install.packages("clustMixType")
install.packages("factoextra")
install.packages("NbClust")
This is my R code:
#Reading Required Datasets
df = as.data.frame(read_excel("dataforclustering.xlsx"))
df2 = df[,-1]
head(df2)
scaled_df = scale(df2)
#This part was to determine the optimal number of clusters
# Elbow method
fviz_nbclust(scaled_df, kmeans, method = "wss") +
geom_vline(xintercept = 4, linetype = 2)+
labs(subtitle = "Elbow method")
# Silhouette method
fviz_nbclust(scaled_df, kmeans, method = "silhouette")+
labs(subtitle = "Silhouette method")
# Gap statistic
# nboot = 50 to keep the function speedy.
# recommended value: nboot= 500 for your analysis.
# Use verbose = FALSE to hide computing progression.
set.seed(123)
fviz_nbclust(scaled_df, kmeans, nstart = 25, method = "gap_stat", nboot =
50)+
labs(subtitle = "Gap statistic method")
Based on the elbow method, which suggested k = 4, I then used the following
code to produce the clusters and try to plot them:
df$MarketSegment <- as.factor(df$MarketSegment)
#kproto comes from the clustMixType package
kclustalgo = kproto(df,4)
summary(kclustalgo)
plot(kclustalgo, vars = c("tolls","transits"))
The problem is that, when using the plot function, it does not generate
anything, it does not plot anything.
Below my dataset:
structure(list(MarketSegment = structure(c(12L, 8L, 4L, 5L, 8L,
8L, 9L, 2L, 8L, 11L, 11L, 12L, 5L, 4L, 10L, 10L, 9L, 11L, 5L,
10L, 10L, 9L, 9L, 9L, 4L, 11L, 10L, 9L, 11L, 4L, 7L, 1L, 2L,
7L, 4L, 6L, 4L, 5L, 4L, 6L, 5L, 11L, 10L, 9L, 8L, 11L, 2L, 4L,
5L, 12L, 10L, 5L, 4L, 5L, 10L, 10L, 11L, 2L, 12L, 5L, 10L, 8L,
8L, 2L, 8L, 13L, 6L, 7L, 4L, 10L, 8L, 3L, 5L, 2L, 7L, 13L, 5L,
5L, 2L, 12L, 4L, 5L, 5L, 12L, 10L, 5L, 11L, 9L, 4L, 2L, 4L, 2L,
9L, 5L, 11L, 10L, 4L, 11L, 12L, 9L, 11L, 10L, 4L, 13L, 4L, 2L,
4L, 5L, 6L, 13L, 2L, 5L, 10L, 3L, 13L, 8L, 11L, 9L, 8L, 10L,
4L, 2L, 11L, 2L, 9L, 4L, 12L, 10L, 8L, 12L, 8L, 10L, 11L, 2L,
8L, 4L, 12L, 9L, 8L, 8L, 11L, 11L, 2L, 9L, 10L, 8L, 12L, 2L,
11L, 8L, 11L, 4L, 2L, 3L, 3L, 8L, 13L, 5L, 5L, 6L, 6L, 2L, 9L,
10L, 2L, 7L, 6L, 2L, 1L, 7L, 6L, 13L, 1L, 2L, 4L, 5L, 12L, 9L,
11L, 9L, 8L, 2L, 9L, 9L, 5L, 11L, 2L, 12L, 2L, 8L, 12L, 4L, 5L,
4L, 10L, 2L, 9L, 2L, 2L, 2L, 9L, 11L, 2L, 12L, 2L, 10L, 12L,
9L, 4L, 12L, 10L, 5L, 12L, 1L, 6L, 5L, 8L, 10L, 9L, 10L, 4L,
7L, 8L, 1L, 9L, 3L, 3L, 1L, 4L, 4L, 2L, 4L, 10L, 11L, 8L, 2L,
9L, 2L, 5L, 4L, 12L, 4L, 5L, 4L, 9L, 4L, 4L, 12L, 9L, 2L, 8L,
12L, 4L, 3L, 7L, 3L, 10L, 7L, 8L, 2L, 6L, 1L, 3L, 6L, 13L, 7L,
13L, 9L, 13L, 8L, 3L, 10L, 10L, 5L, 12L, 9L, 8L, 8L, 11L, 10L,
8L, 12L, 8L, 5L, 9L, 4L, 12L, 11L, 4L, 8L, 5L, 10L, 11L, 11L,
2L, 12L, 5L, 10L, 9L, 13L, 1L, 7L, 9L, 9L, 10L, 3L, 2L, 1L, 8L,
8L, 9L, 10L, 2L, 8L, 13L, 6L, 12L, 4L, 8L, 10L, 9L, 10L, 10L,
5L, 11L, 8L, 8L, 4L, 12L, 8L, 12L, 10L, 9L, 12L, 5L, 11L, 2L,
5L, 5L, 10L, 5L, 5L, 9L, 9L, 5L, 2L, 9L, 1L, 8L, 13L, 7L, 3L,
5L, 1L, 1L, 9L, 10L, 7L, 5L, 3L, 1L, 4L), levels = c("Chemical Tankers",
"Container", "Crude/Product Tankers", "Dry Bulk", "General Cargo",
"LNG Carrier", "LPG Carrier", "Others", "Passengers", "Refrigerated",
"Tankers", "Vehicle Carriers", "Vehicle Carriers/RoRo"), class = "factor"),
Toll = c(45622373.27, 30399013.74, 176306593.66, 18971118.38,
25835490.96, 23740969.7, 22570777.11, 144378273.06, 59115267.47,
71971071.4, 94431934.17, 14252216.8, 25040195.72, 92607705.13,
17595512.81, 22275409.83, 6291531.04, 51104161.27, 25181172.84,
34816907.8, 32777647.65, 7099598.51, 27689930.37, 42046359.26,
173706597.74, 143220682.62, 59053229.17, 39369534.57, 157970209.29,
411908086.08, 30644932.62, 141530616.2, 1086950201, 222938133.49,
347883155.9, 160051827.89, 376203394.59, 44232336.52, 410395911.78,
218235220.1, 35274869.37, 73258945.88, 37821693.14, 81193.19,
25461445.17, 61671172.38, 64984959.44, 166826321.18, 21076499.39,
88337589.73, 46904254.95, 20029152.87, 143083949.3, 21959696.81,
52382607.59, 3478831.59, 46284549.62, 48579258.24, 47417137.43,
25768369.63, 52765742.89, 60329234.95, 52200921.5, 911170775.2,
27854758.26, 188077540.25, 170069.18, 46979713.12, 324994117.34,
42136353.11, 12495006.27, 93066248.53, 46588988.04, 1203041643,
275586213.06, 224722357.56, 38114431.53, 24457874.42, 224106,
52935575.5, 145149052.16, 24254689.17, 21355540.17, 77826892.53,
37047616.49, 25895846.03, 81595647.93, 18824145.98, 157687486.69,
252355857.97, 23554769.2, 42803289.58, 6970409.95, 25223571.18,
44521560.29, 23846694.1, 123861794, 62133036.93, 49025354.84,
27761074.11, 93221253.37, 67681581.53, 326040777.37, 0, 353324758.38,
914308534.52, 375236325.91, 42896733.54, 18760255.6, 198508135.47,
1367150804.75, 42296364.22, 32848434.94, 84984870.35, 209972507.43,
131115.79, 636385.07, 15683638.27, 27432524.55, 34767287.97,
174026078.65, 91872590.71, 77273064.3, 115418664.65, 24248775.39,
184598288.14, 55702797.23, 35938942.48, 37876793.27, 67595978.53,
37585563.97, 38058681.79, 70479369.62, 181080995.57, 43367438.62,
152817300.67, 99222096.54, 29739623.79, 7027238.12, 25482814.45,
52706796.25, 44227271.88, 49125255.46, 7273684.04, 31550474.77,
45171138.63, 113147627.59, 736129089, 118847881.44, 48827559.85,
175552816, 231472438.57, 972466186.8, 20939505.12, 74784961.28,
22048526.85, 184182792.62, 50043224.13, 46567864.3, 64096942.63,
133561525.43, 1184603445, 27481529.81, 35823758.59, 1241926985.25,
336005108, 175196241.59, 1417836913.5, 219080343.22, 447793583.34,
142244858.6, 211282556.89, 282402337.27, 73904457.86, 213236.53,
23845925.9, 47069774.11, 17091622.26, 77288315.4, 20367261.33,
58398395.39, 230933373.58, 26598884.35, 2406557.1, 6480102,
13628284.31, 10263514.77, 66291278.83, 45203889.46, 24439458.61,
62995994.42, 103545550.11, 23582006.69, 106841255.81, 30920698.81,
57152783.67, 6788655.31, 58688264.46, 63623458.42, 381280927.57,
26160209.37, 94398586.99, 548546815.6, 94377076.67, 660333530.6,
58467965.42, 121250943.68, 39897634.25, 253784215.75, 123264396,
58788870.55, 41450428.73, 116407322.67, 37073625.53, 80949.5,
46479259.97, 17935104.29, 44743486.45, 50354870.76, 45978813.8,
381104737.29, 144588856.56, 13453753.84, 215589051.87, 14640417.36,
113367165.56, 100614565.26, 270041980.52, 436045596.44, 399693615.37,
80310709.08, 178202292.6, 37426161.19, 84501310.47, 35095993.84,
115887420.17, 25320445.08, 131720569.81, 20152178.46, 98738563.37,
52761092.05, 126078172.3, 24618706.25, 136326542.07, 11518860.78,
156025722.98, 170794953.78, 105383146.32, 33742975.52, 786732496.2,
44558463.25, 138272099.98, 332758968.08, 73351527.91, 3711095.76,
0, 49843621.55, 22795131.65, 23624194.51, 960690603.6, 0,
174697284.22, 75560763.05, 231180, 196673683.99, 190737686.99,
213184850.38, 43204339.22, 175208475.3, 14294438.32, 105373950.72,
34354378.94, 36201953.3, 152644.76, 4271.52, 21467521.11,
24714178.25, 23397907.04, 84318567.96, 41391735.09, 59207931.58,
96631125.37, 26119366.87, 24050681.28, 6414468.87, 115073972.91,
48806783.58, 53117026.48, 143925878.71, 54427083.34, 29621363.6,
67914181.91, 208255468.52, 172563091.58, 783130968, 87885643.22,
33623583.6, 49862226.49, 39581084.06, 47338366.37, 0, 0,
42059174.7, 55196029.54, 45573526.31, 77542558.18, 948435917.2,
184766344.51, 11715869.41, 11465772.13, 58348554.79, 34159529.23,
1324615521.7, 14214065.75, 204448377.38, 133199367.48, 48301726.87,
171342164.62, 27932981.26, 204453.32, 13799161.85, 36545009.39,
40127237.59, 24856336.87, 81983152.36, 27475201.4, 40720204.5,
143732024.58, 81736659.41, 54145665.75, 63195468.9, 17990069.83,
7063003.98, 53943424.6, 27336061.94, 49141786, 56875952.23,
25301093.8, 21993181.36, 52955818.55, 25793889.09, 28102485.94,
39856771.5, 45181483.95, 42949296.26, 931539910.4, 34918600.8,
134194366.11, 20115045.15, 203545729.19, 68836834.76, 85618322.31,
41411914.83, 203629971.2, 200898608.18, 44469248.2, 35518487.49,
326654852.92, 38518260.2, 99286360.37, 231011004.03, 368789029.42
), Transits = c(557, 2932, 3312, 1015, 3037, 2958, 257, 1797,
2812, 1615, 1912, 251, 1836, 2861, 1592, 1908, 149, 1656,
1596, 2613, 2409, 159, 205, 235, 2472, 2079, 1631, 202, 1838,
3356, 298, 1489, 2493, 1148, 2614, 421, 2758, 651, 2925,
519, 453, 2187, 2568, 2799, 2705, 1928, 1187, 3042, 968,
789, 2216, 817, 2380, 882, 2371, 324, 1667, 1120, 646, 819,
2108, 2737, 2586, 3255, 2210, 796, 4, 440, 2610, 838, 1217,
667, 675, 2615, 1349, 886, 556, 1514, 37622, 665, 3431, 1537,
1075, 721, 1997, 1333, 2081, 217, 2579, 2534, 703, 992, 226,
1771, 1591, 1963, 3306, 1943, 611, 224, 1707, 2151, 3288,
2510, 3081, 2892, 3075, 678, 58, 798, 2642, 616, 566, 413,
691, 22076, 9415, 300, 2881, 2309, 3613, 1428, 1940, 1691,
310, 3549, 561, 2021, 3071, 645, 2641, 2085, 1704, 2126,
2668, 2851, 792, 243, 682, 2881, 1810, 1615, 1043, 170, 2140,
2615, 833, 3524, 2027, 2497, 2342, 2982, 3326, 181, 596,
1986, 787, 878, 813, 181, 340, 2616, 127, 746, 2537, 1526,
425, 2843, 1987, 1552, 343, 782, 1850, 1334, 8088, 1431,
509, 283, 2216, 228, 2625, 2451, 225, 75, 485, 472, 237,
1091, 1069, 2785, 973, 3092, 1597, 3134, 2279, 1093, 155,
1131, 1174, 3020, 221, 1744, 3419, 728, 3604, 2199, 765,
215, 3033, 632, 1453, 926, 504, 431, 2, 913, 2001, 992, 265,
954, 2904, 929, 1696, 2114, 53, 783, 628, 2362, 3004, 2781,
1391, 3939, 2031, 2207, 2653, 1597, 299, 1749, 1061, 3019,
731, 3206, 1558, 3275, 233, 2598, 2752, 810, 248, 3235, 2455,
618, 3220, 647, 51, 3611, 1069, 240, 2086, 3132, 2975, 1799,
610, 3, 802, 1027, 844, 170, 650, 1314, 631, 601, 459, 8494,
1803, 297, 2909, 2941, 2129, 2172, 2643, 807, 2893, 1767,
214, 3109, 676, 1804, 2346, 2692, 856, 1912, 2404, 2264,
3094, 448, 900, 1088, 214, 202, 4921, 3567, 229, 249, 968,
621, 2824, 1886, 1989, 2034, 265, 590, 2425, 1521, 762, 272,
600, 3928, 2811, 5552, 308, 2474, 2442, 1379, 2280, 2897,
2794, 2611, 761, 2795, 1110, 1623, 209, 810, 1681, 1642,
1092, 1677, 825, 2246, 779, 816, 226, 214, 908, 3010, 204,
1503, 1944, 849, 538, 666, 636, 2019, 1994, 196, 665, 1552,
559, 569, 2048, 2170)), row.names = c(NA, -362L), class = "data.frame")
