lab12pdf.pdf - lab12 1)13 PM In[38 Don't change this cell just run it from datascience import import numpy as np import math import matplotlib.pyplot as

lab12pdf.pdf - lab12 1)13 PM In[38 Don't change this cell...

This preview shows page 1 - 4 out of 24 pages.

4/26/19, 1)13 PMlab12Page 1 of 24In [38]:# Don't change this cell; just run it. fromdatascienceimport*importnumpyasnpimportmathimportmatplotlib.pyplotasplt%matplotlibinlineplt.style.use('fivethirtyeight')In [39]:# Don't change this cell either; just run it.defabline(slope, intercept):"""Plot a line from slope and intercept"""axes = plt.gca()x_vals = np.array(axes.get_xlim())y_vals = intercept + slope * x_valsplt.plot(x_vals, y_vals, '--')defstr_mat(A):return'\n'.join([ ' '.join(['{:.3f}'.format(A[i, j]) forj inrange(A.shape[1])]) fori inrange(A.shape[0])])defsort_eigs(eigvals, eigvecs):idx = eigvals.argsort()[::-1] eigvals = eigvals[idx]eigvecs = eigvecs[:,idx]returneigvals, eigvecs1. PCAA matrix doesn't have to represent a linear function. Some matrices, for example, represent data sets insuch a way that every column of the matrix corresponds to a point of the data set.Let's see an example in 2 dimensions. We have here two variables, which is the weights of 30 students inthe fifth grade, and which is their heights, and we're interested in seeing how "related" the two variablesare, e.g. in the sense that changes in the value of one variable "predict" changes in the value of the othervariable.First, let's plot the sample points to get an idea of what we are working with.
Background image
4/26/19, 1)13 PMlab12Page 2 of 24In [3]:np.random.seed(42)X = (np.random.normal(loc=5, scale=15, size=30))+80Y = 0.01*X +4+np.random.normal(0,.25,size=30)plt.ylim(0, 6)plt.xlim(0, 120)plt.scatter(X, Y, alpha=0.5)plt.title('Height and weight of fifth graders')plt.xlabel('weight (lbs)')plt.ylabel('height (ft)')plt.show()1.1. Finding the correlation coecient The correlation coecient is one first way in which we might try to gauge the strength and direction of therelationship between the two variables and .,
Background image
4/26/19, 1)13 PMlab12Page 3 of 241.1.1.In the cell below, calculate the correlation coecient:You may not use np.corrcoefor any other similar methods.Hint:Which values do you need to calculate the correlation coecient? Where can you find these valueswithin the covariance matrix?.,=defCov(,)() ()In [4]:n = X.shape[0]A = np.vstack((X.reshape((1, n)), Y.reshape((1, n))))A_cov = np.cov(A)corr_XY = A_cov.item(1)/(A_cov.item(0) * A_cov.item(3))**.5 # SOLUTIONprint('rho_XY = {}\n'.format(corr_XY))print('Your solution is {}.'.format(('correct' ifnp.isclose(corr_XY, np.corrcoef(A)[0][1]) else'incorrect')))1.1.2. ObservationsBased on the value of the correlation coecient, to what extent do the two variables "predict" each other? Inother words, to what extent do changes in the value of one variable correspond to changes in the value ofthe other variable?
Background image
Image of page 4

You've reached the end of your free preview.

Want to read all 24 pages?

  • Fall '18

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Stuck? We have tutors online 24/7 who can help you get unstuck.
A+ icon
Ask Expert Tutors You can ask You can ask You can ask (will expire )
Answers in as fast as 15 minutes
A+ icon
Ask Expert Tutors