#PREGUNTAS
#Con los datos de huatabampo (CONAGUA, 2017) en R
#Estæ¼ã¸± relacionada la salinidad con el PH?
#A mæ¼ã¸±s profundidad mæ¼ã¸±s salinidad?
#Represente los datos categorizados por mæ¼ã¸³dulo en græ¼ã¸±ficos
#Haga un muestreo por conglomerados por mæ¼ã¸³dulo
#Los datos de temperatura son normales?
library(readxl)
Huatabampo <- read_excel("Huatabampo.xlsx")
View(Huatabampo)
library(ggplot2)
library(PerformanceAnalytics)
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Registered S3 method overwritten by 'xts':
## method from
## as.zoo.xts zoo
##
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
##
## legend
conagua <- (Huatabampo)
conagua
## # A tibble: 293 x 10
## MODULO POZO X Y SNM DELNF CE PPM PH TEMP
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 1 620903 2962392 3.91 2.68 2.83 1811. 6.8 28.5
## 2 1 2 620915 2963671 4.53 2.61 8.35 5344 6.9 29.2
## 3 1 3 620943 2964903 2.80 1.3 8.66 5542. 6.8 28.9
## 4 1 4 620879 2965667 3.64 2.14 8.34 5338. 7.1 29.4
## 5 1 5 620888 2966604 3.49 2.01 9.18 5875. 6.6 28.3
## 6 1 6 621213 2968060 4.81 2 7.9 5056 6.8 28.4
## 7 1 7 620752 2968945 4.18 1.63 9.64 6170. 6.5 28
## 8 1 8 620860 2969749 5.61 2.82 7.17 4589. 6.9 27.5
## 9 1 9 620553 2970660 6.70 3 1.88 1203. 7 28.7
## 10 1 10 621817 2970654 5.94 3 1.93 1235. 7 28.6
## # ... with 283 more rows
#Se agrego una nueva columna con numero para que fuese mæ¼ã¸±s facil muestrearlos.
Huatabampo$id=1:nrow(conagua)
#Observando la grafica de "pairs" y el test de correlacion nos podemos
#dar cuenta de que es inversamente proporcional (la subida o la bajada)
Salinidad = (Huatabampo$PPM)
pH = (Huatabampo$PH)
pairs(Salinidad ~ pH)
data1 = data.frame(Salinidad, pH)
chart.Correlation(data1)
cor(Salinidad, pH)
## [1] -0.544348
cor.test(Salinidad, pH)
##
## Pearson's product-moment correlation
##
## data: Salinidad and pH
## t = -11.07, df = 291, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.6202473 -0.4583503
## sample estimates:
## cor
## -0.544348
#Creo que es correcto, entre mæ¼ã¸±s prfundidad la salinidad podria ser mayor
Altura = (Huatabampo$DELNF)
pairs(Salinidad ~ Altura)
data1 = data.frame(Salinidad, Altura)
chart.Correlation(data1)
cor(Salinidad, Altura)
## [1] -0.535218
cor.test(Salinidad, Altura)
##
## Pearson's product-moment correlation
##
## data: Salinidad and Altura
## t = -10.809, df = 291, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.6122563 -0.4481130
## sample estimates:
## cor
## -0.535218
#Grafica de modulos
#Esta grafica nos muestera que el modulo 1 es el mæ¼ã¸±s alto (que hay mæ¼ã¸±s)
qplot(factor(MODULO), data=Huatabampo, geom = "bar", fill=MODULO, xlab = "Modulo", ylab = "Frecuencia", main = "Modulos")
#Anaslisis exploratorios de datos
head(Huatabampo)
## # A tibble: 6 x 11
## MODULO POZO X Y SNM DELNF CE PPM PH TEMP id
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <int>
## 1 1 1 620903 2962392 3.91 2.68 2.83 1811. 6.8 28.5 1
## 2 1 2 620915 2963671 4.53 2.61 8.35 5344 6.9 29.2 2
## 3 1 3 620943 2964903 2.80 1.3 8.66 5542. 6.8 28.9 3
## 4 1 4 620879 2965667 3.64 2.14 8.34 5338. 7.1 29.4 4
## 5 1 5 620888 2966604 3.49 2.01 9.18 5875. 6.6 28.3 5
## 6 1 6 621213 2968060 4.81 2 7.9 5056 6.8 28.4 6
nrow(Huatabampo)
## [1] 293
ncol(Huatabampo)
## [1] 11
dim(Huatabampo)
## [1] 293 11
colnames(Huatabampo)
## [1] "MODULO" "POZO" "X" "Y" "SNM" "DELNF" "CE"
## [8] "PPM" "PH" "TEMP" "id"
table(Huatabampo$SNM)
##
## 0.9855 1.012 1.162 1.254 1.489 1.766 1.8115 1.842 2.023 2.113
## 1 1 1 1 1 1 1 1 1 1
## 2.1845 2.419 2.472 2.523 2.611 2.796 2.817 2.8215 2.863 3.009
## 1 1 1 1 1 1 1 1 1 1
## 3.059 3.088 3.297 3.316 3.383 3.43 3.454 3.473 3.49 3.525
## 1 1 1 1 1 1 1 1 1 1
## 3.631 3.64 3.641 3.755 3.806 3.864 3.867 3.911 3.9245 4.004
## 1 1 1 1 1 1 1 1 1 1
## 4.052 4.072 4.137 4.164 4.167 4.169 4.181 4.186 4.201 4.207
## 1 1 1 1 1 1 1 1 1 1
## 4.228 4.2635 4.279 4.319 4.3775 4.38 4.394 4.395 4.417 4.462
## 1 1 1 1 1 1 1 1 1 1
## 4.495 4.53 4.5435 4.562 4.582 4.609 4.705 4.721 4.733 4.808
## 1 1 1 1 1 1 1 1 1 1
## 4.8125 4.842 4.85 4.861 4.909 4.9245 4.958 4.988 5.011 5.014
## 1 1 1 1 1 1 1 1 1 1
## 5.032 5.045 5.05 5.055 5.059 5.087 5.123 5.151 5.157 5.178
## 1 1 1 2 1 1 1 1 1 1
## 5.183 5.186 5.245 5.285 5.302 5.35 5.366 5.394 5.405 5.43
## 1 1 1 1 1 1 1 2 1 1
## 5.448 5.505 5.531 5.537 5.557 5.565 5.583 5.614 5.651 5.659
## 1 1 1 1 1 1 1 1 1 1
## 5.674 5.702 5.753 5.792 5.855 5.901 5.921 5.936 5.974 5.981
## 1 1 1 2 1 1 1 1 1 1
## 6.024 6.051 6.0705 6.072 6.085 6.09 6.135 6.153 6.174 6.189
## 1 1 1 1 1 1 1 1 1 1
## 6.203 6.213 6.234 6.292 6.314 6.315 6.331 6.339 6.4008 6.401
## 1 1 1 1 1 1 1 1 1 2
## 6.427 6.476 6.507 6.544 6.578 6.62 6.648 6.658 6.671 6.691
## 1 1 1 1 1 1 1 1 1 1
## 6.695 6.734 6.785 6.799 6.881 6.882 6.897 6.941 6.974 7.056
## 1 1 2 1 1 1 1 1 1 1
## 7.142 7.152 7.179 7.225 7.315 7.395 7.4 7.405 7.454 7.508
## 1 1 1 1 1 1 1 1 1 1
## 7.56 7.575 7.617 7.637 7.696 7.71 7.712 7.805 7.852 7.857
## 1 1 1 1 1 1 1 1 1 1
## 7.873 7.876 7.889 7.914 7.936 7.956 8.0001 8.094 8.103 8.127
## 1 1 1 1 1 1 1 1 1 1
## 8.183 8.218 8.264 8.268 8.27 8.316 8.371 8.403 8.406 8.423
## 1 1 1 1 1 1 1 1 1 1
## 8.452 8.464 8.482 8.499 8.512 8.534 8.554 8.583 8.615 8.632
## 1 1 1 1 1 1 1 1 1 1
## 8.64 8.648 8.667 8.696 8.697 8.705 8.706 8.708 8.754 8.788
## 2 1 1 1 1 1 1 1 1 1
## 8.868 8.919 8.925 8.932 8.945 8.962 8.986 8.988 9.02 9.067
## 1 1 1 1 1 1 1 1 1 1
## 9.1 9.123 9.128 9.131 9.21 9.213 9.274 9.317 9.355 9.402
## 1 1 1 1 1 1 1 1 1 1
## 9.473 9.475 9.522 9.592 9.635 9.65 9.689 9.758 9.761 9.83
## 1 1 1 1 1 1 1 1 1 1
## 9.891 9.934 9.945 9.993 10.005 10.068 10.081 10.124 10.234 10.251
## 1 1 1 1 2 1 1 1 1 1
## 10.257 10.267 10.268 10.302 10.351 10.403 10.428 10.446 10.5 10.529
## 1 1 1 1 1 1 1 1 1 1
## 10.609 10.714 10.791 10.939 10.991 11.028 11.096 11.198 11.269 11.327
## 1 1 1 1 1 1 1 1 1 1
## 11.553 11.592 11.778 11.792 11.92 12.144
## 1 1 1 1 1 1
table(Huatabampo$DELNF)
##
## 0.54 0.6 0.71 0.77 0.81 0.88 0.9 0.97 1.06 1.07 1.09 1.1 1.14 1.29 1.3
## 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1
## 1.34 1.35 1.4 1.42 1.45 1.46 1.52 1.53 1.54 1.57 1.58 1.59 1.63 1.64 1.67
## 1 1 1 1 1 1 1 1 1 2 1 2 2 1 1
## 1.68 1.7 1.72 1.74 1.78 1.79 1.8 1.82 1.84 1.87 1.88 1.9 1.92 1.95 1.96
## 1 4 2 1 1 2 3 1 1 2 1 1 1 3 1
## 1.97 2 2.01 2.02 2.04 2.05 2.07 2.08 2.1 2.11 2.12 2.13 2.14 2.17 2.19
## 2 1 1 1 2 2 3 1 3 2 1 6 1 2 1
## 2.2 2.23 2.24 2.25 2.27 2.29 2.3 2.31 2.33 2.34 2.35 2.36 2.37 2.4 2.42
## 4 1 2 1 1 1 3 1 1 2 1 1 1 5 2
## 2.44 2.45 2.46 2.47 2.5 2.53 2.55 2.56 2.57 2.58 2.59 2.6 2.61 2.65 2.66
## 2 1 1 1 6 1 2 1 1 1 2 8 3 5 2
## 2.68 2.69 2.7 2.72 2.73 2.74 2.78 2.8 2.82 2.9 2.92 3
## 1 1 2 1 1 2 1 3 1 1 1 126
table(Huatabampo$CE)
##
## 0.49 0.61 0.68 0.69 0.7 0.76 0.78 0.79 0.81 0.82 0.89 0.9
## 1 1 1 1 1 1 1 2 2 2 2 1
## 0.91 0.92 0.95 0.96 0.97 1.04 1.05 1.06 1.08 1.09 1.1 1.12
## 1 1 1 1 1 1 1 2 1 2 1 1
## 1.14 1.15 1.18 1.2 1.21 1.22 1.23 1.26 1.29 1.3 1.31 1.32
## 1 3 2 1 1 1 1 2 1 1 1 1
## 1.34 1.36 1.38 1.39 1.4 1.41 1.42 1.43 1.44 1.45 1.48 1.52
## 1 1 1 1 1 1 1 1 1 2 1 3
## 1.53 1.54 1.55 1.56 1.58 1.59 1.6 1.63 1.64 1.65 1.66 1.68
## 1 3 1 1 1 2 1 1 1 2 2 1
## 1.7 1.71 1.72 1.74 1.76 1.78 1.8 1.82 1.84 1.85 1.87 1.88
## 1 2 1 1 1 2 1 3 1 1 2 2
## 1.91 1.92 1.93 1.99 2.02 2.04 2.05 2.06 2.08 2.11 2.13 2.14
## 1 1 1 1 1 1 2 1 1 2 1 2
## 2.16 2.17 2.19 2.21 2.28 2.32 2.4 2.43 2.47 2.5 2.54 2.66
## 2 1 1 1 1 1 2 1 1 2 1 1
## 2.68 2.72 2.74 2.77 2.8 2.83 2.85 2.86 3.01 3.05 3.09 3.1
## 2 1 1 1 2 1 1 1 1 1 1 1
## 3.12 3.15 3.19 3.23 3.25 3.29 3.39 3.47 3.49 3.5 3.56 3.59
## 1 1 1 1 1 1 1 1 1 1 2 1
## 3.6 3.61 3.69 3.72 3.87 3.9 3.96 3.98 4.05 4.14 4.17 4.27
## 1 1 1 1 1 1 2 1 2 1 1 1
## 4.28 4.3 4.32 4.33 4.4 4.44 4.48 4.49 4.73 4.78 4.8 4.83
## 1 1 1 1 1 1 2 1 1 1 1 1
## 4.85 4.87 4.92 4.95 4.98 4.99 5.3 5.44 5.55 5.56 5.92 6.02
## 1 1 1 1 1 1 1 1 1 1 1 1
## 6.05 6.1 6.13 6.15 6.19 6.21 6.22 6.23 6.3 6.48 6.57 6.62
## 1 1 1 1 1 1 1 1 1 1 1 1
## 6.66 6.73 6.8 6.82 6.87 7.03 7.04 7.08 7.12 7.17 7.26 7.27
## 2 1 1 1 1 2 1 1 1 1 1 1
## 7.35 7.44 7.58 7.62 7.65 7.68 7.71 7.82 7.88 7.9 7.92 7.98
## 1 1 1 1 1 1 1 1 1 2 1 1
## 8.07 8.08 8.09 8.12 8.19 8.21 8.28 8.29 8.31 8.33 8.34 8.35
## 1 1 1 1 1 1 2 1 1 1 1 1
## 8.42 8.43 8.46 8.48 8.49 8.54 8.61 8.63 8.65 8.66 8.76 8.79
## 1 1 1 1 1 1 1 1 1 1 1 1
## 8.8 8.88 8.89 8.9 8.97 8.99 9.02 9.04 9.06 9.1 9.13 9.17
## 1 1 1 1 1 1 1 1 1 1 1 2
## 9.18 9.22 9.28 9.3 9.47 9.52 9.55 9.58 9.64 9.66 9.67 9.7
## 1 1 1 1 1 1 1 1 1 1 1 1
## 9.73 9.76 9.8 9.83 9.84 9.89 9.95 9.97 10.02 10.05 10.1 10.16
## 1 1 1 1 1 1 1 1 1 1 1 1
table(Huatabampo$PPM)
##
## 313.6 390.4 435.2 441.6 448 486.4 499.2 505.6 518.4 524.8
## 1 1 1 1 1 1 1 2 2 2
## 569.6 576 582.4 588.8 608 614.4 620.8 665.6 672 678.4
## 2 1 1 1 1 1 1 1 1 2
## 691.2 697.6 704 716.8 729.6 736 755.2 768 774.4 780.8
## 1 2 1 1 1 3 2 1 1 1
## 787.2 806.4 825.6 832 838.4 844.8 857.6 870.4 883.2 889.6
## 1 2 1 1 1 1 1 1 1 1
## 896 902.4 908.8 915.2 921.6 928 947.2 972.8 979.2 985.6
## 1 1 1 1 1 2 1 3 1 3
## 992 998.4 1011.2 1017.6 1024 1043.2 1049.6 1056 1062.4 1075.2
## 1 1 1 2 1 1 1 2 2 1
## 1088 1094.4 1100.8 1113.6 1126.4 1139.2 1152 1164.8 1177.6 1184
## 1 2 1 1 1 2 1 3 1 1
## 1196.8 1203.2 1222.4 1228.8 1235.2 1273.6 1292.8 1305.6 1312 1318.4
## 2 2 1 1 1 1 1 1 2 1
## 1331.2 1350.4 1363.2 1369.6 1382.4 1388.8 1401.6 1414.4 1459.2 1484.8
## 1 2 1 2 2 1 1 1 1 1
## 1536 1555.2 1580.8 1600 1625.6 1702.4 1715.2 1740.8 1753.6 1772.8
## 2 1 1 2 1 1 2 1 1 1
## 1792 1811.2 1824 1830.4 1926.4 1952 1977.6 1984 1996.8 2016
## 2 1 1 1 1 1 1 1 1 1
## 2041.6 2067.2 2080 2105.6 2169.6 2220.8 2233.6 2240 2278.4 2297.6
## 1 1 1 1 1 1 1 1 2 1
## 2304 2310.4 2361.6 2380.8 2476.8 2496 2534.4 2547.2 2592 2649.6
## 1 1 1 1 1 1 2 1 2 1
## 2668.8 2732.8 2739.2 2752 2764.8 2771.2 2816 2841.6 2867.2 2873.6
## 1 1 1 1 1 1 1 1 2 1
## 3027.2 3059.2 3072 3091.2 3104 3116.8 3148.8 3168 3187.2 3193.6
## 1 1 1 1 1 1 1 1 1 1
## 3392 3481.6 3552 3558.4 3788.8 3852.8 3872 3904 3923.2 3936
## 1 1 1 1 1 1 1 1 1 1
## 3961.6 3974.4 3980.8 3987.2 4032 4147.2 4204.8 4236.8 4262.4 4307.2
## 1 1 1 1 1 1 1 1 2 1
## 4352 4364.8 4396.8 4499.2 4505.6 4531.2 4556.8 4588.8 4646.4 4652.8
## 1 1 1 2 1 1 1 1 1 1
## 4704 4761.6 4851.2 4876.8 4896 4915.2 4934.4 5004.8 5043.2 5056
## 1 1 1 1 1 1 1 1 1 2
## 5068.8 5107.2 5164.8 5171.2 5177.6 5196.8 5241.6 5254.4 5299.2 5305.6
## 1 1 1 1 1 1 1 1 2 1
## 5318.4 5331.2 5337.6 5344 5388.8 5395.2 5414.4 5427.2 5433.6 5465.6
## 1 1 1 1 1 1 1 1 1 1
## 5510.4 5523.2 5536 5542.4 5606.4 5625.6 5632 5683.2 5689.6 5696
## 1 1 1 1 1 1 1 1 1 1
## 5740.8 5753.6 5772.8 5785.6 5798.4 5824 5843.2 5868.8 5875.2 5900.8
## 1 1 1 1 1 1 1 2 1 1
## 5939.2 5952 6060.8 6092.8 6112 6131.2 6169.6 6182.4 6188.8 6208
## 1 1 1 1 1 1 1 1 1 1
## 6227.2 6246.4 6272 6291.2 6297.6 6329.6 6368 6380.8 6412.8 6432
## 1 1 1 1 1 1 1 1 1 1
## 6464 6502.4
## 1 1
table(Huatabampo$PH)
##
## 6.1 6.3 6.4 6.5 6.6 6.7 6.8 6.9 7 7.1 7.2 7.3 7.4 7.5
## 1 1 7 17 23 9 58 44 78 30 12 6 6 1
table(Huatabampo$PH)
##
## 6.1 6.3 6.4 6.5 6.6 6.7 6.8 6.9 7 7.1 7.2 7.3 7.4 7.5
## 1 1 7 17 23 9 58 44 78 30 12 6 6 1
table(Huatabampo$TEMP)
##
## 25.6 25.8 26.2 26.3 26.4 26.8 26.9 27 27.1 27.2 27.3 27.4 27.5 27.6 27.7
## 1 1 1 2 2 2 1 2 1 2 4 5 12 1 4
## 27.8 27.9 28 28.1 28.2 28.3 28.4 28.5 28.6 28.7 28.8 28.9 29 29.1 29.2
## 11 14 18 3 12 7 7 9 19 13 12 18 14 11 14
## 29.3 29.4 29.5 29.6 29.7 29.8 29.9 30 30.1 30.2 30.3 30.4 30.5 30.6 30.8
## 4 11 9 3 2 6 4 6 4 3 4 1 1 1 1
## 30.9 31.1 31.2 31.4 31.5 31.7 31.9 32.1
## 1 3 1 1 1 1 1 1
#Por conglomerado
#Aqui se tomo cada modulo y se realizo el muestreo por conglomerados, se
#tomaron de cada Modulo la mitad de los numeros, sin dejar que se repitan
#los numeros (FALSE) para saber asi cual seria bueno muestrar.
set.seed(20170701)
x1 <- 1:109 ; x1
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
## [18] 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
## [35] 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
## [52] 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
## [69] 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
## [86] 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102
## [103] 103 104 105 106 107 108 109
sample(x1, size = 53, replace = FALSE)
## [1] 105 25 76 36 84 67 41 37 93 14 94 2 10 60 39 3 95
## [18] 30 102 29 12 63 64 73 80 17 51 77 83 23 85 56 96 72
## [35] 9 24 50 22 88 103 4 106 92 104 32 97 40 91 79 70 86
## [52] 62 11
conagua1 <- data.frame(conagua)
set.seed(20170701)
x5 <- 110:187 ; x5
## [1] 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
## [18] 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143
## [35] 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
## [52] 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177
## [69] 178 179 180 181 182 183 184 185 186 187
sample(x5, size = 39, replace = FALSE)
## [1] 134 185 145 176 150 146 123 111 119 169 148 112 177 139 162 182 138
## [18] 121 118 125 126 160 122 166 132 163 140 133 130 117 178 164 129 131
## [35] 120 183 152 113 186
set.seed(20170701)
x6 <- 188:277 ; x6
## [1] 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204
## [18] 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221
## [35] 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
## [52] 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
## [69] 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
## [86] 273 274 275 276 277
sample(x6, size = 45, replace = FALSE)
## [1] 212 263 223 271 254 228 224 201 189 197 247 226 190 266 217 274 216
## [18] 199 250 251 204 238 256 210 273 243 211 239 267 208 195 196 258 237
## [35] 207 234 209 198 272 259 230 191 275 276 242
set.seed(20170701)
x7 <- 278:293 ; x7
## [1] 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
sample(x7, size = 8, replace = FALSE)
## [1] 292 286 293 289 281 290 280 291
#Gracias a la grafica de boxplot y al test Shaprio se puede observar mæ¼ã¸±s
#detalladamente que los datos de temperatura no son normales, en el test
#Shapiro no se aproxima a 0.05.
boxplot(Huatabampo$TEMP, col = "blue")
shapiro.test(conagua$TEMP)
##
## Shapiro-Wilk normality test
##
## data: conagua$TEMP
## W = 0.98362, p-value = 0.001981
#Revisar si los datos son iguales
boxplot(Huatabampo$PPM ~ Huatabampo$PH, col = "light pink")
