Network Cost Function code Python Implementation - python

I was implementing Andrew NG’s ML course in Python and in week 5 exercise 4 I was referring to a code. What I didn’t understand was the need to use np.trace() in the final output. Having a problem visualising the matrices
import numpy as np
from scipy.optimize import minimize
import scipy.io
import matplotlib.pyplot as plt
data_dict = scipy.io.loadmat('ex4_orig_octave/ex4data1.mat')
X = data_dict['X']
y = data_dict['y'].ravel()
M = X.shape[0]
N = X.shape[1]
L = 26 # = number of nodes in the hidden layer (including bias node)
K = len(np.unique(y))
X = np.hstack((np.ones((M, 1)), X))
Y = np.zeros((M, K), dtype='uint8')
for i, row in enumerate(Y):
Y[i, y[i] - 1] = 1
weights_dict = scipy.io.loadmat('ex4_orig_octave/ex4weights.mat')
theta_1 = weights_dict['Theta1']
theta_2 = weights_dict['Theta2']
nn_params_saved = np.concatenate((theta_1.flatten(), theta_2.flatten()))
def nn_cost_function(nn_params, X, Y, M, N, L, K):
"""Python version of nnCostFunction.m after completing 'Part 1'."""
# Unroll the parameter vector.
theta_1 = nn_params[:(L - 1) * (N + 1)].reshape(L - 1, N + 1)
theta_2 = nn_params[(L - 1) * (N + 1):].reshape(K, L)
# Calculate activations in the second layer.
a_2 = sigmoid(theta_1.dot(X.T))
# Add the second layer's bias node.
a_2_p = np.vstack((np.ones(M), a_2))
# Calculate the activation of the third layer.
a_3 = sigmoid(theta_2.dot(a_2_p))
# Calculate the cost function.
cost = 1 / M * np.trace(- Y.dot(np.log(a_3)) - (1 - Y).dot(np.log(1 - a_3)))
return cost
cost_saved = nn_cost_function(nn_params_saved, X, Y, M, N, L, K)
print 'Cost at parameters (loaded from ex4weights): %.6f' % cost_saved
print '(this value should be about 0.287629)'

The operation 1/M * np.trace() is calculating the average cost over a batch of size M:
A bit less readable, but significantly faster should be:
np.sum(np.sum(Y.multiply(np.log(a_3.T)),axis=1),axis=0)
, if Y.shape==(M,K) and a_3.shape==(K,M):
Y = lambda : np.random.uniform(size=(5000,10)) # (M,K)
a3 = lambda : np.random.uniform(size=(10,5000)) # (K,M)
timeit.timeit('import numpy as np; np.trace(Y().dot(a3()))', number=10, globals=globals())
# 0.5633535870001651
timeit.timeit('import numpy as np; np.sum(np.sum(np.multiply(Y(),a3().T),axis=1),axis=0)', number=10, globals=globals())
# 0.013223066000136896

Related

Numpy - vectorize the bivariate poisson pmf equation

I'm trying to write a function to evaluate the probability mass function for the bivariate poisson distribution.
This is easy when all of the parameters (x, y, theta1, theta2, theta0) are scalars, but tricky to scale up without loops to allow these parameters to be vectors. I need it to scale such that, for:
theta0 being a scalar - the "correlation parameter" in the equation
theta1 and theta2 having length l
x, y both having length n
the output array would have shape (l, n, n). For example, a slice [j, :, :] from the output array would look like:
The first part (the constant, before the summation) I think i've figured out:
import numpy as np
from scipy.special import factorial
def constant(theta1, theta2, theta0, x, y):
exponential_part = np.exp(-(theta1 + theta2 + theta0)).reshape(-1, 1, 1)
x = np.tile(x, (len(x), 1)).transpose()
y = np.tile(y, (len(y), 1))
double_factorial = (np.power(np.array(theta1).reshape(-1, 1, 1), x)/factorial(x)) * \
(np.power(np.array(theta2).reshape(-1, 1, 1), y)/factorial(y))
return exponential_part * double_factorial
But I'm struggling with the summation part. How can I vectorize a summation where the limits depend on variable arrays?
I think I have this figured out, based on the approach that #w-m suggests: calculate every possible summation term which could appear, based on the maximum x or y value which appears, and use a mask to get rid of the ones you don't want. Assuming you have your x and y terms go from 0 to N, in consecutive order, this is calculating up to three times more terms than are actually required, but this is offset by getting to use vectorization.
Reference implementation
I wrote this by first writing a pure-Python reference implementation, which just implements your problem using loops. With 4 nested loops, it's not exactly fast, but it's handy to have while testing the numpy version.
import numpy as np
from scipy.special import factorial, comb
import operator as op
from functools import reduce
def choose(n, r):
# https://stackoverflow.com/a/4941932/530160
r = min(r, n-r)
numer = reduce(op.mul, range(n, n-r, -1), 1)
denom = reduce(op.mul, range(1, r+1), 1)
return numer // denom # or / in Python 2
def reference_impl_constant(s_theta1, s_theta2, s_theta0, s_x, s_y):
# Cast to float to prevent overflow
s_theta1 = float(s_theta1)
s_theta2 = float(s_theta2)
s_theta0 = float(s_theta0)
s_x = float(s_x)
s_y = float(s_y)
term1 = np.exp(-(s_theta1 + s_theta2 + s_theta0))
term2 = (s_theta1 ** s_x / factorial(s_x))
term3 = (s_theta2 ** s_y / factorial(s_y))
assert term1 >= 0
assert term2 >= 0
assert term3 >= 0
return term1 * term2 * term3
def reference_impl_constant_loop(theta1, theta2, theta0, x, y):
theta_len = theta1.shape[0]
xy_len = x.shape[0]
constant_array = np.zeros((theta_len, xy_len, xy_len))
for i in range(theta_len):
for j in range(xy_len):
for k in range(xy_len):
s_theta1 = theta1[i]
s_theta2 = theta2[i]
s_theta0 = theta0
s_x = x[j]
s_y = y[k]
constant_term = reference_impl_constant(s_theta1, s_theta2, s_theta0, s_x, s_y)
assert constant_term >= 0
constant_array[i, j, k] = constant_term
return constant_array
def reference_impl_summation(s_theta1, s_theta2, s_theta0, s_x, s_y):
sum_ = 0
for i in range(min(s_x, s_y) + 1):
sum_ += choose(s_x, i) * choose(s_y, i) * factorial(i) * ((s_theta0/s_theta1/s_theta2) ** i)
assert sum_ >= 0
return sum_
def reference_impl_summation_loop(theta1, theta2, theta0, x, y):
theta_len = theta1.shape[0]
xy_len = x.shape[0]
summation_array = np.zeros((theta_len, xy_len, xy_len))
for i in range(theta_len):
for j in range(xy_len):
for k in range(xy_len):
s_theta1 = theta1[i]
s_theta2 = theta2[i]
s_theta0 = theta0
s_x = x[j]
s_y = y[k]
summation_term = reference_impl_summation(s_theta1, s_theta2, s_theta0, s_x, s_y)
assert summation_term >= 0
summation_array[i, j, k] = summation_term
return summation_array
def reference_impl(theta1, theta2, theta0, x, y):
# all array inputs must be 1D
assert len(theta1.shape) == 1
assert len(theta2.shape) == 1
assert len(x.shape) == 1
assert len(y.shape) == 1
# theta vectors must have same length
theta_len = theta1.shape[0]
assert theta2.shape[0] == theta_len
# x and y must have same length
xy_len = x.shape[0]
assert y.shape[0] == xy_len
# theta0 is scalar
assert isinstance(theta0, (int, float))
constant_array = np.zeros((theta_len, xy_len, xy_len))
output = np.zeros((theta_len, xy_len, xy_len))
constant_array = reference_impl_constant_loop(theta1, theta2, theta0, x, y)
summation_array = reference_impl_summation_loop(theta1, theta2, theta0, x, y)
output = constant_array * summation_array
return output
Numpy implementation
I split the implementation of this across two functions.
The fast_constant() function calculates everything to the left of the summation symbol. The fast_summation() function calculates everything inside the summation symbol.
import numpy as np
from scipy.special import factorial, comb
def fast_summation(theta1, theta2, theta0, x, y):
x = np.tile(x, (len(x), 1)).transpose()
y = np.tile(y, (len(y), 1))
sum_limit = np.minimum(x, y)
max_sum_limit = np.max(sum_limit)
i = np.arange(max_sum_limit + 1).reshape(-1, 1, 1)
summation_mask = (i <= sum_limit)
theta_ratio = (theta0 / (theta1 * theta2)).reshape(-1, 1, 1, 1)
theta_to_power = np.power(theta_ratio, i)
terms = comb(x, i) * comb(y, i) * factorial(i) * theta_to_power
# mask out terms which aren't part of sum
terms *= summation_mask
# axis 0 is theta
# axis 1 is i
# axis 2 & 3 are x and y
# so sum across axis 1
terms = terms.sum(axis=1)
return terms
def fast_constant(theta1, theta2, theta0, x, y):
theta1 = theta1.astype('float64')
theta2 = theta2.astype('float64')
exponential_part = np.exp(-(theta1 + theta2 + theta0)).reshape(-1, 1, 1)
# x and y must be 1D
assert len(x.shape) == 1
assert len(y.shape) == 1
# x and y must have same shape
assert x.shape == y.shape
x_len, y_len = x.shape[0], y.shape[0]
x = x.reshape((x_len, 1))
y = y.reshape((1, y_len))
double_factorial = (np.power(np.array(theta1).reshape(-1, 1, 1), x)/factorial(x)) * \
(np.power(np.array(theta2).reshape(-1, 1, 1), y)/factorial(y))
return exponential_part * double_factorial
def fast_impl(theta1, theta2, theta0, x, y):
return fast_summation(theta1, theta2, theta0, x, y) * fast_constant(theta1, theta2, theta0, x, y)
Benchmarking
Assuming that X and Y range from 0 to 20, and that theta is centered somewhere inside that range, I get the result that the numpy version is roughly 280 times faster than the pure python reference.
Numerical stability
I'm unsure how numerically stable this is. For example, when I center theta at 100, I get a floating-point overflow. Typically, when computing an expression which has lots of choose and factorial expressions inside it, you'll use some mathematical equivalent which results in smaller intermediate sums. In this case I have so little understanding of the math that I don't know how you'd do that.

Error in implementation of Crank-Nicolson method applied to 1D TDSE?

This is more of a computational physics problem, and I've asked it on physics stack exchange, but no answers on there. This is, I suppose, a mix of the disciplines on here and there (and maybe even mathematics stack exchange), so finding the right place to post is a task in of itself apparently...
I'm attempting to use Crank-Nicolson scheme to solve the TDSE in 1D. The initial wave is a real Gaussian that has been normalised wrt its probability density. As the solution evolves, a depression grows in the central peak of the real part of the wave, and the imaginary part's central trough is perhaps a bit higher than I expect (image below).
Does this behaviour seem reasonable? I have searched around and not seen questions/figures that are similar. I've tested another person's code from Github and it exhibits the same behaviour, which makes me feel a bit better. But I still think the center peak should just decrease in height and increase in width. The likelihood of me getting a physics-based explanation is relatively low here I'd assume, but a computational-based explanation on errors I may have made is more likely.
I'm happy to give more information, for example my code, or the matrices used in the scheme, etc. Thanks in advance!
Here's a link to GIF of time evolution:
And the part of my code relevant to solving the 1D TDSE:
(pretty much the entire thing except the plotting)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation
# Define function for norm.
def normf(dxc, uc, ic):
return sum(dxc * np.square(np.abs(uc[ic, :])))
# Define function for expectation value of position.
def xexpf(dxc, xc, uc, ic):
return sum(dxc * xc * np.square(np.abs(uc[ic, :])))
# Define function for expectation value of squared position.
def xexpsf(dxc, xc, uc, ic):
return sum(dxc * np.square(xc) * np.square(np.abs(uc[ic, :])))
# Define function for standard deviation.
def sdaf(xexpc, xexpsc, ic):
return np.sqrt(xexpsc[ic] - np.square(xexpc[ic]))
# Time t: t0 =< t =< tf. Have N steps at which to evaluate the CN scheme. The
# time interval is dt. decp: variable for plotting to certain number of decimal
# places.
t0 = 0
tf = 20
N = 200
dt = tf / N
t = np.linspace(t0, tf, num = N + 1, endpoint = True)
decp = str(dt)[::-1].find('.')
# Initialise array for filling with norm values at each time step.
norm = np.zeros(len(t))
# Initialise array for expectation value of position.
xexp = np.zeros(len(t))
# Initialise array for expectation value of squared position.
xexps = np.zeros(len(t))
# Initialise array for alternate standard deviation.
sda = np.zeros(len(t))
# Position x: -a =< x =< a. M is an even number. There are M + 1 total discrete
# positions, for the points to be symmetric and centred at x = 0.
a = 100
M = 1200
dx = (2 * a) / M
x = np.linspace(-a, a, num = M + 1, endpoint = True)
# The gaussian function u diffuses over time. sd sets the width of gaussian. u0
# is the initial gaussian at t0.
sd = 1
var = np.power(sd, 2)
mu = 0
u0 = np.sqrt(1 / np.sqrt(np.pi * var)) * np.exp(-np.power(x - mu, 2) / (2 * \
var))
u = np.zeros([len(t), len(x)], dtype = 'complex_')
u[0, :] = u0
# Normalise u.
u[0, :] = u[0, :] / np.sqrt(normf(dx, u, 0))
# Set coefficients of CN scheme.
alpha = dt * -1j / (4 * np.power(dx, 2))
beta = dt * 1j / (4 * np.power(dx, 2))
# Tridiagonal matrices Al and AR. Al to be solved using Thomas algorithm.
Al = np.zeros([len(x), len(x)], dtype = 'complex_')
for i in range (0, M):
Al[i + 1, i] = alpha
Al[i, i] = 1 - (2 * alpha)
Al[i, i + 1] = alpha
# Corner elements for BC's.
Al[M, M], Al[0, 0] = 1 - alpha, 1 - alpha
Ar = np.zeros([len(x), len(x)], dtype = 'complex_')
for i in range (0, M):
Ar[i + 1, i] = beta
Ar[i, i] = 1 - (2 * beta)
Ar[i, i + 1] = beta
# Corner elements for BC's.
Ar[M, M], Ar[0, 0] = 1 - 2*beta, 1 - beta
# Thomas algorithm variables. Following similar naming as in Wiki article.
a = np.diag(Al, -1)
b = np.diag(Al)
c = np.diag(Al, 1)
NT = len(b)
cp = np.zeros(NT - 1, dtype = 'complex_')
for n in range(0, NT - 1):
if n == 0:
cp[n] = c[n] / b[n]
else:
cp[n] = c[n] / (b[n] - (a[n - 1] * cp[n - 1]))
d = np.zeros(NT, dtype = 'complex_')
dp = np.zeros(NT, dtype = 'complex_')
# Iterate over each time step to solve CN method. Maintain boundary
# conditions. Keep track of standard deviation.
for i in range(0, N):
# BC's.
u[i, 0], u[i, M] = 0, 0
# Find RHS.
d = np.dot(Ar, u[i, :])
for n in range(0, NT):
if n == 0:
dp[n] = d[n] / b[n]
else:
dp[n] = (d[n] - (a[n - 1] * dp[n - 1])) / (b[n] - (a[n - 1] * \
cp[n - 1]))
nc = NT - 1
while nc > -1:
if nc == NT - 1:
u[i + 1, nc] = dp[nc]
nc -= 1
else:
u[i + 1, nc] = dp[nc] - (cp[nc] * u[i + 1, nc + 1])
nc -= 1
norm[i] = normf(dx, u, i)
xexp[i] = xexpf(dx, x, u, i)
xexps[i] = xexpsf(dx, x, u, i)
sda[i] = sdaf(xexp, xexps, i)
# Fill in final norm value.
norm[N] = normf(dx, u, N)
# Fill in final position expectation value.
xexp[N] = xexpf(dx, x, u, N)
# Fill in final squared position expectation value.
xexps[N] = xexpsf(dx, x, u, N)
# Fill in final standard deviation value.
sda[N] = sdaf(xexp, xexps, N)

General minimal residual method with right-preconditioner of SSOR

I am trying to implement the algorithm of GMRES with right-preconditioner P for solving the linear system Ax = b . The code is running without error; however, it pops into unprecise result for me because the error I have is very large. For the GMRES method (without preconditioning matrix - remove P in the algorithm), the error I get is around 1e^{-12} and it converges with the same matrix.
import numpy as np
from scipy import sparse
import matplotlib.pyplot as plt
from scipy.linalg import norm as norm
import scipy.sparse as sp
from scipy.sparse import diags
"""The program is to split the matrix into D-diagonal; L: strictly lower matrix; U strictly upper matrix
satisfying: A = D - L - U """
def splitMat(A):
n,m = A.shape
if (n == m):
diagval = np.diag(A)
D = diags(diagval,0).toarray()
L = (-1)*np.tril(A,-1)
U = (-1)*np.triu(A,1)
else:
print("A needs to be a square matrix")
return (L,D,U)
"""Preconditioned Matrix for symmetric successive over-relaxation (SSOR): """
def P_SSOR(A,w):
## Split up matrix A:
L,D,U = splitMat(A)
Comp1 = (D - w*U)
Comp2 = (D - w*L)
Comp1inv = np.linalg.inv(Comp1)
Comp2inv = np.linalg.inv(Comp2)
P = w*(2-w)*np.matmul(Comp1inv, np.matmul(D,Comp2inv))
return P
"""GMRES_SSOR using right preconditioning P:
A - matrix of linear system Ax = b
x0 - initial guess
tol - tolerance
maxit - maximum iteration """
def myGMRES_SSOR(A,x0, b, tol, maxit):
matrixSize = A.shape[0]
e = np.zeros((maxit+1,1))
rr = 1
rstart = 2
X = x0
w = 1.9 ## in ssor
P = P_SSOR(A,w) ### preconditioned matrix
### Starting the GMRES ####
for rs in range(0,rstart+1):
### first check the residual:
if rr<tol:
break
else:
r0 = (b-A.dot(x0))
rho = norm(r0)
e[0] = rho
H = np.zeros((maxit+1,maxit))
Qcol = np.zeros((matrixSize, maxit+1))
Qcol[:,0:1] = r0/rho
for k in range(1, maxit+1):
### Arnodi procedure ##
Qcol[:,k] =np.matmul(np.matmul(A,P), Qcol[:,k-1]) ### This step applies P here:
for j in range(0,k):
H[j,k-1] = np.dot(np.transpose(Qcol[:,k]),Qcol[:,j])
Qcol[:,k] = Qcol[:,k] - (np.dot(H[j,k-1], Qcol[:,j]))
H[k,k-1] =norm(Qcol[:,k])
Qcol[:,k] = Qcol[:,k]/H[k,k-1]
### QR decomposition step ###
n = k
Q = np.zeros((n+1, n))
R = np.zeros((n, n))
R[0, 0] = norm(H[0:n+2, 0])
Q[:, 0] = H[0:n+1, 0] / R[0,0]
for j in range (0, n+1):
t = H[0:n+1, j-1]
for i in range (0, j-1):
R[i, j-1] = np.dot(Q[:, i], t)
t = t - np.dot(R[i, j-1], Q[:, i])
R[j-1, j-1] = norm(t)
Q[:, j-1] = t / R[j-1, j-1]
g = np.dot(np.transpose(Q), e[0:k+1])
Y = np.dot(np.linalg.inv(R), g)
Res= e[0:n] - np.dot(H[0:n, 0:n], Y[0:n])
rr = norm(Res)
#### second check on the residual ###
if rr < tol:
break
#### Updating the solution with the preconditioned matrix ####
X = X + np.matmul(np.matmul(P,Qcol[:, 0:k]), Y) ### This steps applies P here:
return X
######
A = np.random.rand(100,100)
x = np.random.rand(100,1)
b = np.matmul(A,x)
x0 = np.zeros((100,1))
maxit = 100
tol = 0.00001
x = myGMRES_SSOR(A,x0,b,tol,maxit)
res = b - np.matmul(A,x)
print(norm(res))
print("Solution with gmres\n", np.matmul(A,x))
print("---------------------------------------")
print("b matrix:", b)
I hope anyone could help me figure out this!!!
I'm not sure where you got you "Symmetric_successive_over-relaxation" SSOR code from, but it appears to be wrong. You also seem to be assuming that A is symmetric matrix, but in your random test case it is not.
Following SSOR's Wikipedia entry, I replaced your P_SSOR function with
def P_SSOR(A,w):
L,D,U = splitMat(A)
P = 2/(2-w) * (1/w*D+L)*np.linalg.inv(D)*(1/w*D+L).T
return P
and your test matrix with
A = np.random.rand(100,100)
A = A + A.T
and your code works up to a 12 digit residual error.

Regularized Logistic Regression in Python (Andrew ng Course)

I'm starting the ML journey and I'm having troubles with this coding exercise
here is my code
import numpy as np
import pandas as pd
import scipy.optimize as op
# Read the data and give it labels
data = pd.read_csv('ex2data2.txt', header=None, name['Test1', 'Test2', 'Accepted'])
# Separate the features to make it fit into the mapFeature function
X1 = data['Test1'].values.T
X2 = data['Test2'].values.T
# This function makes more features (degree)
def mapFeature(x1, x2):
degree = 6
out = np.ones((x1.shape[0], sum(range(degree + 2))))
curr_column = 1
for i in range(1, degree + 1):
for j in range(i+1):
out[:,curr_column] = np.power(x1, i-j) * np.power(x2, j)
curr_column += 1
return out
# Separate the data into training and target, also initialize theta
X = mapFeature(X1, X2)
y = np.matrix(data['Accepted'].values).T
m, n = X.shape
cols = X.shape[1]
theta = np.matrix(np.zeros(cols))
#Initialize the learningRate(sigma)
learningRate = 1
# Define the Sigmoid Function (Output between 0 and 1)
def sigmoid(z):
return 1 / (1 + np.exp(-z))
def cost(theta, X, y, learningRate):
# This is require to make the optimize function work
theta = theta.reshape(-1, 1)
error = sigmoid(X # theta)
first = np.multiply(-y, np.log(error))
second = np.multiply(1 - y, np.log(1 - error))
j = np.sum((first - second)) / m + (learningRate * np.sum(np.power(theta, 2)) / 2 * m)
return j
# Define the gradient of the cost function
def gradient(theta, X, y, learningRate):
# This is require to make the optimize function work
theta = theta.reshape(-1, 1)
error = sigmoid(X # theta)
grad = (X.T # (error - y)) / m + ((learningRate * theta) / m)
grad_no = (X.T # (error - y)) / m
grad[0] = grad_no[0]
return grad
Result = op.minimize(fun=cost, x0=theta, args=(X, y, learningRate), method='TNC', jac=gradient)
opt_theta = np.matrix(Result.x)
def predict(theta, X):
sigValue = sigmoid(X # theta.T)
p = sigValue >= 0.5
return p
p = predict(opt_theta, X)
print('Train Accuracy: {:f}'.format(np.mean(p == y) * 100))
So, when the learningRate = 1, the accuracy should be around 83,05% but I'm getting 80.5% and when the learningRate = 0, the accuracy should be 91.52% but I'm getting 87.28%
So the question is What am I doing wrong? Why my accuracy is below the problem default answer?
Hope someone can guide me in the right direction. Thanks!
P.D: Here is the dataset, maybe it can help
https://raw.githubusercontent.com/TheGirlWhiteWithBandages/Machine-Learning-Algorithms/master/Logistic%20Regression/ex2data2.txt
Hey guys I found a way to make it even better!
Here is the code
import numpy as np
import pandas as pd
import scipy.optimize as op
from sklearn.preprocessing import PolynomialFeatures
# Read the data and give it labels
data = pd.read_csv('ex2data2.txt', header=None, names=['Test1', 'Test2', 'Accepted'])
# Separate the data into training and target
X = (data.iloc[:, 0:2]).values
y = (data.iloc[:, 2:3]).values
# Modify the features to a certain degree (Polynomial)
poly = PolynomialFeatures(6)
m = y.size
XX = poly.fit_transform(data.iloc[:, 0:2].values)
# Initialize Theta
theta = np.zeros(XX.shape[1])
# Define the Sigmoid Function (Output between 0 and 1)
def sigmoid(z):
return(1 / (1 + np.exp(-z)))
# Define the Regularized cost function
def costFunctionReg(theta, reg, *args):
# This is require to make the optimize function work
h = sigmoid(XX # theta)
first = np.log(h).T # - y
second = np.log(1 - h).T # (1 - y)
J = (1 / m) * (first - second) + (reg / (2 * m)) * np.sum(np.square(theta[1:]))
return J
# Define the Regularized gradient function
def gradientReg(theta, reg, *args):
theta = theta.reshape(-1, 1)
h = sigmoid(XX # theta)
grad = (1 / m) * (XX.T # (h - y)) + (reg / m) * np.r_[[[0]], theta[1:]]
return grad.flatten()
# Define the predict Function
def predict(theta, X):
sigValue = sigmoid(X # theta.T)
p = sigValue >= 0.5
return p
# A loop to test between different values for sigma (reg parameter)
for i, Sigma in enumerate([0, 1, 100]):
# Optimize costFunctionReg
res2 = op.minimize(costFunctionReg, theta, args=(Sigma, XX, y), method=None, jac=gradientReg)
# Get the accuracy of the model
accuracy = 100 * sum(predict(res2.x, XX) == y.ravel()) / y.size
# Get the Error between different weights
error1 = costFunctionReg(res2.x, Sigma, XX, y)
# print the accuracy and error
print('Train accuracy {}% with Lambda = {}'.format(np.round(accuracy, decimals=4), Sigma))
print(error1)
Thanks for all your help!
try out this:
# import library
import pandas as pd
import numpy as np
dataset = pd.read_csv('ex2data2.csv',names = ['Test #1','Test #2','Accepted'])
# splitting to x and y variables for features and target variable
x = dataset.iloc[:,:-1].values
y = dataset.iloc[:,-1].values
print('x[0] ={}, y[0] ={}'.format(x[0],y[0]))
m, n = x.shape
print('#{} Number of training samples, #{} features per sample'.format(m,n))
# import library FeatureMapping
from sklearn.preprocessing import PolynomialFeatures
# We also add one column of ones to interpret theta 0 (x with power of 0 = 1) by
include_bias as True
pf = PolynomialFeatures(degree = 6, include_bias = True)
x_poly = pf.fit_transform(x)
pd.DataFrame(x_poly).head(5)
m,n = x_poly.shape
# define theta as zero
theta = np.zeros(n)
# define hyperparameter λ
lambda_ = 1
# reshape (-1,1) because we just have one feature in y column
y = y.reshape(-1,1)
def sigmoid(z):
return 1/(1+np.exp(-z))
def lr_hypothesis(x,theta):
return np.dot(x,theta)
def compute_cost(theta,x,y,lambda_):
theta = theta.reshape(n,1)
infunc1 = -y*(np.log(sigmoid(lr_hypothesis(x,theta)))) - ((1-y)*(np.log(1 - sigmoid(lr_hypothesis(x,theta)))))
infunc2 = (lambda_*np.sum(theta[1:]**2))/(2*m)
j = np.sum(infunc1)/m+ infunc2
return j
# gradient[0] correspond to gradient for theta(0)
# gradient[1:] correspond to gradient for theta(j) j>0
def compute_gradient(theta,x,y,lambda_):
gradient = np.zeros(n).reshape(n,)
theta = theta.reshape(n,1)
infunc1 = sigmoid(lr_hypothesis(x,theta))-y
gradient_in = np.dot(x.transpose(),infunc1)/m
gradient[0] = gradient_in[0,0] # theta(0)
gradient[1:] = gradient_in[1:,0]+(lambda_*theta[1:,]/m).reshape(n-1,) # theta(j) ; j>0
gradient = gradient.flatten()
return gradient
You can now test your cost and gradient without optimization. Th below code will optimize the model:
# hyperparameters
m,n = x_poly.shape
# define theta as zero
theta = np.zeros(n)
# define hyperparameter λ
lambda_array = [0, 1, 10, 100]
import scipy.optimize as opt
for i in range(0,len(lambda_array)):
# Train
print('======================================== Iteration {} ===================================='.format(i))
optimized = opt.minimize(fun = compute_cost, x0 = theta, args = (x_poly, y,lambda_array[i]),
method = 'TNC', jac = compute_gradient)
new_theta = optimized.x
# Prediction
y_pred_train = predictor(x_poly,new_theta)
cm_train = confusion_matrix(y,y_pred_train)
t_train,f_train,acc_train = acc(cm_train)
print('With lambda = {}, {} correct, {} wrong ==========> accuracy = {}%'
.format(lambda_array[i],t_train,f_train,acc_train*100))
Now you should see output like this :
=== Iteration 0 === With lambda = 0, 104 correct, 14 wrong ==========> accuracy = 88.13559322033898%
=== Iteration 1 === With lambda = 1, 98 correct, 20 wrong ==========> accuracy = 83.05084745762711%
=== Iteration 2 === With lambda = 10, 88 correct, 30 wrong ==========> accuracy = 74.57627118644068%
=== Iteration 3 === With lambda = 100, 72 correct, 46 wrong ==========> accuracy = 61.016949152542374%

Understanding matrix obtained from indexing with arrays

In code listed in logistic regression code, I saw the following code snippet. What throws me off is the expression:
probs[range(num_examples),y].
Can someone tell me what dimension this matrix has? My guess is that it's a N*K by N*K matrix, but I am not sure. Thanks.
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(0)
N = 100 # number of points per class
D = 2 # dimensionality
K = 3 # number of classes
X = np.zeros((N*K,D))
y = np.zeros(N*K, dtype='uint8')
for j in xrange(K):
ix = range(N*j,N*(j+1))
r = np.linspace(0.0,1,N) # radius
t = np.linspace(j*4,(j+1)*4,N) + np.random.randn(N)*0.2 # theta
X[ix] = np.c_[r*np.sin(t), r*np.cos(t)]
y[ix] = j
#Train a Linear Classifier
# initialize parameters randomly
W = 0.01 * np.random.randn(D,K)
b = np.zeros((1,K))
# some hyperparameters
step_size = 1e-0
reg = 1e-3 # regularization strength
# gradient descent loop
num_examples = X.shape[0]
for i in xrange(200):
# evaluate class scores, [N x K]
scores = np.dot(X, W) + b
# compute the class probabilities
exp_scores = np.exp(scores)
probs = exp_scores / np.sum(exp_scores, axis=1, keepdims=True) # [N x K]
# compute the loss: average cross-entropy loss and regularization
corect_logprobs = -np.log(probs[range(num_examples),y])
data_loss = np.sum(corect_logprobs)/num_examples
reg_loss = 0.5*reg*np.sum(W*W)
loss = data_loss + reg_loss
if i % 10 == 0:
probs[range(num_examples), y] seems to be a 1D slice, where:
range(num_examples) is a vector spanning the length of your samples
y is a 1D vector, length N*K

Categories