Posted on | Edited on | In

description: cluster colors in a flower image through k-means

downloading and reading image file

1
2
3
4
library("jpeg")
imageurl<-"https://thumbs-prod.si-cdn.com/WRp3AC1A1q3d4_lCe_fzfMmIu0o=/256x256/https://public-media.smithsonianmag.com/accounts/avatars/IMG_E1531.JPG"
dFile <- download.file(imageurl, "lotus.jpg") # download file to workspace
img <- readJPEG("lotus.jpg") # read local image

processing image data

1
2
3
4
5
6
7
8
9
10
imgDm <- dim(img)
imgDm # [1]  879 1200    3
imgRGB <- data.frame(
  x = rep(1:imgDm[2], each = imgDm[1]), 
  y = rep(imgDm[1]:1, imgDm[2]), 
  R = as.vector(img[,,1]),
  G = as.vector(img[,,2]),
  B = as.vector(img[,,3])
)
imgRGB # X 1 y 879 R .. G .. B ..

set a theme for drawing the image

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
library(ggplot2)
plotTheme <- function(){
  theme(
    panel.background = element_rect(
      size = 3,
      colour = "black",
      fill = "white"
    ),
    axis.ticks = element_line(
      size = 2
    ),
    panel.grid.major = element_line(
      colour = "gray80",
      linetype = "dotted"
    ),
    panel.grid.minor = element_line(
      colour = "gray90",
      linetype = "dashed"
    ),
    axis.title.x = element_text(
      size = rel(1.2),
      face = "bold"
    ),
    axis.title.y = element_text(
      size = rel(1.2),
      face = "bold"
    ),
    plot.title = element_text(
      size = 20,
      face = "bold",
      vjust = 1.5
    )
  )
}

image clustering using K-means clustering

1
2
3
4
5
6
7
8
9
10
kClusters <- 3 
kMeans <- kmeans(imgRGB[,c("R","G","B")], centers  = kCluster)
kColours <- rgb(kMeans$centers[kMeans$cluster,])

ggplot(data = imgRGB, aes(x = x, y = y)) +
  geom_point(colour = kColours) + 
  labs(title = paste("k-Means Clustering of", kClusters, "Colours")) + 
  xlab("x") + 
  ylab("y") + 
  plotTheme()

outcome

Posted on | Edited on | In

description: build ANN network from wine data in r language

read table data

1
2
3
4
wine <- read.table("https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data",
    sep=",", # 分隔符为 , comma
    col.names=c("Type","Alcohol","Malic","Ash","Alcalinity","Magnesium","Phenols","Flavanoids","Nonflavanoids","Proanthocyanins","Color","Hue","Dilution","Proline")
)

preview data

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
print(wine)
#     Type Alcohol Malic  Ash Alcalinity Magnesium Phenols Flavanoids
# 1      1   14.23  1.71 2.43       15.6       127    2.80       3.06
# 2      1   13.20  1.78 2.14       11.2       100    2.65       2.76
# 3      1   13.16  2.36 2.67       18.6       101    2.80       3.24
# 4      1   14.37  1.95 2.50       16.8       113    3.85       3.49
# 5      1   13.24  2.59 2.87       21.0       118    2.80       2.69
# ....

print(nrow(wine))
# [1] 178

print(ncol(wine))
# [1] 14

print(summary(wine))
#       Type          Alcohol          Malic            Ash       
#  Min.   :1.000   Min.   :11.03   Min.   :0.740   Min.   :1.360  
#  1st Qu.:1.000   1st Qu.:12.36   1st Qu.:1.603   1st Qu.:2.210  
#  Median :2.000   Median :13.05   Median :1.865   Median :2.360  
#  Mean   :1.938   Mean   :13.00   Mean   :2.336   Mean   :2.367 
# ...

attribute to categorical data

1
2
3
4
5
6
7
8
wine$Type=factor(wine$Type)
print(summary(wine))
# Type      Alcohol          Malic            Ash          Alcalinity   
#  1:59   Min.   :11.03   Min.   :0.740   Min.   :1.360   Min.   :10.60  
#  2:71   1st Qu.:12.36   1st Qu.:1.603   1st Qu.:2.210   1st Qu.:17.20  
#  3:48   Median :13.05   Median :1.865   Median :2.360   Median :19.50  
#         Mean   :13.00   Mean   :2.336   Mean   :2.367   Mean   :19.49  
# ...

data pre-processing and transformation

1
2
3
4
5
6
7
8
9
wine.scale <- cbind(wine[1], scale(wine[-1]))
print(summary(wine.scale))
apply(wine.scale[-1], 2, sd)
#  Type      Alcohol             Malic              Ash          
#  1:59   Min.   :-2.42739   Min.   :-1.4290   Min.   :-3.66881  
#  2:71   1st Qu.:-0.78603   1st Qu.:-0.6569   1st Qu.:-0.57051  
#  3:48   Median : 0.06083   Median :-0.4219   Median :-0.02375  
#         Mean   : 0.00000   Mean   : 0.0000   Mean   : 0.00000  
# ...

partitioning the data into training and test data

1
2
3
4
5
6
7
8
data.size <- nrow(wine.scale) 
set.seed(1111) 
samp <- c(sample(1:data.size, data.size*0.7))
data.tr <- wine.scale[samp, ]
data.test <- wine.scale[-samp, ]

summary(data.tr)
summary(data.test)

data mining using a neural Network classification technique

1
2
3
4
5
6
7
8
9
10
11
12
13
library(nnet)
model.nnet <- nnet(Type ~ ., 
                   data = data.tr,
                   size=2, # 2 level 
                   decay=5e-04,
                   maxit=200) # stopped after 200 iterations
summary(model.nnet)
# initial  value 164.152084 
# iter  10 value 7.066118
# iter  20 value 1.286566
# iter  30 value 0.542334
# iter  40 value 0.444873
# ...

pattern (model) evaluation

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
predicted <- predict(model.nnet,
                     data.test,
                     type="class")
predicted

actual <- data.test$Type
model.confusion.matrix <- table(actual, predicted)
model.confusion.matrix 

confusion.matrix.rate = prop.table(model.confusion.matrix) * 100
round(confusion.matrix.rate, digit=2)

diag.index <- cbind(1:3, 1:3)

error.overall = sum(confusion.matrix.rate) - sum(confusion.matrix.rate[diag.index])
paste("Error Rate =", round(error.overall, digit=2), "%")

Data mining Task using a nearest neighbour approach

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
P1=c(1,3) 
P2=c(2,4)
P3=c(6,6)

N1=c(2,1) 
N2=c(5,3)
N3=c(6,4)

train=rbind(P1,P2,P3,N1,N2,N3) # build the classification matrix 
plot(train)

class=factor(c(rep("lover",3),rep("hater",3))) # [1] lover lover lover hater hater hater
class

test=c(1,4) # testing data to be classified 
test # 1 4 

library(class)
summary(knn(train, test, class, k=3)) # hater 0 lover 1

test=c(6,4)
summary(knn(train, test, class, k=3)) # hater 1 lover 0

Posted on | Edited on | In

python numpy datetime64 today

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
>>> import numpy as np
>>> import datetime
>>> today = np.datetime64(datetime.datetime.now())
>>> today
numpy.datetime64('2018-07-12T19:12:39.167044')
>>> past = np.datetime64('2018-01-01')
>>> past
numpy.datetime64('2018-01-01')
>>> dif = today - past
>>> dif
numpy.timedelta64(16657959167044,'us')
>>> dif = np.timedelta64(dif, 'D')
>>> dif
numpy.timedelta64(192,'D')
>>> dif.astype(int)
192

more on searchfor.space

Posted on | Edited on | In

python timedelta to seconds

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import numpy as np 
import datetime

today = np.datetime64(datetime.datetime.today())
today
# numpy.datetime64('2018-07-12T19:28:08.889374')

past = np.datetime64('2018-07-11')
past
# numpy.datetime64('2018-07-11')

dif = today - past
dif
# numpy.timedelta64(156488889374,'us')

dif.astype(int)
# 1870066718

more on searchfor.space

Posted on | Edited on

description: python parse string into datetime

parse string into datetime

1
2
3
import datetime 
datetime.datetime.strptime('2018-01-01', "%Y-%m-%d")
# datetime.datetime(2018, 1, 1, 0, 0)

more on search4fan.github.io

Posted on | Edited on | In

description: python print format string example

python Using % and .format() for formating print output

1
2
3
4
5
for i in range(1, 60):
    interaction = '%s' % ('#' *i)
    print('\r{}'.format(interaction), end='')
    time.sleep(1)
# #############...

more on search4fan.github.io

Posted on | Edited on | In

description: pandas select columns by name

python select columns from dataframe by name

1
2
3
4
5
6
7
8
9
import pandas 
d = pandas.DataFrame([[1,2,3,4]], columns=['a','b','c','d'])
# d
#    a  b  c  d
# 0  1  2  3  4
d2 = d[['b','c']]
# d2
#    b  c
# 0  2  3

more on search4fan.github.io

Posted on | Edited on | In

description: python add one day to a date

python datetime date add one day

1
2
3
4
5
6
import datetime
d = datetime.datetime.strptime('2018-02-01', '%Y-%m-%d')
# d
# datetime.datetime(2018, 2, 1, 0, 0)
d + datetime.timedelta(days=1)
# datetime.datetime(2018, 2, 2, 0, 0)

more on search4fan.github.io

Posted on | Edited on

description: python pandas rename or change column names

python rename column headers

1
2
3
4
5
6
7
8
9
10
import pandas 
d1 = pandas.DataFrame([[1,2,3]])
# d1
#    0  1  2
# 0  1  2  3

d2 = pandas.DataFrame(d1.values, columns = ['a', 'b', 'c'])
# d2
#    a  b  c
# 0  1  2  3

more on search4fan.github.io

Posted on | Edited on | In

description: change dataframe column into set and iterate

change dataframe column into a set

1
2
3
4
5
6
7
8
9
10
11
12
import pandas
a = pandas.DataFrame([[1,2],[2,3],[4,5]], columns=['a','b'])
# a
#    a  b
# 0  1  2
# 1  2  3
b = a['a'].unique()
# b
# array([1, 2, 4], dtype=int64)
b = set(b)
# b
# {1, 2, 4}

iterate dataframe column set

1
2
3
4
5
for item in b:
    print(item)
# 1
# 2
# 4

combine into a single code

1
2
3
4
5
for item in a['a'].unique():
    print(item)
# 1
# 2
# 4

more on search4fan.github.io