• Tidak ada hasil yang ditemukan

Suharsimi, Arikunto. 2002. Prosedur Penelitian: suatu pendekatan praktek. Jakarta : Rineka Cipta.

Suharsimi, Arikunto. 2018. Prosedur Penelitian: suatu pendekatan praktek. Jakarta : Rineka Cipta.

S. Tom and Ian Davidson. 2002. Visual Data Mining. Jhon Willey and Sons

Kuswandi, 2004. Cara mengukur Kepuasan Karyawan. Elex Media, Jakarta

Mulyana S, Edi Winarko. Teknik Visulalisasi dalam Data Mining. Seminar Nasional Informatika. Mei 2009. UPN Veteran Yogyakarta.

Analisis Data Kategorik. 2010. Modul. Departemen Statistika-FMIPA IPB.

Juni Miniarti . 2013. “Pengelompokan Sekolah Menengah Pertama Berdasarkan Rata-Rata Nilai Ujian Akhir Nasional Di Kota Binjai dengan Analisis Hierrarkhi Clustering”. Skripsi.

Pareira D.G, A. Alfonso, and F.M. Medeiros. Overview of Friedman’s Test and Post-Hoc Analysis. Communication in Statistics-Simulation and Computation. November, 2015.

Ig. Aris Dwiatmoko, Paulina H. Prima Rosa dan Ridowati Gunawan. Analisis Statistis Data Nilai Ujian Nasional Dan Nilai Sekolah Menengah Atas di Daerah Istimewa Yogyakarta. Jurnal Widya Teknik Volume 14 (2). 2015.

G. Ian, Y. Bengio, and A.Courville. 2016. Deep Learning. The MIT Press, London.

Sano A.V.D, H. Nindito. Application of K-Means Algorithm for Cluster Analysis on Proverty of Provinces in Indonesia. Com Tech Vol 7 No 2. Hal (141-150).

Juni 2016.

Keyser J. 2016. How to Program Computer Scinnce Concepts and Python Exercises Course Guide Book. USA.

Halswanter T. 2016. An Introduction to Statistics with Python. Springer, USA.

James G, D.Witten, T.Hestie, and R.Tibshirani. 2017. An Introduction to Statistical Learning with Application in R. Springer, USA.

Liu M, Yueh-Min Huang. The Use of Data Science for Education : The Case of Social Emotional Learning. Smart Leraning Enviroments.Volume 4 No 1.

2017.

Gries P., J. Campbell, J.Montojo. 2017. Practical Programming : An Introduction to Computer Science using Python 3.6-3rd Edition. The Pragmatic Bookself : USA

V. Jan and K. D. Witte. Data Analytic Applications in Education. 2018. CRC Press, London

Kadir. 2018.Statitika Terapan : Konsep, contoh, dan Analisis Data. Jakarta : Rajawali Press.

Stevencua , Jhon Setiawan . Data Visualization of Proverty Level at Provinces in Indonesian from The Year 2013-2015. International Journal of New Media Technology (JNMT). Vol V No1, Juni 2018.

Ahmar A.S,D.Napitulu, R.Rahim, R.Hidayat, Y.Sonata, M.Azmi. Using K-Means Clustering to Cluster Provinces in Indonesia. 2nd International Conference on Statistics, Mathematics, Teaching, and Research. IOP Conferencee Series 1028 (2018).

Pradana C.C.B. 2019. Pengelompokkan Data Evaluasi Pembelajaran Menggunakan Algoritma K-Means++ Clustering. Skripsi : Universitas Sanata Dharma.

M.Eric. 2019. Python Crush Course 2nd Edition. San Fransisco.

Watt J, Borhani R, K K Aggelos. 2020. Machine Learning Refined : Foundation, Algorithms, and Application. Cambridge University Press, USA

Sari N. Devita. 2020. Analisis Komponen Utama untuk Menentukan Faktor-Faktor yang Mempengaruhi Pemilihan Transportasi Online. Skripsi : Universitas Sanata Dharma

V. Anton, T. Albrecht. Unsupervised Classification of Single-Molecule Data with Autoencoders and Transfer Learning. Machine Learning Science and Technology. IOP Publishing. Volume 1 (2020)

Rao C.R, E.J Wegman, and J.L.Solka. Data Mining and Data Visualization.

coursera-statistics-making-sense-of-data (video pembelajaran)

Data Processing Using Python (video pembelajaran)

Applied Data Science with Python Specialization (video pembelajaran) Unsupervised Machine Learning Project with R (video pembelajaran)

https://www.coursera.org/courses?query=free (video pembelajaran)

https://sdm.data.kemdikbud.go.id/upload/files/15Arus%20Siswa%20Revisi.pdf (diakses pada Mei 2020)

Data Science dan Prospeknya di Era Digital-Medium.com (diakses Juni 2020)

https://www.datacamp.com/community/tutorials/k-means-clustering-python.

(diakses pada Juli 2020)

https://medium.com/@gifadelyaninursyafitri/k-means-clustering-menggunakan-python-deeb0881333c (diakses pada Juli 2020)

https://scikit-learn.org/stable/modules/manifold.html (diakses pada Juli 2020) https://pythonspot.com/matplotlib-scatterplot/ (diakses pada Juli 2020)

https://rstudiopubsstatic.s3.amazonaws.com/634784_ce55ab9fd5c945049153dac5 dcfe6b0b.html#normalisasi-data (diakses pada Juli 2020)

https://www.geeksforgeeks.org/elbow-method-for-optimal-value-of-k-in-kmeans/

(diakses pada Agustus 2020)

https://www.guru99.com/scipy-tutorial.html

LAMPIRAN A: PROGRAM UNTUK CAPAIAN NILAI SECARA NASIONAL import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

plt.title('Box Plot Capaian Nilai Rata-Rata Nasional') plt.show()

from pandas import Series, DataFrame import seaborn as sns

plt.title('Box Plot Capaian Nilai Rata-Rata Nasional Mata Pelajaran') plt.show()

LAMPIRAN B: PROGRAM UNTUK CAPAIAN NILAI RATA-RATA PROVINSI import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet1")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.tahun_2016,data2.tahun_2017,data2.tahun_2018,data2.tahun_2019]) data2.describe()

print(data2.describe())

plt.title('Box Plot Capaian Nilai Rata-Rata Nasional 2016-2019')

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.show()

from pandas import Series, DataFrame import seaborn as sns

LAMPIRAN C: PROGRAM UNTUK CAPAIAN NILAI RATA-RATA PROVINSI PER MATA PELAJARAN import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet5")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.bindo_2016,data2.bindo_2017,data2.bindo_2018,data2.bindo_2019]) data2.describe()

print (data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian Nilai Rata-Rata Provinsi Mapel Bahasa Indonesia 2016-2019') plt.show()

Boxplot mapel Bindo

import numpy as np import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

plt.title('Histogram Capaian Bahasa Indonesia 2016')

#plt.title('Histogram Capaian Bahasa Indonesia 2017')

#plt.title('Histogram Capaian Bahasa Indonesia 2018')

#plt.title('Histogram Capaian Bahasa Indonesia 2019') plt.show()

from pandas import Series, DataFrame import seaborn as sns

plt.xlabel=('tahun 2016','tahun 2017','tahun 2018','tahun 2019')

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"])

Boxplot mapel Bing

plt.title('Box Plot Capaian Nilai Rata-Rata Provinsi Mapel Bahasa Inggris 2016-2019') plt.show()

import numpy as np import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

plt.title('Histogram Capaian Bahasa Inggris 2016')

#plt.title('Histogram Capaian Bahasa Inggris 2017')

#plt.title('Histogram Capaian Bahasa Inggris 2018')

#plt.title('Histogram Capaian Bahasa Inggris 2019') plt.show()

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet7")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.matek_2016,data2.matek_2017,data2.matek_2018,data2.matek_2019]) data2.describe()

print(data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian Nilai Rata-Rata Provinsi Mapel Matematika 2016-2019') plt.show()

from pandas import Series, DataFrame import seaborn as sns

#_=plt.xlabel("Matematika 2018")

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet8")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.ipa_2016,data2.ipa_2017,data2.ipa_2018,data2.ipa_2019]) data2.describe()

print(data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian NilaiRata-Rata Provinsi Mapel IPA 2016-2019') plt.show()

Boxplot mapel IPA

import numpy as np import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

LAMPIRAN D: PROGRAM UNTUK CAPAIAN NILAI RATA-RATA PER ZONA WAKTU import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet2")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.tahun_2016,data2.tahun_2017,data2.tahun_2018,data2.tahun_2019]) data2.describe()

print (data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian Nilai Rata-Rata Nasional WIT 2016-2019')

plt.show()

Boxplot WIT

import numpy as np import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet3")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.tahun_2016,data2.tahun_2017,data2.tahun_2018,data2.tahun_2019]) data2.describe()

print(data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian Nilai Rata-Rata Nasional WITA 2016-2019')

plt.show()

Boxplot WITA

import numpy as np import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\margaretha.xlsx") data2=data1.parse("Sheet4")

print(data2)

plt.label=['tahun 2016','tahun 2017','tahun 2018','tahun 2019']

plt.boxplot([data2.tahun_2016,data2.tahun_2017,data2.tahun_2018,data2.tahun_2019]) data2.describe()

print(data2.describe())

plt.legend(["1=tahun 2016","2=tahun 2017","3=tahun 2018","4=tahun 2019"]) plt.title('Box Plot Capaian Nilai Rata-Rata Nasional WIB 2016-2019')

plt.show()

Boxplot WIB

LAMPIRAN E: PROGRAM UNTUK CAPAIAN NILAI RATA-RATA ANTAR ZONA WAKTU import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

import matplotlib.pyplot as plt

data1=pd.ExcelFile("D:\Thonny\marto.xlsx") data2=data1.parse("Sheet6")

data3=data1.parse("Sheet7") data4=data1.parse("Sheet8") ax=plt.gca()

ax.set_ylim([40,68]) ax.set_xlim([0,4])

plt.boxplot([data2.wit_2016,data3.wita_2016,data4.wib_2016])

#plt.boxplot([data2.wit_2017,data3.wita_2017,data4.wib_2017])

#plt.boxplot([data2.wit_2018,data3.wita_2018,data4.wib_2018])

#plt.boxplot([data2.wit_2019,data3.wita_2019,data4.wib_2019]) plt.legend(["1=WIT","2=WITA","3=WIB"])

plt.title('Box Plot Perbandingan Nilai Per Satuan Waktu 2016') data2.describe()

data3.describe() data4.describe() print(data2.describe()) print(data3.describe()) print(data4.describe()) plt.show()

Boxplot zona waktu

LAMPIRAN F: HASIL LISTING PROGRAM UNTUK PCA (PERANGAKAT LUNAK R) 10 68.02 54.55 45.81 51.33 11 66.88 51.00 44.17 50.26 12 70.30 52.90 44.51 52.33 13 70.34 50.40 43.19 47.31 14 70.78 57.16 52.51 55.83 15 70.21 57.96 47.83 59.51 16 70.49 55.62 52.57 57.07 17 66.41 60.00 57.93 60.74 18 63.64 53.76 49.46 56.29 19 66.87 57.48 54.06 59.04 20 65.50 54.47 51.18 56.98 21 66.78 59.68 53.68 57.66 22 68.89 54.22 46.55 58.11 23 61.64 54.73 47.62 49.95 24 63.37 50.03 42.51 52.04 25 62.93 54.43 48.98 53.05 26 67.95 44.30 35.51 46.18 27 65.61 62.71 57.81 59.27 28 73.03 46.90 37.20 47.93 29 64.34 53.49 49.21 55.38 30 65.30 49.25 38.86 45.67 31 73.97 55.56 43.12 51.57 32 60.29 46.59 40.62 49.31 33 69.55 63.69 61.46 63.12 34 66.57 47.59 38.05 47.91

>attach(data)

> data[]=lapply(data,function(x) if(is.numeric(x)){scale(x,center=TRUE,scale=TRUE)}else x)

>eigen(cov(data)) eigen() decomposition

$values

[1] 2.90585095 0.91390082 0.12582050 0.05442774

$vectors

[,1] [,2] [,3] [,4]

[1,] -0.2332135 0.95895776 -0.04032885 -0.1561572 [2,] -0.5647950 -0.08281114 -0.64924283 0.5026258 [3,] -0.5568060 -0.26640223 -0.08699446 -0.7819392 [4,] -0.5626590 -0.05071671 0.75451262 0.3339960

>data_pca=prcomp(data,center=TRUE,scale=TRUE)

>data_pca

Standard deviations (1, .., p=4):

[1] 1.7046557 0.9559816 0.3547119 0.2332975

Rotation (n x k) = (4 x 4):

PC1 PC2 PC3 PC4

y1 -0.2332135 -0.95895776 0.04032885 0.1561572 y2 -0.5647950 0.08281114 0.64924283 -0.5026258 y3 -0.5568060 0.26640223 0.08699446 0.7819392 y4 -0.5626590 0.05071671 -0.75451262 -0.3339960

>install.packages('psych')

--- Please select a CRAN mirror for use in this session ---

Warning: failed to download mirrors file (cannot open URL 'https://cran.r-project.org/CRAN_mirrors.csv');

using local file 'C:/PROGRA~1/R/R-36~1.0/doc/CRAN_mirrors.csv'

Warning: unable to access index for repository https://repo.bppt.go.id/cran/src/contrib:

cannot open URL 'https://repo.bppt.go.id/cran/src/contrib/PACKAGES'

Warning: unable to access index for repository https://repo.bppt.go.id/cran/bin/windows/contrib/3.6:

cannot open URL 'https://repo.bppt.go.id/cran/bin/windows/contrib/3.6/PACKAGES' Warning messages:

1: In download.file(url, destfile = f, quiet = TRUE) :

InternetOpenUrl failed: 'The server name or address could not be resolved' 2: package ‘psych’ is not available (for R version 3.6.0)

>library(psych) Warning message:

package ‘psych’ was built under R version 3.6.2

> fit <- principal(data, nfactors=1, rotate="varimax")

> fit

Principal Components Analysis

Call: principal(r = data, nfactors = 1, rotate = "varimax")

Standardized loadings (pattern matrix) based upon correlation matrix PC1 h2 u2 com

Test of the hypothesis that 1 component is sufficient.

The root mean square of the residuals (RMSR) is 0.1 with the empirical chi square 4.2 with prob< 0.12 Fit based upon off diagonal values = 0.98>

>data<-read.csv(file.choose(),header=T,sep=",") 10 58.40 44.95 43.20 47.63 11 57.47 46.24 45.18 45.88 12 61.35 46.00 46.91 49.25

13 61.23 41.68 44.78 46.16 14 64.75 50.41 52.82 52.49 15 67.77 48.81 45.67 49.02 16 68.14 47.86 42.80 46.71 17 61.53 56.09 56.30 54.13 18 61.14 50.39 47.87 48.93 19 63.41 51.62 51.65 52.16 20 63.45 52.76 52.78 53.54 21 61.19 58.17 55.38 51.29 22 67.54 50.41 43.63 50.45 23 59.20 48.19 46.02 48.59 24 61.21 49.63 47.88 48.48 25 57.48 50.91 48.12 47.40 26 60.07 41.26 41.32 44.85 27 58.12 57.00 53.56 50.11 28 66.93 42.99 42.97 47.64 29 61.12 48.67 48.24 50.30 30 58.76 44.27 42.16 44.50 31 66.93 49.20 47.34 49.48 32 56.91 44.48 42.28 44.97 33 64.02 58.08 58.41 54.99 34 64.90 45.64 40.69 45.36

>attach(data)

The following objects are masked from data (pos = 4):

y1, y2, y3, y4

>data=read.csv(file.choose(),header=T) Error in file.choose() : file choice cancelled

> data[]=lapply(data,function(x) if(is.numeric(x)){scale(x,center=TRUE,scale=TRUE)}else x)

>eigen(cov(data)) eigen() decomposition

$values

[1] 2.80002588 0.96637104 0.19316564 0.04043744

$vectors

[,1] [,2] [,3] [,4]

[1,] -0.3070382 0.8569975 -0.3560571 0.2109649 [2,] -0.5025958 -0.4433962 -0.7257534 -0.1551747 [3,] -0.5690559 -0.2181653 0.3784050 0.6966987 [4,] -0.5738470 0.1461475 0.4509046 -0.6678515

>data_pca=prcomp(data,center=TRUE,scale=TRUE)

>>data_pca

Error: unexpected '>' in ">"

>data_pca

Standard deviations (1, .., p=4):

[1] 1.6733278 0.9830417 0.4395061 0.2010906

Rotation (n x k) = (4 x 4):

PC1 PC2 PC3 PC4

y1 -0.3070382 -0.8569975 -0.3560571 -0.2109649 y2 -0.5025958 0.4433962 -0.7257534 0.1551747 y3 -0.5690559 0.2181653 0.3784050 -0.6966987 y4 -0.5738470 -0.1461475 0.4509046 0.6678515

> fit <- principal(data, nfactors=1, rotate="varimax")

> fit

Principal Components Analysis

Call: principal(r = data, nfactors = 1, rotate = "varimax")

Standardized loadings (pattern matrix) based upon correlation matrix PC1 h2 u2 com

Test of the hypothesis that 1 component is sufficient.

The root mean square of the residuals (RMSR) is 0.17 with the empirical chi square 11.24 with prob< 0.0036

Fit based upon off diagonal values = 0.93>

>data=read.csv(file.choose(),header=T) 10 60.61 45.20 38.71 42.81 11 59.20 44.74 38.62 41.90 12 62.56 44.58 37.31 43.03 13 62.36 44.74 36.86 42.12 14 65.09 50.54 45.48 47.48 15 65.47 48.65 41.00 47.22 16 66.87 51.16 41.85 47.38 17 57.11 49.11 41.44 45.05 18 58.39 45.85 39.38 44.97 19 59.12 47.60 41.49 46.01 20 61.99 50.26 45.19 49.16 21 62.21 58.18 51.53 50.77 22 67.76 53.82 41.62 50.21 23 56.16 42.95 36.32 42.14 24 61.80 51.63 43.47 47.72 25 59.27 52.46 46.91 48.65 26 62.13 43.67 35.88 41.94 27 60.16 57.80 49.86 48.58 28 67.88 47.67 40.95 46.99 29 56.81 44.91 38.24 44.05 30 59.74 46.47 37.47 41.98 31 69.98 54.07 43.86 47.24 32 56.11 43.12 37.37 42.69 33 61.29 52.53 48.13 49.37 34 64.78 47.19 39.48 45.69

>attach(data)

The following objects are masked from data (pos = 3):

y1, y2, y3, y4

The following objects are masked from data (pos = 5):

y1, y2, y3, y4

> data[]=lapply(data,function(x) if(is.numeric(x)){scale(x,center=TRUE,scale=TRUE)}else x)

>eigen(cov(data)) eigen() decomposition

$values

[1] 3.32822563 0.51812326 0.10365996 0.04999115

$vectors

[,1] [,2] [,3] [,4]

[1,] -0.4300257 0.85538110 -0.1537894 -0.2444378 [2,] -0.5146113 -0.33010198 -0.7580451 0.2271024 [3,] -0.5151896 -0.39894199 0.3170072 -0.6891527 [4,] -0.5336972 0.01418239 0.5488378 0.6432288

> fit <- principal(data, nfactors=1, rotate="varimax")

> fit

Principal Components Analysis

Call: principal(r = data, nfactors = 1, rotate = "varimax")

Standardized loadings (pattern matrix) based upon correlation matrix PC1 h2 u2 com

Test of the hypothesis that 1 component is sufficient.

The root mean square of the residuals (RMSR) is 0.09 with the empirical chi square 3.52 with prob< 0.17

Fit based upon off diagonal values = 0.99>

>data=read.csv(file.choose(),header=T) 10 60.12 45.14 41.26 43.45 11 58.12 43.86 40.34 41.85

12 62.00 44.39 40.03 42.88 13 62.32 45.05 40.52 42.78 14 63.65 48.51 45.04 46.29 15 66.59 48.85 42.05 47.08 16 68.82 51.32 44.12 47.92 17 57.71 47.46 40.84 43.72 18 60.33 44.48 41.12 43.71 19 59.97 46.33 42.47 45.26 20 61.80 45.75 44.47 45.65 21 60.30 51.69 50.47 48.98 22 69.42 52.19 43.87 49.03 23 56.87 43.26 38.76 41.79 24 64.75 45.90 46.29 45.78 25 58.76 48.46 46.23 47.63 26 62.61 43.81 39.74 42.78 27 58.49 52.60 49.15 50.07 28 67.89 48.33 44.34 47.90 29 56.04 44.69 40.74 43.51 30 60.29 48.10 41.91 43.98 31 70.19 54.25 47.50 50.18 32 55.40 42.09 39.68 40.45 33 61.11 49.51 48.28 48.96 34 64.45 47.55 42.40 45.04

>attach(data)

The following objects are masked from data (pos = 3):

y1, y2, y3, y4

The following objects are masked from data (pos = 4):

y1, y2, y3, y4

The following objects are masked from data (pos = 6):

y1, y2, y3, y4

> data[]=lapply(data,function(x) if(is.numeric(x)){scale(x,center=TRUE,scale=TRUE)}else x)

>eigen(cov(data)) eigen() decomposition

$values

[1] 3.53054718 0.32439639 0.12677534 0.01828109

$vectors

[,1] [,2] [,3] [,4]

[1,] -0.4641254 0.8545390 0.1213037 -0.1990880 [2,] -0.5051840 -0.1972462 -0.8227453 -0.1702156 [3,] -0.5021493 -0.4651447 0.5245839 -0.5062590 [4,] -0.5265196 -0.1204051 0.1821739 0.8216401

> fit <- principal(data, nfactors=1, rotate="varimax")

> fit

Principal Components Analysis

Call: principal(r = data, nfactors = 1, rotate = "varimax")

Standardized loadings (pattern matrix) based upon correlation matrix PC1 h2 u2 com

y1 0.87 0.76 0.239 1 y2 0.95 0.90 0.099 1 y3 0.94 0.89 0.110 1

y4 0.99 0.98 0.021 1 PC1 SS loadings 3.53 Proportion Var 0.88

Mean item complexity = 1

Test of the hypothesis that 1 component is sufficient.

The root mean square of the residuals (RMSR) is 0.06 with the empirical chi square 1.43 with prob< 0.49 Fit based upon off diagonal values = 1>

LAMPIRAN G : PROGRAM K MEANS import numpy as np

import pandas as pd

from pandas import Series, DataFrame import seaborn as sns

sct = ax.scatter(x_scaled[:,1], x_scaled[:,0], s = 100,c = data2.kluster, marker = "o", alpha = 0.5)

centers = kmeans.cluster_centers_

ax.scatter(centers[:,1], centers[:,0], c='blue', s=200, alpha=0.5) plt.title("Hasil Klustering K-Means")

# km=KMeans(n_clusters=k)

# km=km.fit(data2_transformed)

# Sum_of_squared_distances.append(km.inertia_)

#plt.plot(K,Sum_of_squared_distances,"bx-")

#plt.plot(range (1,15),Sum_of_squared_distances)

#plt.xlabel("k")

#plt.ylabel("Sum_of_squared_distances")

#plt.title("Elbow Method For Optimal k")

#kl=KneeLocator(

# range(1,15),Sum_of_squared_distances, curve="convex", direction="decreasing"

# )

LAMPIRAN H: PROGRAM UJI STATISTIK

print('mean tidak sama')

Uji

Dokumen terkait