Clean up: replace code dump with proper system prompt for chat

R/sir_model.R

@@ -530,462 +530,3 @@ sir_three_group_pu <- function(## parameters related to popn
   
 }
 
-function_in_string <- "You are in expert in these functions being run in a shiny app:
-
-avg_contact_matrix_3gp <- function(dbar_a, dbar_b, dbar_c,
-                                   N_a, N_b, N_c,
-                                   beta_a, beta_b) {
-  #h_a, h_b) {
-  
-  # fraction of total degree in group a and group b 
-  m_a <- (N_a * dbar_a) / ((N_a * dbar_a) + (N_b * dbar_b) + (N_c * dbar_c))
-  m_b <- (N_b * dbar_b) / ((N_a * dbar_a) + (N_b * dbar_b) + (N_c * dbar_c))
-  m_c <- (N_c * dbar_c) / ((N_a * dbar_a) + (N_b * dbar_b) + (N_c * dbar_c))
-  
-  q_aa <- m_a^(1/beta_a) 
-  q_bb <- m_b^(1/beta_b) 
-  
-  #q_aa <- h_a
-  #q_bb <- h_b
-  
-  
-  ## for a's contacts w/ other groups, assume they are distributed
-  ## in proportion to the other groups' share of edges
-
-  q_ab <- (1-q_aa) * (m_b / (m_b + m_c)) 
-  q_ac <- (1-q_aa) * (m_c / (m_b + m_c)) 
-  
-  # implied by q_ab and q_ac
-  q_ba <- q_ab*(dbar_a*N_a)/(N_b*dbar_b)
-  # and then q_bc has to make them add up to 1
-  q_bc <- (1 - (q_ba + q_bb))
-  
-  q_ca <- q_ac*dbar_a*N_a/(N_c*dbar_c)
-  
-  q_cb <- q_bc * (dbar_b*N_b)/(dbar_c*N_c)
-  
-  # q_cc is residual
-  q_cc <- 1 - (q_ca + q_cb)
-  
-  # implied beta_c
-  beta_c_implied <- log(m_c) / log(q_bb)
-  
-  # q matrix
-  q_beta <- t(matrix(c(q_aa, q_ab, q_ac, 
-                       q_ba, q_bb, q_bc,
-                       q_ca, q_cb, q_cc),
-                     nrow=3)) 
-  ## this matrix has the avg number of contacts between groups
-
-  c_mat <- q_beta
-  c_mat[1,] <- c_mat[1,] * dbar_a 
-  c_mat[2,] <- c_mat[2,] * dbar_b
-  c_mat[3,] <- c_mat[3,] * dbar_c
-  
-  return(c_mat)
-  
-}
-
-
-sir_three_group_pu <- function(## parameters related to popn
-  N0 = 10000000, # population size
-  frac_a = 0.33, # fraction of population in group A
-  frac_b = 0.33, # fraction of population in group B
-  ## parameters related to contacts
-  cmax = NA, # initial/max average number of contacts per day (specify only if its the same for both groups, otherwise NA)
-  cmax_a = 8, cmax_b = 8, cmax_c=8, # initial/max average number of contacts per day by group 
-  cmin = NA, # min average contact
-  cmin_a = 3, cmin_b = 3, cmin_c=3,
-  beta_a=1, # homophily parameter for group a (beta_a = 1 means unbiased mixing; bigger values mean homophily) 
-  beta_b=1, # homophily parameter for group b (beta_b = 1 means unbiased mixing; bigger values mean homophily) 
-  #h_a=.5, # proportion of group A's total contact with members of their own group 
-  #h_b=.5, # proportion of group A's total contact with members of their own group 
-  ##
-  zeta = NA, # responsiveness of contact to deaths
-  zeta_a = 0.01, zeta_b = 0, zeta_c = 0.005,
-  trans_p = 0.05, # probability of transmission given contact (or susceptibility to infection given contact)
-  rho=1/10,# 1 / infectious period  or recovery rate
-  mu = NA,# probability of dying following infection
-  mu_a = 0.01, mu_b = 0.01, mu_c = .01, # can let it differ between groups to crudely account for difference in age composition between groups
-  kappa=0.9, # scaling factor for probability of transmission given contact resulting from protective behavior; kappa=1 means no protection, kappa = 0 means perfect protection
-  phi = NA, # waning of protective behavior
-  phi_a = 0, phi_b=0, phi_c=0,
-  I0_a=1, I0_b=1, I0_c=1, #intial infected in each group
-  time = 500, # time steps for simulation
-  pi = NA, # background rate of adopting protective behavior
-  pi_a = 0.05, pi_b = 0.05, pi_c = 0.05,
-  ell = 1, # time window for considering deaths that influence adoption of protective behavior
-  vacc = NA, # vaccination rate (goes from S to R)
-  # in Roubenoff et al. we assume about 2 million daily doses are distributed which is ~ 0.6 % of the population per day
-  vacc_a = 0.006, vacc_b = 0.006, vacc_c = 0.006,
-  vstart = 365, # start of vaccination
-  gamma = 1/182.5, # wanning immunity
-  
-  get_params=FALSE) {
-  # set following parameters to be the same for both groups unless specified otherwise 
-  
-  if(!is.na(mu)){  
-    mu_a<-mu  
-    mu_b<-mu
-    mu_c<-mu
-  }
-  
-  if(!is.na(zeta)){  
-    zeta_a<-zeta  
-    zeta_b<-zeta
-    zeta_c<-zeta
-  }
-  
-  if(!is.na(pi)){  
-    pi_a<-pi 
-    pi_b<-pi
-    pi_c<-pi
-  }
-  
-  if(!is.na(phi)){  
-    phi_a<-phi 
-    phi_b<-phi
-    phi_c<-phi
-  } 
-  
-  
-  if(!is.na(vacc)){  
-    vacc_a<-vacc
-    vacc_b<-vacc
-    vacc_c<-vacc
-  }
-  
-  if(!is.na(cmin)){  
-    cmin_a<-cmin
-    cmin_b<-cmin
-    cmin_c<-cmin
-  }
-  
-  
-  if(!is.na(cmax)){  
-    cmax_a<-cmax
-    cmax_b<-cmax
-    cmax_c<-cmax
-  }
-  
-  N0_a = N0 * frac_a 
-  N0_b = N0 * frac_b
-  N0_c = N0 * (1 - frac_a - frac_b)
-  
-  
-  
-  params<-c(‘trans_p’ = trans_p, # probability of transmission given contact
-            ‘beta_a’= beta_a, # homophily parameter for group a (beta_a = 1 means unbiased mixing; beta_a > 1 means homophily)
-            ‘beta_b’= beta_b, # homophily parameter for group b (beta_b = 1 means unbiased mixing; beta_b > 1 means homophily)
-            #’h_a’= h_a, # # proportion of group A's total contact with members of their own group (bounded by population size and total contacts in group B)
-            #’h_b’= h_b, # # proportion of group A's total contact with members of their own group (bounded by population size and total contacts in group B)
-            ‘cmax_a’ = cmax_a, ‘cmax_b’ = cmax_b, ‘cmax_c’ = cmax_c, # upper and lower bounds for contacts
-            ‘zeta_a’ = zeta_a, ‘zeta_b’ = zeta_b, ‘zeta_c’ = zeta_c, # responsiveness of contact to deaths
-            ‘pi_a’ = pi_a, ‘pi_b’ = pi_b, ‘pi_c’ = pi_c, # background rate of adopting protective behavior
-            ‘kappa’ = kappa, # scaling factor for probability of transmission given contact resulting from protective behavior; kappa=1 means no protection, kappa = 0 means perfect protection
-            ‘phi_a’=phi_a, ‘phi_b’ = phi_b, ‘phi_c’ = phi_c, # waning rate of protective behavior
-            ‘rho’=rho, # 1 / infectious period
-            ‘mu_a’=mu_a, ‘mu_b’ = mu_b, ‘mu_c’ = mu_c, # probability of dying following infection
-            ‘time’=time, # time steps in simulation
-            ‘I0_a’=I0_a, ‘I0_b’=I0_b, ‘I0_c’=I0_c, # starting number infected in each group
-            ‘N0_a’ = N0_a, ‘N0_b’= N0_b, ‘N0_c’=N0_c, # population size in each group at time zero
-            ‘ell’=ell, # time window for considering deaths that influence adoption of protective behavior
-            ‘vacc_a’=vacc_a, ‘vacc_b’=vacc_b, ‘vacc_c’=vacc_c, # vaccination rate
-            ‘vstart’ = vstart, # start of vaccination
-            ‘gamma’ = gamma #waning immunity
-  ) # responsiveness to proportion of protected individuals for adopting protective behavior
-  
-  state<-c( 
-    
-    #group a
-    ca <- cmax_a,
-    SUa<-(N0_a - I0_a),
-    SPa<-0,
-    IUa<-I0_a,
-    IPa<-0,
-    RUa<-0,
-    RPa<-0,
-    DUa<-0,
-    DPa<-0,
-    
-    #group b
-    cb <- cmax_b,
-    SUb<-N0_b - I0_b,
-    SPb<-0,
-    IUb<-I0_b,
-    IPb<-0,
-    RUb<-0,
-    RPb<-0,
-    DUb<-0,
-    DPb<-0,
-    
-    #group c 
-    cc <- cmax_c,
-    SUc<-N0_c - I0_c,
-    SPc<-0,
-    IUc<-I0_c,
-    IPc<-0,
-    RUc<-0,
-    RPc<-0,
-    DUc<-0,
-    DPc<-0
-  )
-  
-  names(state)<- c(‘ca’,’SUa’, ‘SPa’, ‘IUa’, ‘IPa’, ‘RUa’, ‘RPa’, ‘DUa’, ‘DPa’,
-                   ‘cb’,’SUb’, ‘SPb’, ‘IUb’, ‘IPb’, ‘RUb’, ‘RPb’, ‘DUb’, ‘DPb’,
-                   ‘cc’,’SUc’, ‘SPc’, ‘IUc’, ‘IPc’, ‘RUc’, ‘RPc’, ‘DUc’, ‘DPc’)
-  
-  sir_up<-function(t, state, parameter){
-    
-    with(as.list(c(parameter, state)), {
-      
-      
-      if(t<ell){
-        lag_ell<-rep(0, length(state))
-      }
-      else{
-        lag_ell<-lagvalue(t-ell) #provide access to past (lagged) values of all state variables; below we make sure we only look at D
-      }
-      
-      
-      if(t<vstart){
-        vacc_a <- 0
-        vacc_b <- 0
-        vacc_c <- 0
-      }
-      else{
-        vacc_a <- vacc_a
-        vacc_b <- vacc_b
-        vacc_c <- vacc_c
-      }
-      
-      # for the transitions there are seven processes that are currently modeled:
-      # 1: transmission process (infection, recovery/death)
-      # 2: changes in contact rate for group A in response to deaths
-      # 3: adoption of protective behavior 
-      # 5: waning of protective behavior
-      # 6: vaccination
-      # 7: waning of immunity
-      
-      
-      
-      # recalculate population size (will change due to deaths)
-      N_a = SUa + IUa + RUa + SPa + IPa + RPa 
-      N_b = SUb + IUb + RUb + SPb + IPb + RPb
-      N_c = SUc + IUc + RUc + SPc + IPc + RPc
-      
-      
-      
-      # contact matrix
-      c_mat <- avg_contact_matrix_3gp(dbar_a = ca,
-                                      dbar_b = cb,
-                                      dbar_c = cc,
-                                      N_a = N_a,
-                                      N_b = N_b,
-                                      N_c = N_c,
-                                      beta_a = beta_a,
-                                      beta_b = beta_b)
-      #h_a = h_a,
-      #h_b = h_b)
-      
-      ## TODO - should we throw an error if any implied contacts are negative? 
-      
-      
-      ################################
-      ## transitions for group a
-      ################################
-      
-      # Force of infection
-      lambda_a =  trans_p*(c_mat[1,1]*(IUa/N_a + kappa*IPa/N_a) + c_mat[1,2]*(IUb/N_b + kappa*IPb/N_b) + c_mat[1,3]*(IUc/N_c + kappa*IPc/N_c))
-      
-      
-      # change in contacts in response to deaths occuring over a time window defined by ell (constrained to maximum/minimum observed values)
-      
-      deaths_t <- rho*mu_a*IUa + rho*mu_a*IPa + rho*mu_b*IUb + rho*mu_b*IPb + rho*mu_c*IUc + rho*mu_c*IPc
-      
-      
-      deaths_tminusell <- rho*mu_a*(lag_ell[which(names(state) == ‘IUa’)]) + 
-        rho*mu_a*(lag_ell[which(names(state) == ‘IPa’)]) + 
-        rho*mu_b*(lag_ell[which(names(state) == ‘IUb’)]) + 
-        rho*mu_b*(lag_ell[which(names(state) == ‘IPb’)]) +
-        rho*mu_c*(lag_ell[which(names(state) == ‘IUc’)]) + 
-        rho*mu_c*(lag_ell[which(names(state) == ‘IPc’)])
-      
-      cum_deaths_ell <- DUa - lag_ell[which(names(state) == ‘DUa’)] +
-        DPa - lag_ell[which(names(state) == ‘DPa’)] +
-        DUb - lag_ell[which(names(state) == ‘DUb’)] +
-        DPb - lag_ell[which(names(state) == ‘DPb’)] +
-        DUc - lag_ell[which(names(state) == ‘DUc’)] +
-        DPc - lag_ell[which(names(state) == ‘DPc’)]
-      
-      dca <-  (-zeta_a)*(cmax_a - cmin_a)*(deaths_t - deaths_tminusell)*exp(-zeta_a*(cum_deaths_ell))
-      
-      dSUa <- -SUa*lambda_a - #transmission process
-        pi_a * SUa + # adoption of protective behavior
-        phi_a * SPa + #waning of protective behavior
-        gamma * RUa - #waning immunity
-        vacc_a * SUa
-      
-      dSPa <- -SPa*kappa*lambda_a +
-        pi_a * SUa - 
-        phi_a * SPa  +
-        gamma * RPa -
-        vacc_a * SPa
-      
-      dIUa <- SUa*lambda_a  -
-        pi_a*IUa + 
-        phi_a * IPa -
-        (rho) * IUa 
-      
-      dIPa <- SPa*kappa*lambda_a +
-        pi_a * IUa - 
-        phi_a * IPa -
-        (rho) * IPa 
-      
-      dRUa <- rho * (1-mu_a) * IUa  -
-        pi_a * RUa + 
-        phi_a * RPa  - 
-        gamma * RUa +
-        vacc_a * SUa
-      
-      dRPa <- rho * (1-mu_a) * IPa  +
-        pi_a * RUa - 
-        phi_a * RPa  - 
-        gamma * RPa +
-        vacc_a * SPa
-      
-      dDUa <- rho*mu_a*IUa
-      
-      dDPa <- rho*mu_a*IPa
-      
-      
-      ################################
-      ## transitions for group b
-      ################################
-      
-      # Force of infection
-      lambda_b = trans_p*(c_mat[2,1]*(IUa/N_a + kappa*IPa/N_a) + c_mat[2,2]*(IUb/N_b + kappa*IPb/N_b) + c_mat[2,3]*(IUc/N_c + kappa*IPc/N_c) )
-      
-      
-      # change in contacts in response to deaths (constrained to maximum/minimum observed values)
-      dcb <-  (-zeta_b)*(cmax_b - cmin_b)*(deaths_t - deaths_tminusell)*exp(-zeta_b*(cum_deaths_ell))
-      
-      
-      dSUb <- -SUb*lambda_b -
-        pi_b * SUb + 
-        phi_b * SPb +
-        gamma * RUb -
-        vacc_b * SUb
-      
-      dSPb <- -SPb*kappa*lambda_b  +
-        pi_b * SUb - 
-        phi_b * SPb  +
-        gamma * RPb -
-        vacc_b * SPb
-      
-      dIUb <- SUb*lambda_b -
-        pi_b * IUb + 
-        phi_b * IPb -
-        (rho) * IUb 
-      
-      dIPb <- SPb*kappa*lambda_b +
-        pi_b * IUb - 
-        phi_b * IPb -
-        (rho) * IPb 
-      
-      dRUb <- (1-mu_b) * rho * IUb -
-        pi_b * RUb +
-        phi_b * RPb  -
-        gamma * RUb +
-        vacc_b * SUb
-      
-      dRPb <- (1-mu_b) * rho * IPb +
-        pi_b * RUb - 
-        phi_b * RPb  -
-        gamma * RPb +
-        vacc_b * SPb
-      
-      dDUb <- rho*mu_b*IUb
-      
-      dDPb <- rho*mu_b*IPb
-      
-      
-      ################################
-      ## transitions for group c 
-      ################################
-      
-      # Force of infection
-      lambda_c = trans_p*(c_mat[3,1]*(IUa/N_a + kappa*IPa/N_a) + c_mat[3,2]*(IUb/N_b + kappa*IPb/N_b) + c_mat[3,3]*(IUc/N_c + kappa*IPc/N_c) )
-      
-      
-      # change in contacts in response to deaths (constrained to maximum/minimum observed values)
-      dcc <-  (-zeta_c)*(cmax_c - cmin_c)*(deaths_t - deaths_tminusell)*exp(-zeta_c*(cum_deaths_ell))
-      
-      
-      dSUc <- -SUc*lambda_c -
-        pi_c * SUc + 
-        phi_c * SPc  +
-        gamma * RUc -
-        vacc_c * SUc
-      
-      dSPc <- -SPc*kappa*lambda_c  +
-        pi_c * SUc - 
-        phi_c * SPc  +
-        gamma * RPc -
-        vacc_c * SPc
-      
-      dIUc <- SUc*lambda_c -
-        pi_c * IUc + 
-        phi_c * IPc -
-        (rho) * IUc 
-      
-      dIPc <- SPc*kappa*lambda_c +
-        pi_c * IUc - 
-        phi_c * IPc -
-        (rho) * IPc 
-      
-      dRUc <- (1-mu_c) * rho * IUc -
-        pi_c * RUc +
-        phi_c * RPc  -
-        gamma * RUc +
-        vacc_c * SUc
-      
-      dRPc <- (1-mu_c) * rho * IPc +
-        pi_c * RUc - 
-        phi_c * RPc  -
-        gamma * RPc +
-        vacc_c * SPc
-      
-      dDUc <- rho*mu_c*IUc
-      
-      dDPc <- rho*mu_c*IPc
-      
-      
-      
-      
-      return(list(c(dca, dSUa, dSPa, dIUa, dIPa, dRUa, dRPa, dDUa, dDPa,
-                    dcb, dSUb, dSPb, dIUb, dIPb, dRUb, dRPb, dDUb, dDPb,
-                    dcc, dSUc, dSPc, dIUc, dIPc, dRUc, dRPc, dDUc, dDPc
-      )))
-    })
-  }
-  
-  times<-seq(from=0, to=time, by=1)
-  
-  as.data.frame(dede(state, times, sir_up, params))->sim
-  
-  if(get_params){
-    return(list(sim=sim, params=params))
-  }
-  
-  else{
-    return(sim)
-  }
-  
-  
-  
-}
-"
-
-function_in_string <- gsub("\\s+", " ", function_in_string)
-function_in_string <- trimws(function_in_string)

app.R

@@ -713,8 +713,41 @@ Chenoweth, M., Li, M., Gomez-Lopez, I. N., & Kollman, K. (2020). <i>National Nei
     )
   })
 
-  # Set OPENAI_API_KEY environment variable before running the app
-  # Sys.setenv(OPENAI_API_KEY = "your-api-key-here")
+  # System prompt for chat assistant
+  chat_system_prompt <- "You are an expert assistant for the Partisan Epidemic Simulator, a Shiny app that models how partisan differences in health behaviors affect epidemic outcomes.
+
+## About the Model
+This is a three-party SIR (Susceptible-Infected-Recovered) model that simulates disease spread among Republicans, Democrats, and Independents. The model incorporates:
+
+- **Contact rates**: Different average daily contacts for each political group (Republicans typically have higher contact rates based on BICS survey data)
+- **Protective behavior**: Rates of adopting protective measures like masking (Democrats adopt faster, Republicans slower)
+- **Responsiveness to deaths (zeta)**: How groups adjust contact behavior based on mortality (Republicans show more responsiveness)
+- **Vaccination rates**: Differential uptake across groups (Democrats ~74%, Independents ~61%, Republicans ~57%)
+- **Contact homophily (beta)**: Tendency to interact with similar political affiliations (beta=1 means random mixing, higher values mean more within-group contact)
+- **Mortality rates**: Age-adjusted death rates by party
+
+## Key Parameters
+- **cmax**: Maximum daily contacts per group
+- **pi**: Rate of adopting protective behavior
+- **phi**: Rate of abandoning protective behavior (waning)
+- **zeta**: Responsiveness of contact reduction to deaths
+- **beta**: Homophily parameter (contact preference for own group)
+- **kappa**: Protective behavior effectiveness (1=no protection, 0=perfect)
+- **vacc**: Daily vaccination rate per group
+
+## Model Scenarios
+- **Homogenous**: No partisan differences (baseline for comparison)
+- **Partisan Behavior**: Full model with partisan heterogeneity
+- **Manual**: User-controlled parameters
+
+## Interpreting Results
+- Higher prevalence peaks indicate worse outbreaks
+- Earlier peaks suggest faster spread
+- Differences between party lines show disparate disease burden
+- 'Excess deaths' compares partisan model to homogenous baseline
+
+Be concise, helpful, and reference the specific metrics the user is viewing when answering questions."
+
   chat_history <- reactiveVal("")
 
   # Build context string for chat based on current user view
@@ -772,7 +805,7 @@ Chenoweth, M., Li, M., Gomez-Lopez, I. N., & Kollman, K. (2020). <i>National Nei
         body = toJSON(list(
           model = "Qwen/Qwen3-VL-235B-A22B-Instruct:novita",
           messages = list(
-            list(role = "system", content = function_in_string),
+            list(role = "system", content = chat_system_prompt),
             list(role = "user", content = message_with_context)
           ),
           max_tokens = 500,