library(ggdist)

summarize.estimator <- function(sims.df, suffix='naive', coefname='x'){

    reported_vars <- c(
                       'Bxy',
                       paste0('B',coefname,'y.est.',suffix),
                       paste0('B',coefname,'y.ci.lower.',suffix),
                       paste0('B',coefname,'y.ci.upper.',suffix)
                       )

    
    grouping_vars <- c('N','m','B0', 'Bxy', 'Bzy', 'Bzx', 'Px', 'Py','y_explained_variance', 'prediction_accuracy','outcome_formula','proxy_formula','truth_formula','z_bias','y_bias')

    grouping_vars <- grouping_vars[grouping_vars %in% names(df)]

    part <- sims.df[,
                    unique(c(reported_vars,
                             grouping_vars)),
                    with=FALSE]


    true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
    zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
    bias <- part[[paste0('B',coefname,'y')]] - part[[paste0('B',coefname,'y.est.',suffix)]]
    sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))

    part <- part[,':='(true.in.ci = true.in.ci,
                       zero.in.ci = zero.in.ci,
                       bias=bias,
                       sign.correct =sign.correct)]


    part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
                          mean.bias = mean(bias),
                          mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]],na.rm=T),
                          var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]],na.rm=T),
                          est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.975,na.rm=T),
                          est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.025,na.rm=T),
                          mean.ci.upper = mean(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],na.rm=T),
                          mean.ci.lower = mean(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],na.rm=T),
                          median.ci.upper = median(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],na.rm=T),
                          median.ci.lower = median(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],na.rm=T),
                          ci.upper.975 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.975,na.rm=T),
                          ci.upper.025 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.025,na.rm=T),
                          ci.lower.975 = quantile(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],0.975,na.rm=T),
                          ci.lower.025 = quantile(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],0.025,na.rm=T),
                          N.ci.is.NA = sum(is.na(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]])),
                          N.sims = .N,
                          p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
                          variable=coefname,
                          method=suffix
                          ),
                      by=grouping_vars,
                      ]
    
    return(part.plot)
}