Seeds Dataset
library(readr)
seeds_dataset_3_ <- read_delim("C:/Users/lazarus/Downloads/seeds_dataset (3).txt",
delim = "\t", escape_double = FALSE,
trim_ws = TRUE)
## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)
## Rows: 209 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (1): 1
## dbl (7): 15.26, 14.84, 0.871, 5.763, 3.312, 2.221, 5.22
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
View(seeds_dataset_3_)
sdf1<-seeds_dataset_3_[,-8]
View(sdf1)
summary(sdf1)
## 15.26 14.84 0.871 5.763
## Min. :10.59 Min. :12.41 Min. :0.8081 Min. :0.8189
## 1st Qu.:12.26 1st Qu.:13.45 1st Qu.:0.8576 1st Qu.:5.2430
## Median :14.34 Median :14.29 Median :0.8740 Median :5.5160
## Mean :14.85 Mean :14.56 Mean :0.8713 Mean :5.5630
## 3rd Qu.:17.32 3rd Qu.:15.73 3rd Qu.:0.8878 3rd Qu.:5.9800
## Max. :21.18 Max. :17.25 Max. :0.9183 Max. :6.6750
## NA's :3
## 3.312 2.221 5.22
## Min. :2.630 Min. :0.7651 Min. :3.485
## 1st Qu.:2.955 1st Qu.:2.6400 1st Qu.:5.045
## Median :3.244 Median :3.6000 Median :5.228
## Mean :3.281 Mean :3.7006 Mean :5.408
## 3rd Qu.:3.568 3rd Qu.:4.7730 3rd Qu.:5.879
## Max. :5.325 Max. :8.4560 Max. :6.735
## NA's :1 NA's :4
#assign labels to columns
feature_name<- c('area', 'perimeter','compactness','length_of_kernel','width_of_kernel','asymetry_coefficient','length_of_kernel_groove')
colnames(sdf1)<-feature_name
is.na(sdf1)
## area perimeter compactness length_of_kernel width_of_kernel
## [1,] FALSE FALSE FALSE FALSE FALSE
## [2,] FALSE FALSE FALSE FALSE FALSE
## [3,] FALSE FALSE FALSE FALSE FALSE
## [4,] FALSE FALSE FALSE FALSE FALSE
## [5,] FALSE FALSE FALSE FALSE FALSE
## [6,] FALSE FALSE FALSE FALSE FALSE
## [7,] FALSE FALSE FALSE FALSE FALSE
## [8,] FALSE FALSE FALSE FALSE FALSE
## [9,] FALSE FALSE FALSE FALSE FALSE
## [10,] FALSE FALSE FALSE FALSE FALSE
## [11,] FALSE FALSE FALSE FALSE FALSE
## [12,] FALSE FALSE FALSE FALSE FALSE
## [13,] FALSE FALSE FALSE FALSE FALSE
## [14,] FALSE FALSE FALSE FALSE FALSE
## [15,] FALSE FALSE FALSE FALSE FALSE
## [16,] FALSE FALSE FALSE FALSE FALSE
## [17,] FALSE FALSE FALSE FALSE FALSE
## [18,] FALSE FALSE FALSE FALSE FALSE
## [19,] FALSE FALSE FALSE FALSE FALSE
## [20,] FALSE FALSE FALSE FALSE FALSE
## [21,] FALSE FALSE FALSE FALSE FALSE
## [22,] FALSE FALSE FALSE FALSE FALSE
## [23,] FALSE FALSE FALSE FALSE FALSE
## [24,] FALSE FALSE FALSE FALSE FALSE
## [25,] FALSE FALSE FALSE FALSE FALSE
## [26,] FALSE FALSE FALSE FALSE FALSE
## [27,] FALSE FALSE FALSE FALSE FALSE
## [28,] FALSE FALSE FALSE FALSE FALSE
## [29,] FALSE FALSE FALSE FALSE FALSE
## [30,] FALSE FALSE FALSE FALSE FALSE
## [31,] FALSE FALSE FALSE FALSE FALSE
## [32,] FALSE FALSE FALSE FALSE FALSE
## [33,] FALSE FALSE FALSE FALSE FALSE
## [34,] FALSE FALSE FALSE FALSE FALSE
## [35,] FALSE FALSE TRUE FALSE TRUE
## [36,] FALSE FALSE FALSE FALSE FALSE
## [37,] FALSE FALSE FALSE FALSE FALSE
## [38,] FALSE FALSE FALSE FALSE FALSE
## [39,] FALSE FALSE FALSE FALSE FALSE
## [40,] FALSE FALSE FALSE FALSE FALSE
## [41,] FALSE FALSE FALSE FALSE FALSE
## [42,] FALSE FALSE FALSE FALSE FALSE
## [43,] FALSE FALSE FALSE FALSE FALSE
## [44,] FALSE FALSE FALSE FALSE FALSE
## [45,] FALSE FALSE FALSE FALSE FALSE
## [46,] FALSE FALSE FALSE FALSE FALSE
## [47,] FALSE FALSE FALSE FALSE FALSE
## [48,] FALSE FALSE FALSE FALSE FALSE
## [49,] FALSE FALSE FALSE FALSE FALSE
## [50,] FALSE FALSE FALSE FALSE FALSE
## [51,] FALSE FALSE FALSE FALSE FALSE
## [52,] FALSE FALSE FALSE FALSE FALSE
## [53,] FALSE FALSE FALSE FALSE FALSE
## [54,] FALSE FALSE FALSE FALSE FALSE
## [55,] FALSE FALSE FALSE FALSE FALSE
## [56,] FALSE FALSE FALSE FALSE FALSE
## [57,] FALSE FALSE FALSE FALSE FALSE
## [58,] FALSE FALSE FALSE FALSE FALSE
## [59,] FALSE FALSE FALSE FALSE FALSE
## [60,] FALSE FALSE FALSE FALSE FALSE
## [61,] FALSE FALSE FALSE FALSE FALSE
## [62,] FALSE FALSE FALSE FALSE FALSE
## [63,] FALSE FALSE FALSE FALSE FALSE
## [64,] FALSE FALSE FALSE FALSE FALSE
## [65,] FALSE FALSE FALSE FALSE FALSE
## [66,] FALSE FALSE FALSE FALSE FALSE
## [67,] FALSE FALSE FALSE FALSE FALSE
## [68,] FALSE FALSE FALSE FALSE FALSE
## [69,] FALSE FALSE FALSE FALSE FALSE
## [70,] FALSE FALSE FALSE FALSE FALSE
## [71,] FALSE FALSE FALSE FALSE FALSE
## [72,] FALSE FALSE FALSE FALSE FALSE
## [73,] FALSE FALSE FALSE FALSE FALSE
## [74,] FALSE FALSE FALSE FALSE FALSE
## [75,] FALSE FALSE FALSE FALSE FALSE
## [76,] FALSE FALSE FALSE FALSE FALSE
## [77,] FALSE FALSE FALSE FALSE FALSE
## [78,] FALSE FALSE FALSE FALSE FALSE
## [79,] FALSE FALSE FALSE FALSE FALSE
## [80,] FALSE FALSE FALSE FALSE FALSE
## [81,] FALSE FALSE FALSE FALSE FALSE
## [82,] FALSE FALSE FALSE FALSE FALSE
## [83,] FALSE FALSE FALSE FALSE FALSE
## [84,] FALSE FALSE FALSE FALSE FALSE
## [85,] FALSE FALSE FALSE FALSE FALSE
## [86,] FALSE FALSE FALSE FALSE FALSE
## [87,] FALSE FALSE FALSE FALSE FALSE
## [88,] FALSE FALSE FALSE FALSE FALSE
## [89,] FALSE FALSE FALSE FALSE FALSE
## [90,] FALSE FALSE FALSE FALSE FALSE
## [91,] FALSE FALSE FALSE FALSE FALSE
## [92,] FALSE FALSE FALSE FALSE FALSE
## [93,] FALSE FALSE FALSE FALSE FALSE
## [94,] FALSE FALSE FALSE FALSE FALSE
## [95,] FALSE FALSE FALSE FALSE FALSE
## [96,] FALSE FALSE FALSE FALSE FALSE
## [97,] FALSE FALSE FALSE FALSE FALSE
## [98,] FALSE FALSE FALSE FALSE FALSE
## [99,] FALSE FALSE FALSE FALSE FALSE
## [100,] FALSE FALSE FALSE FALSE FALSE
## [101,] FALSE FALSE FALSE FALSE FALSE
## [102,] FALSE FALSE FALSE FALSE FALSE
## [103,] FALSE FALSE FALSE FALSE FALSE
## [104,] FALSE FALSE FALSE FALSE FALSE
## [105,] FALSE FALSE FALSE FALSE FALSE
## [106,] FALSE FALSE FALSE FALSE FALSE
## [107,] FALSE FALSE FALSE FALSE FALSE
## [108,] FALSE FALSE FALSE FALSE FALSE
## [109,] FALSE FALSE FALSE FALSE FALSE
## [110,] FALSE FALSE FALSE FALSE FALSE
## [111,] FALSE FALSE FALSE FALSE FALSE
## [112,] FALSE FALSE FALSE FALSE FALSE
## [113,] FALSE FALSE FALSE FALSE FALSE
## [114,] FALSE FALSE FALSE FALSE FALSE
## [115,] FALSE FALSE FALSE FALSE FALSE
## [116,] FALSE FALSE FALSE FALSE FALSE
## [117,] FALSE FALSE FALSE FALSE FALSE
## [118,] FALSE FALSE FALSE FALSE FALSE
## [119,] FALSE FALSE FALSE FALSE FALSE
## [120,] FALSE FALSE FALSE FALSE FALSE
## [121,] FALSE FALSE FALSE FALSE FALSE
## [122,] FALSE FALSE FALSE FALSE FALSE
## [123,] FALSE FALSE FALSE FALSE FALSE
## [124,] FALSE FALSE FALSE FALSE FALSE
## [125,] FALSE FALSE FALSE FALSE FALSE
## [126,] FALSE FALSE FALSE FALSE FALSE
## [127,] FALSE FALSE FALSE FALSE FALSE
## [128,] FALSE FALSE FALSE FALSE FALSE
## [129,] FALSE FALSE FALSE FALSE FALSE
## [130,] FALSE FALSE FALSE FALSE FALSE
## [131,] FALSE FALSE FALSE FALSE FALSE
## [132,] FALSE FALSE FALSE FALSE FALSE
## [133,] FALSE FALSE FALSE FALSE FALSE
## [134,] FALSE FALSE FALSE FALSE FALSE
## [135,] FALSE FALSE FALSE FALSE FALSE
## [136,] FALSE FALSE FALSE FALSE FALSE
## [137,] FALSE FALSE FALSE FALSE FALSE
## [138,] FALSE FALSE FALSE FALSE FALSE
## [139,] FALSE FALSE FALSE FALSE FALSE
## [140,] FALSE FALSE FALSE FALSE FALSE
## [141,] FALSE FALSE FALSE FALSE FALSE
## [142,] FALSE FALSE FALSE FALSE FALSE
## [143,] FALSE FALSE FALSE FALSE FALSE
## [144,] FALSE FALSE FALSE FALSE FALSE
## [145,] FALSE FALSE FALSE FALSE FALSE
## [146,] FALSE FALSE FALSE FALSE FALSE
## [147,] FALSE FALSE FALSE FALSE FALSE
## [148,] FALSE FALSE FALSE FALSE FALSE
## [149,] FALSE FALSE FALSE FALSE FALSE
## [150,] FALSE FALSE FALSE FALSE FALSE
## [151,] FALSE FALSE FALSE FALSE FALSE
## [152,] FALSE FALSE FALSE FALSE FALSE
## [153,] FALSE FALSE FALSE FALSE FALSE
## [154,] FALSE FALSE FALSE FALSE FALSE
## [155,] FALSE FALSE FALSE FALSE FALSE
## [156,] FALSE FALSE FALSE FALSE FALSE
## [157,] FALSE FALSE FALSE FALSE FALSE
## [158,] FALSE FALSE FALSE FALSE FALSE
## [159,] FALSE FALSE FALSE FALSE FALSE
## [160,] FALSE FALSE FALSE FALSE FALSE
## [161,] FALSE FALSE FALSE FALSE FALSE
## [162,] FALSE FALSE FALSE FALSE FALSE
## [163,] FALSE FALSE FALSE FALSE FALSE
## [164,] FALSE FALSE FALSE FALSE FALSE
## [165,] FALSE FALSE FALSE FALSE FALSE
## [166,] FALSE FALSE FALSE FALSE FALSE
## [167,] FALSE FALSE FALSE FALSE FALSE
## [168,] FALSE FALSE FALSE FALSE FALSE
## [169,] FALSE FALSE TRUE FALSE FALSE
## [170,] FALSE FALSE TRUE FALSE FALSE
## [171,] FALSE FALSE FALSE FALSE FALSE
## [172,] FALSE FALSE FALSE FALSE FALSE
## [173,] FALSE FALSE FALSE FALSE FALSE
## [174,] FALSE FALSE FALSE FALSE FALSE
## [175,] FALSE FALSE FALSE FALSE FALSE
## [176,] FALSE FALSE FALSE FALSE FALSE
## [177,] FALSE FALSE FALSE FALSE FALSE
## [178,] FALSE FALSE FALSE FALSE FALSE
## [179,] FALSE FALSE FALSE FALSE FALSE
## [180,] FALSE FALSE FALSE FALSE FALSE
## [181,] FALSE FALSE FALSE FALSE FALSE
## [182,] FALSE FALSE FALSE FALSE FALSE
## [183,] FALSE FALSE FALSE FALSE FALSE
## [184,] FALSE FALSE FALSE FALSE FALSE
## [185,] FALSE FALSE FALSE FALSE FALSE
## [186,] FALSE FALSE FALSE FALSE FALSE
## [187,] FALSE FALSE FALSE FALSE FALSE
## [188,] FALSE FALSE FALSE FALSE FALSE
## [189,] FALSE FALSE FALSE FALSE FALSE
## [190,] FALSE FALSE FALSE FALSE FALSE
## [191,] FALSE FALSE FALSE FALSE FALSE
## [192,] FALSE FALSE FALSE FALSE FALSE
## [193,] FALSE FALSE FALSE FALSE FALSE
## [194,] FALSE FALSE FALSE FALSE FALSE
## [195,] FALSE FALSE FALSE FALSE FALSE
## [196,] FALSE FALSE FALSE FALSE FALSE
## [197,] FALSE FALSE FALSE FALSE FALSE
## [198,] FALSE FALSE FALSE FALSE FALSE
## [199,] FALSE FALSE FALSE FALSE FALSE
## [200,] FALSE FALSE FALSE FALSE FALSE
## [201,] FALSE FALSE FALSE FALSE FALSE
## [202,] FALSE FALSE FALSE FALSE FALSE
## [203,] FALSE FALSE FALSE FALSE FALSE
## [204,] FALSE FALSE FALSE FALSE FALSE
## [205,] FALSE FALSE FALSE FALSE FALSE
## [206,] FALSE FALSE FALSE FALSE FALSE
## [207,] FALSE FALSE FALSE FALSE FALSE
## [208,] FALSE FALSE FALSE FALSE FALSE
## [209,] FALSE FALSE FALSE FALSE FALSE
## asymetry_coefficient length_of_kernel_groove
## [1,] FALSE FALSE
## [2,] FALSE FALSE
## [3,] FALSE FALSE
## [4,] FALSE FALSE
## [5,] FALSE FALSE
## [6,] FALSE FALSE
## [7,] FALSE TRUE
## [8,] FALSE FALSE
## [9,] FALSE FALSE
## [10,] FALSE FALSE
## [11,] FALSE FALSE
## [12,] FALSE FALSE
## [13,] FALSE FALSE
## [14,] FALSE FALSE
## [15,] FALSE FALSE
## [16,] FALSE FALSE
## [17,] FALSE FALSE
## [18,] FALSE FALSE
## [19,] FALSE FALSE
## [20,] FALSE FALSE
## [21,] FALSE FALSE
## [22,] FALSE FALSE
## [23,] FALSE FALSE
## [24,] FALSE FALSE
## [25,] FALSE FALSE
## [26,] FALSE FALSE
## [27,] FALSE FALSE
## [28,] FALSE FALSE
## [29,] FALSE FALSE
## [30,] FALSE FALSE
## [31,] FALSE FALSE
## [32,] FALSE FALSE
## [33,] FALSE FALSE
## [34,] FALSE FALSE
## [35,] FALSE FALSE
## [36,] FALSE FALSE
## [37,] FALSE FALSE
## [38,] FALSE FALSE
## [39,] FALSE FALSE
## [40,] FALSE FALSE
## [41,] FALSE FALSE
## [42,] FALSE FALSE
## [43,] FALSE FALSE
## [44,] FALSE FALSE
## [45,] FALSE FALSE
## [46,] FALSE FALSE
## [47,] FALSE FALSE
## [48,] FALSE FALSE
## [49,] FALSE FALSE
## [50,] FALSE FALSE
## [51,] FALSE FALSE
## [52,] FALSE FALSE
## [53,] FALSE FALSE
## [54,] FALSE FALSE
## [55,] FALSE FALSE
## [56,] FALSE FALSE
## [57,] FALSE FALSE
## [58,] FALSE FALSE
## [59,] FALSE FALSE
## [60,] FALSE TRUE
## [61,] FALSE FALSE
## [62,] FALSE FALSE
## [63,] FALSE FALSE
## [64,] FALSE FALSE
## [65,] FALSE FALSE
## [66,] FALSE FALSE
## [67,] FALSE FALSE
## [68,] FALSE FALSE
## [69,] FALSE FALSE
## [70,] FALSE FALSE
## [71,] FALSE FALSE
## [72,] FALSE FALSE
## [73,] FALSE FALSE
## [74,] FALSE FALSE
## [75,] FALSE FALSE
## [76,] FALSE FALSE
## [77,] FALSE FALSE
## [78,] FALSE FALSE
## [79,] FALSE FALSE
## [80,] FALSE FALSE
## [81,] FALSE FALSE
## [82,] FALSE FALSE
## [83,] FALSE FALSE
## [84,] FALSE FALSE
## [85,] FALSE FALSE
## [86,] FALSE FALSE
## [87,] FALSE FALSE
## [88,] FALSE FALSE
## [89,] FALSE FALSE
## [90,] FALSE FALSE
## [91,] FALSE FALSE
## [92,] FALSE FALSE
## [93,] FALSE FALSE
## [94,] FALSE FALSE
## [95,] FALSE FALSE
## [96,] FALSE FALSE
## [97,] FALSE FALSE
## [98,] FALSE FALSE
## [99,] FALSE FALSE
## [100,] FALSE FALSE
## [101,] FALSE FALSE
## [102,] FALSE FALSE
## [103,] FALSE FALSE
## [104,] FALSE FALSE
## [105,] FALSE FALSE
## [106,] FALSE FALSE
## [107,] FALSE FALSE
## [108,] FALSE FALSE
## [109,] FALSE FALSE
## [110,] FALSE FALSE
## [111,] FALSE FALSE
## [112,] FALSE FALSE
## [113,] FALSE FALSE
## [114,] FALSE FALSE
## [115,] FALSE FALSE
## [116,] FALSE FALSE
## [117,] FALSE FALSE
## [118,] FALSE FALSE
## [119,] FALSE FALSE
## [120,] FALSE FALSE
## [121,] FALSE FALSE
## [122,] FALSE FALSE
## [123,] FALSE FALSE
## [124,] FALSE FALSE
## [125,] FALSE FALSE
## [126,] FALSE FALSE
## [127,] FALSE FALSE
## [128,] FALSE FALSE
## [129,] FALSE FALSE
## [130,] FALSE FALSE
## [131,] FALSE FALSE
## [132,] FALSE FALSE
## [133,] FALSE FALSE
## [134,] FALSE FALSE
## [135,] FALSE TRUE
## [136,] FALSE FALSE
## [137,] FALSE FALSE
## [138,] FALSE FALSE
## [139,] FALSE FALSE
## [140,] FALSE FALSE
## [141,] FALSE FALSE
## [142,] FALSE FALSE
## [143,] FALSE FALSE
## [144,] FALSE FALSE
## [145,] FALSE FALSE
## [146,] FALSE FALSE
## [147,] FALSE FALSE
## [148,] FALSE FALSE
## [149,] FALSE FALSE
## [150,] FALSE FALSE
## [151,] FALSE FALSE
## [152,] FALSE FALSE
## [153,] FALSE FALSE
## [154,] FALSE FALSE
## [155,] FALSE FALSE
## [156,] FALSE FALSE
## [157,] FALSE FALSE
## [158,] FALSE FALSE
## [159,] FALSE FALSE
## [160,] FALSE FALSE
## [161,] FALSE FALSE
## [162,] FALSE FALSE
## [163,] FALSE FALSE
## [164,] FALSE FALSE
## [165,] FALSE FALSE
## [166,] FALSE FALSE
## [167,] FALSE FALSE
## [168,] FALSE FALSE
## [169,] FALSE FALSE
## [170,] FALSE FALSE
## [171,] FALSE FALSE
## [172,] FALSE FALSE
## [173,] FALSE FALSE
## [174,] FALSE FALSE
## [175,] FALSE FALSE
## [176,] FALSE FALSE
## [177,] FALSE FALSE
## [178,] FALSE FALSE
## [179,] FALSE FALSE
## [180,] FALSE FALSE
## [181,] FALSE FALSE
## [182,] FALSE FALSE
## [183,] FALSE FALSE
## [184,] FALSE FALSE
## [185,] FALSE FALSE
## [186,] FALSE FALSE
## [187,] FALSE FALSE
## [188,] FALSE FALSE
## [189,] FALSE FALSE
## [190,] FALSE FALSE
## [191,] FALSE FALSE
## [192,] FALSE FALSE
## [193,] FALSE FALSE
## [194,] FALSE FALSE
## [195,] FALSE FALSE
## [196,] FALSE FALSE
## [197,] FALSE FALSE
## [198,] FALSE FALSE
## [199,] FALSE FALSE
## [200,] FALSE FALSE
## [201,] FALSE TRUE
## [202,] FALSE FALSE
## [203,] FALSE FALSE
## [204,] FALSE FALSE
## [205,] FALSE FALSE
## [206,] FALSE FALSE
## [207,] FALSE FALSE
## [208,] FALSE FALSE
## [209,] FALSE FALSE
sdf1<-na.omit(sdf1) #remove all rows that contain NA
sdf1 #view to see how many rows were removed
## # A tibble: 202 × 7
## area perimeter compactness length_of_kernel width_of_kernel
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 14.9 14.6 0.881 5.55 3.33
## 2 14.3 14.1 0.905 5.29 3.34
## 3 13.8 13.9 0.896 5.32 3.38
## 4 16.1 15.0 0.903 5.66 3.56
## 5 14.4 14.2 0.895 5.39 3.31
## 6 14.7 14.5 0.880 5.56 3.26
## 7 16.6 15.5 0.875 6.05 3.46
## 8 16.4 15.2 0.888 5.88 3.50
## 9 15.3 14.8 0.870 5.71 3.24
## 10 14.0 14.2 0.880 5.44 3.20
## # ℹ 192 more rows
## # ℹ 2 more variables: asymetry_coefficient <dbl>, length_of_kernel_groove <dbl>
sdf_scales<-scale(sdf1)
View(sdf_scales)
summary(sdf_scales)
## area perimeter compactness length_of_kernel
## Min. :-1.4741 Min. :-1.6584 Min. :-2.6858 Min. :-1.6660
## 1st Qu.:-0.8848 1st Qu.:-0.8568 1st Qu.:-0.5997 1st Qu.:-0.8450
## Median :-0.1810 Median :-0.1732 Median : 0.1077 Median :-0.2220
## Mean : 0.0000 Mean : 0.0000 Mean : 0.0000 Mean : 0.0000
## 3rd Qu.: 0.8875 3rd Qu.: 0.9444 3rd Qu.: 0.6902 3rd Qu.: 0.8195
## Max. : 2.1439 Max. : 2.0278 Max. : 2.0249 Max. : 2.3287
## width_of_kernel asymetry_coefficient length_of_kernel_groove
## Min. :-1.67149 Min. :-1.96257 Min. :-1.8263
## 1st Qu.:-0.81804 1st Qu.:-0.74280 1st Qu.:-0.7605
## Median :-0.07136 Median :-0.05537 Median :-0.3873
## Mean : 0.00000 Mean : 0.00000 Mean : 0.0000
## 3rd Qu.: 0.79395 3rd Qu.: 0.72728 3rd Qu.: 0.9281
## Max. : 2.02700 Max. : 3.14933 Max. : 2.2870
#need to find distance
d<-dist(scale(sdf1))
#create cluster
h<-hclust(d)
#plot cluster dendrogram
plot(h)
#replace the row number with the class (categories)
plot(h, hang=-0.1, labels=sdf1[["V8"]], cex=0.5)
seeds_dataset_3_
## # A tibble: 209 × 8
## `15.26` `14.84` `0.871` `5.763` `3.312` `2.221` `5.22` `1`
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 14.9 14.6 0.881 5.55 3.33 1.02 4.96 "1"
## 2 14.3 14.1 0.905 5.29 3.34 2.70 4.82 "1"
## 3 13.8 13.9 0.896 5.32 3.38 2.26 4.80 "1"
## 4 16.1 15.0 0.903 5.66 3.56 1.36 5.18 "1"
## 5 14.4 14.2 0.895 5.39 3.31 2.46 4.96 "1"
## 6 14.7 14.5 0.880 5.56 3.26 3.59 5.22 "1"
## 7 14.1 14.1 0.891 5.42 3.30 2.7 NA "5\t\t1"
## 8 16.6 15.5 0.875 6.05 3.46 2.04 5.88 "1"
## 9 16.4 15.2 0.888 5.88 3.50 1.97 5.53 "1"
## 10 15.3 14.8 0.870 5.71 3.24 4.54 5.31 "1"
## # ℹ 199 more rows
plot(h, hang=-0.1, labels=seeds_dataset_3_$x8, cex=0.5)
## Warning: Unknown or uninitialised column: `x8`.
plot(h, hang=-0.1, labels=seeds_dataset_3_[["x8"]], cex=0.5)
#seeds_nan<-seeds_dataset[, -8]
#is.na(seeds_nan)
#seeds_nan<-na.omit(seeds_nan) #remove all rows that contain NA
seeds_nan<-na.omit(seeds_dataset_3_)
seeds_nan
## # A tibble: 202 × 8
## `15.26` `14.84` `0.871` `5.763` `3.312` `2.221` `5.22` `1`
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 14.9 14.6 0.881 5.55 3.33 1.02 4.96 1
## 2 14.3 14.1 0.905 5.29 3.34 2.70 4.82 1
## 3 13.8 13.9 0.896 5.32 3.38 2.26 4.80 1
## 4 16.1 15.0 0.903 5.66 3.56 1.36 5.18 1
## 5 14.4 14.2 0.895 5.39 3.31 2.46 4.96 1
## 6 14.7 14.5 0.880 5.56 3.26 3.59 5.22 1
## 7 16.6 15.5 0.875 6.05 3.46 2.04 5.88 1
## 8 16.4 15.2 0.888 5.88 3.50 1.97 5.53 1
## 9 15.3 14.8 0.870 5.71 3.24 4.54 5.31 1
## 10 14.0 14.2 0.880 5.44 3.20 1.72 5.00 1
## # ℹ 192 more rows
plot(h, hang=-0.1, labels=seeds_nan[["x8"]], cex=0.5)
#cut it at 3 because we have 3 categories
C<-cutree(h,3)
C
## [1] 1 1 1 1 1 1 1 1 2 2 1 2 2 1 2 1 1 2 2 2 1 2 2 1 2 2 1 2 2 1 2 2 2 1 1 1 2
## [38] 2 2 2 1 1 2 1 1 1 2 1 2 2 1 2 2 1 1 1 2 2 2 2 2 2 2 2 2 2 3 1 1 3 1 1 1 3
## [75] 3 1 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 3 3 3 3 1 3 3 3 3 3 3 1 3 3 3 3 3 3 3
## [112] 3 3 3 3 3 3 1 1 3 1 3 3 3 3 3 3 3 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2
## [149] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
## [186] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
length(C)
## [1] 202
dim(seeds_nan)
## [1] 202 8