analiza todo abril

html-parser.R

@@ -12,13 +12,22 @@ library(tidyverse) # for ggplot
 # Set search variables: words and datelimits -----
 # word <- "Cifuentes|Javier Ramos|Enrique Álvarez Conde|Pablo Chico|María Teresa Feito|Alicia López de los Cobos|Cecilia Rosado|Clara Souto|Amalia Calonge|Universidad Rey Juan Carlos"
 # word <- "vox|Vox|VOX|Santiago Abascal|ortega smith|francisco serrano"
+# partidos y líderes
 word1 <- "vox|Vox|VOX|Santiago Abascal|Abascal"
 word2 <- "Podemos|Pablo Iglesias|Iglesias"
 word3 <- "PP|Pablo Casado|Casado"
 word4 <- "PSOE|Pedro Sánchez|Sánchez"
-word5 <- "C's|Ciudadanos|Albert Rivera|Rivera"
+word5 <- "C's|Cs|Ciudadanos|Albert Rivera|Rivera"
 word6 <- "PACMA|Silvia Barquero|Barquero"
 
+# partidos y líderes
+word1 <- "vox|Vox"
+word2 <- "vox|Vox|VOX"
+word3 <- "vox|Vox|VOX|Abascal"
+word4 <- "vox|Vox|VOX|Santiago Abascal|Abascal"
+word5 <- "vox|Vox|VOX|Santiago Abascal|Abascal|Ortega Smith"
+word6 <- "vox|Vox|VOX|Santiago Abascal|Abascal|Ortega Smith|Rocio Monasterio|Monasterio"
+
 word  <- ""
 word <- data.frame(matrix(ncol = 1,nrow = 6 ))
 names(word)  <- c("word")
@@ -30,7 +39,7 @@ word$word[4] <- word4
 word$word[5] <- word5
 word$word[6] <- word6
 
-# Select word to be displayed in plots
+# # Select word to be displayed in plots
 word1_explain <- "VOX" #
 word2_explain <- "Podemos" #
 word3_explain <- "PP" #
@@ -38,6 +47,14 @@ word4_explain <- "PSOE" #
 word5_explain <- "Cs" #
 word6_explain <- "PACMA" #
 
+# # Select word to be displayed in plots
+word1_explain <- "VOXmin" #
+word2_explain <- "VOXmay" #
+word3_explain <- "VOXabascal" #
+word4_explain <- "VOXsantiagoabascal" #
+word5_explain <- "VOXortega" #
+word6_explain <- "VOXmonasterio" #
+
 word$explain[1] <- word1_explain
 word$explain[2] <- word2_explain
 word$explain[3] <- word3_explain
@@ -46,7 +63,7 @@ word$explain[5] <- word5_explain
 word$explain[6] <- word6_explain
 
 # Set time limits
-my_limit <- c(as.POSIXct("2019-04-12 00:00:01"), as.POSIXct("2019-04-24 00:00:01"))
+my_limit <- c(as.POSIXct("2019-04-01 00:00:01"), as.POSIXct("2019-04-26 00:12:01"))
 my_init <- as.POSIXlt("2019-04-12 00:00:00")
 
 # open compressed file
@@ -97,7 +114,7 @@ ggplot(list[list$newspaper == "larazon", ]) +
 selected <- list[(list$newspaper == "eldiario" | list$newspaper == "elconfidencial" | 
                     list$newspaper == "elpais"| list$newspaper == "larazon" | list$newspaper == "elespanol") &
                    # list$date > "2018-10-01", ]
-                   list$date > "2019-04-11", ]
+                   list$date > "2019-03-31", ]
 
 # Create results dataframe
 results <- ""
@@ -182,7 +199,6 @@ for (i in 1:nrow(selected)) {
 
 results <- results %>% select(-a,-b,-c,-d,-e,-f,-aa,-bb,-cc,-dd,-ee,-ff,-aaa,-bbb,-ccc,-ddd,-eee,-fff)
 
-
 # results5 <- ""
 # results5 <- data.frame(matrix(ncol = 1,nrow = 5  ))
 # names(results5)  <- c("newspaper")
@@ -198,7 +214,8 @@ results$date <- as.POSIXct( paste(results$year,"-",results$month,"-",results$day
 
 # Save results 
 # save(results,file="data/results-vox-01.Rda")
-save(results,file="data/results-vox'podemos-generales2019-b-6-partidos.Rda")
+save(results,file="data/results-generales2019-6-partidos-1-25abril.Rda")
+# save(results,file="data/results-vox-diferencias-busqueda.Rda")
 # Load other results
 # load("data/results-cifuentes-01.Rda")
 
@@ -513,15 +530,15 @@ ggplot(data=results_long_n[results_long_n$newspaper=="eldiario",]) + #ylim(c(0,3
        caption = "")
 
 # para todos los periodicos -------
-ggplot(data=results_long_per) + 
+ggplot(data=results_long_per) + #%>% filter(key== "n_selected_news_3_VOXabscal" | key== "n_selected_news_2_VOXmay") ) + 
   geom_line(aes(x=date, y=value, color=key),size=0.1) +
-  geom_smooth(aes(x=date, y=value, color=key),size=1,se = FALSE) + #,span=0.3
-  scale_x_datetime(date_breaks = "1 day", date_labels = "%d", 
+  geom_smooth(aes(x=date, y=value, color=key),size=1,se = FALSE,span=0.6) + #,span=0.3
+  scale_x_datetime(date_breaks = "2 day", date_labels = "%d", 
                    limits = my_limit) +
   theme_minimal(base_family = "Roboto Condensed", base_size = 14) +
   scale_color_manual(values=paltidos) +
-  labs(title = paste("Porcentaje de noticias en página de inicio"),
-       subtitle = "12 abril - 24 abril 2019",
+  labs(title = paste("% de noticias en página de inicio"),
+       subtitle = "1 abril - 24 abril 2019",
        x = NULL,
        y = NULL,
        caption = "Datos: HomePageX. numeroteca.org") +
@@ -537,15 +554,15 @@ ggplot(data=results_long_per) +
 
 
 # para todos los partidos -------
-ggplot(data=results_long_n) + 
+ggplot(data=results_long_per) + 
   geom_line(aes(x=date, y=value, color=newspaper),size=0.2) +
   geom_smooth(aes(x=date, y=value, color=newspaper),size=1.3,se = FALSE) + #,span=0.3
-  scale_x_datetime(date_breaks = "1 day", date_labels = "%d", 
+  scale_x_datetime(date_breaks = "2 day", date_labels = "%d", 
                    limits = my_limit) +
   theme_minimal(base_family = "Roboto Condensed", base_size = 14) +
   scale_colour_brewer(palette = "Set2") +
-  labs(title = paste("Número de noticias en página de inicio"),
-       subtitle = "12 abril - 24 abril 2019",
+  labs(title = paste("% de noticias en página de inicio"),
+       subtitle = "1 abril - 24 abril 2019",
        x = NULL,
        y = NULL,
        caption = "Datos: HomePageX. numeroteca.org") +
@@ -559,7 +576,9 @@ ggplot(data=results_long_n) +
   ) +
   facet_wrap(~key)
 
-
+# medias per day
+results_long_n %>% 
+  groups_by(date)
 
 
 # --------  Analysis and comparision with Pageonex.com paper front pages data ---------