Home > Software design >  Generate graphs for dates that are not in my database
Generate graphs for dates that are not in my database

Time：10-16

The function below generates graphs for the days present in date2, that is, 01/07, 02/07 and 04/07. However, I would like to know if it is possible to adjust my function or maybe make a new function so that, if I don't have a date in date2, for example, 15/10 or any other day different from what I have in date2, it would consider using the following condition of my function:

  if (nrow(datas)<=2){
    abline(h=m,lwd=2) 
    points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,m  .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}

So the graph for dates that are not present in date2 will have no points, just a line in m. It is possible?

Executable code below:

library(dplyr)
library(tidyverse)
library(lubridate)

df1 <- structure(
  list(date1= c("2021-06-28","2021-06-28","2021-06-28"),
       date2 = c("2021-07-01","2021-07-02","2021-07-04"),
       Category = c("ABC","ABC","ABC"),
       Week= c("Wednesday","Wednesday","Wednesday"),
       DR1 = c(4,1,0),
       DR01 = c(4,1,0), DR02= c(4,2,0),DR03= c(9,5,0),
       DR04 = c(5,4,0),DR05 = c(5,4,0),DR06 = c(5,4,0),DR07 = c(5,4,0),DR08 = c(5,4,0)),
  class = "data.frame", row.names = c(NA, -3L))


f1 <- function(dmda, CategoryChosse) {
  
  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week')) %>%
    mutate(across(matches("^DR0\\d $"), ~.x   
                    get(paste0(cur_column(), '_PV')),
                  .names = '{col}_{col}_PV')) %>%
    select(date1:Category, DR01_DR01_PV:last_col())
  
  SPV<-data.frame(SPV)
  
  mat1 <- df1 %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(starts_with("DR0")) %>%
    pivot_longer(cols = everything()) %>%
    arrange(desc(row_number())) %>%
    mutate(cs = cumsum(value)) %>%
    filter(cs == 0) %>%
    pull(name)
  
  (dropnames <- paste0(mat1,"_",mat1, "_PV"))
  
  SPV <- SPV %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(-any_of(dropnames))
  
  if(length(grep("DR0", names(SPV))) == 0) {
    SPV[head(mat1,10)] <- NA_real_
  }
  
  datas <-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category) %>%
    summarize(across(starts_with("DR0"), sum)) %>%
    pivot_longer(cols= -Category, names_pattern = "DR0(. )", values_to = "val") %>%
    mutate(name = readr::parse_number(name))
  colnames(datas)[-1]<-c("Days","Numbers")
  
  
  datas <- datas %>% 
    group_by(Category) %>% 
    slice((as.Date(dmda) - min(as.Date(df1$date1) [
      df1$Category == first(Category)])):max(Days) 1) %>%
    ungroup
  
  m<-df1 %>%
    group_by(Category,Week) %>%
    summarize(across(starts_with("DR1"), mean))
  
  m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
  
  maxrange <-  range(min(0, datas$Numbers, na.rm = TRUE), na.rm = TRUE)
  maxrange[1] <- maxrange[1] - (maxrange[1] %%10)   35
  
  max<-max(0, datas$Days, na.rm = TRUE) 1
  
  plot(Numbers ~ Days,  xlim= c(0,max),  ylim= c(0,maxrange[1]),
       xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
  
  if (nrow(datas)<=2){
    abline(h=m,lwd=2) 
    points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,m  .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else if(any(table(datas$Numbers) >= 3) & length(unique(datas$Numbers)) == 1){
    yz <- unique(datas$Numbers)
    lines(c(0,datas$Days), c(yz, datas$Numbers), lwd = 2)
    points(0, yz, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,yz  .5,round(yz,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else{
    mod <- nls(Numbers ~ b1*Days^2 b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
    new.data <- data.frame(Days = with(datas, seq(min(Days),max(Days),len = 45)))
    new.data <- rbind(0, new.data)
    lines(new.data$Days,predict(mod,newdata = new.data),lwd=2)
    coef<-coef(mod)[1]
    points(0, coef, col="red",pch=19,cex = 2,xpd=TRUE)
    text(.99,coef   1,max(0, round(coef,1)), cex=1.1,pos=4,offset =1,col="black")
  }
  
}
f1("2021-07-01", "ABC")
f1("2021-07-02", "ABC")
f1("2021-07-04", "ABC")

enter image description here enter image description here enter image description here

CodePudding user response：

Now that the function run I understand the problem. You have to make a "by-pass" to exclude the part when you need to match date2.

datas <- datas %>%
group_by(Category) %>%
slice((as.Date(dmda) - min(as.Date(df1$date1) [
df1$Category == first(Category)])):max(Days) 1) %>%
ungroup

This part cannot work without it. Then you have to define m. I think you can still use this if(is.null(df1$date2[df1$date2 == dmda])) to make the by-pass.

f1 <- function(dmda, CategoryChosse) {
  
  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week')) %>%
    mutate(across(matches("^DR0\\d $"), ~.x   
                    get(paste0(cur_column(), '_PV')),
                  .names = '{col}_{col}_PV')) %>%
    select(date1:Category, DR01_DR01_PV:last_col())
  
  SPV<-data.frame(SPV)
  
  
  mat1 <- df1 %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(starts_with("DR0")) %>%
    pivot_longer(cols = everything()) %>%
    arrange(desc(row_number())) %>%
    mutate(cs = cumsum(value)) %>%
    filter(cs == 0) %>%
    pull(name)
  
  (dropnames <- paste0(mat1,"_",mat1, "_PV"))
  
  SPV <- SPV %>%
    filter(date2 == dmda, Category == CategoryChosse) %>%
    select(-any_of(dropnames))
  
  if(length(grep("DR0", names(SPV))) == 0) {
    SPV[head(mat1,10)] <- NA_real_
  }
  
  # About here you need to make the by-pass
  
  datas <-SPV %>%
    filter(date2 == ymd(dmda)) %>%
    group_by(Category) %>%
    summarize(across(starts_with("DR0"), sum)) %>%
    pivot_longer(cols= -Category, names_pattern = "DR0(. )", values_to = "val") %>%
    mutate(name = readr::parse_number(name))
  colnames(datas)[-1]<-c("Days","Numbers")
  
  
  datas <- datas %>% 
    group_by(Category) %>% 
    slice((as.Date(dmda) - min(as.Date(df1$date1) [
      df1$Category == first(Category)])):max(Days) 1) %>%
    ungroup    # This cannot work since you can't match the datas
  
  m<-df1 %>%
    group_by(Category,Week) %>%
    summarize(across(starts_with("DR1"), mean))
  
  m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
  
  maxrange <-  range(min(0, datas$Numbers, na.rm = TRUE), na.rm = TRUE)
  maxrange[1] <- maxrange[1] - (maxrange[1] %%10)   35
  
  max<-max(0, datas$Days, na.rm = TRUE) 1
  
  plot(Numbers ~ Days,  xlim= c(0,max),  ylim= c(0,maxrange[1]),
       xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
  
  if(nrow(datas)<=2){
    abline(h=m,lwd=2) 
    points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE) 
    text(.1,m  .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else if(any(table(datas$Numbers) >= 3) & length(unique(datas$Numbers)) == 1){
    yz <- unique(datas$Numbers)
    lines(c(0,datas$Days), c(yz, datas$Numbers), lwd = 2)
    points(0, yz, col = "red", pch = 19, cex = 2, xpd = TRUE)
    text(.1,yz  .5,round(yz,1), cex=1.1,pos=4,offset =1,col="black")}
  
  else{
    mod <- nls(Numbers ~ b1*Days^2 b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
    new.data <- data.frame(Days = with(datas, seq(min(Days),max(Days),len = 45)))
    new.data <- rbind(0, new.data)
    lines(new.data$Days,predict(mod,newdata = new.data),lwd=2)
    coef<-coef(mod)[1]
    points(0, coef, col="red",pch=19,cex = 2,xpd=TRUE)
    text(.99,coef   1,max(0, round(coef,1)), cex=1.1,pos=4,offset =1,col="black")
  }
  
}

CodePudding user response：

May be change the condition as here


f1 <- function(dmda, CategoryChosse) {
  
  x<-df1 %>% select(starts_with("DR0"))
  
  x<-cbind(df1, setNames(df1$DR1 - x, paste0(names(x), "_PV")))
  PV<-select(x, date2,Week, Category, DR1, ends_with("PV"))
  
  med<-PV %>%
    group_by(Category,Week) %>%
    summarize(across(ends_with("PV"), median))
  
  SPV<-df1%>%
    inner_join(med, by = c('Category', 'Week')) %>%
    mutate(across(matches("^DR0\\d $"), ~.x   
                    get(paste0(cur_column(), '_PV')),
                  .names = '{col}_{col}_PV')) %>%
    select(date1:Category, DR01_DR01_PV:last_col())
  
  SPV<-data.frame(SPV)
  
  m<-df1 %>%
    group_by(Category,Week) %>%
    summarize(across(starts_with("DR1"), mean))
  
  
  datas <- data.frame()
  if(any(with(df1, date2 == dmda, Category == CategoryChosse), na.rm = TRUE)) {
      mat1 <- df1 %>%
        filter(date2 == dmda, Category == CategoryChosse) %>%
        select(starts_with("DR0")) %>%
        pivot_longer(cols = everything()) %>%
        arrange(desc(row_number())) %>%
        mutate(cs = cumsum(value)) %>%
        filter(cs == 0) %>%
        pull(name)
      
      (dropnames <- paste0(mat1,"_",mat1, "_PV"))
      
      SPV <- SPV %>%
        filter(date2 == dmda, Category == CategoryChosse) %>%
        select(-any_of(dropnames))
      
      if(length(grep("DR0", names(SPV))) == 0) {
        SPV[head(mat1,10)] <- NA_real_
      }
      
      datas <-SPV %>%
        filter(date2 == ymd(dmda)) %>%
        group_by(Category) %>%
        summarize(across(starts_with("DR0"), sum)) %>%
        pivot_longer(cols= -Category, names_pattern = "DR0(. )", values_to = "val") %>%
        mutate(name = readr::parse_number(name))
      colnames(datas)[-1]<-c("Days","Numbers")
      
      
      datas <- datas %>% 
        group_by(Category) %>% 
        slice((as.Date(dmda) - min(as.Date(df1$date1) [
          df1$Category == first(Category)])):max(Days) 1) %>%
        ungroup
      
     
      m<-subset(m, Week == df1$Week[match(ymd(dmda), ymd(df1$date2))] & Category == CategoryChosse)$DR1
      maxrange <-  range(min(0, datas$Numbers, na.rm = TRUE), na.rm = TRUE)
      maxrange[1] <- maxrange[1] - (maxrange[1] %%10)   35
      
      max<-max(0, datas$Days, na.rm = TRUE) 1
      
      plot(Numbers ~ Days,  xlim= c(0,max),  ylim= c(0,maxrange[1]),
           xaxs='i',data = datas,main = paste0(dmda, "-", CategoryChosse))
      
      if (nrow(datas)<=2){
        abline(h=m,lwd=2) 
        points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
        text(.1,m  .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
      
      else if(any(table(datas$Numbers) >= 3) & length(unique(datas$Numbers)) == 1){
        yz <- unique(datas$Numbers)
        lines(c(0,datas$Days), c(yz, datas$Numbers), lwd = 2)
        points(0, yz, col = "red", pch = 19, cex = 2, xpd = TRUE)
        text(.1,yz  .5,round(yz,1), cex=1.1,pos=4,offset =1,col="black")}
      
      else{
        mod <- nls(Numbers ~ b1*Days^2 b2,start = list(b1 = 0,b2 = 0),data = datas, algorithm = "port")
        new.data <- data.frame(Days = with(datas, seq(min(Days),max(Days),len = 45)))
        new.data <- rbind(0, new.data)
        lines(new.data$Days,predict(mod,newdata = new.data),lwd=2)
        coef<-coef(mod)[1]
        points(0, coef, col="red",pch=19,cex = 2,xpd=TRUE)
        text(.99,coef   1,max(0, round(coef,1)), cex=1.1,pos=4,offset =1,col="black")
      }
  } else {
    if (nrow(datas)<=2){
      m <- m$DR1[1]
      Days <- seq(0, 8, by = 2)
      Numbers <- seq(0, 8, by = 2) * m * 5
      
      plot(Numbers ~ Days,  xlim= c(0,max(Days)   2),  ylim= c(0,max(Numbers)),
           xaxs='i', main = paste0(dmda, "-", CategoryChosse), type = "n")
      
      abline(h=m,lwd=2) 
      points(0, m, col = "red", pch = 19, cex = 2, xpd = TRUE)
      text(.1,m  .5, round(m,1), cex=1.1,pos=4,offset =1,col="black")}
    
    
  }
  
  
}

-checking

f1("2021-07-01", "ABC")
f1("2021-07-02", "ABC")
f1("2021-07-04", "ABC")
f1("2021-15-10", "ABC")

Page link：https//www.codepudding.com/Softwaredesign/154338.html

Prev:nth group labelling (count only graduates with new group)
Next:How to create a list of elements in columns based on another in R dataframe
  • Related

About Us:  Contact Us      Terms of Service       Privacy Policy

Copyright © 2010-2023，Powered By CodePudding