library(readxl)
saham <- read_excel("D:/Matana/Semester 5/ANALISIS MULTIVARIAT/saham saham/rangkuman saham.xlsx")
## New names:
## • `` -> `...1`
saham
## # A tibble: 10 × 40
## ...1 `45293` `45294` `45295` `45296` `45299` `45300` `45301` `45302` `45303`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 BBRI 5001. 4935. 5023. 5067. 4957. 5023. 5023. 5067. 5155.
## 2 BMRI 5294. 5273. 5489. 5554. 5532. 5510. 5554. 5575. 5683.
## 3 BBCA 8893. 8823. 8941. 9035. 9035. 9082. 9011. 9035. 9153.
## 4 TLKM 3486. 3459. 3468. 3398. 3398. 3459. 3494. 3486. 3503.
## 5 BBNI 4708. 4686. 4905. 4883. 4883. 4949. 4905. 4905. 4905.
## 6 ASII 4720. 4637. 4720. 4658. 4617. 4617. 4575. 4596. 4637.
## 7 ICBP 10199. 10175. 10582. 10271. 10295. 10559. 10870. 10654. 10702.
## 8 UNVR 3283. 3265. 3255. 3255. 3218. 3172. 3154. 3154. 3209.
## 9 INDF 5961. 5915. 5961. 5961. 5915. 5892. 5869. 5869. 5892.
## 10 KLBF 1551. 1536. 1522. 1512. 1522. 1522. 1512. 1527. 1527.
## # ℹ 30 more variables: `45306` <dbl>, `45307` <dbl>, `45308` <dbl>,
## # `45309` <dbl>, `45310` <dbl>, `45313` <dbl>, `45314` <dbl>, `45315` <dbl>,
## # `45316` <dbl>, `45317` <dbl>, `45320` <dbl>, `45321` <dbl>, `45322` <dbl>,
## # `45323` <dbl>, `45324` <dbl>, `45327` <dbl>, `45328` <dbl>, `45329` <dbl>,
## # `45334` <dbl>, `45335` <dbl>, `45337` <dbl>, `45338` <dbl>, `45341` <dbl>,
## # `45342` <dbl>, `45343` <dbl>, `45344` <dbl>, `45345` <dbl>, `45348` <dbl>,
## # `45349` <dbl>, `45350` <dbl>
data_cluster <- saham[, -1]
set.seed(123) # biar hasilnya konsisten
k2 <- kmeans(data_cluster, centers = 2)
k2$cluster
## [1] 2 2 1 2 2 2 1 2 2 2
k2$centers
## 45293 45294 45295 45296 45299 45300 45301 45302
## 1 9546.382 9499.027 9761.511 9653.065 9665.037 9820.309 9940.549 9844.604
## 2 4250.572 4213.362 4293.031 4286.208 4255.359 4268.106 4260.829 4272.328
## 45303 45306 45307 45308 45309 45310 45313 45314
## 1 9927.520 9915.373 9879.636 9927.168 9963.610 10071.703 9999.876 9976.109
## 2 4314.034 4300.500 4296.058 4255.761 4240.851 4235.941 4207.891 4179.102
## 45315 45316 45317 45320 45321 45322 45323 45324
## 1 9952.697 9940.902 9894.075 9964.492 9927.873 10144.059 10119.059 10119.059
## 2 4178.147 4128.371 4124.083 4151.366 4203.391 4214.464 4212.277 4274.974
## 45327 45328 45329 45334 45335 45337 45338
## 1 10012.200 10059.732 10047.232 10202.152 10035.084 10225.742 10177.152
## 2 4256.077 4286.344 4301.856 4322.951 4270.501 4332.375 4352.006
## 45341 45342 45343 45344 45345 45348 45349
## 1 10201.62 10260.421 10200.918 10213.594 10166.062 10154.267 10213.594
## 2 4320.16 4379.467 4385.921 4368.803 4325.058 4305.761 4304.655
## 45350
## 1 10272.568
## 2 4337.937
set.seed(123)
k3 <- kmeans(data_cluster, centers = 3)
k3$cluster
## [1] 3 3 1 2 3 3 1 2 3 2
k3$centers
## 45293 45294 45295 45296 45299 45300 45301 45302
## 1 9546.382 9499.027 9761.511 9653.065 9665.037 9820.309 9940.549 9844.604
## 2 2773.221 2753.533 2748.576 2722.089 2712.949 2717.919 2720.210 2722.084
## 3 5136.983 5089.259 5219.703 5224.680 5180.804 5198.218 5185.200 5202.475
## 45303 45306 45307 45308 45309 45310 45313 45314
## 1 9927.520 9915.373 9879.636 9927.168 9963.610 10071.703 9999.876 9976.109
## 2 2746.406 2729.567 2724.718 2689.553 2671.739 2642.353 2617.007 2626.768
## 3 5254.610 5243.060 5238.862 5195.486 5182.318 5192.094 5162.422 5110.502
## 45315 45316 45317 45320 45321 45322 45323 45324
## 1 9952.697 9940.902 9894.075 9964.492 9927.873 10144.059 10119.059 10119.059
## 2 2651.521 2635.720 2624.552 2599.053 2611.555 2590.658 2613.955 2630.547
## 3 5094.123 5023.962 5023.802 5082.754 5158.492 5188.748 5171.271 5261.631
## 45327 45328 45329 45334 45335 45337 45338
## 1 10012.200 10059.732 10047.23 10202.152 10035.084 10225.742 10177.152
## 2 2638.479 2653.893 2645.70 2540.434 2494.425 2541.085 2557.685
## 3 5226.636 5265.814 5295.55 5392.462 5336.147 5407.149 5428.598
## 45341 45342 45343 45344 45345 45348 45349
## 1 10201.624 10260.421 10200.918 10213.594 10166.062 10154.267 10213.594
## 2 2543.650 2555.451 2521.945 2503.389 2493.862 2458.526 2435.464
## 3 5386.065 5473.876 5504.308 5488.052 5423.776 5414.102 5426.170
## 45350
## 1 10272.568
## 2 2458.531
## 3 5465.581
print(k2)
## K-means clustering with 2 clusters of sizes 2, 8
##
## Cluster means:
## 45293 45294 45295 45296 45299 45300 45301 45302
## 1 9546.382 9499.027 9761.511 9653.065 9665.037 9820.309 9940.549 9844.604
## 2 4250.572 4213.362 4293.031 4286.208 4255.359 4268.106 4260.829 4272.328
## 45303 45306 45307 45308 45309 45310 45313 45314
## 1 9927.520 9915.373 9879.636 9927.168 9963.610 10071.703 9999.876 9976.109
## 2 4314.034 4300.500 4296.058 4255.761 4240.851 4235.941 4207.891 4179.102
## 45315 45316 45317 45320 45321 45322 45323 45324
## 1 9952.697 9940.902 9894.075 9964.492 9927.873 10144.059 10119.059 10119.059
## 2 4178.147 4128.371 4124.083 4151.366 4203.391 4214.464 4212.277 4274.974
## 45327 45328 45329 45334 45335 45337 45338
## 1 10012.200 10059.732 10047.232 10202.152 10035.084 10225.742 10177.152
## 2 4256.077 4286.344 4301.856 4322.951 4270.501 4332.375 4352.006
## 45341 45342 45343 45344 45345 45348 45349
## 1 10201.62 10260.421 10200.918 10213.594 10166.062 10154.267 10213.594
## 2 4320.16 4379.467 4385.921 4368.803 4325.058 4305.761 4304.655
## 45350
## 1 10272.568
## 2 4337.937
##
## Clustering vector:
## [1] 2 2 1 2 2 2 1 2 2 2
##
## Within cluster sum of squares by cluster:
## [1] 59110722 662495984
## (between_SS / total_SS = 74.0 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"
print(k3)
## K-means clustering with 3 clusters of sizes 2, 3, 5
##
## Cluster means:
## 45293 45294 45295 45296 45299 45300 45301 45302
## 1 9546.382 9499.027 9761.511 9653.065 9665.037 9820.309 9940.549 9844.604
## 2 2773.221 2753.533 2748.576 2722.089 2712.949 2717.919 2720.210 2722.084
## 3 5136.983 5089.259 5219.703 5224.680 5180.804 5198.218 5185.200 5202.475
## 45303 45306 45307 45308 45309 45310 45313 45314
## 1 9927.520 9915.373 9879.636 9927.168 9963.610 10071.703 9999.876 9976.109
## 2 2746.406 2729.567 2724.718 2689.553 2671.739 2642.353 2617.007 2626.768
## 3 5254.610 5243.060 5238.862 5195.486 5182.318 5192.094 5162.422 5110.502
## 45315 45316 45317 45320 45321 45322 45323 45324
## 1 9952.697 9940.902 9894.075 9964.492 9927.873 10144.059 10119.059 10119.059
## 2 2651.521 2635.720 2624.552 2599.053 2611.555 2590.658 2613.955 2630.547
## 3 5094.123 5023.962 5023.802 5082.754 5158.492 5188.748 5171.271 5261.631
## 45327 45328 45329 45334 45335 45337 45338
## 1 10012.200 10059.732 10047.23 10202.152 10035.084 10225.742 10177.152
## 2 2638.479 2653.893 2645.70 2540.434 2494.425 2541.085 2557.685
## 3 5226.636 5265.814 5295.55 5392.462 5336.147 5407.149 5428.598
## 45341 45342 45343 45344 45345 45348 45349
## 1 10201.624 10260.421 10200.918 10213.594 10166.062 10154.267 10213.594
## 2 2543.650 2555.451 2521.945 2503.389 2493.862 2458.526 2435.464
## 3 5386.065 5473.876 5504.308 5488.052 5423.776 5414.102 5426.170
## 45350
## 1 10272.568
## 2 2458.531
## 3 5465.581
##
## Clustering vector:
## [1] 3 3 1 2 3 3 1 2 3 2
##
## Within cluster sum of squares by cluster:
## [1] 59110722 86838233 66120124
## (between_SS / total_SS = 92.3 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"
library(cluster)
sil_c3 <- silhouette(k3$cluster, dist(saham))
## Warning in dist(saham): NAs introduced by coercion
avg_sil <- mean(sil_c3[,"sil_width"])
cat("average silhouette width:", avg_sil)
## average silhouette width: 0.5895029
library(cluster)
sil_c2 <- silhouette(k2$cluster, dist(saham))
## Warning in dist(saham): NAs introduced by coercion
avg_sil <- mean(sil_c2[,"sil_width"])
cat("average silhouette width:", avg_sil)
## average silhouette width: 0.6724336
library(factoextra)
## Loading required package: ggplot2
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
fviz_cluster(k2, data = data_cluster)
library(ppclust)
fcm_c3 <- fcm(x=data_cluster, centers = 3)
summary(fcm_c3)
## Summary for 'fcm_c3'
##
## Number of data objects: 10
##
## Number of clusters: 3
##
## Crisp clustering vector:
## [1] 2 2 1 3 2 2 1 3 2 3
##
## Initial cluster prototypes:
## 45293 45294 45295 45296 45299 45300 45301
## Cluster 1 10199.423 10175.480 10582.500 10271.250 10295.192 10558.558 10869.808
## Cluster 2 5294.356 5272.747 5488.843 5553.672 5532.062 5510.453 5553.672
## Cluster 3 3283.235 3264.738 3255.489 3255.489 3218.495 3172.252 3153.755
## 45302 45303 45306 45307 45308 45309 45310
## Cluster 1 10654.327 10702.211 10654.327 10606.442 10654.327 10797.980 11061.35
## Cluster 2 5575.282 5683.329 5618.500 5640.110 5640.110 5640.110 5640.11
## Cluster 3 3153.755 3209.247 3172.252 3153.755 3070.518 3052.021 2996.53
## 45313 45314 45315 45316 45317 45320 45321
## Cluster 1 10917.692 10893.749 10917.692 10917.692 10965.576 10917.692 10750.097
## Cluster 2 5618.500 5618.500 5532.062 5424.014 5445.624 5596.891 5748.158
## Cluster 3 2885.547 2941.039 2959.536 2922.542 2922.542 2848.553 2894.796
## 45322 45323 45324 45327 45328 45329 45334
## Cluster 1 11276.827 11085.29 11085.289 10989.520 11037.403 10941.635 11157.115
## Cluster 2 5748.158 5661.72 5769.768 5899.425 5921.035 6007.474 6137.131
## Cluster 3 2867.050 2867.05 2931.790 2959.536 3005.779 3024.276 2700.576
## 45335 45337 45338 45341 45342 45343 45344
## Cluster 1 10893.749 11157.115 10965.576 11085.289 11061.346 10989.520 11109.230
## Cluster 2 6072.303 6223.570 6223.570 6180.351 6180.351 6266.789 6137.131
## Cluster 3 2589.594 2709.825 2617.339 2589.594 2552.599 2487.860 2515.605
## 45345 45348 45349 45350
## Cluster 1 11061.346 11061.346 11109.230 11109.230
## Cluster 2 6093.912 6093.912 6115.522 6158.741
## Cluster 3 2487.860 2395.374 2423.120 2497.108
##
## Final cluster prototypes:
## 45293 45294 45295 45296 45299 45300 45301
## Cluster 1 9566.339 9519.878 9787.667 9671.587 9683.974 9843.205 9970.590
## Cluster 2 5135.156 5090.201 5223.821 5233.476 5189.320 5210.069 5199.652
## Cluster 3 2778.420 2758.235 2753.528 2731.738 2719.628 2716.711 2714.209
## 45302 45303 45306 45307 45308 45309 45310
## Cluster 1 9870.196 9951.728 9938.233 9902.067 9949.524 9989.996 10103.910
## Cluster 2 5216.843 5269.809 5261.350 5258.344 5218.265 5205.531 5216.773
## Cluster 3 2717.226 2744.251 2724.810 2717.729 2677.466 2661.054 2628.613
## 45313 45314 45315 45316 45317 45320 45321
## Cluster 1 10029.388 10005.605 9984.025 9972.655 9929.494 9995.322 9953.793
## Cluster 2 5193.737 5143.613 5128.915 5055.115 5051.861 5126.098 5196.528
## Cluster 3 2591.782 2605.611 2629.451 2610.178 2599.254 2564.943 2583.489
## 45322 45323 45324 45327 45328 45329 45334
## Cluster 1 10181.585 10150.257 10150.325 10043.946 10091.478 10075.837 10232.937
## Cluster 2 5228.433 5211.577 5294.942 5267.038 5303.944 5330.632 5437.450
## Cluster 3 2564.181 2581.640 2608.869 2617.006 2636.362 2630.248 2503.574
## 45335 45337 45338 45341 45342 45343 45344
## Cluster 1 10062.320 10255.578 10201.634 10229.703 10285.342 10225.461 10242.222
## Cluster 2 5383.847 5465.583 5484.717 5442.540 5533.727 5561.578 5539.931
## Cluster 3 2450.717 2499.972 2502.731 2485.868 2493.061 2458.531 2448.565
## 45345 45348 45349 45350
## Cluster 1 10194.689 10183.319 10242.134 10298.834
## Cluster 2 5479.678 5471.078 5480.432 5519.450
## Cluster 3 2434.386 2394.085 2380.658 2408.979
##
## Distance between the final cluster prototypes
## Cluster 1 Cluster 2
## Cluster 2 875437594
## Cluster 3 2154415031 284587088
##
## Difference between the initial and final cluster prototypes
## 45293 45294 45295 45296 45299 45300 45301
## Cluster 1 -633.0834 -655.6024 -794.8331 -599.6633 -611.2188 -715.3522 -899.2173
## Cluster 2 -159.2007 -182.5460 -265.0219 -320.1959 -342.7419 -300.3837 -354.0201
## Cluster 3 -504.8145 -506.5027 -501.9610 -523.7509 -498.8673 -455.5414 -439.5458
## 45302 45303 45306 45307 45308 45309 45310
## Cluster 1 -784.1309 -750.4829 -716.0941 -704.3758 -704.8031 -807.9849 -957.4356
## Cluster 2 -358.4391 -413.5199 -357.1508 -381.7664 -421.8450 -434.5787 -423.3368
## Cluster 3 -436.5288 -464.9959 -447.4420 -436.0261 -393.0521 -390.9675 -367.9171
## 45313 45314 45315 45316 45317 45320
## Cluster 1 -888.3046 -888.1438 -933.6675 -945.0376 -1036.0825 -922.3703
## Cluster 2 -424.7636 -474.8874 -403.1466 -368.8991 -393.7627 -470.7928
## Cluster 3 -293.7649 -335.4279 -330.0846 -312.3639 -323.2879 -283.6103
## 45321 45322 45323 45324 45327 45328
## Cluster 1 -796.3032 -1095.2426 -935.0324 -934.9642 -945.5739 -945.9254
## Cluster 2 -551.6298 -519.7256 -450.1424 -474.8261 -632.3877 -617.0910
## Cluster 3 -311.3073 -302.8696 -285.4106 -322.9213 -342.5293 -369.4163
## 45329 45334 45335 45337 45338 45341
## Cluster 1 -865.7973 -924.1782 -831.4294 -901.5368 -763.9418 -855.5856
## Cluster 2 -676.8412 -699.6811 -688.4556 -757.9872 -738.8528 -737.8108
## Cluster 3 -394.0275 -197.0025 -138.8763 -209.8530 -114.6085 -103.7257
## 45342 45343 45344 45345 45348 45349
## Cluster 1 -776.00398 -764.05880 -867.00816 -866.65667 -878.026822 -867.0963
## Cluster 2 -646.62321 -705.21075 -597.20020 -614.23414 -622.834087 -635.0897
## Cluster 3 -59.53846 -29.32849 -67.04071 -53.47395 -1.289337 -42.4615
## 45350
## Cluster 1 -810.39634
## Cluster 2 -639.29040
## Cluster 3 -88.12887
##
## Root Mean Squared Deviations (RMSD): 3769.634
## Mean Absolute Deviation (MAD): 825627.6
##
## Membership degrees matrix (top and bottom 5 rows):
## Cluster 1 Cluster 2 Cluster 3
## 1 0.000901234 0.99587737 0.003221395
## 2 0.014327175 0.96057669 0.025096139
## 3 0.931616603 0.05081346 0.017569937
## 4 0.015407699 0.20465004 0.779942265
## 5 0.003577185 0.98077840 0.015644420
## ...
## Cluster 1 Cluster 2 Cluster 3
## 6 0.020959567 0.77243103 0.20660940
## 7 0.967842877 0.02210660 0.01005053
## 8 0.002189302 0.01901970 0.97879100
## 9 0.025716749 0.93649686 0.03778639
## 10 0.015761947 0.07900602 0.90523204
##
## Descriptive statistics for the membership degrees by clusters
## Size Min Q1 Mean Median Q3 Max
## Cluster 1 2 0.9316166 0.9406732 0.9497297 0.9497297 0.9587863 0.9678429
## Cluster 2 5 0.7724310 0.9364969 0.9292321 0.9605767 0.9807784 0.9958774
## Cluster 3 3 0.7799423 0.8425871 0.8879884 0.9052320 0.9420115 0.9787910
##
## Dunn's Fuzziness Coefficients:
## dunn_coeff normalized
## 0.8639274 0.7958911
##
## Within cluster sum of squares by cluster:
## 1 2 3
## 59110722 66120124 86838233
## (between_SS / total_SS = 92.45%)
##
## Available components:
## [1] "u" "v" "v0" "d" "x"
## [6] "cluster" "csize" "sumsqrs" "k" "m"
## [11] "iter" "best.start" "func.val" "comp.time" "inpargs"
## [16] "algorithm" "call"
res.fcm3 <- ppclust2(fcm_c3, "kmeans")
factoextra::fviz_cluster(res.fcm3, data_cluster,
ellipse.type = "convex",
palette = "jco",
repel = TRUE)
sil_c3 <- silhouette(k3$cluster, dist(saham))
## Warning in dist(saham): NAs introduced by coercion
avg_sil <- mean(sil_c3[,"sil_width"])
cat("average silhouette width:", avg_sil)
## average silhouette width: 0.5895029
sil_c33 <- silhouette(fcm_c3$cluster, dist(saham))
## Warning in dist(saham): NAs introduced by coercion
avg_sil <- mean(sil_c33[,"sil_width"])
cat("average silhouette width:", avg_sil)
## average silhouette width: 0.5895029