I'm a beginner in numpy and I want to vectorise this function:
I don't quite understand what I need to do but this is what I've come up with:
n = 1000000
h = 1/n
x = np.arange(1,n,1)
def f(x):
return x ** 3
def rec(x):
result = np.zeros_like(x)
result[x < n] = f((x[x < n])*h)
return result
integral = 0.5*h + h*rec(x)
print integral
I end up with an array of 0's. Could someone please point me in the right direction?
Try:
def trap(f, a, b, n):
xs = np.linspace(a, b, n + 1)
ys = f(xs)
return (0.5 * ys[0] + 0.5 * ys[-1] + np.sum(ys[1:-1])) * (b - a) / n
Related
import numpy as np
def af(a,b):
return np.array([[a,b],[b**2, b]])
np.random.seed(1)
n = 2
m = 2
T = 50
alpha = 0.2
beta = 3
# A = np.eye(n) - alpha * np.random.rand(n, n)
B = np.random.randn(n, m)
x_0 = beta * np.random.randn(n)
import cvxpy as cp
x = cp.Variable((n, T + 1))
u = cp.Variable((m, T))
A = cp.Parameter((2,2))
cost = 0
constr = []
for t in range(T):
cost += cp.sum_squares(x[:, t + 1]) + cp.sum_squares(u[:, t])
A = af(*x[:,t])
constr += [x[:, t + 1] == A # x[:, t] + B # u[:, t], cp.norm(u[:, t], "inf") <= 1]
# sums problem objectives and concatenates constraints.
constr += [x[:, T] == 0, x[:, 0] == x_0]
problem = cp.Problem(cp.Minimize(cost), constr)
problem.solve()
I want to use python function (lambdify function) as cvxpy parameter. I tried this method, please let me know if cvxpy support python function as parameter. thank you.
I am trying to compute a series, and I am running into an issue that I don't know why is occurring.
"RuntimeWarning: divide by zero encountered in double_scalars"
When I checked the code, it didn't seem to have any singularities, so I am confused. Here is the code currently(log stands for natural logarithm)(edit: extending code if that helps):
from numpy import pi, log
#Create functions to calculate the sums
def phi(z: int):
k = 0
phi = 0
#Loop through 1000 times to try to approximate the series value as if it went to infinity
while k <= 100:
phi += ((1/(k+1)) - (1/(k+(2*z))))
k += 1
return phi
def psi(z: int):
psi = 0
k = 1
while k <= 101:
psi += ((log(k))/( k**(2*z)))
k += 1
return psi
def sig(z: int):
sig = 0
k = 1
while k <= 101:
sig += ((log(k))**2)/(k^(2*z))
k += 1
return sig
def beta(z: int):
beta = 0
k = 1
while k <= 101:
beta += (1/(((2*z)+k)^2))
k += 1
return beta
#Create the formula to approximate the value. For higher accuracy, either calculate more derivatives of Bernoulli numbers or increase the boundry of k.
def Bern(z :int):
#Define Euler–Mascheroni constant
c = 0.577215664901532860606512
#Begin computations (only approximation)
B = (pi/6) * (phi(1) - c - 2 * log(2 * pi) - 1) - z * ((pi/6) * ((phi(1)- c - (2 * log(2 * pi)) - 1) * (phi(1) - c) + beta(1) - 2 * psi(1)) - 2 * (psi(1) * (phi(1) - c) + sig(1) + 2 * psi(1) * log(2 * pi)))
#output
return B
A = int(input("Choose any value: "))
print("The answer is", Bern(A + 1))
Any help would be much appreciated.
are you sure you need a ^ bitwise exclusive or operator instead of **? I've tried to run your code with input parameter z = 1. And on a second iteration the result of k^(2*z) was equal to 0, so where is from zero division error come from (2^2*1 = 0).
I have function, which convert result from FFT to octave band (or 1/n - octave):
Function OctaveFilter(LowFreq, HighFreq, Im, Re) 'For amplitude
Dim i, j, SortedData(), F_From(), F_To()
Redim SortedData(Bins * n), F_From(Bins * n), F_To(Bins * n)
Dim p
For i = 1 To Bins * n
F_To(i) = Int(HighFreq(i) / df)
F_From(i) = Int(LowFreq(i) / df)
if (F_From(i) = 0) Then F_From(i) = 1 ' We cannot start from index 0
Next
For i = 1 To Bins * n
SortedData(i) = 0
For j = F_From(i) To F_To(i)
If (Length >= j) Then
SortedData(i) = SortedData(i) + Im(j)^2 + Re(j)^2
End If
Next
Next
SortInBins = sqrt(SortedData)
End Function
For example this FFT:
Amplitude
converts to this 1/3- octave bands:
1/3 - octave
But from FFT I also have Re and Im part. I want to convert these parts to octave band too. Is it the same function? How can I convert this Im part imaginary part to similar result (1/3 - octave) ?
I have two dataframes (X & Y). I would like to link them together and to predict the probability that each potential match is correct.
X = pd.DataFrame({'A': ["One", "Two", "Three"]})
Y = pd.DataFrame({'A': ["One", "To", "Free"]})
Method A
I have not yet fully understood the theory but there is an approach presented in:
Sayers, A., Ben-Shlomo, Y., Blom, A.W. and Steele, F., 2015. Probabilistic record linkage. International journal of epidemiology, 45(3), pp.954-964.
Here is my attempt to implementat it in Pandas:
# Probability that Matches are True Matches
m = 0.95
# Probability that non-Matches are True non-Matches
u = min(len(X), len(Y)) / (len(X) * len(Y))
# Priors
M_Pr = u
U_Pr = 1 - M_Pr
O_Pr = M_Pr / U_Pr # Prior odds of a match
# Combine the dataframes
X['key'] = 1
Y['key'] = 1
Z = pd.merge(X, Y, on='key')
Z = Z.drop('key',axis=1)
X = X.drop('key',axis=1)
Y = Y.drop('key',axis=1)
# Levenshtein distance
def Levenshtein_distance(s1, s2):
if len(s1) > len(s2):
s1, s2 = s2, s1
distances = range(len(s1) + 1)
for i2, c2 in enumerate(s2):
distances_ = [i2+1]
for i1, c1 in enumerate(s1):
if c1 == c2:
distances_.append(distances[i1])
else:
distances_.append(1 + min((distances[i1], distances[i1 + 1], distances_[-1])))
distances = distances_
return distances[-1]
L_D = np.vectorize(Levenshtein_distance, otypes=[float])
Z["D"] = L_D(Z['A_x'], Z['A_y'])
# Max string length
def Max_string_length(X, Y):
return max(len(X), len(Y))
M_L = np.vectorize(Max_string_length, otypes=[float])
Z["L"] = M_L(Z['A_x'], Z['A_y'])
# Agreement weight
def Agreement_weight(D, L):
return 1 - ( D / L )
A_W = np.vectorize(Agreement_weight, otypes=[float])
Z["C"] = A_W(Z['D'], Z['L'])
# Likelihood ratio
def Likelihood_ratio(C):
return (m/u) - ((m/u) - ((1-m) / (1-u))) * (1-C)
L_R = np.vectorize(Likelihood_ratio, otypes=[float])
Z["G"] = L_R(Z['C'])
# Match weight
def Match_weight(G):
return math.log(G) * math.log(2)
M_W = np.vectorize(Match_weight, otypes=[float])
Z["R"] = M_W(Z['G'])
# Posterior odds
def Posterior_odds(R):
return math.exp( R / math.log(2)) * O_Pr
P_O = np.vectorize(Posterior_odds, otypes=[float])
Z["O"] = P_O(Z['R'])
# Probability
def Probability(O):
return O / (1 + O)
Pro = np.vectorize(Probability, otypes=[float])
Z["P"] = Pro(Z['O'])
I have verified that this gives the same results as in the paper. Here is a sensitivity check on m, showing that it doesn't make a lot of difference:
Method B
These assumptions won't apply to all applications but in some cases each row of X should match a row of Y. In that case:
The probabilities should sum to 1
If there are many credible candidates to match to then that should reduce the probability of getting the right one
then:
X["I"] = X.index
# Combine the dataframes
X['key'] = 1
Y['key'] = 1
Z = pd.merge(X, Y, on='key')
Z = Z.drop('key',axis=1)
X = X.drop('key',axis=1)
Y = Y.drop('key',axis=1)
# Levenshtein distance
def Levenshtein_distance(s1, s2):
if len(s1) > len(s2):
s1, s2 = s2, s1
distances = range(len(s1) + 1)
for i2, c2 in enumerate(s2):
distances_ = [i2+1]
for i1, c1 in enumerate(s1):
if c1 == c2:
distances_.append(distances[i1])
else:
distances_.append(1 + min((distances[i1], distances[i1 + 1], distances_[-1])))
distances = distances_
return distances[-1]
L_D = np.vectorize(Levenshtein_distance, otypes=[float])
Z["D"] = L_D(Z['A_x'], Z['A_y'])
# Max string length
def Max_string_length(X, Y):
return max(len(X), len(Y))
M_L = np.vectorize(Max_string_length, otypes=[float])
Z["L"] = M_L(Z['A_x'], Z['A_y'])
# Agreement weight
def Agreement_weight(D, L):
return 1 - ( D / L )
A_W = np.vectorize(Agreement_weight, otypes=[float])
Z["C"] = A_W(Z['D'], Z['L'])
# Normalised Agreement Weight
T = Z .groupby('I') .agg({'C' : sum})
D = pd.DataFrame(T)
D.columns = ['T']
J = Z.set_index('I').join(D)
J['P1'] = J['C'] / J['T']
Comparing it against Method A:
Method C
This combines method A with method B:
# Normalised Probability
U = Z .groupby('I') .agg({'P' : sum})
E = pd.DataFrame(U)
E.columns = ['U']
K = Z.set_index('I').join(E)
K['P1'] = J['P1']
K['P2'] = K['P'] / K['U']
We can see that method B (P1) doesn't take account of uncertainty whereas method C (P2) does.
I have two arrays:
L, M, N = 6, 31, 500
A = np.random.random((L, M, N))
B = np.random.random((L, L))
I am trying to get an array C such that:
C = B * A
C has dimension [L, M, N]
I tried answer posted at this link but it hasn't given me the desired output.
A for loop version of above code is:
L, M, N = 6, 31, 500
A = np.random.random((L, M, N))
B = np.random.random((L, L))
z1 = []
for j in range(M):
a = np.squeeze(A[:, j, :])
z1.append(np.dot(B, a))
z2 = np.stack(z1)
I think you are looking for numpy.tensordot() where you can specify along which axes to sum:
np.tensordot(B,A,axes=(1,0))