Project 2
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.manifold import TSNE
from sklearn.linear_model import LinearRegression
cardata = pd.read_csv('Cars_mileage.csv')
print(cardata)
HP MPG VOL SP WT 0 49 53.700681 89 104.185353 28.762059 1 55 50.013401 92 105.461264 30.466833 2 55 50.013401 92 105.461264 30.193597 3 70 45.696322 92 113.461264 30.632114 4 53 50.504232 92 104.461264 29.889149 .. ... ... ... ... ... 76 322 36.900000 50 169.598513 16.132947 77 238 19.197888 115 150.576579 37.923113 78 263 34.000000 50 151.598513 15.769625 79 295 19.833733 119 167.944460 39.423099 80 236 12.101263 107 139.840817 34.948615 [81 rows x 5 columns]
print(cardata.describe())
HP MPG VOL SP WT count 81.000000 81.000000 81.000000 81.000000 81.000000 mean 117.469136 34.422076 98.765432 121.540272 32.412577 std 57.113502 9.131445 22.301497 14.181432 7.492813 min 49.000000 12.101263 50.000000 99.564907 15.712859 25% 84.000000 27.856252 89.000000 113.829145 29.591768 50% 100.000000 35.152727 101.000000 118.208698 32.734518 75% 140.000000 39.531633 113.000000 126.404312 37.392524 max 322.000000 53.700681 160.000000 169.598513 52.997752
cardata.hist(figsize=(10,8))
plt.show()
km=KMeans(n_clusters=3)
print(km)
KMeans(n_clusters=3)
y=km.fit_predict(cardata[["HP","MPG","VOL",'SP',"WT"]])
print(y)
[4 4 4 4 4 4 4 5 5 0 4 5 0 4 4 4 4 5 4 0 0 4 0 0 0 5 0 0 4 0 0 0 0 0 0 0 0 0 0 6 0 0 0 0 0 0 0 0 6 6 6 6 6 2 2 6 0 6 0 0 2 6 2 2 2 8 2 2 2 7 3 2 2 2 2 2 3 7 3 1 7]
cardata["cluster"]=y
print(cardata)
HP MPG VOL SP WT cluster 0 49 53.700681 89 104.185353 28.762059 0 1 55 50.013401 92 105.461264 30.466833 0 2 55 50.013401 92 105.461264 30.193597 0 3 70 45.696322 92 113.461264 30.632114 0 4 53 50.504232 92 104.461264 29.889149 0 .. ... ... ... ... ... ... 76 322 36.900000 50 169.598513 16.132947 1 77 238 19.197888 115 150.576579 37.923113 1 78 263 34.000000 50 151.598513 15.769625 1 79 295 19.833733 119 167.944460 39.423099 1 80 236 12.101263 107 139.840817 34.948615 1 [81 rows x 6 columns]
car0=cardata[cardata.cluster==0]
car1=cardata[cardata.cluster==1]
car2=cardata[cardata.cluster==2]
print(car0,car1,car2)
HP MPG VOL SP WT cluster 0 49 53.700681 89 104.185353 28.762059 0 1 55 50.013401 92 105.461264 30.466833 0 2 55 50.013401 92 105.461264 30.193597 0 3 70 45.696322 92 113.461264 30.632114 0 4 53 50.504232 92 104.461264 29.889149 0 5 70 45.696322 89 113.185353 29.591768 0 6 55 50.013401 92 105.461264 30.308480 0 7 62 46.716554 50 102.598513 15.847758 0 8 62 46.716554 50 102.598513 16.359484 0 9 80 42.299078 94 115.645204 30.920154 0 10 73 44.652834 89 111.185353 29.363341 0 11 92 39.354094 50 117.598513 15.753535 0 12 92 39.354094 99 122.105055 32.813592 0 13 73 44.652834 89 111.185353 29.378436 0 14 66 45.734893 89 108.185353 29.347279 0 15 73 44.652834 89 111.185353 29.604527 0 16 78 42.789909 91 114.369293 29.535784 0 17 92 39.354094 50 117.598513 16.194122 0 18 78 42.789909 91 114.369293 29.929394 0 19 90 38.901834 103 118.472936 33.516974 0 20 92 38.411003 99 119.105055 32.324650 0 21 74 42.828479 107 110.840817 34.908211 0 22 95 38.310606 101 120.288996 32.675828 0 23 81 40.474723 96 113.829145 31.837122 0 24 95 38.310606 89 119.185353 28.781728 0 25 92 38.411003 50 114.598513 16.043175 0 26 92 38.411003 117 120.760520 38.062823 0 27 92 38.411003 99 119.105055 32.835069 0 28 52 43.469434 104 99.564907 34.483207 0 29 103 35.404192 107 121.840817 35.549360 0 30 84 39.431235 114 113.484609 37.042350 0 31 84 39.431235 101 112.288996 33.234361 0 32 102 36.285456 97 119.921115 31.380041 0 33 102 36.285456 113 121.392639 37.573290 0 34 81 39.531633 101 111.288996 32.701644 0 35 90 37.958743 98 115.013085 31.911223 0 36 90 37.958743 88 114.093383 28.754000 0 37 102 34.070668 86 116.909442 27.879915 0 38 102 34.070668 86 116.909442 28.630502 0 40 95 35.152727 113 116.392639 37.392524 0 41 95 35.152727 106 115.748847 35.027176 0 42 102 34.070668 92 117.461264 30.527427 0 43 95 35.152727 88 114.093383 28.343976 0 44 93 35.643558 102 114.380966 33.078632 0 45 100 34.561499 99 117.105055 32.621916 0 46 100 34.561499 111 118.208698 36.498617 0 47 98 35.052330 103 116.472936 33.910056 0 49 115 29.629936 101 118.288996 33.458472 0 50 115 29.629936 101 118.288996 33.213954 0 51 115 29.629936 101 118.288996 33.436711 0 52 115 29.629936 124 120.404312 40.398164 0 56 96 31.113584 92 110.461264 30.147543 0 57 115 29.629936 101 118.288996 32.734518 0 58 100 30.131923 94 112.645204 30.615283 0 59 100 28.860225 115 115.576579 37.662874 0 HP MPG VOL SP WT cluster 69 245 21.273708 112 158.300669 37.141733 1 70 280 19.678507 50 164.598513 15.823060 1 76 322 36.900000 50 169.598513 16.132947 1 77 238 19.197888 115 150.576579 37.923113 1 78 263 34.000000 50 151.598513 15.769625 1 79 295 19.833733 119 167.944460 39.423099 1 80 236 12.101263 107 139.840817 34.948615 1 HP MPG VOL SP WT cluster 39 130 31.014131 92 128.461264 30.115434 2 48 130 31.014131 86 127.909442 28.070597 2 53 180 24.487367 113 143.392639 37.620695 2 54 160 26.852279 113 135.392639 37.254392 2 55 130 27.856252 124 126.404312 40.589068 2 60 145 27.354265 111 130.208698 36.888153 2 61 120 24.609132 116 117.668550 37.860411 2 62 140 23.515917 131 126.048103 43.390988 2 63 140 23.515917 123 125.312342 40.722831 2 64 150 23.605158 121 128.128401 40.159482 2 65 165 40.050000 50 126.598513 15.712859 2 66 165 23.103172 114 132.484609 37.979956 2 67 165 23.103172 127 133.680223 41.573975 2 68 165 23.103172 123 133.312342 40.472042 2 71 162 23.203569 135 133.415985 44.013139 2 72 162 23.203569 132 133.140074 43.353123 2 73 140 19.086341 160 124.715241 52.997752 2 74 140 19.086341 129 121.864163 42.618698 2 75 175 18.762837 129 132.864163 42.778219 2
plt.scatter(car1.HP,car1["MPG"],color="red")
plt.show()
plt.scatter(car1.HP,car1["VOL"],color="green")
plt.show()
plt.scatter(car1.HP,car1["SP"],color="purple")
plt.show()
plt.scatter(car1.HP,car1["WT"],color="red")
plt.show()
plt.scatter(car0.HP,car0["MPG"],color="red")
plt.scatter(car1.HP,car1["MPG"],color='blue')
plt.scatter(car2.HP,car2["MPG"],color="green")
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="")
plt.legend()
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
plt.scatter(car0.HP,car0["VOL"],color="red")
plt.scatter(car1.HP,car1["VOL"],color='blue')
plt.scatter(car2.HP,car2["VOL"],color="green")
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="")
plt.legend()
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
plt.scatter(car0.HP,car0["SP"],color="red")
plt.scatter(car1.HP,car1["SP"],color='blue')
plt.scatter(car2.HP,car2["SP"],color="green")
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="")
plt.legend()
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
plt.scatter(car0.HP,car0["WT"],color="red")
plt.scatter(car1.HP,car1["WT"],color='blue')
plt.scatter(car2.HP,car2["WT"],color="green")
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="")
plt.legend()
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
def minmax(col):
for i in range(0,len(col)):
value=(float(col[i]))-(float(min(col))) / (float(max(col))-float(min(col)))
ex.append(value)
ex=[]
minmax(cardata.HP)
cardata["HP_new"]=ex
print(cardata)
HP MPG VOL SP WT HP_new 0 49 53.700681 89 104.185353 28.762059 48.820513 1 55 50.013401 92 105.461264 30.466833 54.820513 2 55 50.013401 92 105.461264 30.193597 54.820513 3 70 45.696322 92 113.461264 30.632114 69.820513 4 53 50.504232 92 104.461264 29.889149 52.820513 .. ... ... ... ... ... ... 76 322 36.900000 50 169.598513 16.132947 321.820513 77 238 19.197888 115 150.576579 37.923113 237.820513 78 263 34.000000 50 151.598513 15.769625 262.820513 79 295 19.833733 119 167.944460 39.423099 294.820513 80 236 12.101263 107 139.840817 34.948615 235.820513 [81 rows x 6 columns]
ex=[]
minmax(cardata["MPG"])
cardata["MPG_new"]=ex
print(cardata)
HP MPG VOL SP WT HP_new MPG_new 0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782 1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501 2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501 3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423 4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332 .. ... ... ... ... ... ... ... 76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100 77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988 78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100 79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833 80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363 [81 rows x 7 columns]
ex=[]
minmax(cardata["VOL"])
cardata["VOL_new"]=ex
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new
0 0 1 88.545455
1 0 1 91.545455
2 0 1 91.545455
3 0 1 91.545455
4 0 1 91.545455
.. ... ... ...
76 1 2 49.545455
77 1 9 114.545455
78 1 2 49.545455
79 1 4 118.545455
80 1 9 106.545455
[81 rows x 10 columns]
ex=[]
minmax(cardata["SP"])
cardata["SP_new"]=ex
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new SP_new
0 0 1 88.545455 102.763680
1 0 1 91.545455 104.039590
2 0 1 91.545455 104.039590
3 0 1 91.545455 112.039590
4 0 1 91.545455 103.039590
.. ... ... ... ...
76 1 2 49.545455 168.176840
77 1 9 114.545455 149.154906
78 1 2 49.545455 150.176840
79 1 4 118.545455 166.522787
80 1 9 106.545455 138.419144
[81 rows x 11 columns]
ex=[]
minmax(cardata["WT"])
cardata["WT_new"]=ex
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new SP_new WT_new
0 0 1 88.545455 102.763680 28.340632
1 0 1 91.545455 104.039590 30.045406
2 0 1 91.545455 104.039590 29.772170
3 0 1 91.545455 112.039590 30.210687
4 0 1 91.545455 103.039590 29.467722
.. ... ... ... ... ...
76 1 2 49.545455 168.176840 15.711521
77 1 9 114.545455 149.154906 37.501686
78 1 2 49.545455 150.176840 15.348198
79 1 4 118.545455 166.522787 39.001672
80 1 9 106.545455 138.419144 34.527188
[81 rows x 12 columns]
km=KMeans(n_clusters=3)
print(km)
KMeans(n_clusters=3)
new_value=km.fit_predict(cardata[["HP_new","MPG_new"]])
cardata["cluster_new"]=new_value
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new
0 0
1 0
2 0
3 0
4 0
.. ...
76 1
77 1
78 1
79 1
80 1
[81 rows x 8 columns]
new_value=km.fit_predict(cardata[["HP_new","VOL_new"]])
cardata["cluster_new"]=new_value
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new SP_new WT_new
0 1 1 88.545455 102.763680 28.340632
1 1 1 91.545455 104.039590 30.045406
2 1 1 91.545455 104.039590 29.772170
3 1 1 91.545455 112.039590 30.210687
4 1 1 91.545455 103.039590 29.467722
.. ... ... ... ... ...
76 2 2 49.545455 168.176840 15.711521
77 5 9 114.545455 149.154906 37.501686
78 2 2 49.545455 150.176840 15.348198
79 5 4 118.545455 166.522787 39.001672
80 5 9 106.545455 138.419144 34.527188
[81 rows x 12 columns]
new_value=km.fit_predict(cardata[["HP_new","SP_new"]])
cardata["cluster_new"]=new_value
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new SP_new WT_new
0 3 1 88.545455 102.763680 28.340632
1 3 1 91.545455 104.039590 30.045406
2 3 1 91.545455 104.039590 29.772170
3 6 1 91.545455 112.039590 30.210687
4 3 1 91.545455 103.039590 29.467722
.. ... ... ... ... ...
76 8 2 49.545455 168.176840 15.711521
77 5 9 114.545455 149.154906 37.501686
78 5 2 49.545455 150.176840 15.348198
79 1 4 118.545455 166.522787 39.001672
80 5 9 106.545455 138.419144 34.527188
[81 rows x 12 columns]
new_value=km.fit_predict(cardata[["HP_new","WT_new"]])
cardata["cluster_new"]=new_value
print(cardata)
HP MPG VOL SP WT HP_new MPG_new \
0 49 53.700681 89 104.185353 28.762059 48.820513 53.409782
1 55 50.013401 92 105.461264 30.466833 54.820513 49.722501
2 55 50.013401 92 105.461264 30.193597 54.820513 49.722501
3 70 45.696322 92 113.461264 30.632114 69.820513 45.405423
4 53 50.504232 92 104.461264 29.889149 52.820513 50.213332
.. ... ... ... ... ... ... ...
76 322 36.900000 50 169.598513 16.132947 321.820513 36.609100
77 238 19.197888 115 150.576579 37.923113 237.820513 18.906988
78 263 34.000000 50 151.598513 15.769625 262.820513 33.709100
79 295 19.833733 119 167.944460 39.423099 294.820513 19.542833
80 236 12.101263 107 139.840817 34.948615 235.820513 11.810363
cluster_new cluster VOL_new SP_new WT_new
0 7 1 88.545455 102.763680 28.340632
1 7 1 91.545455 104.039590 30.045406
2 7 1 91.545455 104.039590 29.772170
3 3 1 91.545455 112.039590 30.210687
4 7 1 91.545455 103.039590 29.467722
.. ... ... ... ... ...
76 5 2 49.545455 168.176840 15.711521
77 0 9 114.545455 149.154906 37.501686
78 4 2 49.545455 150.176840 15.348198
79 5 4 118.545455 166.522787 39.001672
80 0 9 106.545455 138.419144 34.527188
[81 rows x 12 columns]
car0=cardata[cardata.cluster_new==0]
car1=cardata[cardata.cluster_new==1]
car2=cardata[cardata.cluster_new==2]
plt.scatter(car0.HP,car0["MPG_new"],color="red")
plt.scatter(car1.HP,car1["MPG_new"],color="blue")
plt.scatter(car2.HP,car2["MPG_new"],color="green")
print(km.cluster_centers_)
print(km.algorithm)
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="*")
plt.legend()
plt.show()
No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.
[[ 86.58414918 38.77594231] [268.24908425 22.99268566] [150.55735493 24.78945382]] auto
car0=cardata[cardata.cluster_new==0]
car1=cardata[cardata.cluster_new==1]
car2=cardata[cardata.cluster_new==2]
plt.scatter(car0.HP,car0["VOL_new"],color="red")
plt.scatter(car1.HP,car1["VOL_new"],color="blue")
plt.scatter(car2.HP,car2["VOL_new"],color="green")
print(km.cluster_centers_)
print(km.algorithm)
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="*")
plt.legend()
plt.show()
No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.
[[239.48717949 36.24972679] [ 95.85622711 30.52521062] [142.32051282 42.37489064] [ 75.89194139 30.86617921] [271.32051282 15.37491598] [308.32051282 27.35659628] [120.37606838 34.00938738] [ 55.19551282 26.61739378] [166.37606838 37.44061735]] auto
car0=cardata[cardata.cluster_new==0]
car1=cardata[cardata.cluster_new==1]
car2=cardata[cardata.cluster_new==2]
plt.scatter(car0.HP,car0["SP_new"],color="red")
plt.scatter(car1.HP,car1["SP_new"],color="blue")
plt.scatter(car2.HP,car2["SP_new"],color="green")
print(km.cluster_centers_)
print(km.algorithm)
plt.scatter(km.cluster_centers_[:,0],
km.cluster_centers_[:,1],
color="purple",marker="*")
plt.legend()
plt.show()
[[239.48717949 36.24972679] [ 95.85622711 30.52521062] [142.32051282 42.37489064] [ 75.89194139 30.86617921] [271.32051282 15.37491598] [308.32051282 27.35659628] [120.37606838 34.00938738] [ 55.19551282 26.61739378] [166.37606838 37.44061735]] auto
car0=cardata[cardata.cluster_new==0]
car1=cardata[cardata.cluster_new==1]
car2=cardata[cardata.cluster_new==2]
plt.scatter(car0.HP,car0["MPG_new"],color="red")
plt.scatter(car1.HP,car1["MPG_new"],color="blue")
plt.scatter(car2.HP,car2["MPG_new"],color="green")
print(km.cluster_centers_)
print(km.algorithm)
plt.scatter(km.cluster_centers_[:,0],km.cluster_centers_[:,1],color="purple",marker="*")
plt.legend()
plt.show()
[[239.48717949 36.24972679] [ 95.85622711 30.52521062] [142.32051282 42.37489064] [ 75.89194139 30.86617921] [271.32051282 15.37491598] [308.32051282 27.35659628] [120.37606838 34.00938738] [ 55.19551282 26.61739378] [166.37606838 37.44061735]] auto
#elbow curve
k_range =range(1,10)
sse=[]
for k in k_range:
km=KMeans(n_clusters=k)
km.fit(cardata[["HP_new","MPG_new"]])
sse.append(km.inertia_)
print(sse)
plt.plot(k_range,sse)
plt.show()
C:\Users\Admin\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1. warnings.warn(
[267626.83547069365, 90696.74184835266, 31508.87696331378, 17453.76836647474, 12521.939792827963, 8081.473788216265, 6170.608026067637, 4464.0842722293455, 3857.5298496941414]
k_range =range(1,10)
sse=[]
for k in k_range:
km=KMeans(n_clusters=k)
km.fit(cardata[["HP_new","VOL_new"]])
sse.append(km.inertia_)
print(sse)
plt.plot(k_range,sse)
plt.show()
C:\Users\Admin\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1. warnings.warn(
[300744.7160493827, 124912.80115830115, 58942.978835978836, 43343.27155483405, 34405.116792929286, 26527.852579365077, 21058.84841269841, 17726.16193036354, 14979.611418992885]
k_range =range(1,10)
sse=[]
for k in k_range:
km=KMeans(n_clusters=k)
km.fit(cardata[["HP_new","SP_new"]])
sse.append(km.inertia_)
print(sse)
plt.plot(k_range,sse)
plt.show()
C:\Users\Admin\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1. warnings.warn(
[277045.21295974904, 91944.91154016042, 31371.985934869954, 17591.584497874916, 12171.721518338545, 7929.548012730878, 5739.266263613302, 3884.3621374702157, 3215.768868932697]
k_range =range(1,10)
sse=[]
for k in k_range:
km=KMeans(n_clusters=k)
km.fit(cardata[["HP_new","WT_new"]])
sse.append(km.inertia_)
print(sse)
plt.plot(k_range,sse)
plt.show()
C:\Users\Admin\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1. warnings.warn(
[265447.5525686185, 90529.8448677072, 32036.741783879886, 19187.340728265353, 14180.230381758134, 10073.618221157674, 8146.488655655978, 6908.161187242607, 5060.312205399491]
