solve most of predefined challenges

vignettes/funwithdata.Rmd

@@ -48,8 +48,8 @@ talks <- res$talks
 ## Analysis
 
 Now we can start analysing our parsed dataset, e.g. find out which party gives the most talks:
-```{r, fig.width=10}
-join_redner(reden, res) %>%
+```{r, fig.width=8}
+join_redner(res$reden, res) %>%
     group_by(fraktion) %>%
     summarize(n = n()) %>%
     arrange(n) %>%
@@ -58,7 +58,7 @@ join_redner(reden, res) %>%
 
 ### Count a word occurence
 
-```{r, fig.width=10}
+```{r, fig.width=8}
 find_word(res, "hitler") %>%
     filter(occurences > 0) %>%
     join_redner(res) %>%
@@ -68,3 +68,74 @@ find_word(res, "hitler") %>%
     arrange(desc(n)) %>%
     bar_plot_fraktionen()
 ```
+
+### Who gives the most speeches?
+
+```{r}
+res$reden %>%
+    group_by(redner) %>%
+    summarize(n = n()) %>%
+    arrange(-n) %>%
+    left_join(res$redner, by=c("redner" = "id")) %>%
+    head(10)
+```
+
+### Who talks the longest?
+
+```{r}
+res$talks %>%
+    mutate(content_len = str_length(content)) %>%
+    group_by(redner) %>%
+    summarize(avg_content_len = mean(content_len)) %>%
+    arrange(-avg_content_len) %>%
+    left_join(res$redner, by=c("redner" = "id")) %>%
+    head(10)
+```
+
+### Which party gives the most applause to which parties?
+
+```{r}
+res$applause %>%
+    left_join(res$redner, by=c("on_redner" = "id")) %>%
+    select(on_fraktion = fraktion, where(is.logical)) %>%
+    group_by(on_fraktion) %>%
+    arrange(on_fraktion) %>%
+    summarize("AfD" = sum(`AfD`),
+              "BÜNDNIS 90 / DIE GRÜNEN" = sum(`BÜNDNIS_90_DIE_GRÜNEN`),
+              "CDU/CSU" = sum(`CDU_CSU`),
+              "DIE LINKE" = sum(`DIE_LINKE`),
+              "FDP" = sum(`FDP`),
+              "SPD" = sum(`SPD`))
+```
+
+### Which party comments the most on which parties?
+
+```{r}
+res$comments %>%
+    left_join(res$redner, by=c("on_redner" = "id")) %>%
+    select(by_fraktion = fraktion.x, on_fraktion = fraktion.y) %>%
+    group_by(on_fraktion) %>%
+    summarize(`AfD` = sum(str_detect(by_fraktion, "AfD"), na.rm=T),
+              `BÜNDNIS 90 / DIE GRÜNEN` = sum(str_detect(by_fraktion, "BÜNDNIS 90/DIE GRÜNEN"), na.rm=T),
+              `CDU/CSU` = sum(str_detect(by_fraktion, "CDU/CSU"), na.rm = T),
+              `DIE LINKE` = sum(str_detect(by_fraktion, "DIE LINKE"), na.rm=T),
+              `FDP` = sum(str_detect(by_fraktion, "FDP"), na.rm=T),
+              `SPD` = sum(str_detect(by_fraktion, "SPD"), na.rm=T))
+```
+
+### When are which topics discussed the most?
+
+```{r, fig.width=8}
+pandemic_pattern <- "(?i)virus|corona|covid|lockdown"
+climate_pattern <- "(?i)klimawandel|erderwärmung|co2|treibhaus|methan|kyoto-protokoll|klimaabkommen"
+pension_pattern <- "(?i)rente|pension|altersarmut"
+
+word_usage_by_date(res, c(pandemic = pandemic_pattern,
+                          climate = climate_pattern,
+                          pension = pension_pattern)) %>%
+    ggplot(aes(x = date, y = count, color = pattern)) +
+    xlab("date of session") +
+    ylab("occurence of word per session") +
+    labs(color = "Topic") +
+    geom_point()
+```