Final project

%pylab inline import pandas as pd import numpy as np

Populating the interactive namespace from numpy and matplotlib

data = pd.read_csv('adultdata.csv')

data

def calc_error(y_arr, x_arr, w, train=False): err_sum=0.0 for j in range(len(y_arr)): y_out = (x_arr[j].dot(w)>=0.0) and 1 or -1 # make a prediction, +1 (versi) or -1 (vir) err = y_arr[j]-y_out # compare to known species err_sum += abs(err) and 1 or 0 # accumulate the total error if train: w += eta*err*x_arr[j] # adjust the weights during training only return err_sum def train(y, x, w): return calc_error(y, xnew, w, train=True) def test(y, x, w): return calc_error(y, x, w)

data.Race = np.array([x.strip() for x in data.Race.values]) data

data.Race = np.where(data.Race.values!='White',1,2) data

data.Sex = np.array([x.strip() for x in data.Sex.values]) data

data.Sex = np.where(data.Sex.values!='Male',1,2) data

data.Income = np.array([x.strip() for x in data.Income.values]) data

data.Country = np.array([x.strip() for x in data.Country.values]) data

data.Country = np.where(data.Country.values!='United-States',1,2) data

Trainingdata = [] Traininganswers = [] for i in range(0,99): Trainingdata.append([1, data['Age'][i] * data['Race'][i]* data['Country'][i], data['Sex'][i]]) for i in range(0,99): if data['Income'][i] == '>50K': Traininganswers.append(1) else: Traininganswers.append(-1) Trainingdata = np.array(Trainingdata) Traininganswers = np.array(Traininganswers) print(Trainingdata) print(Traininganswers)

[[  1 200   2]
 [  1 152   2]
 [  1 106   2]
 [  1  28   1]
 [  1 148   1]
 [  1  49   1]
 [  1 208   2]
 [  1 124   1]
 [  1 168   2]
 [  1  74   2]
 [  1  30   2]
 [  1  92   1]
 [  1  64   2]
 [  1  80   2]
 [  1  34   2]
 [  1 100   2]
 [  1 128   2]
 [  1 152   2]
 [  1 172   1]
 [  1 160   2]
 [  1 108   1]
 [  1  70   2]
 [  1 172   2]
 [  1 236   1]
 [  1 224   2]
 [  1  76   2]
 [  1  54   2]
 [  1 156   2]
 [  1 196   2]
 [  1  92   2]
 [  1  40   2]
 [  1 180   2]
 [  1 120   2]
 [  1  44   2]
 [  1  96   2]
 [  1  84   2]
 [  1  76   1]
 [  1 124   2]
 [  1 192   2]
 [  1 124   2]
 [  1 212   2]
 [  1  96   2]
 [  1 196   1]
 [  1 100   2]
 [  1 114   2]
 [  1 212   2]
 [  1 176   1]
 [  1 228   2]
 [  1 160   2]
 [  1  50   1]
 [  1  72   1]
 [  1  94   1]
 [  1 200   2]
 [  1 188   2]
 [  1 172   2]
 [  1  92   2]
 [  1  70   2]
 [  1 164   2]
 [  1 120   2]
 [  1 120   2]
 [  1 128   2]
 [  1 192   2]
 [  1 168   2]
 [  1 144   2]
 [  1 112   1]
 [  1 212   1]
 [  1 196   2]
 [  1 100   2]
 [  1  76   2]
 [  1  62   1]
 [  1 116   2]
 [  1  92   2]
 [  1 224   2]
 [  1 316   2]
 [  1  54   2]
 [  1 160   2]
 [  1 268   2]
 [  1  72   1]
 [  1 124   2]
 [  1  72   2]
 [  1 104   2]
 [  1 160   2]
 [  1 160   2]
 [  1 184   1]
 [  1 236   2]
 [  1 176   1]
 [  1 212   1]
 [  1 196   2]
 [  1 132   2]
 [  1 120   2]
 [  1 172   1]
 [  1 228   2]
 [  1 148   1]
 [  1  56   1]
 [  1 136   2]
 [  1 116   2]
 [  1 192   2]
 [  1 148   2]
 [  1  96   1]]
[ 1  1  1 -1  1 -1  1  1  1 -1 -1 -1 -1  1 -1  1  1  1  1  1 -1 -1  1 -1
  1 -1  1 -1 -1 -1 -1  1 -1 -1 -1 -1 -1  1 -1 -1  1 -1  1 -1  1  1 -1  1
  1 -1 -1  1  1 -1  1 -1 -1  1  1  1  1  1  1  1 -1  1  1 -1 -1 -1  1 -1
  1 -1 -1  1  1 -1 -1 -1 -1  1  1  1  1  1 -1  1 -1 -1  1  1 -1 -1  1 -1
  1  1 -1]

xlim(0, 300) # plot x from 0 to 4 ylim(0, 3) # plot y from 0 to 4 greaterthan5k = (Traininganswers==1) # boolean, have covid? lessthanorequal5k = invert(greaterthan5k) # boolean, inverse of have covid? title("Income data") xlabel("Age x Race x Country") ylabel("Gender (M(2), F(1)") plot(Trainingdata[greaterthan5k,1], Trainingdata[greaterthan5k,2],'b.',label="Earns greater than 5k") plot(Trainingdata[lessthanorequal5k,1], Trainingdata[lessthanorequal5k,2],'r.',label="Earns less than 5K") legend() grid()

def calc_error(y_arr, x_arr, w, train=False): err_sum=0.0 for j in range(len(y_arr)): y_out = (x_arr[j].dot(w)>=0.0) and 1 or -1 # make a prediction, +1 (versi) or -1 (vir) err = y_arr[j]-y_out # compare to known species err_sum += abs(err) and 1 or 0 # accumulate the total error if train: w += eta*err*x_arr[j] # adjust the weights during training only return err_sum def train(y, x, w): return calc_error(y, x, w, train=True) def test(y, x, w): return calc_error(y, x, w)

eta=0.1 # how much should we "nudge" the weights each time? w = rand(len(Trainingdata[0]))*.05 # random array of "small" weights err_test=[] err_train=[] train_iters=100 print(Traininganswers[:20]) for i in range(train_iters): err_train.append(train(Traininganswers[:10], Trainingdata[:10], w)) err_test.append(test(Traininganswers[10:], Trainingdata[10:], w)) title("Training and testing error.") plot(range(train_iters),err_train,'b', label="Train") plot(range(train_iters),err_test,'r', label="Test") xlabel("Iteration") ylabel("Error") legend() grid()

[ 1  1  1 -1  1 -1  1  1  1 -1 -1 -1 -1  1 -1  1  1  1  1  1]

xx,yy = meshgrid(linspace(min(Trainingdata[:,1])-1,max(Trainingdata[:,1]+1),100), linspace(min(Trainingdata[:,2])-1,max(Trainingdata[:,2]+1),100)) z=w[0]+xx*w[1] + yy*w[2] contourf(xx,yy,z,levels=[-10,0,+10]) title("Income data") xlabel("Age x Race x Country") ylabel("Gender (M(2), F(1)") plot(Trainingdata[greaterthan5k,1], Trainingdata[greaterthan5k,2],'b.',label="Earns greater than 5k") plot(Trainingdata[lessthanorequal5k,1], Trainingdata[lessthanorequal5k,2],'r.',label="Earns less than 5K") legend() grid()