library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
India_Menu <- read_csv("India_Menu.csv")
## Rows: 141 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Menu Category, Menu Items, Per Serve Size
## dbl (10): Energy (kCal), Protein (g), Total fat (g), Sat Fat (g), Trans fat ...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
DT::datatable(India_Menu)
db1<-India_Menu %>% select_if(is.numeric)
db1
## # A tibble: 141 × 10
## `Energy (kCal)` `Protein (g)` `Total fat (g)` `Sat Fat (g)` `Trans fat (g)`
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 402. 10.2 13.8 5.34 0.16
## 2 340. 8.5 11.3 4.27 0.2
## 3 653. 20.3 39.4 17.1 0.18
## 4 675. 21.0 39.1 19.7 0.26
## 5 512. 15.3 23.4 10.5 0.17
## 6 833. 24.2 37.9 16.8 0.28
## 7 356. 7.91 15.1 6.11 0.24
## 8 228. 5.45 11.4 5.72 0.09
## 9 401. 15.7 15.7 5.47 0.16
## 10 348. 15.4 14.2 5.79 0.21
## # … with 131 more rows, and 5 more variables: `Cholesterols (mg)` <dbl>,
## # `Total carbohydrate (g)` <dbl>, `Total Sugars (g)` <dbl>,
## # `Added Sugars (g)` <dbl>, `Sodium (mg)` <dbl>
db1$`Sodium (mg)`[is.na(db1$`Sodium (mg)`)] <- 152.025
db1
## # A tibble: 141 × 10
## `Energy (kCal)` `Protein (g)` `Total fat (g)` `Sat Fat (g)` `Trans fat (g)`
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 402. 10.2 13.8 5.34 0.16
## 2 340. 8.5 11.3 4.27 0.2
## 3 653. 20.3 39.4 17.1 0.18
## 4 675. 21.0 39.1 19.7 0.26
## 5 512. 15.3 23.4 10.5 0.17
## 6 833. 24.2 37.9 16.8 0.28
## 7 356. 7.91 15.1 6.11 0.24
## 8 228. 5.45 11.4 5.72 0.09
## 9 401. 15.7 15.7 5.47 0.16
## 10 348. 15.4 14.2 5.79 0.21
## # … with 131 more rows, and 5 more variables: `Cholesterols (mg)` <dbl>,
## # `Total carbohydrate (g)` <dbl>, `Total Sugars (g)` <dbl>,
## # `Added Sugars (g)` <dbl>, `Sodium (mg)` <dbl>
install.packages("psych")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)
library(psych)
corPlot(db1)
sumax=sum(db1$`Protein (g)`)
sumax
## [1] 1056.59
sumay=sum(db1$`Sodium (mg)`)
sumay
## [1] 50841
n=length(db1$`Protein (g)`)
n
## [1] 141
xpory = db1$`Protein (g)`*db1$`Sodium (mg)`
xpory
## [1] 7230.7712 4635.3900 21803.2282 22793.1616 16083.9720 36961.2474
## [7] 4584.6360 2129.5330 12000.7278 8191.5376 19926.0392 27357.5012
## [13] 63060.1400 22974.3670 4741.5456 2329.1226 9435.9795 4908.7489
## [19] 64570.2759 15144.5137 3141.8975 7066.8448 15900.5136 4853.3274
## [25] 10923.5658 30339.2615 517.6470 1038.4241 2070.5204 1415.0668
## [31] 2653.4144 5085.3855 0.0000 14.0000 1606.7673 1142.0416
## [37] 8223.3186 5967.8610 8888.6640 12067.2500 18058.7384 7296.3055
## [43] 5295.3640 531.2518 0.1664 54.4445 0.1664 0.5358
## [49] 0.7085 544.1478 1136.0196 1629.6806 771.8080 1222.9490
## [55] 1842.1104 998.1504 1605.5928 2184.0640 949.8060 1514.5453
## [61] 2274.8992 373.2228 1125.3233 1594.5930 3009.5835 419.9220
## [67] 482.6862 7.7504 10.8042 20.5842 4.9335 7.0760
## [73] 13.4420 6.8338 9.6264 18.5328 2.7702 2.3328
## [79] 2.3064 341.6060 940.8714 1280.9268 2005.5780 513.6899
## [85] 742.3936 274.2945 306.5931 14.3752 3.8112 4.6340
## [91] 225.2725 1053.0891 81.1522 139.0501 147.5100 385.2611
## [97] 53.1454 98.9740 322.8480 680.7600 336.3934 1020.0440
## [103] 165.4965 540.2220 34108.4331 22945.2358 17298.3101 47761.7448
## [109] 75240.4769 50852.5712 32467.7628 3896.4007 14015.5533 3630.8816
## [115] 8169.4200 0.0000 0.0000 0.0000 0.0000 0.0000
## [121] 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
## [127] 0.0000 67.6856 101.2472 71.5768 0.0000 0.0000
## [133] 115.0864 29.4398 1.9572 211.5021 5.6840 0.0000
## [139] 547.5870 0.0588 7.0200
sumxpory = sum(xpory)
sumxpory
## [1] 872025.6
Sxy=sumxpory-(sumax*sumay)/n
Sxy
## [1] 491046.2
xalcuadrado=db1$`Protein (g)`*db1$`Protein (g)`
x_alcuadrado=sum(xalcuadrado)
x_alcuadrado
## [1] 17648.07
yalcuadrado=db1$`Sodium (mg)`*db1$`Sodium (mg)`
y_alcuadrado=sum(yalcuadrado)
y_alcuadrado
## [1] 49495212
Sxx= x_alcuadrado-sumax^2/n
Sxx
## [1] 9730.46
Syy= y_alcuadrado-sumay^2/n
Syy
## [1] 31163242
pendiente = Sxy/Sxx
pendiente
## [1] 50.46485
SSR=pendiente*Sxy
SSR
## [1] 24780573
SSE=Syy-SSR
SSE
## [1] 6382669
VarError=SSE/(n-2)
VarError
## [1] 45918.48
VarPend=VarError/Sxx
VarPend
## [1] 4.719045
VarInter=VarError*x_alcuadrado/(n*Sxx)
VarInter
## [1] 590.6526
regresion <- lm(`Sodium (mg)` ~ `Protein (g)`, data = db1)
summary(regresion)
##
## Call:
## lm(formula = `Sodium (mg)` ~ `Protein (g)`, data = db1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1123.80 -61.84 1.98 73.12 1059.07
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -17.586 24.303 -0.724 0.471
## `Protein (g)` 50.465 2.172 23.231 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 214.3 on 139 degrees of freedom
## Multiple R-squared: 0.7952, Adjusted R-squared: 0.7937
## F-statistic: 539.7 on 1 and 139 DF, p-value: < 2.2e-16
##si el p valor es menor a 0,05 se rechaza la hipotesis nula y se acepta la alternativa.
##Ho=0 (no hay efecto) Ha =! 0 (si hay efecto)
install.packages("ggplot2")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)
library(ggplot2)
##
## Attaching package: 'ggplot2'
##
## The following objects are masked from 'package:psych':
##
## %+%, alpha
library(ggpubr)
ggplot(db1, aes(x =`Protein (g)`, y =`Sodium (mg)`, color=`Protein (g)`)) +
geom_point(color=7) +
ggtitle("Proteina(g) vs Sodium(mg)")+
xlab("Proteina(g)")+
ylab("Sodium(mg)")+
geom_smooth(method = "lm",se=T,col="green")+
stat_regline_equation(label.y = 2000)+
stat_cor(label.y = 1500)
## `geom_smooth()` using formula 'y ~ x'
