library(tidyverse)
library(rgdal)
library(rgeos)
library(sp)
library(ggmap)

sp_council <- readOGR("../../../data/gis/city_council/Council_Districts_2016.shp", verbose = FALSE)
sp_council <- spChFIDs(sp_council, as.character(sp_council$DISTRICT))

sp_divs <- readOGR("../../../data/gis/2016/2016_Ward_Divisions.shp", verbose = FALSE)
sp_divs <- spChFIDs(sp_divs, as.character(sp_divs$WARD_DIVSN))
sp_divs <- spTransform(sp_divs, CRS(proj4string(sp_council)))

load("../../../data/processed_data/df_major_2017_12_01.Rda")

ggcouncil <- fortify(sp_council) %>% mutate(council_district = id)
ggdivs <- fortify(sp_divs) %>% mutate(WARD_DIVSN = id)

races <- tribble(
  ~year, ~OFFICE, ~office_name,
  "2015", "MAYOR", "Mayor",
  "2015", "COUNCIL AT LARGE", "City Council",
  "2016", "PRESIDENT OF THE UNITED STATES", "President",
  "2017", "DISTRICT ATTORNEY", "District Attorney"
) %>% mutate(election_name = paste(year, office_name))

candidate_votes <- df_major %>% 
  filter(election == "primary" & PARTY == "DEMOCRATIC") %>%
  inner_join(races %>% select(year, OFFICE)) %>%
  mutate(WARD_DIVSN = paste0(WARD16, DIV16)) %>%
  group_by(WARD_DIVSN, OFFICE, year, election) %>%
  mutate(
    total_votes = sum(VOTES),
    pvote = VOTES / sum(VOTES)
  ) %>% 
  group_by()

turnout_df <- candidate_votes %>%
  filter(OFFICE != "COUNCIL AT LARGE") %>% 
  group_by(WARD_DIVSN, OFFICE, year, election) %>%
  summarise(total_votes = sum(VOTES)) %>%
  left_join(
    sp_divs@data %>% select(WARD_DIVSN, AREA_SFT)
  )

turnout_df$AREA_SFT <- asnum(turnout_df$AREA_SFT)

get_labpt_df <- function(sp){
  mat <- sapply(sp@polygons, slot, "labpt")
  df <- data.frame(x = mat[1,], y=mat[2,])
  return(
    cbind(sp@data, df)
  )
}

ggplot(ggcouncil, aes(x=long, y=lat)) +
  geom_polygon(
    aes(group=group),
    fill = strong_green, color = "white", size = 1
  ) +
  geom_text(
    data = get_labpt_df(sp_council),
    aes(x=x,y=y,label=DISTRICT)
  ) +
  theme_map_sixtysix() +
  coord_map() +
  ggtitle("Council Districts")

DISTRICT <- "3"
sp_district <- sp_council[row.names(sp_council) == DISTRICT,]

bbox <- sp_district@bbox
## expand the bbox 20%for mapping
bbox <- rowMeans(bbox) + 1.2 * sweep(bbox, 1, rowMeans(bbox))

basemap <- get_map(bbox, maptype="toner-lite")

district_map <- ggmap(
  basemap, 
  extent="normal", 
  base_layer=ggplot(ggcouncil, aes(x=long, y=lat, group=group)),
  maprange = FALSE
) +
  theme_map_sixtysix() +
  coord_map(xlim=bbox[1,], ylim=bbox[2,])

sp_divs$council_district <- over(
  gCentroid(sp_divs, byid = TRUE), 
  sp_council
)$DISTRICT

sp_divs$in_bbox <- sapply(
  sp_divs@polygons,
  function(p) {
    coords <- p@Polygons[[1]]@coords
    any(
      coords[,1] > bbox[1,1] &
      coords[,1] < bbox[1,2] &
      coords[,2] > bbox[2,1] &
      coords[,2] < bbox[2,2] 
    )
  }
)

ggdivs <- ggdivs %>% 
  left_join(
    sp_divs@data %>% select(WARD_DIVSN, in_bbox)
  )

district_map +
  geom_polygon(
    aes(alpha = (id == DISTRICT)),
    fill="black",
    color = "grey50",
    size=2
  ) +
  scale_alpha_manual(values = c(`TRUE` = 0.2, `FALSE` = 0), guide = FALSE) +
  ggtitle(sprintf("Council District %s", DISTRICT))

candidate_votes <- candidate_votes %>%
  left_join(sp_divs@data %>% select(WARD_DIVSN, council_district))

## Choose the top two candidates in district 3
# Except for city council, where we choose Gym and Thomas
# candidate_votes %>% 
#   group_by(OFFICE, year, CANDIDATE) %>% 
#   summarise(
#     city_votes = sum(VOTES), 
#     district_votes = sum(VOTES * (council_district == DISTRICT))
#   ) %>% 
#   arrange(desc(district_votes)) %>%
#   filter(OFFICE == "COUNCIL AT LARGE")

candidates_to_compare <- tribble(
  ~year, ~OFFICE, ~CANDIDATE, ~candidate_name, ~row,
  "2015", "COUNCIL AT LARGE", "HELEN GYM", "Helen Gym", 1,
  "2015", "COUNCIL AT LARGE", "ISAIAH THOMAS", "Isaiah Thomas", 2,
  "2015", "MAYOR", "JIM KENNEY", "Jim Kenney",  1,
  "2015", "MAYOR", "ANTHONY HARDY WILLIAMS", "Anthony Hardy Williams", 2,
  "2016", "PRESIDENT OF THE UNITED STATES", "BERNIE SANDERS", "Bernie Sanders", 1,
  "2016", "PRESIDENT OF THE UNITED STATES", "HILLARY CLINTON", "Hillary Clinton", 2,
  "2017", "DISTRICT ATTORNEY", "LAWRENCE S KRASNER", "Larry Krasner", 1,
  "2017", "DISTRICT ATTORNEY", "TARIQ KARIM EL SHABAZZ","Tariq Karim El Shabazz", 2
)

candidate_votes <- candidate_votes %>%
  left_join(races) %>%
  left_join(candidates_to_compare)

vote_adjustment <- function(pct_vote, office){
  ifelse(office == "COUNCIL AT LARGE", pct_vote * 4, pct_vote)
}

district_map +
  geom_polygon(
    data = ggdivs %>%
      filter(in_bbox) %>%
      left_join(
        candidate_votes %>% filter(!is.na(row))
      ),
    aes(fill = 100 * vote_adjustment(pvote, OFFICE))
  ) +
  scale_fill_viridis_c("Percent of Vote") +
  theme(
    legend.position =  "bottom",
    legend.direction = "horizontal",
    legend.justification = "center"
  ) +
  geom_polygon(
    fill=NA,
    color = "white",
    size=1
  ) +
  geom_label(
    data=candidates_to_compare %>% left_join(races),
    aes(label = candidate_name),
    group=NA,
    hjust=0, vjust=1,
    x=-75.258,
    y=39.985
  ) +
  facet_grid(row ~ election_name) +
  theme(strip.text.y = element_blank()) +
  ggtitle(
    sprintf("Candidate performance in District %s", DISTRICT), 
    "Percent of vote (times 4 for Council, times 1 for other offices)"
  )

# hist(turnout_df$total_votes / turnout_df$AREA_SFT)

turnout_df <- turnout_df %>%
  left_join(races)

district_map +
  geom_polygon(
    data = ggdivs %>%
      filter(in_bbox) %>%
      left_join(turnout_df, by =c("id" = "WARD_DIVSN")),
    aes(fill = pmin(total_votes / AREA_SFT, 0.0005))
  ) +
  scale_fill_viridis_c(guide = FALSE) +
  geom_polygon(
    fill=NA,
    color = "white",
    size=1
  ) +
  facet_wrap(~ election_name) +
  ggtitle(
    "Votes per mile in the Democratic Primary", 
    sprintf("Council District %s", DISTRICT)
  )

turnout_wide <- turnout_df %>%
  group_by() %>%
  mutate(
    votes_per_sf = total_votes / AREA_SFT,
    key = paste0("votes_", year)
  ) %>%
  select(WARD_DIVSN, key, votes_per_sf) %>%
  spread(key = key, value = votes_per_sf)

district_map +
  geom_polygon(
    data = ggdivs %>%
      filter(in_bbox) %>%
      left_join(turnout_wide),
    aes(
      fill = (votes_2017 - votes_2015)*5280^2
    )
  ) +
  scale_fill_gradient2(
    "Change in votes per mile\n  2015 - 2017",
    low=strong_orange,
    mid="white",
    high=strong_purple,
    midpoint=0
  ) +
  geom_polygon(
    fill=NA,
    color = "black",
    size=1
  )  +
  theme(legend.position = "bottom", legend.direction = "horizontal") +
  ggtitle(
    sprintf("Change in votes per mile, District %s", DISTRICT),
    "Orange: More votes in 2015, Purple: More in 2017"
  )

district_categories <- candidate_votes %>% 
    filter(
      council_district == DISTRICT & 
        candidate_name %in% c("Larry Krasner", "Bernie Sanders")
    ) %>%
    group_by(WARD_DIVSN) %>%
    mutate(votes_2016 = total_votes[year == 2016]) %>%
    select(WARD_DIVSN, votes_2016, candidate_name, pvote) %>%
    spread(key=candidate_name, value=pvote)

ggplot(
  district_categories,
  aes(x = 100 * `Bernie Sanders`, y = 100 * `Larry Krasner`)
) +
  geom_point(aes(size = votes_2016), alpha = 0.7) +
  scale_size_area("Total Votes in 2016")+
  theme_sixtysix() +
  xlab("Percent of Vote for Bernie Sanders") +
  ylab("Percent of Vote for Larry Krasner") +
  coord_fixed() + 
  geom_abline(slope = -1, intercept =  100) +
  annotate(
    geom = "text",
    x = c(35, 20),
    y = c(15, 87),
    hjust = 0,
    label = c("West & Southwest", "University City"),
    color = c(strong_green, strong_purple),
    fontface="bold"
  ) +
  ggtitle("Divisions' vote", sprintf("District %s Democratic Primary", DISTRICT))

district_categories$category <- with(
  district_categories,
  (`Bernie Sanders` + `Larry Krasner`) > 1.0
)
district_categories$cat_name <- ifelse(
  district_categories$category,
  "University City",
  "West & Southwest"
)

district_map + 
  geom_polygon(
    data = ggdivs %>% 
      left_join(district_categories) %>% 
      filter(!is.na(cat_name)),
    aes(fill = cat_name)
  ) +
  scale_fill_manual(
    "",
    values = c("University City" = strong_purple, "West & Southwest" = strong_green)
  ) +
  ggtitle(sprintf("District %s neighborhood divisions", DISTRICT))

neighborhood_summary <- candidate_votes %>% 
  inner_join(candidates_to_compare) %>%
  group_by(candidate_name, election_name) %>%
  mutate(
    citywide_votes = sum(VOTES),
    citywide_pvote = 100 * sum(VOTES) / sum(total_votes)
  ) %>%
  filter(council_district == DISTRICT) %>%
  left_join(district_categories) %>%
  group_by(candidate_name, citywide_votes, citywide_pvote, election_name, cat_name) %>%
  summarise(
    votes = sum(VOTES),
    pvote = 100 * sum(VOTES) / sum(total_votes),
    total_votes = sum(total_votes)
  ) %>%
  group_by(candidate_name, election_name) %>%
  mutate(
    district_votes = sum(votes),
    district_pvote = 100 * sum(votes) / sum(total_votes)
  ) %>% select(
    election_name, candidate_name, citywide_pvote, district_pvote, cat_name, pvote, total_votes
  ) %>%
  gather(key="key", value="value", pvote, total_votes) %>%
  unite("key", cat_name, key) %>%
  spread(key, value)


neighborhood_summary %>%
  knitr::kable(
    digits=0, 
    format.args=list(big.mark=','),
    col.names=c("Election", "Candidate", "Citywide %", sprintf("District %s %%", DISTRICT), "University City %", "University City Turnout", "West & Southwest %", "West & Southwest Turnout")
  )

get_line <- function(x_total_votes, y_total_votes){
  ## solve p_x t_x+ p_y t_y > 50
  tot <- x_total_votes + y_total_votes
  tx <- x_total_votes / tot
  ty <- y_total_votes / tot

  slope <- -tx / ty
  intercept <- 50 / ty  # use 50 since proportions are x100
  c(intercept, slope)
}

line_2017 <- with(
  neighborhood_summary,
  get_line(
    `University City_total_votes`[candidate_name == "Larry Krasner"],
    `West & Southwest_total_votes`[candidate_name == "Larry Krasner"]
  )
)

## get the two-candidate vote
neighborhood_summary <- neighborhood_summary %>%
  group_by(election_name)  %>% 
  mutate(
    ucity_pvote_2cand = `University City_pvote` / sum(`University City_pvote`),
    wsw_pvote_2cand = `West & Southwest_pvote`/sum(`West & Southwest_pvote`)
  )

line_2015 <- with(
  neighborhood_summary,
  get_line(
    `University City_total_votes`[candidate_name == "Jim Kenney"],
    `West & Southwest_total_votes`[candidate_name == "Jim Kenney"]
  )
)

library(ggrepel)

ggplot(
  neighborhood_summary,
  aes(
    x=100*ucity_pvote_2cand,
    y=100*wsw_pvote_2cand
  )
) +
  geom_point() +
  geom_text_repel(aes(label=candidate_name)) +
  geom_abline(
    intercept = c(line_2015[1], line_2017[1]),
    slope = c(line_2015[2], line_2017[2]),
    linetype="dashed"
  ) +
  coord_fixed() + 
  scale_x_continuous(
    "University City percent of vote",
    breaks = seq(0,100,10)
  ) +
  scale_y_continuous(
    "West & Southwest percent of vote",
    breaks = seq(0, 100, 10)
  ) +
  annotate(
    geom="text",
    label=paste(c(2015, 2017), "turnout"),
    x=c(10, 8),
    y=c(
      line_2015[1] + 10 * line_2015[2],
      line_2017[1] + 8 * line_2017[2]
    ),
    hjust=0,
    vjust=-0.2,
    angle = atan(c(line_2015[2], line_2017[2])) / pi * 180,
    color="grey40"
  )+
  annotate(
    geom="text",
    x = 70,
    y=75,
    label="Candidate wins",
    fontface="bold",
    color = strong_green
  ) +
  geom_hline(yintercept = 50, color="grey50") +
  geom_vline(xintercept = 50, color="grey50")+
  expand_limits(x=100, y=80)+
  theme_sixtysix() +
  ggtitle(
    "The relative strength of W & SW Philly and U City",
    "Candidates to the top-right of the lines win."
  )