Fincas
Pedro González
2024-04-12
pacman::p_load(pacman,dplyr,GGally,ggplot2,ggthemes,ggvis,httr,lubridate,plotly,rio,rmarkdown,shiny,stringr,tidyr,tidyverse,lattice,caret,pls,MASS,yarrr,psych,ggcorrplot,GGally,CCA,CCP,rpart,rpart.plot,ggrepel)library(tidyverse)
library(rpart)
library(rpart.plot)
library(caret)
library(rio)
library(stats)df<-import("CafesFincasTMod.xlsx")
df## Finca Dias T Puntaje pH Brix Acidez_T cafeina ACQA
## 1 Corpachi 3 20.0 86.63 5.013333 1.200000 0.01552704 676.8915 412.7191
## 2 Corpachi 5 20.0 86.88 5.023333 1.270000 0.01522152 639.2415 432.7061
## 3 Corpachi 7 20.0 87.19 4.953333 1.070000 0.01521936 613.4221 395.6890
## 4 Corpachi 3 24.0 86.28 5.076667 1.200000 0.01318979 705.0421 426.3423
## 5 Corpachi 5 24.0 87.09 5.026667 2.000000 0.01250129 665.7463 347.7119
## 6 Corpachi 7 24.0 85.79 4.976667 1.930000 0.01251373 684.4820 432.7155
## 7 Corpachi 3 30.0 86.32 5.013333 2.000000 0.01387144 737.6643 490.8567
## 8 Corpachi 5 30.0 86.21 4.900833 1.933333 0.01382723 644.5686 444.3011
## 9 Corpachi 7 30.0 86.61 4.973333 2.000000 0.01487416 665.9543 794.6219
## 10 Lamastus 3 24.0 88.56 5.126667 1.666667 0.01486505 642.1583 358.4777
## 11 Lamastus 5 24.0 89.22 5.120000 1.733333 0.01487919 687.7630 387.1427
## 12 Lamastus 7 24.0 88.92 5.133333 1.733333 0.01759923 754.7001 455.3662
## 13 Lamastus 3 17.4 88.67 5.156667 1.533333 0.01385646 593.4005 337.9377
## 14 Lamastus 5 17.4 89.06 5.116667 1.600000 0.01283884 666.6153 365.9894
## 15 Lamastus 7 17.4 88.78 5.140000 1.866667 0.01522806 698.9411 424.4354
## 16 Lamastus 3 30.0 89.17 5.136667 1.666667 0.01351684 707.1914 395.0926
## 17 Lamastus 5 30.0 89.06 5.126667 1.800000 0.01792097 728.4771 445.4386
## 18 Lamastus 7 30.0 89.22 5.136667 1.600000 0.01655830 663.1918 427.2639
## 19 Nuguo 3 24.0 88.64 4.803333 1.666667 0.01418219 637.0126 962.5415
## 20 Nuguo 5 24.0 88.83 4.717083 1.400000 0.01455186 545.7977 722.3411
## 21 Nuguo 7 24.0 88.89 4.810000 1.466667 0.01354944 557.9616 545.4887
## 22 Nuguo 3 16.8 88.75 4.813333 2.000000 0.01628978 713.2795 1079.2788
## 23 Nuguo 5 16.8 88.64 4.793333 1.600000 0.01628978 603.5466 936.4135
## 24 Nuguo 7 16.8 88.86 4.816667 1.600000 0.01628978 638.5900 822.7184
## 25 Nuguo 3 30.0 88.83 4.756667 1.000000 0.01187095 496.6943 665.4603
## 26 Nuguo 5 30.0 89.36 4.773333 1.200000 0.01454032 621.4622 352.6826
## 27 Nuguo 7 30.0 89.44 4.773333 1.000000 0.01375357 549.8571 335.5529
## 28 Hartman 3 22.0 89.44 5.123333 1.466667 0.01253475 616.1912 334.2410
## 29 Hartman 5 22.0 88.17 5.146667 1.733333 0.01352358 698.7151 340.8357
## 30 Hartman 7 22.0 89.31 5.123333 1.600000 0.01624853 660.3540 312.9145
## 31 Hartman 3 24.0 89.06 5.106667 1.533333 0.01318423 634.0289 349.6764
## 32 Hartman 5 24.0 89.14 5.113333 1.466667 0.01624368 638.4986 339.9476
## 33 Hartman 7 24.0 88.86 5.120000 1.533333 0.01442571 602.5066 393.0651
## 34 Hartman 3 30.0 88.81 5.126667 1.600000 0.01488552 634.9193 382.7102
## 35 Hartman 5 30.0 88.58 5.113333 1.466667 0.01284032 565.5702 342.1963
## 36 Hartman 7 30.0 88.72 5.110000 1.800000 0.01487284 652.2148 356.7956
## CCQA BCQA Polifenoles DPPH ABTS Altitud
## 1 692.0006 397.6602 2605.202 9.558333 9.272007 1375
## 2 751.4449 431.4551 2655.128 8.116667 8.922589 1375
## 3 714.3046 401.5600 2419.110 8.341667 9.428944 1375
## 4 796.3562 452.5129 2523.502 7.916667 9.850906 1375
## 5 530.6221 316.1868 2512.155 8.191667 9.682600 1375
## 6 867.3671 471.4100 2646.050 8.408333 9.369725 1375
## 7 982.9008 544.0083 2861.355 8.258333 8.848266 1375
## 8 887.8658 493.3681 2514.427 7.450000 9.074013 1375
## 9 613.9056 563.8531 2394.150 6.941667 9.598452 1375
## 10 791.6082 400.7497 2398.688 6.533333 11.485583 1725
## 11 839.1843 435.6342 2600.663 8.950000 10.424579 1725
## 12 1011.9601 515.0036 2859.372 9.091667 12.159479 1725
## 13 818.8040 388.6442 2162.672 7.875000 10.441773 1725
## 14 814.6953 422.3483 2385.072 8.966667 10.525564 1725
## 15 934.7048 469.6386 2564.352 8.483333 10.658000 1725
## 16 861.2222 445.8483 2416.843 7.225000 10.287493 1725
## 17 1021.1566 483.3067 2301.103 8.441667 11.028307 1725
## 18 970.3016 492.1124 2455.422 8.166667 9.828609 1725
## 19 1438.7022 799.8410 2382.803 7.275000 8.802599 1850
## 20 1273.0713 668.2987 2051.472 6.416667 8.034790 1850
## 21 1150.4129 579.1414 2115.015 6.366667 8.212699 1850
## 22 2364.1469 1154.8671 2802.638 8.475000 11.703458 1850
## 23 1707.4406 881.4282 2357.838 6.533333 9.865311 1850
## 24 1955.6328 965.0719 2559.813 6.641667 9.656431 1850
## 25 1093.1416 584.1859 1972.043 6.191667 8.563113 1850
## 26 808.2782 399.2524 2257.983 7.358333 9.521237 1850
## 27 703.9463 363.8275 1997.005 6.983333 7.875763 1850
## 28 778.5748 383.9267 2112.743 6.166667 11.198028 1800
## 29 777.0782 393.8884 2169.478 7.083333 11.367056 1800
## 30 709.6745 351.0742 2455.422 7.766667 12.571379 1800
## 31 805.8314 399.1329 2407.765 7.825000 11.345927 1800
## 32 787.0173 383.5201 2382.800 7.475000 11.895268 1800
## 33 861.9407 425.5310 2267.063 7.091667 10.517353 1800
## 34 832.5573 432.7403 2498.540 8.000000 9.151861 1800
## 35 799.2656 390.4530 2205.788 5.208333 8.752717 1800
## 36 824.1285 402.3845 2484.923 6.058333 8.689695 1800Pretratamiento de los datos
- Se tomaron 3 niveles de temperatura: 1) Finca_T, 2) T24, 3) T30
- El tiempo en días se bloqueo en 3 niveles: 3,5,7
- La alitud en m se bloqueo en 2 niveles: 1) H1=Altitud<1700 2) H2=Altitud>=1700
Cada uno de estos parámetros se convirtió al tipo factor
df <- df %>% filter(Dias>0)
df0<- df %>% mutate(Temp=ifelse(T<24,"Finca_T",ifelse(T==24.0,"T24","T30")),Altura=ifelse(Altitud<1700,"H1","H2"))
df0$Finca<-factor(df0$Finca)
df0$Tiempo<-factor(df0$Dias)
df0$Altura<-factor(df0$Altura)
df0$Temp<-factor(df0$Temp)df3<-df0 %>% filter(Dias>=2)
boxplot(Puntaje~Finca,data=df0,col=c("blue","orange","red","green"))
library(stats)
#modelo<-lm(Puntaje~Temp+Altitud+Tiempo+Brix,data=df0)
modelo<-lm(Puntaje~T+Altitud+Dias+Brix,data=df)
summary(modelo)##
## Call:
## lm(formula = Puntaje ~ T + Altitud + Dias + Brix, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.87854 -0.39225 -0.00819 0.33329 0.72275
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 79.5015449 0.9878009 80.483 < 2e-16 ***
## T 0.0034453 0.0162057 0.213 0.833
## Altitud 0.0052903 0.0004095 12.918 5.12e-14 ***
## Dias 0.0328103 0.0461337 0.711 0.482
## Brix -0.2173427 0.2745752 -0.792 0.435
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4505 on 31 degrees of freedom
## Multiple R-squared: 0.85, Adjusted R-squared: 0.8307
## F-statistic: 43.92 on 4 and 31 DF, p-value: 2.402e-12PRUEBAS DE NORMALIDAD
qqnorm(modelo$residuals)
qqline(modelo$residuals,col="blue")
plot(modelo$fitted.values,df0$Puntaje,xlim=c(85,90),ylim=c(85,90))
abline(0,1,col="blue")
Prueba de Normalidad Shapiro-Wilks
shapiro.test(modelo$residuals)##
## Shapiro-Wilk normality test
##
## data: modelo$residuals
## W = 0.96513, p-value = 0.3078El p-value>0.05 indica que podemos asumir que la distribución de los datos no es significativamente diferente a la distribución normal. En otras palabras los datos siguen una distribución normal
Efecto del Tiempo de Fermentación a diferentes temperaturas sobre el puntaje del café
library(ggrepel)
library(ggplot2)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(Puntaje=mean(Puntaje))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo Puntaje
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 86.6
## 2 H1 Finca_T 5 86.9
## 3 H1 Finca_T 7 87.2
## 4 H1 T24 3 86.3
## 5 H1 T24 5 87.1
## 6 H1 T24 7 85.8
## 7 H1 T30 3 86.3
## 8 H1 T30 5 86.2
## 9 H1 T30 7 86.6
## 10 H2 Finca_T 3 89.0
## 11 H2 Finca_T 5 88.6
## 12 H2 Finca_T 7 89.0
## 13 H2 T24 3 88.8
## 14 H2 T24 5 89.1
## 15 H2 T24 7 88.9
## 16 H2 T30 3 88.9
## 17 H2 T30 5 89
## 18 H2 T30 7 89.1g = df1 %>% ggplot() + aes(x = Tiempo, y = Puntaje, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="Puntaje")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(cafeina=mean(cafeina))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo cafeina
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 677.
## 2 H1 Finca_T 5 639.
## 3 H1 Finca_T 7 613.
## 4 H1 T24 3 705.
## 5 H1 T24 5 666.
## 6 H1 T24 7 684.
## 7 H1 T30 3 738.
## 8 H1 T30 5 645.
## 9 H1 T30 7 666.
## 10 H2 Finca_T 3 641.
## 11 H2 Finca_T 5 656.
## 12 H2 Finca_T 7 666.
## 13 H2 T24 3 638.
## 14 H2 T24 5 624.
## 15 H2 T24 7 638.
## 16 H2 T30 3 613.
## 17 H2 T30 5 639.
## 18 H2 T30 7 622.g = df1 %>% ggplot() + aes(x = Tiempo, y = cafeina, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="Cafeina")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(Brix=mean(Brix))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo Brix
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 1.2
## 2 H1 Finca_T 5 1.27
## 3 H1 Finca_T 7 1.07
## 4 H1 T24 3 1.2
## 5 H1 T24 5 2
## 6 H1 T24 7 1.93
## 7 H1 T30 3 2
## 8 H1 T30 5 1.93
## 9 H1 T30 7 2
## 10 H2 Finca_T 3 1.67
## 11 H2 Finca_T 5 1.64
## 12 H2 Finca_T 7 1.69
## 13 H2 T24 3 1.62
## 14 H2 T24 5 1.53
## 15 H2 T24 7 1.58
## 16 H2 T30 3 1.42
## 17 H2 T30 5 1.49
## 18 H2 T30 7 1.47g = df1 %>% ggplot() + aes(x = Tiempo, y = Brix, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="Brix")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(pH=mean(pH))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo pH
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 5.01
## 2 H1 Finca_T 5 5.02
## 3 H1 Finca_T 7 4.95
## 4 H1 T24 3 5.08
## 5 H1 T24 5 5.03
## 6 H1 T24 7 4.98
## 7 H1 T30 3 5.01
## 8 H1 T30 5 4.90
## 9 H1 T30 7 4.97
## 10 H2 Finca_T 3 5.03
## 11 H2 Finca_T 5 5.02
## 12 H2 Finca_T 7 5.03
## 13 H2 T24 3 5.01
## 14 H2 T24 5 4.98
## 15 H2 T24 7 5.02
## 16 H2 T30 3 5.01
## 17 H2 T30 5 5.00
## 18 H2 T30 7 5.01g = df1 %>% ggplot() + aes(x = Tiempo, y = pH, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="pH")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(Acidez=mean(Acidez_T))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo Acidez
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 0.0155
## 2 H1 Finca_T 5 0.0152
## 3 H1 Finca_T 7 0.0152
## 4 H1 T24 3 0.0132
## 5 H1 T24 5 0.0125
## 6 H1 T24 7 0.0125
## 7 H1 T30 3 0.0139
## 8 H1 T30 5 0.0138
## 9 H1 T30 7 0.0149
## 10 H2 Finca_T 3 0.0142
## 11 H2 Finca_T 5 0.0142
## 12 H2 Finca_T 7 0.0159
## 13 H2 T24 3 0.0141
## 14 H2 T24 5 0.0152
## 15 H2 T24 7 0.0152
## 16 H2 T30 3 0.0134
## 17 H2 T30 5 0.0151
## 18 H2 T30 7 0.0151g = df1 %>% ggplot() + aes(x = Tiempo, y = Acidez, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="Acidez")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(ABTS=mean(ABTS))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo ABTS
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 9.27
## 2 H1 Finca_T 5 8.92
## 3 H1 Finca_T 7 9.43
## 4 H1 T24 3 9.85
## 5 H1 T24 5 9.68
## 6 H1 T24 7 9.37
## 7 H1 T30 3 8.85
## 8 H1 T30 5 9.07
## 9 H1 T30 7 9.60
## 10 H2 Finca_T 3 11.1
## 11 H2 Finca_T 5 10.6
## 12 H2 Finca_T 7 11.0
## 13 H2 T24 3 10.5
## 14 H2 T24 5 10.1
## 15 H2 T24 7 10.3
## 16 H2 T30 3 9.33
## 17 H2 T30 5 9.77
## 18 H2 T30 7 8.80g = df1 %>% ggplot() + aes(x = Tiempo, y = ABTS, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="ABTS")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(CCQA=mean(CCQA))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo CCQA
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 692.
## 2 H1 Finca_T 5 751.
## 3 H1 Finca_T 7 714.
## 4 H1 T24 3 796.
## 5 H1 T24 5 531.
## 6 H1 T24 7 867.
## 7 H1 T30 3 983.
## 8 H1 T30 5 888.
## 9 H1 T30 7 614.
## 10 H2 Finca_T 3 1321.
## 11 H2 Finca_T 5 1100.
## 12 H2 Finca_T 7 1200.
## 13 H2 T24 3 1012.
## 14 H2 T24 5 966.
## 15 H2 T24 7 1008.
## 16 H2 T30 3 929.
## 17 H2 T30 5 876.
## 18 H2 T30 7 833.g = df1 %>% ggplot() + aes(x = Tiempo, y = CCQA, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="CCQA")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(DPPH=mean(DPPH))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo DPPH
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 9.56
## 2 H1 Finca_T 5 8.12
## 3 H1 Finca_T 7 8.34
## 4 H1 T24 3 7.92
## 5 H1 T24 5 8.19
## 6 H1 T24 7 8.41
## 7 H1 T30 3 8.26
## 8 H1 T30 5 7.45
## 9 H1 T30 7 6.94
## 10 H2 Finca_T 3 7.51
## 11 H2 Finca_T 5 7.53
## 12 H2 Finca_T 7 7.63
## 13 H2 T24 3 7.21
## 14 H2 T24 5 7.61
## 15 H2 T24 7 7.52
## 16 H2 T30 3 7.14
## 17 H2 T30 5 7.00
## 18 H2 T30 7 7.07g = df1 %>% ggplot() + aes(x = Tiempo, y = DPPH, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="DPPH")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)
df1<- df0 %>% group_by(Altura,Temp,Tiempo) %>% summarize(Polifenoles=mean(Polifenoles))## `summarise()` has grouped output by 'Altura', 'Temp'. You can override using
## the `.groups` argument.df1## # A tibble: 18 × 4
## # Groups: Altura, Temp [6]
## Altura Temp Tiempo Polifenoles
## <fct> <fct> <fct> <dbl>
## 1 H1 Finca_T 3 2605.
## 2 H1 Finca_T 5 2655.
## 3 H1 Finca_T 7 2419.
## 4 H1 T24 3 2524.
## 5 H1 T24 5 2512.
## 6 H1 T24 7 2646.
## 7 H1 T30 3 2861.
## 8 H1 T30 5 2514.
## 9 H1 T30 7 2394.
## 10 H2 Finca_T 3 2359.
## 11 H2 Finca_T 5 2304.
## 12 H2 Finca_T 7 2527.
## 13 H2 T24 3 2396.
## 14 H2 T24 5 2345.
## 15 H2 T24 7 2414.
## 16 H2 T30 3 2296.
## 17 H2 T30 5 2255.
## 18 H2 T30 7 2312.g = df1 %>% ggplot() + aes(x = Tiempo, y = Polifenoles, color = Altura) + geom_line(aes(group = Altura)) +geom_point()
g +labs(x="Tiempo de Fermentación",y="Polifenoles")+scale_color_manual(values=c("orange", "blue")) +facet_wrap(~Temp)