Análise de Dados Dandara

#https://github.com/EmilHvitfeldt/r-color-palettes
library(ggplot2)
library(RColorBrewer)
#library(colorRamps)


#getPalette <- colorRampPalette(brewer.pal(12, "Set3"))

gg_color_hue <- function(n) {
  hues = seq(15, 375, length = n + 1)
  hcl(h = hues, l = 65, c = 100)[1:n]
}

# library(scales)
# show_col(hue_pal()(30))

cor = gg_color_hue(9)

#cor <- getPalette(9)
#cor <-brewer.pal(12, "Set3")  

# my.path <- dirname(rstudioapi::getActiveDocumentContext()$path)
# setwd(my.path)

pkg <- c("dplyr",
         "car",
         "agricolae",
         "knitr",
         "TukeyC",
         "dae",
         "showtext",
         "readxl",
         "tidyverse",
         "magrittr")

# instale os pacotes abaixo

# install.packages(pkg)

# carregar pacotes
sapply(pkg,
       library,
       character.only = TRUE,
       logical.return = TRUE)

##     dplyr       car agricolae     knitr    TukeyC       dae  showtext    readxl 
##      TRUE      TRUE      TRUE      TRUE      TRUE      TRUE      TRUE      TRUE 
## tidyverse  magrittr 
##      TRUE      TRUE

showtext_opts(dpi = 300)

options(knitr.table.format = "pandoc")
options(knitr.kable.NA = '')



# leitura de dados

Resultados

ANOVA

model[["ANOVA"]] %>% kable(digits = 3)

	Df	Sum Sq	Mean Sq	F value	Pr(>F)
rep	3	1643.269	547.756	19.038	0.000
Lote	4	8657.835	2164.459	75.227	0.000
Ea	12	345.269	28.772
Sementes	1	18954.324	18954.324	227.848	0.000
Lote:Sementes	4	630.321	157.580	1.894	0.164
Eb	15	1247.829	83.189
Tempo	6	899.703	149.950	61.167	0.000
Tempo:Lote	24	236.134	9.839	4.013	0.000
Tempo:Sementes	6	295.057	49.176	20.060	0.000
Tempo:Lote:Sementes	24	353.699	14.737	6.012	0.000
Ec	180	441.265	2.451

# Teste de Tukey

Teste de Tukey

par(mfrow = c(1, 3), cex = 0.6)
plot(
  out1,
  xlab = "Lote",
  las = 1,
  variation = "IQR",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
  main = "Grupos e Amplitude interquartil"
)
plot(
  out2,
  xlab = "Sementes",
  variation = "IQR",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
  main = "Grupos e Amplitude interquartil"
)
plot(
  out3,
  xlab = "Tempo",
  variation = "IQR",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
  main = "Grupos e Amplitude interquartil"
)

# Anova com pacote base para comparar com agricolae e fazer os gráficos de interação

Interação

par(mfrow = c(1, 1))


pss %>% with(
  interaction.plot(
    Lote,
    Tempo,
    CE,
    xlab = 'Lote',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    #col = c('red', "green", "blue", "pink", "black", "orange"),
    col = cor,
    lwd = 2
  )
)

pss %>% with(
  interaction.plot(
    Sementes,
    Tempo,
    CE,
    xlab = 'Sementes',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    #col = c('red', "green", "blue", "pink", "black", "orange"),
    col = cor,
    lwd = 2
  )
)

boxplot(
  CE ~ Tempo,
  data = pss,
  col = cor,
  xlab = "Tempo",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)'
)

pss %>% with(
  interaction.plot(
    Lote,
    Sementes,
    CE,
    xlab = 'Lote',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    #col = c("red", "green", 'blue'),
    col = cor,
    lwd = 2
  )
)

boxplot(
  CE ~ Sementes,
  data = pss,
  col = cor,
  xlab = "Sementes",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)'
)

pss %>% with(
  interaction.plot(
    Tempo,
    Sementes,
    CE,
    xlab = 'Tempo',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    #col = c("red", "green", 'blue'),
    col = cor,
    lwd = 2
  )
)

boxplot(
  CE ~ Lote,
  data = pss,
  col = cor,
  xlab = "Lote",
  ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)'
)

pss %>% with(
  interaction.plot(
    Sementes,
    Lote,
    CE,
    xlab = 'Sementes',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    #col = c('red', "green", "blue", "pink", "black", "orange", "cyan"),
    col = cor,
    lwd = 2
  )
)

pss %>% with(
  interaction.plot(
    Tempo,
    Lote,
    CE,
    xlab = 'Tempo',
    ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
    col = cor,
    lwd = 2
  )
)

Gráfico de interação tripla

Interação Tripla

a<- interaction.ABC.plot(CE,
                     Tempo,
                     Lote,
                     Sementes,
                     title="",
                     ylab = 'Condutividade Elétrica (µS.cm-1 .g-1)',
                     data = pss) + theme_minimal()

# Observa-se efeito significativo de épocas, cultivares e interação.

Testes de comparação de médias

Efeitos principais

Lote

tkc <- AOV %>% TukeyC(which = 'Lote',
                      error = 'rep:Lote')

tkc[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3	G4
UNA1	35.32	a
UNA2	27.62		b
BUERAREMA	24.40			c
ITAJUIPE	21.60			c	d
ITAMARACA	21.11				d

Sementes

tke <- AOV %>% TukeyC(which = 'Sementes',
                      error = 'rep:Lote:Sementes')

tke[["out"]][["Result"]] %>% kable

	Means	G1	G2
50	33.70	a
25	18.31		b

Tempo

tkd <- AOV %>% TukeyC(which = 'Tempo',
                      error = 'Within')

tkd[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
19h	28.05	a
17h	27.56	a	b
11h	26.95	a	b
15h	26.84	a	b
13h	26.04	a	b
7h	25.08		b
9h	22.46			c

Lote dentro de Tempo

A/Tempo

tkq <- AOV %>% TukeyC(which = 'Lote:Tempo',
                      error = 'Within',
                      fl1 = 1)

tkq[["out"]][["Result"]] %>% kable

	Means	G1	G2
UNA1/19h	38.44	a
UNA1/17h	37.64	a	b
UNA1/15h	36.76	a	b
UNA1/13h	35.98	a	b
UNA1/7h	34.46	a	b
UNA1/11h	33.36	a	b
UNA1/9h	31.44		b

B/Tempo

tks <- AOV %>% TukeyC(which = 'Lote:Tempo',
                      error = 'Within',
                      fl1 = 2)

tks[["out"]][["Result"]] %>% kable

	Means	G1
UNA2/19h	30.51	a
UNA2/17h	29.86	a
UNA2/15h	29.15	a
UNA2/13h	28.12	a
UNA2/11h	26.55	a
UNA2/7h	26.07	a
UNA2/9h	24.62	a

C/Tempo

tkw <- AOV %>% TukeyC(which = 'Lote:Tempo',
                      error = 'Within',
                      fl1 = 3)

tkw[["out"]][["Result"]] %>% kable

	Means	G1
BUERAREMA/11h	26.88	a
BUERAREMA/19h	25.73	a
BUERAREMA/17h	25.62	a
BUERAREMA/15h	24.88	a
BUERAREMA/13h	24.02	a
BUERAREMA/7h	23.76	a
BUERAREMA/9h	20.54	a

D/Tempo

tkr <- AOV %>% TukeyC(which = 'Lote:Tempo',
                      error = 'Within',
                      fl1 = 4)

tkr[["out"]][["Result"]] %>% kable

	Means	G1
ITAJUIPE/11h	24.24	a
ITAJUIPE/19h	23.15	a
ITAJUIPE/17h	22.65	a
ITAJUIPE/15h	21.98	a
ITAJUIPE/13h	21.27	a
ITAJUIPE/7h	20.79	a
ITAJUIPE/9h	17.90	a

E/Tempo

tkt <- AOV %>% TukeyC(which = 'Lote:Tempo',
                      error = 'Within',
                      fl1 = 5)

tkt[["out"]][["Result"]] %>% kable

	Means	G1
ITAMARACA/11h	23.72	a
ITAMARACA/19h	22.45	a
ITAMARACA/17h	22.04	a
ITAMARACA/15h	21.45	a
ITAMARACA/13h	20.77	a
ITAMARACA/7h	20.34	a
ITAMARACA/9h	17.80	a

Sementes dentro de Tempo

25/Tempo

tkq1 <- AOV %>% TukeyC(which = 'Sementes:Tempo',
                       error = 'Within',
                       fl1 = 1)

tkq1[["out"]][["Result"]] %>% kable

	Means	G1
25/11h	19.82	a
25/19h	19.35	a
25/17h	19.02	a
25/15h	18.59	a
25/13h	18.05	a
25/7h	17.34	a
25/9h	16.98	a

50/Tempo

tks1 <- AOV %>% TukeyC(which = 'Sementes:Tempo',
                       error = 'Within',
                       fl1 = 2)

tks1[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/19h	36.76	a
50/17h	36.11	a	b
50/15h	35.09	a	b
50/11h	34.09	a	b
50/13h	34.02	a	b
50/7h	32.82		b
50/9h	27.94			c

Lote / Sementes dentro de Tempo

A/Sementes/Tempo

tkq2 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 1,
  fl2 = 1
)

tkq2[["out"]][["Result"]] %>% kable

	Means	G1
UNA1/25/19h	27.00	a
UNA1/25/17h	26.62	a
UNA1/25/15h	26.23	a
UNA1/25/13h	25.60	a
UNA1/25/7h	24.32	a
UNA1/25/11h	23.85	a
UNA1/25/9h	22.27	a

tkq3 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 1,
  fl2 = 2
)

tkq3[["out"]][["Result"]] %>% kable

	Means	G1	G2
UNA1/50/19h	49.88	a
UNA1/50/17h	48.65	a	b
UNA1/50/15h	47.30	a	b
UNA1/50/13h	46.35	a	b
UNA1/50/7h	44.60	a	b
UNA1/50/11h	42.88	a	b
UNA1/50/9h	40.60		b

B/Sementes/Tempo

tkq5 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 2,
  fl2 = 1
)

tkq5[["out"]][["Result"]] %>% kable

	Means	G1
UNA2/25/9h	23.73	a
UNA2/25/11h	23.23	a
UNA2/25/19h	21.00	a
UNA2/25/17h	20.52	a
UNA2/25/15h	20.07	a
UNA2/25/13h	19.52	a
UNA2/25/7h	19.45	a

tkq6 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 2,
  fl2 = 2
)

tkq6[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
UNA2/50/19h	40.02	a
UNA2/50/17h	39.20	a
UNA2/50/15h	38.23	a	b
UNA2/50/13h	36.73	a	b
UNA2/50/7h	32.69	a	b	c
UNA2/50/11h	29.88		b	c
UNA2/50/9h	25.52			c

C/Sementes/Tempo

tkq8 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 3,
  fl2 = 1
)

tkq8[["out"]][["Result"]] %>% kable

	Means	G1
BUERAREMA/25/11h	19.57	a
BUERAREMA/25/19h	18.18	a
BUERAREMA/25/17h	17.90	a
BUERAREMA/25/15h	17.40	a
BUERAREMA/25/13h	16.75	a
BUERAREMA/25/7h	16.09	a
BUERAREMA/25/9h	14.47	a

tkq9 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 3,
  fl2 = 2
)

tkq9[["out"]][["Result"]] %>% kable

	Means	G1
BUERAREMA/50/11h	34.17	a
BUERAREMA/50/17h	33.35	a
BUERAREMA/50/19h	33.27	a
BUERAREMA/50/15h	32.35	a
BUERAREMA/50/7h	31.43	a
BUERAREMA/50/13h	31.30	a
BUERAREMA/50/9h	26.60	a

D/Sementes/Tempo

tko2 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 4,
  fl2 = 1
)

tko2[["out"]][["Result"]] %>% kable

	Means	G1
ITAJUIPE/25/11h	15.65	a
ITAJUIPE/25/19h	14.85	a
ITAJUIPE/25/17h	14.62	a
ITAJUIPE/25/15h	14.25	a
ITAJUIPE/25/13h	13.80	a
ITAJUIPE/25/7h	12.66	a
ITAJUIPE/25/9h	11.47	a

tko3 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 4,
  fl2 = 2
)

tko3[["out"]][["Result"]] %>% kable

	Means	G1
ITAJUIPE/50/11h	32.83	a
ITAJUIPE/50/19h	31.45	a
ITAJUIPE/50/17h	30.68	a
ITAJUIPE/50/15h	29.70	a
ITAJUIPE/50/7h	28.91	a
ITAJUIPE/50/13h	28.75	a
ITAJUIPE/50/9h	24.32	a

E/Sementes/Tempo

tko5 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 5,
  fl2 = 1
)

tko5[["out"]][["Result"]] %>% kable

	Means	G1
ITAMARACA/25/11h	16.77	a
ITAMARACA/25/19h	15.73	a
ITAMARACA/25/17h	15.43	a
ITAMARACA/25/15h	15.00	a
ITAMARACA/25/13h	14.60	a
ITAMARACA/25/7h	14.19	a
ITAMARACA/25/9h	12.97	a

tko6 <- AOV %>% TukeyC(
  which = 'Lote:Sementes:Tempo',
  error = 'Within',
  fl1 = 5,
  fl2 = 2
)

tko6[["out"]][["Result"]] %>% kable

	Means	G1
ITAMARACA/50/11h	30.67	a
ITAMARACA/50/19h	29.18	a
ITAMARACA/50/17h	28.65	a
ITAMARACA/50/15h	27.90	a
ITAMARACA/50/13h	26.95	a
ITAMARACA/50/7h	26.49	a
ITAMARACA/50/9h	22.62	a

# library(easyanova)
# r2 = ea2(pss, design = 9)

Sementes/Tempo

25/Tempo

tkv1 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo',
  error = 'Within',
  fl1 = 1
)

tkv1[["out"]][["Result"]] %>% kable

	Means	G1
25/11h	19.82	a
25/19h	19.35	a
25/17h	19.02	a
25/15h	18.59	a
25/13h	18.05	a
25/7h	17.34	a
25/9h	16.98	a

50/Tempo

tkv2 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo',
  error = 'Within',
  fl1 = 2
)

tkv2[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/19h	36.76	a
50/17h	36.11	a	b
50/15h	35.09	a	b
50/11h	34.09	a	b
50/13h	34.02	a	b
50/7h	32.82		b
50/9h	27.94			c

Sementes/Tempo/Lote

25/Tempo/Lote

tkp1 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 1
)

tkp1[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
25/7h/UNA1	24.32	a
25/7h/UNA2	19.45	a	b
25/7h/BUERAREMA	16.09		b	c
25/7h/ITAMARACA	14.19		b	c
25/7h/ITAJUIPE	12.66			c

tkp2 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 2
)

tkp2[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
25/9h/UNA2	23.73	a
25/9h/UNA1	22.27	a	b
25/9h/BUERAREMA	14.47		b	c
25/9h/ITAMARACA	12.97			c
25/9h/ITAJUIPE	11.47			c

tkp3 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 3
)

tkp3[["out"]][["Result"]] %>% kable

	Means	G1
25/11h/UNA1	23.85	a
25/11h/UNA2	23.23	a
25/11h/BUERAREMA	19.57	a
25/11h/ITAMARACA	16.77	a
25/11h/ITAJUIPE	15.65	a

tkp4 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 4
)

tkp4[["out"]][["Result"]] %>% kable

	Means	G1	G2
25/13h/UNA1	25.60	a
25/13h/UNA2	19.52	a	b
25/13h/BUERAREMA	16.75		b
25/13h/ITAMARACA	14.60		b
25/13h/ITAJUIPE	13.80		b

tkp5 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 5
)

tkp5[["out"]][["Result"]] %>% kable

	Means	G1	G2
25/15h/UNA1	26.23	a
25/15h/UNA2	20.07	a	b
25/15h/BUERAREMA	17.40		b
25/15h/ITAMARACA	15.00		b
25/15h/ITAJUIPE	14.25		b

tkp6 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 6
)


tkp6[["out"]][["Result"]] %>% kable

	Means	G1	G2
25/17h/UNA1	26.62	a
25/17h/UNA2	20.52	a	b
25/17h/BUERAREMA	17.90		b
25/17h/ITAMARACA	15.43		b
25/17h/ITAJUIPE	14.62		b

tkp7 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 1,
  fl2 = 7
)


tkp7[["out"]][["Result"]] %>% kable

	Means	G1	G2
25/19h/UNA1	27.00	a
25/19h/UNA2	21.00	a	b
25/19h/BUERAREMA	18.18		b
25/19h/ITAMARACA	15.73		b
25/19h/ITAJUIPE	14.85		b

50/Tempo/Lote

tkm1 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 1
)

tkm1[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/7h/UNA1	44.60	a
50/7h/UNA2	32.69		b
50/7h/BUERAREMA	31.43		b	c
50/7h/ITAJUIPE	28.91		b	c
50/7h/ITAMARACA	26.49			c

tkm2 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 2
)

tkm2[["out"]][["Result"]] %>% kable

	Means	G1	G2
50/9h/UNA1	40.60	a
50/9h/BUERAREMA	26.60		b
50/9h/UNA2	25.52		b
50/9h/ITAJUIPE	24.32		b
50/9h/ITAMARACA	22.62		b

tkm3 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 3
)

tkm3[["out"]][["Result"]] %>% kable

	Means	G1	G2
50/11h/UNA1	42.88	a
50/11h/BUERAREMA	34.17		b
50/11h/ITAJUIPE	32.83		b
50/11h/ITAMARACA	30.67		b
50/11h/UNA2	29.88		b

tkm4 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 4
)

tkm4[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/13h/UNA1	46.35	a
50/13h/UNA2	36.73		b
50/13h/BUERAREMA	31.30		b	c
50/13h/ITAJUIPE	28.75		b	c
50/13h/ITAMARACA	26.95			c

tkm5 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 5
)

tkm5[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/15h/UNA1	47.30	a
50/15h/UNA2	38.23		b
50/15h/BUERAREMA	32.35		b	c
50/15h/ITAJUIPE	29.70			c
50/15h/ITAMARACA	27.90			c

tkm6 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 6
)

tkm6[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/17h/UNA1	48.65	a
50/17h/UNA2	39.20		b
50/17h/BUERAREMA	33.35		b	c
50/17h/ITAJUIPE	30.68			c
50/17h/ITAMARACA	28.65			c

tkm7 <- AOV %>% TukeyC(
  which = 'Sementes:Tempo:Lote',
  error = 'Within',
  fl1 = 2,
  fl2 = 7
)

tkm7[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
50/19h/UNA1	49.88	a
50/19h/UNA2	40.02		b
50/19h/BUERAREMA	33.27		b	c
50/19h/ITAJUIPE	31.45			c
50/19h/ITAMARACA	29.18			c

######################################################

Resultados

ANOVA

Germinação

ger <- read_excel("CEjeni.xlsx", sheet = "ger")
ger$lote <- ger$lote %>% factor(.,c("UNA1","UNA2", "BUERAREMA",  "ITAJUIPE" ,  "ITAMARACA")) 
ger <- ger[order(ger$lote),]

av <- aov(ger_per ~ lote, ger)

anova(av) %>% kable

	Df	Sum Sq	Mean Sq	F value	Pr(>F)
lote	4	3891.2	972.8000	9.306122	0.0005484
Residuals	15	1568.0	104.5333

cv(av) %>% kable

	x
cv	17.27

boxplot(ger_per ~ lote,
        ger,
        col = cor,
        xlab = "Lote",
        ylab = 'Germinação (%)')

tk <- TukeyC(av)

tk[["out"]][["Result"]] %>% kable

	Means	G1	G2
ITAMARACA	75.00	a
ITAJUIPE	73.00	a
BUERAREMA	62.00	a	b
UNA1	43.00		b
UNA2	43.00		b

######################################################

Resultados

ANOVA

Emergência

emer <- read_excel("CEjeni.xlsx", sheet = "emer")

emer %<>% gather(lote_r,
                value, -DIAS,
                na.rm = TRUE)


emer %>% separate(lote_r,c("lote","r")) -> emer
names(emer)[1] <- "dias"

emer$lote <- emer$lote %>% factor(.,c("UNA1","UNA2", "BUERAREMA",  "ITAJUIPE" ,  "ITAMARACA")) 
emer <- emer[order(emer$lote),]
#emer$value[emer$value == 0] <- NA



av <- aov(value ~ lote,emer)



anova(av) %>% kable

	Df	Sum Sq	Mean Sq	F value	Pr(>F)
lote	4	4966.48	1241.62000	18.56908	0
Residuals	795	53157.60	66.86491

cv(av) %>% kable

	x
cv	118

boxplot(value ~ lote,
        emer,
        col = cor,
        xlab = "Lote",
        ylab = 'Emergência (%)')

tk <- TukeyC(av)

tk[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
BUERAREMA	10.08	a
UNA1	7.93	a	b
UNA2	7.23		b
ITAJUIPE	6.98		b
ITAMARACA	2.45			c

emer %>% ggplot(aes(x=dias, y=value, fill=lote)) +
  geom_bar(stat = "identity") +
  xlab('Dias') + ylab('Emergência (%)')+
  theme_bw() +
  scale_fill_manual(values=cor, name="Lote")+
  theme(
    text = element_text(size = 10),
    axis.text.y = element_text(
      angle = 90,
      hjust = 1,
      colour = "black"
    ),
    axis.text.x = element_text(
      angle = 45,
      hjust = 1,
      colour = "black"
    )
  ) + facet_wrap(~lote)

#####################

######################################################

Resultados

ANOVA

T50

t50 <- read_excel("CEjeni.xlsx", sheet = "T50")


t50 %<>% gather(lote_r,
                 value, -DIAS,
                 na.rm = TRUE)


t50 %>% separate(lote_r,c("lote","r")) -> t50
names(t50)[1] <- "dias"

t50$lote <- t50$lote %>% factor(.,c("UNA1","UNA2", "BUERAREMA",  "ITAJUIPE" ,  "ITAMARACA")) 
t50 <- t50[order(t50$lote),]
#emer$value[emer$value == 0] <- NA






av <- aov(value ~ lote,t50)
anova(av) %>% kable

	Df	Sum Sq	Mean Sq	F value	Pr(>F)
lote	4	5395.58	1348.89500	32.55088	0
Residuals	795	32944.47	41.43958

cv(av) %>% kable

	x
cv	65.86

boxplot(value ~ lote,
        t50,
        col = cor,
        xlab = "Lote",
        ylab = 'T50')

tk <- TukeyC(av)

tk[["out"]][["Result"]] %>% kable

	Means	G1	G2	G3
ITAMARACA	13.24	a
BUERAREMA	11.66	a	b
ITAJUIPE	10.38		b
UNA2	6.86			c
UNA1	6.73			c

######################################################

Outros gráficos

names(t50)[4] <- "t50"
names(emer)[4] <- "emer"

df <- merge(t50,emer)

sum_my_rise <- function(x, num_var, ...){
  group_var <- quos(...)
  num_var <- enquo(num_var)
  x %>%
    group_by(!!!group_var) %>%
    summarize(mean = mean(!!num_var), n = n(), 
              min = min(!!num_var),
              max = max(!!num_var),
              sd = sd(!!num_var), se = sd/sqrt(n),
              sum = sum(!!num_var))
}

library(emmeans)


a1 <- aov(t50 ~ lote, data=df)
leastsquare = emmeans(a1,
                      pairwise ~ lote,
                      adjust="tukey")
tkp<-multcomp::cld(leastsquare$emmeans,
                   alpha=0.05,
                   Letters=letters,
                   reversed=T,
                   adjust="tukey") 
ww <- sum_my_rise(df, t50,lote)
ok <- merge(tkp,ww)
pd = position_dodge(1)
p <- ggplot(data = ok, aes(x = lote, y = mean, fill = lote, label=.group)) + 
  theme_minimal() 
p <- p + geom_bar(stat = "identity", position = "dodge") + 
  labs(y = "T50", x = "",
       title = "") +
  geom_text(position = pd, vjust=-0.5, hjust=2) +
  scale_fill_manual(values=cor, name="Lote")+
geom_errorbar(aes(ymin  = mean - se,
                  ymax  = mean + se),
              width = 0.2,
              size  = 0.7,
              position = pd,
              color = "black") +
  theme(
    text = element_text(size = 10),
    axis.text.y = element_text(
      angle = 90,
      hjust = 1,
      colour = "black"),
    axis.text.x = element_text(
      angle = 45,
      hjust = 1,
      colour = "black"
    ))
p

#######################

df$emer <- df$emer/100

a1 <- aov(emer ~ lote, data=df)
leastsquare = emmeans(a1,
                      pairwise ~ lote,
                      adjust="tukey")
tkp<-multcomp::cld(leastsquare$emmeans,
                   alpha=0.05,
                   Letters=letters,
                   reversed=T,
                   adjust="tukey") 
ww <- sum_my_rise(df, emer,lote)
ok <- merge(tkp,ww)
pd = position_dodge(1)
p <- ggplot(data = ok, aes(x = lote, y = mean, fill = lote, label=.group)) + 
  theme_minimal() 
p <- p + geom_bar(stat = "identity", position = "dodge") + 
  labs(y = "Emergência (%)", x = "",
       title = "") +
  scale_y_continuous(labels = scales::percent_format(accuracy = 1))+
  geom_text(position = pd, vjust=-0.5, hjust=2) +
  scale_fill_manual(values=cor, name="Lote")+
  geom_errorbar(aes(ymin  = mean - se,
                    ymax  = mean + se),
                width = 0.2,
                size  = 0.7,
                position = pd,
                color = "black") +
  theme(
    text = element_text(size = 10),
    axis.text.y = element_text(
      angle = 90,
      hjust = 1,
      colour = "black"),
    axis.text.x = element_text(
      angle = 45,
      hjust = 1,
      colour = "black"
    ))
p

#######################################

ger <- read_excel("CEjeni.xlsx", sheet = "ger")
ger$lote <- ger$lote %>% factor(.,c("UNA1","UNA2", "BUERAREMA",  "ITAJUIPE" ,  "ITAMARACA")) 
ger <- ger[order(ger$lote),]

ger$ger_per <- ger$ger_per/100

a1 <- aov(ger_per ~ lote, data=ger)
leastsquare = emmeans(a1,
                      pairwise ~ lote,
                      adjust="tukey")
tkp<-multcomp::cld(leastsquare$emmeans,
                   alpha=0.05,
                   Letters=letters,
                   reversed=T,
                   adjust="tukey") 
ww <- sum_my_rise(ger, ger_per,lote)
ok <- merge(tkp,ww)
pd = position_dodge(1)


p <- ggplot(data = ok, aes(x = lote, y = mean, fill = lote, label=.group)) + 
  theme_minimal() 
p <- p + geom_bar(stat = "identity", position = "dodge") + 
  labs(y = "Germinação (%)", x = "",
       title = "") +
  scale_y_continuous(labels = scales::percent_format(accuracy = 1))+
  geom_text(position = pd, vjust=-0.5, hjust=2) +
  scale_fill_manual(values=cor, name="Lote")+
  geom_errorbar(aes(ymin  = mean - se,
                    ymax  = mean + se),
                width = 0.2,
                size  = 0.7,
                position = pd,
                color = "black") +
  theme(
    text = element_text(size = 10),
    axis.text.y = element_text(
      angle = 90,
      hjust = 1,
      colour = "black"),
    axis.text.x = element_text(
      angle = 45,
      hjust = 1,
      colour = "black"
    ))
p

Análise de Dados Dandara

Cid Edson Póvoas

2020-05-22