, 0]
if class_list.index(y) == 0:
y = 0
else:
y = 1
pred = 0
if o > 0.5:
pred = 1
pp += 1
else:
pred = 0
if pred == y:
num_corr += 1
if pred == 1:
tp += 1
else:
num_incorr += 1
actual_pos = np.sum(test_set_label_matrix == class_list[1])
recall = tp / actual_pos
precision = tp / pp
F1 = 2 * precision * recall / (precision + recall)
F1_test.append(F1)
# prediction on training set
num_corr = 0
num_incorr = 0
# true positive
tp = 0
# predicted positive
pp = 0
for idx in range(total_num_training):
net = np.dot(w, ordered_training_set_feature_matrix[idx, :])
o = func.sigmoid(net)
y = training_set_label_matrix[idx, 0]
if class_list.index(y) == 0:
y = 0
else:
y = 1
pred = 0
if o > 0.5:
pred = 1
pp += 1
else:
pred = 0
if pred == y:
num_corr += 1
if pred == 1:
tp += 1
else:
num_incorr += 1
actual_pos = np.sum(training_set_label_matrix == class_list[1])
recall = tp / actual_pos
precision = tp / pp
F1 = 2 * precision * recall / (precision + recall)
F1_training.append(F1)
plt.plot(range(1,
int(max_epoch) + 1),
F1_training,
label="on training set")
plt.plot(range(1, int(max_epoch) + 1), F1_test, label="on test set")
plt.title("F1 vs #epoches on heart dataset, learning rate = 0.05")
plt.ylabel("F1")
plt.xlabel("#epoches")
plt.legend()
plt.show()
input_value = [age[iteration], cr_amnt[iteration], duration[iteration]]
current_in.append(input_value)
current_out.append(risk[iteration])
# and then we will make numpy arrays, they are easier to use in this case
train_in = np.array(current_in)
train_out = np.array(current_out).T
# There is a learning process
for itera in range(cluster_training_iterations[clusters[iteration] - 1]):
input_layer = train_in # our input layer is now numpy array we made above
output_layer = sigmoid(
np.dot(input_layer,
weights[clusters[iteration] -
1])) # to predict output we use sigmoid function
error = train_out - output_layer # we need to compute the error
adj = error * sig_der(
output_layer
) # and then compute adjustment by using sigmoid derivative
weights[clusters[iteration] - 1] += np.dot(
input_layer.T, adj) # and then just update our weights
clusters_done[
clusters[iteration] -
1] += 1 # after each lerning process we add the set to the done of the clusters
# there we subtract iterations of clusters to prevent from overtrain
if clusters_done[clusters[iteration] - 1] % int(
def main():
## Load Data
# The first two columns contains the exam scores and the third column
# contains the label.
data = np.loadtxt("./ex2data1.txt", delimiter=',')
X = data[:, :2]
y = data[:, 2]
## Part 1: Plotting
print("""Plotting data with + indicating (y = 1) examples and o
indicating (y = 0) examples.""")
plotData(X, y)
plt.xlabel("Exam 1 score")
plt.ylabel("Exam 2 score")
plt.legend(["Admitted", "Not admitted"])
## Part 2: Compute Cost and Gradient
# Setup the data matrix appropriately, and add ones for the intercept term
m, n = X.shape
# Add intercept term to x and X_test
X = np.hstack([np.ones((m, 1)), X])
# Initialize fitting parameters
initial_theta = np.zeros((n + 1, 1))
# Compute and display initial cost and gradient
cost = costFunction(initial_theta, X, y)
grad = gradient(initial_theta, X, y)
print("\nCost at initial theta (zeros): {}".format(cost))
print("Expected cost (approx): 0.693")
print("Gradient at initial theta (zeros):\n{}".format(grad))
print("Expected gradients (approx):\n -0.1000\n -12.0092\n -11.2628")
# Compute and display cost and gradient with non-zero theta
test_theta = np.array([-24, 0.2, 0.2])
cost = costFunction(test_theta, X, y)
grad = gradient(test_theta, X, y)
print("\nCost at test theta: {}".format(cost))
print("Expected cost (approx): 0.218")
print("Gradient at test theta:\n{}".format(grad))
print("Expected gradients (approx):\n 0.043\n 2.566\n 2.647")
## Part 3: Optimizing using fminunc
options = {"maxiter": 400}
## Two implementation here
# theta, cost = scipy_fminunc(costFunction, initial_theta, (X, y), options)
theta, cost = tf_fmin(X, y, initial_theta)
# Print theta to screen
print("Cost at theta found by fminunc: {}".format(cost))
print("Expected cost (approx): 0.203")
print("theta: {}".format(theta))
print("Expected theta (approx): \n-25.161\n 0.206\n 0.201")
# Plot Boundary
plotDecisionBoundary(theta, X, y)
# Put some labels
plt.xlabel("Exam 1 score")
plt.ylabel("Exam 2 score")
# Legend, specific for the exercise
plt.legend(["Admitted", "Not admitted", "Decision Boundary"])
plt.axis([30, 100, 30, 100])
## Part 4: Predict and Accuracies
prob = sigmoid(np.array([1, 45, 85]) @ theta)
print(
"For a student with scores 45 and 85, we predict an admission probability of {}"
.format(prob))
print("Expected value: 0.775 +/- 0.002")
# Compute accuracy on our training set
p = predict(theta, X)
print("Train Accuracy: {}".format(
np.mean(np.float64(p == y.reshape(-1, 1))) * 100))
print("Expected accuracy (approx): 89.0")
plt.show()