library(tidyverse)
CROPS <- rbind(read_csv("Data/Crop_Choice/IRRIG_2002.csv"),read_csv("Data/Crop_Choice/IRRIG_2005.csv"))
DITCH_PARCEL <- CROPS[,c(4,11:19)] %>% pivot_longer(-PARCEL_ID,values_to="ditch") %>% filter(!is.na(ditch)) %>% select(-name)
WELL_PARCEL <- 	CROPS[,c(4,seq(21,80,by=3))] %>% pivot_longer(-PARCEL_ID,values_to="wdid") %>% filter(!is.na(wdid)) %>% select(-name)
WELL_DITCHES <- WELL_PARCEL %>% left_join(DITCH_PARCEL)  %>% mutate(ditch=as.character(ditch))
NAMED_DITCHES <- (WELL_DITCHES  %>% filter(!is.na(ditch))   %>% group_by(ditch)  %>% summarize(size=n()) %>% arrange(desc(size)) )[1:10,] %>% pull(ditch)
WELL_DITCHES[!(WELL_DITCHES$ditch  %in% NAMED_DITCHES) & !is.na(WELL_DITCHES$ditch) ,3] <- "Other"
WELL_DITCHES <- WELL_DITCHES[-which(duplicated(WELL_DITCHES)),]
WELL_DITCHES <- WELL_DITCHES  %>% filter(!is.na(ditch),!is.na(wdid)) 
WELL_DITCHES$ROW_NUM <- 1:nrow(WELL_DITCHES)
WELL_DITCHES <- WELL_DITCHES %>% select(-PARCEL_ID) %>% unique %>% pivot_wider(values_from=ditch,names_from=ditch,names_prefix="ditch_")
WELL_DITCHES[,-1:-2][!is.na(WELL_DITCHES[,-1:-2])] <- '1'
WELL_DITCHES[,-1:-2][is.na(WELL_DITCHES[,-1:-2])] <- '0'
WELL_DITCHES <-  WELL_DITCHES %>% mutate_if(is.character,as.numeric) %>% select(-ROW_NUM)  %>% unique
WELL_DITCHES <- WELL_DITCHES   %>% group_by(wdid) %>%   mutate(across(colnames(WELL_DITCHES)[2:12], max, na.rm = TRUE)) %>% ungroup  %>% unique
dir.create("Data/Output_Data",showWarnings=FALSE)
write_csv(WELL_DITCHES,"Data/Output_Data/Ditch_Indicators.csv")
###########Determine what percentage of land supplied by a well goes to each crop, across 2002 and 2005 
CROP <- CROPS %>% select(CAL_YEAR,PARCEL_ID,ACRES,CROP_TYPE)
CROP$CROP_TYPE <- ifelse(CROP$CROP_TYPE=='WHEAT_FALL','SMALL_GRAINS',CROP$CROP_TYPE)
CROP$CROP_TYPE <- ifelse(CROP$CROP_TYPE=='NEW_ALFALFA','ALFALFA',CROP$CROP_TYPE)
CROP$CROP_TYPE <- ifelse(CROP$CROP_TYPE %in% c('COVER_CROP','VEGETABLES'),'OTHER',CROP$CROP_TYPE)

CROP_2002 <- WELL_PARCEL %>% left_join(CROP %>% filter(CAL_YEAR==2002))%>% filter(!is.na(CROP_TYPE)) %>% unique 
CROP_2005 <- WELL_PARCEL %>% left_join(CROP %>% filter(CAL_YEAR==2005))%>% filter(!is.na(CROP_TYPE)) %>% unique 

CROP_2002 <- CROP_2002 %>% group_by(wdid,CROP_TYPE,CAL_YEAR) %>% summarize(ACRES=sum(ACRES)) %>% group_by(wdid,CAL_YEAR) %>% mutate(PERCENT=ACRES/sum(ACRES))  %>% arrange(wdid) %>% ungroup %>% select(-ACRES) %>% pivot_wider(values_from=PERCENT,names_from=CROP_TYPE,names_prefix="PER_") %>% replace(is.na(.), 0)
CROP_2005 <- CROP_2005 %>% group_by(wdid,CROP_TYPE,CAL_YEAR) %>% summarize(ACRES=sum(ACRES)) %>% group_by(wdid,CAL_YEAR) %>% mutate(PERCENT=ACRES/sum(ACRES))  %>% arrange(wdid) %>% ungroup %>% select(-ACRES) %>% pivot_wider(values_from=PERCENT,names_from=CROP_TYPE,names_prefix="PER_") %>% replace(is.na(.), 0)
PRE_2009_CROPS <- full_join(CROP_2002 %>% select(-CAL_YEAR) ,CROP_2005 %>% select(-CAL_YEAR)) %>% group_by(wdid) %>% summarize(across(colnames(CROP_2002)[3:7], mean, na.rm = TRUE))
PRE_2009_CROPS <- PRE_2009_CROPS  %>% clean_names()
write_csv(PRE_2009_CROPS ,"Data/Output_Data/Crops_Before_2009.csv")