From 98e89cfea6eff132ad3d8add214b7b130eeba232 Mon Sep 17 00:00:00 2001
From: SEK1RO <vlad@sek1.ro>
Date: Tue, 2 Dec 2025 14:30:05 +0300
Subject: [PATCH] feat(ds): r4

---
 ds/25-1/{r2 => r}/2.R             |   0
 ds/25-1/r/4.R                     | 101 ++++++++++++++++++++++++++++++
 ds/25-1/r/income_elec_state.Rdata | Bin 0 -> 1155 bytes
 ds/25-1/{r2 => r}/r2.Rproj        |   0
 ds/25-1/{r2 => r}/zipIncome.txt   |   0
 5 files changed, 101 insertions(+)
 rename ds/25-1/{r2 => r}/2.R (100%)
 create mode 100644 ds/25-1/r/4.R
 create mode 100644 ds/25-1/r/income_elec_state.Rdata
 rename ds/25-1/{r2 => r}/r2.Rproj (100%)
 rename ds/25-1/{r2 => r}/zipIncome.txt (100%)

diff --git a/ds/25-1/r2/2.R b/ds/25-1/r/2.R
similarity index 100%
rename from ds/25-1/r2/2.R
rename to ds/25-1/r/2.R
diff --git a/ds/25-1/r/4.R b/ds/25-1/r/4.R
new file mode 100644
index 0000000..e5bf2db
--- /dev/null
+++ b/ds/25-1/r/4.R
@@ -0,0 +1,101 @@
+setwd('/home/sek1ro/git/public/lab/ds/25-1/r')
+load("./income_elec_state.Rdata")
+df = income_elec_state
+df$incomelog = log10(df$income)
+remove(income_elec_state)
+
+elbow_wss = function(df) {
+  max_k = 10
+  wss = numeric(max_k)
+  
+  for (i in 1:max_k) {
+    res = kmeans(df[,1:2], centers = i)
+    wss[i] = res$tot.withinss 
+  }
+  
+  plot(1:max_k, wss, type="b")
+  
+  wss_diff = diff(wss)
+  wss_ratio = wss_diff[-1] / wss_diff[-length(wss_diff)]
+  return(which.min(wss_ratio))
+}
+
+library(ggplot2)
+
+plot_kmeans = function(data, k, log) {
+  res = kmeans(data, centers = k)
+  centers = as.data.frame(res$centers)
+  centers$cluster = as.factor(1:k)
+  data$cluster = as.factor(res$cluster)
+  data$state = rownames(df)
+  
+  plt = ggplot() +
+    geom_point(
+      data = data,
+      aes(
+        x = income,
+        y = elec, 
+        color = cluster
+      )
+    ) +
+    geom_text(
+      data = data,
+      vjust = 1.5,
+      size = 2,
+      aes(
+        x = income,
+        y = elec,
+        label = state
+      )
+    ) +
+    geom_point(
+      data = centers,
+      shape = 17,
+      size = 5,
+      aes(
+        x = income,
+        y = elec,
+        color = cluster,
+      )
+    ) +
+    theme_minimal()
+  
+  if (log) {
+    plt = plt + scale_x_log10() + scale_y_log10()
+  }
+  
+  print(plt)
+}
+
+data = df[,c("income", "elec")]
+datalog = df[,c("incomelog", "elec")]
+k = elbow_wss(data)
+klog = elbow_wss(datalog)
+plot_kmeans(data, k, log=FALSE)
+plot_kmeans(data, klog, log=TRUE)
+
+
+library(maps)
+res = kmeans(data, centers = k)
+map_color = res$cluster[order(names(res$cluster))]
+map("state", fill = TRUE, col = map_color)
+
+Q1 = quantile(df$elec, 0.25)
+Q3 = quantile(df$elec, 0.75)
+IQR = Q3 - Q1
+min = Q1 - 1.5 * IQR
+max = Q3 + 1.5 * IQR
+df = subset(df,  df$elec > min & df$elec < max)
+
+data = df[,c("income", "elec")]
+datalog = df[,c("incomelog", "elec")]
+k = elbow_wss(data)
+klog = elbow_wss(datalog)
+plot_kmeans(data, k, log=FALSE)
+plot_kmeans(data, klog, log=TRUE)
+
+library(ggdendro)
+distance = dist(df, method = "euclidean")
+clust = hclust(distance, method = "complete")
+plot(ggdendrogram(clust))
+cutree(clust, k = k)
diff --git a/ds/25-1/r/income_elec_state.Rdata b/ds/25-1/r/income_elec_state.Rdata
new file mode 100644
index 0000000000000000000000000000000000000000..c3d710a4e58e3c67bf11001a9f2ada0540501fc6
GIT binary patch
literal 1155
zcmZ9KUucbS7{@>7yzizhLT<QFWF;<E)}q{<&cV*k&bv7~+nJ@-aU4baqiuy!$iE8;
z7fQ*6{0k{&8WAn|Ga1SMe`TSFxv>j`d}sSTtzCTI@ArM4_j#W0^ZUK2SVLKHLopC0
zJXudq(hutq!ly_)b!}^|ttH=-Z_ekMIy$qRdGMzFFMvtna=11KM}NV~jf4toptl=V
z?Sa!}gyzhKD_w-VyU@J|u5O3h^Py+Aw8}qa;mLmJ`Uo#d;OjGZzXKkvhk-tL{0C0$
zgKw{(zl6}lL-6GY+_?dl_Y#`-8D4LKH#_0p0{A{4Js0l((2PbnmV?3NaCotL{M4-J
zg#6=h?m7%@g$rBY<R$1^3FjBWnY2ue?&Yu3VaTsHQ<x%XR(PAZNAVeAdGIO)?c%)^
zx`YBK@Wn&==9c)PSboFrq~+Zk&K*$fxiCS{;d^Jr3GoTB_V=`}U#Oa!!c)EX3J-)j
zp;<^Nuk-a=q<4vRhW=)Ks~!B`ihU426weY4DlXq%zhYxAwxBiJlJC&6T1>Y;a@&O?
zw>|pi4`2HDvRrev!<D(8q<D3<Gh4c*T^+}LUew;Up>*t|^3mSmbl_C7)>Pb7#Hoa3
zYf>&2#7tE>6}O70sl*DGO;$TqpLQx^+1jX!MG{V>8=OimacY@$j#|Hr#WLnTsCN}h
ztDLH~&OwF6OeJljxK#w^Dli98b6;mFWpiuHOJKVt?VPLa{Ngq(VzHRb$e8<j>lbNs
fo@3^!%CZ&aAY$&5<}Ypzf~4zG8`EF+cNqTwF*cb?

literal 0
HcmV?d00001

diff --git a/ds/25-1/r2/r2.Rproj b/ds/25-1/r/r2.Rproj
similarity index 100%
rename from ds/25-1/r2/r2.Rproj
rename to ds/25-1/r/r2.Rproj
diff --git a/ds/25-1/r2/zipIncome.txt b/ds/25-1/r/zipIncome.txt
similarity index 100%
rename from ds/25-1/r2/zipIncome.txt
rename to ds/25-1/r/zipIncome.txt