DR SEGURA

#packges

library("tidyverse")

#abro copia_df

df <- read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSFXHAlpWr7P2GHtqOi3F3_KLXFVbLxl5Q2armt4NS1Ju9iXrnrNL3AElAK4cfyllxWqLuJPLi-pMJs/pub?gid=1082241407&single=true&output=csv")

#summary

summary(df)

    NOMBRE               EDAD          RUT            TAMAÑO.PROSTATA    METODO         
 Length:75          Min.   :52.0   Length:75          Min.   : 30.0   Length:75         
 Class :character   1st Qu.:63.5   Class :character   1st Qu.: 50.0   Class :character  
 Mode  :character   Median :69.0   Mode  :character   Median : 65.0   Mode  :character  
                    Mean   :69.7                      Mean   : 73.5                     
                    3rd Qu.:75.0                      3rd Qu.: 87.5                     
                    Max.   :89.0                      Max.   :190.0                     
 UFM.QMAX.PRE       UFM.QMAX.POST        PSA.pre            PSA.post        
 Length:75          Length:75          Length:75          Length:75         
 Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                            
                                                                            
                                                                            
   RPM.PRE          VEJIGA.DE.LUCHA      RPM.POST            FECHA            BIOPSIA..GR.  
 Length:75          Length:75          Length:75          Length:75          Min.   :  6.0  
 Class :character   Class :character   Class :character   Class :character   1st Qu.: 32.0  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character   Median : 50.0  
                                                                             Mean   : 51.9  
                                                                             3rd Qu.: 61.0  
                                                                             Max.   :170.0  
 X..RESECCION    TECNICA.QX        TIEMPO.ENUCLEACION TIEMPO.MORCELACION HORAS.DE.SONDA
 Mode:logical   Length:75          Min.   : 30.0      Min.   : 5.0       Min.   :12    
 NA's:75        Class :character   1st Qu.: 45.0      1st Qu.:10.0       1st Qu.:24    
                Mode  :character   Median : 60.0      Median :15.0       Median :24    
                                   Mean   : 62.9      Mean   :16.7       Mean   :29    
                                   3rd Qu.: 77.5      3rd Qu.:20.0       3rd Qu.:24    
                                   Max.   :180.0      Max.   :50.0       Max.   :72    
 HORAS.IRRIGACION  ESTADIA.DIA   COMPLICACION.INTRA.OPERATORIO   DISURIA         
 Min.   :10.0     Min.   :1.00   Length:75                     Length:75         
 1st Qu.:12.0     1st Qu.:1.00   Class :character              Class :character  
 Median :12.0     Median :1.00   Mode  :character              Mode  :character  
 Mean   :14.9     Mean   :1.44                                                   
 3rd Qu.:12.0     3rd Qu.:1.50                                                   
 Max.   :48.0     Max.   :7.00                                                   
   URGENCIA             RAO            INCONTINENCIA          ITU           
 Length:75          Length:75          Length:75          Length:75         
 Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                            
                                                                            
                                                                            
  HEMATURIA          REINGRESO              X             CANCER.PROSTATA   
 Length:75          Length:75          Length:75          Length:75         
 Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                            
                                                                            
                                                                            
 CANCER.PROSTATA.IRRADIADO     X.1            LITIASIS.CONCOMITANTE MORCELACIÓN.2DO.TIEMPO
 Length:75                 Length:75          Length:75             Length:75             
 Class :character          Class :character   Class :character      Class :character      
 Mode  :character          Mode  :character   Mode  :character      Mode  :character      
                                                                                          
                                                                                          
                                                                                          

#Edad (B)

options(digits=3) #agregar solo un decimal 
df %>% 
summarise(promedio = mean(EDAD), desviacion = sd(EDAD), rango= max(EDAD)-min(EDAD))

#histograma edad

hist(df$EDAD)

#Tamaño prostata (D)

options(digits=3) #agregar solo un decimal 
df %>% 
summarise(promedio = mean(TAMAÑO.PROSTATA), desviacion = sd(TAMAÑO.PROSTATA), rango= max(TAMAÑO.PROSTATA)-min(TAMAÑO.PROSTATA))

#Biopsia (GR) (N)

options(digits=3) #agregar solo un decimal 
df %>% 
summarise(promedio = mean(BIOPSIA..GR.), desviacion = sd(BIOPSIA..GR.), rango= max(BIOPSIA..GR.)-min(BIOPSIA..GR.))

#Tecnica QX (P)

#Tiempo de enucleación (Q)

options(digits=3) #agregar solo un decimal 
  df %>% 
summarise(promedio = mean(TIEMPO.ENUCLEACION), desviacion = sd(TIEMPO.ENUCLEACION), rango= max(TIEMPO.ENUCLEACION)-min(TIEMPO.ENUCLEACION))

#Tiempo de Morcelacion (R)

options(digits=3) #agregar solo un decimal 
  df %>% 
summarise(promedio = mean(TIEMPO.MORCELACION), desviacion = sd(TIEMPO.MORCELACION), rango= max(TIEMPO.MORCELACION)-min(TIEMPO.MORCELACION))

#horas de sonda (S)

options(digits=3) #agregar solo un decimal 
  df %>% 
summarise(promedio = mean(HORAS.DE.SONDA), desviacion = sd(HORAS.DE.SONDA), rango= max(HORAS.DE.SONDA)-min(HORAS.DE.SONDA))

#horas de sonda (clasifico por horas de sonda) (S)

#horas de irrigacion (T)

options(digits=3) #agregar solo un decimal 
  df %>% 
summarise(promedio = mean(HORAS.IRRIGACION), desviacion = sd(HORAS.IRRIGACION), rango= max(HORAS.IRRIGACION)-min(HORAS.IRRIGACION))

#horas de irrigacion (clasifico por horas de irrigacion) (T)

#Estadia dia (U)

options(digits=3) #agregar solo un decimal 
  df %>% 
summarise(promedio = mean(ESTADIA.DIA), desviacion = sd(ESTADIA.DIA), rango= max(ESTADIA.DIA)-min(ESTADIA.DIA))

#estadia dia (clasifico por estadia dia)(U)

#Variables de frecuencia para datos amarillos y verdes (61 datos) #abrir el df para esta planilla de datos

df1 <- read_csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSFXHAlpWr7P2GHtqOi3F3_KLXFVbLxl5Q2armt4NS1Ju9iXrnrNL3AElAK4cfyllxWqLuJPLi-pMJs/pub?gid=1359141274&single=true&output=csv")

#agrupo por Disuria (W)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(DISURIA) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#agrupo por Urgencia (X)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(URGENCIA) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#Agrupo por RAO (Y)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(RAO) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#Agrupo por Incontinencia (Z)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(INCONTINENCIA) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#Agrupo por ITU (AA)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(ITU) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#Agrupo por Hematuria (AB)

options(digits=3) #agregar solo un decimal 
  df1 %>% 
  group_by(HEMATURIA) %>%
  summarise(n=n(), Porcentaje =  `n`/61*100)   #son 61 datos 

#Agrupo por reingreso

#abro el df2 para t.test

df3 <- read_csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSFXHAlpWr7P2GHtqOi3F3_KLXFVbLxl5Q2armt4NS1Ju9iXrnrNL3AElAK4cfyllxWqLuJPLi-pMJs/pub?gid=1545735592&single=true&output=csv")

#summary

summary(df3)

#t.test para UFM (existen diferencias)

t.test(df3$`Valor UFM`~df3$UFM)

    Welch Two Sample t-test

data:  df3$`Valor UFM` by df3$UFM
t = 13, df = 70, p-value <2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 11.1 15.1
sample estimates:
mean in group UFM QMAX POST  mean in group UFM QMAX PRE 
                       22.3                         9.2 

#t.test para PSA (existen diferencias)

t.test(df3$`Valor PSA`~df3$PSA) #Existen diferencias

    Welch Two Sample t-test

data:  df3$`Valor PSA` by df3$PSA
t = -7, df = 43, p-value = 4e-08
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -5.54 -2.97
sample estimates:
mean in group PSA post  mean in group PSA pre 
                 0.654                  4.909 

#t.test para RPM (existen diferencias)

t.test(df3$`Valor RPM`~df3$RPM)

    Welch Two Sample t-test

data:  df3$`Valor RPM` by df3$RPM
t = -13, df = 43, p-value <2e-16
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -142 -105
sample estimates:
mean in group RPM POST  mean in group RPM PRE 
                   4.7                  128.5