R, Python 분석과 프로그래밍의 친구 (by R Friend)

(1) 산점도 (Scatter Plot)

(2) 그룹별 산점도 (Scatter Plot by Groups)

(3) 4개 변수로 산점도 크기 및 색깔 다르게 그리기 (Scatterplot with 4 variables)

(4) 산점도 행렬 (Scatter Plot Matrix)

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

# iris data loading

iris = sns.load_dataset('iris')

iris.shape

(150, 5)

iris.head()

  (1) seaborn을 이용한 산점도 행렬 (scatterplot matrix by seaborn)

# scatterplot matrix with histogram only for continuous variables

sns.pairplot(iris, diag_kind='hist')

plt.show()

# Scatterplot matrix with different color by group and kde

sns.pairplot(iris, 

             diag_kind='kde',

             hue="species", 

             palette='bright') # pastel, bright, deep, muted, colorblind, dark

plt.show()

  (2) pandas를 이용한 산점도 행렬 (scatterplot matrix by pandas)

# scatterplot matrix by pandas scatter_matrix()

from pandas.plotting import scatter_matrix

scatter_matrix(iris, 

               alpha=0.5, 

               figsize=(8, 8), 

               diagonal='kde')

plt.show()

  (3) plotly를 이용한 산점도 행렬 (interactive scatterplot matrix by plotly)

# import plotly standard

import plotly.plotly as py

import plotly.graph_objs as go

import plotly.figure_factory as ff

# Cufflinks wrapper on plotly

import cufflinks as cf

# Display all cell outputs

from IPython.core.interactiveshell import InteractiveShell

# plotly + cufflinks in offline mode

from plotly.offline import iplot

cf.go_offline()

# set the global theme

cf.set_config_file(world_readable=True, theme='pearl', offline=True)

fig = ff.create_scatterplotmatrix(

    iris[['petal_width', 'petal_length', 'sepal_width', 'sepal_length']],

    height=800,

    width=800, 

    diag='histogram') # scatter, histogram, box

iplot(fig) # offline mode

# scatterplot matrix by plotly with box plot at diagonal & different color by index(GROUP)

fig = ff.create_scatterplotmatrix(

    iris,

    height=800,

    width=800, 

    diag='box', # scatter, histogram, box

    index='species')

iplot(fig)

> str(airquality)
'data.frame':	153 obs. of  6 variables:
 $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
 $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
 $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
 $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
 $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
 $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...
> 

> # 1~4번째 변수만 선택

> airquality_1 <- airquality[,c(1:4)]
> str(airquality_1)
'data.frame':	153 obs. of  4 variables:
 $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
 $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
 $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
 $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ... 

> # 결측값 개수 확인
> sum(is.na(airquality_1$Ozone)) # 37
[1] 37
> sum(is.na(airquality_1$Solar.R)) # 7
[1] 7
> sum(is.na(airquality_1$Wind)) # 0
[1] 0
> sum(is.na(airquality_1$Temp)) # 0
[1] 0
> 
> # 결측값 있는 상태에서 상관계수 계산했을 때
> cor(airquality_1)
        Ozone Solar.R       Wind       Temp
Ozone       1      NA         NA         NA
Solar.R    NA       1         NA         NA
Wind       NA      NA  1.0000000 -0.4579879
Temp       NA      NA -0.4579879  1.0000000
> 
> # 결측값 있는 행 전체 삭제
> airquality_2 <- na.omit(airquality_1)
> str(airquality_2)
'data.frame':	111 obs. of  4 variables:
 $ Ozone  : int  41 36 12 18 23 19 8 16 11 14 ...
 $ Solar.R: int  190 118 149 313 299 99 19 256 290 274 ...
 $ Wind   : num  7.4 8 12.6 11.5 8.6 13.8 20.1 9.7 9.2 10.9 ...
 $ Temp   : int  67 72 74 62 65 59 61 69 66 68 ...
 - attr(*, "na.action")=Class 'omit'  Named int [1:42] 5 6 10 11 25 26 27 32 33 34 ...
  .. ..- attr(*, "names")= chr [1:42] "5" "6" "10" "11" ...
> sum(is.na(airquality_2$Ozone)) # 0
[1] 0
> sum(is.na(airquality_2$Solar.R)) # 0
[1] 0 

## put histograms on the diagonal
panel.hist <- function(x, ...)
{
  usr <- par("usr"); on.exit(par(usr))
  par(usr = c(usr[1:2], 0, 1.5) )
  h <- hist(x, plot = FALSE)
  breaks <- h$breaks; nB <- length(breaks)
  y <- h$counts; y <- y/max(y)
  rect(breaks[-nB], 0, breaks[-1], y, col = "cyan", ...)
} 

# source: help(pairs)

## put (absolute) correlations on the upper panels,
## with size proportional to the correlations.
panel.cor <- function(x, y, digits = 2, prefix = "", cex.cor, ...)
{
  usr <- par("usr"); on.exit(par(usr))
  par(usr = c(0, 1, 0, 1))
  r <- abs(cor(x, y))
  txt <- format(c(r, 0.123456789), digits = digits)[1]
  txt <- paste0(prefix, txt)
  if(missing(cex.cor)) cex.cor <- 0.8/strwidth(txt)
  text(0.5, 0.5, txt, cex = cex.cor * r)
} 

# source : help(pairs)

## put linear regression line on the scatter plot
panel.lm <- function(x, y, col=par("col"), bg=NA, pch=par("pch"),
                     cex=1, col.smooth="black", ...) {
  points(x, y, pch=pch, col=col, bg=bg, cex=cex)
  abline(stats::lm(y~x), col=col.smooth, ...)
} 

> ## 산점도 행렬(scatter-plot matrix), 상관계수(correlation), 히스토그램(histogram)
> pairs(airquality_2, 
+       lower.panel = panel.lm, # 아래쪽 산점도에 선형 직선 추가
+       upper.panel = panel.cor, # 위쪽에는 상관계수 숫자 (상관계수에 크기 비례)
+       diag.panel = panel.hist, # 대각선에는 히스토그램
+       pch="*",  # 점 모양은 * 로
+       main = "scatter-plot matrix, correlation coef., histogram"
+       )

> # 범주(그룹)을 색깔로 구분하여 산점도 행렬 그리기
> pairs(iris[1:4], main = "Anderson's Iris Data -- 3 species",
+       pch = 21, bg = c("red", "green3", "blue")[unclass(iris$Species)])

 * R script source : help(pairs)