forked from acherm/wikipediamatrix-bench
-
Notifications
You must be signed in to change notification settings - Fork 0
/
.Rhistory
163 lines (163 loc) · 6.17 KB
/
.Rhistory
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
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
base <- read.csv2("/Users/Donatien/git/wikipediamatrix-bench/wikimatrix/Stat.csv", header = TRUE, sep=";", dec=",")
View(base)
View(base)
# Installer
install.packages("tm") # pour le text mining
install.packages("SnowballC") # pour le text stemming
install.packages("wordcloud") # générateur de word-cloud
install.packages("RColorBrewer") # Palettes de couleurs
# Charger
library("tm")
library("SnowballC")
library("wordcloud")
library("RColorBrewer")
# Lire le fichier texte
filePath <- "/Users/Donatien/Desktop/test.txt"
text <- readLines(filePath)
# Charger les données comme un corpus
docs <- Corpus(VectorSource(text))
View(docs)
View(docs)
toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
docs <- tm_map(docs, toSpace, "/")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "\\|")
# Convertir le texte en minuscule
docs <- tm_map(docs, content_transformer(tolower))
# Text stemming
# docs <- tm_map(docs, stemDocument)
dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
set.seed(1234)
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=200, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=1000, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=1000, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
barplot(d[1:10,]$freq, las = 2, names.arg = d[1:10,]$word,
col ="lightblue", main ="Most frequent words",
ylab = "Word frequencies")
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=500, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=500, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=100, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
max.words=100, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=100, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
install.packages("tm") # pour le text mining
install.packages("SnowballC") # pour le text stemming
install.packages("wordcloud") # générateur de word-cloud
install.packages("RColorBrewer") # Palettes de couleurs
# Charger
library("tm")
library("SnowballC")
library("wordcloud")
library("RColorBrewer")
# Lire le fichier texte
filePath <- "/Users/Donatien/Desktop/test.txt"
text <- readLines(filePath)
# Charger les données comme un corpus
docs <- Corpus(VectorSource(text))
toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
docs <- tm_map(docs, toSpace, "/")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "\\|")
# Convertir le texte en minuscule
docs <- tm_map(docs, content_transformer(tolower))
# Supprimer les nombres
docs <- tm_map(docs, removeNumbers)
# Supprimer les mots vides anglais
docs <- tm_map(docs, removeWords, stopwords("english"))
# Supprimer votre propre liste de mots non désirés
docs <- tm_map(docs, removeWords, c("blabla1", "blabla2"))
# Supprimer les ponctuations
docs <- tm_map(docs, removePunctuation)
# Supprimer les espaces vides supplémentaires
docs <- tm_map(docs, stripWhitespace)
# Text stemming
# docs <- tm_map(docs, stemDocument)
dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 10)
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=100, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
# Charger
library("tm")
library("SnowballC")
library("wordcloud")
library("RColorBrewer")
# Lire le fichier texte
filePath <- "/Users/Donatien/Desktop/test.txt"
text <- readLines(filePath)
# Charger les données comme un corpus
docs <- Corpus(VectorSource(text))
toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
docs <- tm_map(docs, toSpace, "/")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "\\|")
# Convertir le texte en minuscule
docs <- tm_map(docs, content_transformer(tolower))
# Supprimer les nombres
docs <- tm_map(docs, removeNumbers)
# Supprimer les mots vides anglais
docs <- tm_map(docs, removeWords, stopwords("english"))
# Supprimer votre propre liste de mots non désirés
docs <- tm_map(docs, removeWords, c("blabla1", "blabla2"))
# Supprimer les ponctuations
docs <- tm_map(docs, removePunctuation)
# Supprimer les espaces vides supplémentaires
docs <- tm_map(docs, stripWhitespace)
# Text stemming
# docs <- tm_map(docs, stemDocument)
dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 10)
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=100, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=FALSE, rot.per=0.35,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=FALSE, rot.per=0.1,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=FALSE, rot.per=1,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=FALSE, rot.per=0.4,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=TRUE, rot.per=0.4,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=TRUE, rot.per=0.4,
colors=brewer.pal(8, "Dark2"))
wordcloud(words = d$word, freq = d$freq, min.freq = 10,
max.words=250, random.order=FALSE, rot.per=0.4,
colors=brewer.pal(8, "Dark2"))
barplot(d[1:10,]$freq, las = 2, names.arg = d[1:10,]$word,
col ="lightblue", main ="Most frequent words",
ylab = "Word frequencies")
barplot(d[1:10,]$freq, las = 2, names.arg = d[1:10,]$word,
col ="lightblue", main ="Most frequent words",
ylab = "Word frequencies")