Paquetes
library(pacman)
p_load("dplyr", "stringr", "ggplot2", "wordcloud","rmdformats","vembedr", "xfun")Video de youtube de la charla
embed_url("https://www.youtube.com/watch?v=gGd5_DKqcCU")Funciones
FreqCategory <- function(value) {
strCategory <- ifelse(value <=5, " 5",
ifelse(value <=10, " 10",
ifelse(value <=20, " 20",
ifelse(value <=50, " 50",
ifelse(value <=100, " 100",
ifelse(value <=500, " 500",
ifelse(value <=1000, " 1,000",
">1,000")))))))
strCategory
}Datos del texto
setwd("~/ea9am")
video <- readLines("video.txt")
head(video)## [1] "[Música]" "" "[Música]" "" "[Música]" ""Conteo de lineas
# Longitud de vector
intLineCount <- length(video)
intLineCount## [1] 2606Palabras por linea
lstUNPrfLines <- str_split(video," ")
# palabras por linea
vciUNPrfWperL <- unlist(lapply(lstUNPrfLines, length))
# imprimir media de palabras por linea
mean(vciUNPrfWperL)## [1] 3.527629Conteo de palabras
# deslistar para obtener un vector de palabras
vcsUNPrfWords <- unlist(lstUNPrfLines)
# recuento total de palabras = longitud del vector
intWordCount <- length(vcsUNPrfWords)
# imprimir
intWordCount## [1] 9193Mostrar palabras
head(vcsUNPrfWords,100)## [1] "[Música]" "" "[Música]" "" "[Música]"
## [6] "" "[Música]" "" "a" ""
## [11] "[Música]" "" "[Música]" "" "y"
## [16] "" "y" "" "[Música]" ""
## [21] "ah" "" "[Música]" "" "[Música]"
## [26] "" "[Música]" "" "[Música]" ""
## [31] "[Música]" "" "[Música]" "" "ah"
## [36] "" "hola" "que" "tal" ""
## [41] "bienvenidos" "al" "tercer" "y" "último"
## [46] "dÃa" "de" "" "monterrey" "este"
## [51] "es" "un" "dÃa" "muy" "especial"
## [56] "" "porque" "por" "primera" "ocasión"
## [61] "se" "introduce" "" "un" "tema"
## [66] "que" "es" "muy" "importante" "para"
## [71] "todos" "" "no" "sólo" "para"
## [76] "la" "comunidad" "emprendedora" "y" ""
## [81] "relacionada" "con" "temas" "de" "innovación"
## [86] "sino" "" "también" "con" "la"
## [91] "ciudad" "con" "las" "" "comunidades"
## [96] "y" "con" "el" "planeta" "que"Limpieza de palabras
# lower case
vcsUNPrfWords <- str_to_lower(vcsUNPrfWords)
# remove numbers
vcsUNPrfWords <- str_replace_all(vcsUNPrfWords, pattern="[[:digit:]]", "")
# remove punctuation
vcsUNPrfWords <- str_replace_all(vcsUNPrfWords, pattern="[[:punct:]]", "")
# remove white spaces
vcsUNPrfWords <- str_replace_all(vcsUNPrfWords, pattern="[[:space:]]", "")
# remove special chars
vcsUNPrfWords <- str_replace_all(vcsUNPrfWords, pattern="[~@#$%&-_=<>]", "")
# remove empty vectors
vcsUNPrfWords <- vcsUNPrfWords[vcsUNPrfWords != ""]
# hack & remove $
vcsUNPrfWords <- str_replace_all(vcsUNPrfWords, pattern="$", "")
# head
head(vcsUNPrfWords,100)## [1] "mãºsica" "mãºsica" "mãºsica" "mãºsica"
## [5] "a" "mãºsica" "mãºsica" "y"
## [9] "y" "mãºsica" "ah" "mãºsica"
## [13] "mãºsica" "mãºsica" "mãºsica" "mãºsica"
## [17] "mãºsica" "ah" "hola" "que"
## [21] "tal" "bienvenidos" "al" "tercer"
## [25] "y" "ãºltimo" "dãa" "de"
## [29] "monterrey" "este" "es" "un"
## [33] "dãa" "muy" "especial" "porque"
## [37] "por" "primera" "ocasiã³n" "se"
## [41] "introduce" "un" "tema" "que"
## [45] "es" "muy" "importante" "para"
## [49] "todos" "no" "sã³lo" "para"
## [53] "la" "comunidad" "emprendedora" "y"
## [57] "relacionada" "con" "temas" "de"
## [61] "innovaciã³n" "sino" "tambiã©n" "con"
## [65] "la" "ciudad" "con" "las"
## [69] "comunidades" "y" "con" "el"
## [73] "planeta" "que" "el" "dãa"
## [77] "de" "hoy" "vamos" "a"
## [81] "ver" "el" "tema" "de"
## [85] "live" "human" "being" "que"
## [89] "tiene" "que" "ver" "con"
## [93] "los" "temas" "de" "sostenibilidad"
## [97] "que" "son" "muy" "importantes"Data frame de palabras normales
# make data frame
dfrUNPrfWords <- data.frame(vcsUNPrfWords)
colnames(dfrUNPrfWords) <- c("Words")
dfrUNPrfWords$Words <- as.character(dfrUNPrfWords$Words)
# normal word count
head(dfrUNPrfWords,10)## Words
## 1 mãºsica
## 2 mãºsica
## 3 mãºsica
## 4 mãºsica
## 5 a
## 6 mãºsica
## 7 mãºsica
## 8 y
## 9 y
## 10 mãºsicaConteo de palabras “normales”
# resumiendo los datos
dfrUNPrfFreq <- dfrUNPrfWords %>%
group_by(Words) %>%
summarise(Freq=n()) %>%
arrange(desc(Freq))
head(dfrUNPrfFreq)## # A tibble: 6 x 2
## Words Freq
## <chr> <int>
## 1 de 477
## 2 que 379
## 3 la 275
## 4 y 245
## 5 en 211
## 6 el 170Nube de palabras normales
wordcloud(dfrUNPrfFreq$Words[1:100], dfrUNPrfFreq$Freq[1:100], random.order=F, max.words=100, colors=brewer.pal(8, "Dark2"))
Data frame de palabras realmente significantes
En esta sección se quitan las “stop words”
# significant words only
# remove all words with len <= 2
dfrUNPrfWords <- filter(dfrUNPrfWords, str_length(Words)>2)
# remover las "stop words" o palabras comunes como conjunciones
vcsCmnWords <- c("de","que","en","y","la","a","el","es","una","un","pues","no","para","los","se","las","como","con","más","por","lo","hay","del","o","entonces","este","está","nos","pero","también","creo","porque","también","yo","ya","esta","si","me","al","son","tiene","donde","bueno","ha","sobre","ejemplo","bien","gracias","ser","eso","todo","uso","ver","tener","esto","estos","muchas","cómo","cuando","sea","tenemos","su","tienen","así","desde","han","parte","ahí","les","tal","qué","estar")
dfrUNPrfWords <- filter(dfrUNPrfWords, !(Words %in% vcsCmnWords))
# remover las palabras no significativas para este contexto
vcsBadWords <- c("decir","muy","están")
dfrUNPrfWords <- filter(dfrUNPrfWords, !(Words %in% vcsBadWords))
# show
head(dfrUNPrfWords)## Words
## 1 mãºsica
## 2 mãºsica
## 3 mãºsica
## 4 mãºsica
## 5 mãºsica
## 6 mãºsicaConteo de palabras significativas
dfrUNPrfFreq <- dfrUNPrfWords %>%
group_by(Words) %>%
summarise(Freq=n()) %>%
arrange(desc(Freq))
head(dfrUNPrfFreq)## # A tibble: 6 x 2
## Words Freq
## <chr> <int>
## 1 tambiã©n 67
## 2 inteligencia 49
## 3 artificial 45
## 4 caso 35
## 5 estamos 33
## 6 todos 29“Cola” de palabras significativas
tail(dfrUNPrfFreq)## # A tibble: 6 x 2
## Words Freq
## <chr> <int>
## 1 vincula 1
## 2 visualizaciã³n 1
## 3 viviendo 1
## 4 vuelve 1
## 5 word 1
## 6 zona 1Eliminar palabras dispersas
# palabras con una frecuencia absoluta menor a 5
dfrUNPrfFreq <- filter(dfrUNPrfFreq, Freq>5)
tail(dfrUNPrfFreq)## # A tibble: 6 x 2
## Words Freq
## <chr> <int>
## 1 primero 6
## 2 rol 6
## 3 sã³lo 6
## 4 sistema 6
## 5 teniendo 6
## 6 vida 6Conteo final de palabras
# total word count = length of vector
intWordCountFinal <- length(dfrUNPrfFreq$Words)
# print
intWordCountFinal## [1] 152Categorización por frecuencias
# add FrequencyCategory colum
dfrUNPrfFreq <- mutate(dfrUNPrfFreq, Fcat=FreqCategory(dfrUNPrfFreq$Freq))
# new data frame for Frequency Of Categorized Frequencies ...
dfrUNPrfFocf <- dfrUNPrfFreq %>% group_by(Fcat) %>% summarise(Rfrq=n())
#
dfrUNPrfFocf$Fcat <- factor(dfrUNPrfFocf$Fcat, levels=dfrUNPrfFocf$Fcat, ordered=T)
# head
head(dfrUNPrfFocf,10)## # A tibble: 4 x 2
## Fcat Rfrq
## <ord> <int>
## 1 " 10" 95
## 2 " 20" 44
## 3 " 50" 12
## 4 " 100" 1Nueva nube de palabras
wordcloud(dfrUNPrfFreq$Words[1:50], dfrUNPrfFreq$Freq[1:50], random.order=F, max.words=100, colors=brewer.pal(8, "Dark2"))
Gráfica de barras de palabras
ggplot(slice(dfrUNPrfFreq,1:30), aes(x=reorder(Words,-Freq),y=Freq)) +
geom_bar(stat="identity", fill=rainbow(30)) +
ylab("Frequency") +
xlab("Words") +
ggtitle("Primeras 30 palabras con mayor frecuencia") +
theme(plot.title=element_text(size=rel(1.5), colour="blue")) +
coord_flip()
Gráfica de frecuencia
ggplot(dfrUNPrfFocf, aes(Fcat,Rfrq))+
geom_bar(stat="identity", width=0.8, fill=rainbow(length(dfrUNPrfFocf$Fcat))) +
xlab("Words With Frequency Less Than") + ylab("Frequency") +
theme(axis.text.x=element_text(angle=60, hjust=1, vjust=1),axis.text.y=element_text(angle=60, hjust=1, vjust=1),plot.title=element_text(size=rel(1.5), colour="blue")) +
ggtitle("Frequency Of Word Count")
Longitud de palabras
dfrUNPrfChrs <- data.frame(Chars=nchar(dfrUNPrfFreq$Words))
#intRowCount <- nrow(table(dfrUNPrfChrs))
ggplot(dfrUNPrfChrs, aes(x=Chars)) +
geom_histogram(binwidth=1, fill='blue') +
geom_vline(xintercept=mean(nchar(dfrUNPrfFreq$Words)), color='black', size=1.5, alpha=.5) +
xlab("Word Length (Chars)") + ylab("Number Of Words (Frequency)")