5/8/24, 10:16 AM localweighted - Jupyter Notebook
In [1]: import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
In [2]: data = pd.read_csv('tips.csv')
print("\n Input Data \n\n\n", data.head())
Input Data
total_bill tip sex smoker day time size
0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
4 24.59 3.61 Female No Sun Dinner 4
In [3]: #Take the first and second column of the data
colA = np.array(data.total_bill)
colB= np.array(data.tip)
#Convert these columns to numpy matrices
mcolA = np.mat(colA) #total_bill
mcolB = np.mat(colB) #tip
In [4]: print(np.shape(colA))
print(np.shape(mcolA))
print(np.shape(colB))
print(np.shape(mcolB))
(244,)
(1, 244)
(244,)
(1, 244)
In [5]: m= np. shape (mcolB)[1] #mhas stored number of columns
one= np.ones((1, m), dtype = int) #Prepared a ones matrix
In [6]: # horizontal stacking to prepare input matrix
X = np.hstack((one.T, mcolA.T)) # X is Input matrix: Transpose of one matri
print(X.shape)
#print(X)
(244, 2)
localhost:8888/notebooks/localweighted.ipynb 1/4
5/8/24, 10:16 AM localweighted - Jupyter Notebook
In [7]: def kernel(point, xmat, k):
m,n = np.shape(xmat)
weights = np.eye(m) #Identity matrix
for j in range(m):
diff = point - X[j] #numerator
weights[j, j] = np.exp(diff * diff.T/(-2.0 * k**2))
return weights
In [8]: def localWeight (point, xmat, ymat, k):
wt = kernel (point, xmat, k)
W = (X.T * (wt*X)).I * (X.T * wt * ymat.T)
return W
In [9]: def localweightRegression(xmat, ymat, k):
m,n = np.shape(xmat) # Capture the shape of input matrix
ypred = np.zeros(m) # initializeoutput matrix from ZEROS
for i in range(m):
ypred[i] = xmat[i] * localWeight(xmat[i], xmat, ymat, k)
return ypred
In [10]: ypred = localweightRegression(X,mcolB, 0.5)
localhost:8888/notebooks/localweighted.ipynb 2/4
5/8/24, 10:16 AM localweighted - Jupyter Notebook
In [11]: print(ypred)
[ 2.89600072 1.79792676 3.4522923 3.52469879 3.55735533 4.30366513
1.74542033 3.3728316 2.44785581 2.48880782 1.8083104 4.79767983
2.4062242 2.96892092 2.48153633 3.60296925 1.79915825 2.69663122
2.89434019 3.31271154 2.99001488 3.16455055 2.45092913 5.81565108
3.01841158 2.97028536 2.25892138 2.0276448 3.60793899 2.97252695
1.95484881 2.99194322 2.44464168 3.32920123 2.96499951 3.21755765
2.7072132 2.89066608 2.88520305 4.24629839 2.56138533 2.92431206
2.4541946 1.95650777 3.76134349 3.00455741 3.53901817 4.09179973
3.66290968 3.00808646 2.0045738 1.80493014 4.74741353 1.89792722
4.27129464 2.93423809 3.43543432 3.4808215 1.94126954 7.23057352
3.16455055 2.41735695 1.88491665 3.00455741 2.93692617 3.09292596
2.77475539 1. 3.14256163 2.45273299 2.00874844 2.90170782
3.36328249 4.29987815 2.49550941 1.79043042 2.99001488 3.59729086
3.57479198 2.91358841 2.92392492 2.84629776 1.85736502 3.64623342
2.53190263 4.74356864 2.12713771 3.00620863 3.72100147 3.50603051
3.89403235 3.48271177 1.00112776 2.71243715 3.56803152 4.72571737
3.64447065 2.00820525 3.4522923 1.99806175 1.96577236 2.40748575
2.73357888 3.49064434 3.41892711 2.40849865 3.24526888 4.2646515
3.01146825 2.51405069 2.46876909 2.66849559 3.43658805 3.28533993
4.15216662 2.91465427 4.00576716 1.80257051 1.99658663 3.20974122
2.01171454 2.27845294 2.5103734 2.51807015 1.99932995 4.09338498
1.67174976 2.51473657 1.97178927 3.61791048 2.87096561 3.1570832
1.92407281 1.99643407 3.00910865 1.6698732 1.79915825 2.49729675
2.54147716 2.17623457 2.92511195 5.25976981 4.85670868 3.48788364
2.76596129 1.6615036 2.89846777 2.01463497 1.94169058 2.19910914
2.48355546 2.16463303 2.91203372 3.50429058 3.00467675 4.06514336
4.81733982 4.08416499 2.26675738 2.79134571 3.59411672 2.02187921
2.65306522 2.41735695 2.92857426 3.46560955 3.35741098 4.29599956
1.79551232 1.79993042 10.00000018 2.46330009 2.66849559 4.28421141
2.87744196 3.10778925 2.98471053 2.51633495 1.95831242 4.86189257
4.8411461 3.75181006 3.49981959 3.78290831 4.09278339 3.32920123
3.4114179 3.79013071 3.0155603 3.77491673 2.43081117 3.01565605
3.66451838 2.4064311 2.82356452 2.13199516 1.79792676 4.99343222
2.11637142 2.31297787 2.88065888 2.0384983 2.11637142 2.75218276
3.26218779 2.78322035 3.36532098 4.25846558 3.22538732 2.04326216
3.88698994 3.96972235 8.6847072 2.21946704 3.74312332 2.08272891
3.74790142 2.00369567 1.94456856 3.81795418 2.00085407 2.27845294
1.68568026 2.53190263 2.27845294 2.68589476 1.8514574 3.22847809
2.22342127 3.56617451 3.24368916 2.43081117 2.00568726 1.82360332
2.40872825 1.85736502 2.01207171 3.26367062 4.73341892 3.93042418
3.58402268 3.52143297 2.97207458 2.86850167]
localhost:8888/notebooks/localweighted.ipynb 3/4
5/8/24, 10:16 AM localweighted - Jupyter Notebook
In [12]: import matplotlib.pyplot as plt
xsort = X.copy()
xsort.sort(axis=0)
plt.scatter(colA, colB, color='blue')
plt.plot(xsort[:, 1], ypred[X[:, 1].argsort(0)], color='yellow', linewidth=
plt.xlabel('Total Bill')
plt.ylabel('Tip')
plt.show()
In [ ]:
In [ ]:
In [ ]:
In [ ]:
localhost:8888/notebooks/localweighted.ipynb 4/4
