Ngày 1: Giới thiệu R
pthao
2025-06-16
#Ngày 1: Giới thiệu R #dữ liệu “birthwt.csv”
file.choose()## [1] "D:\\HOC TAP\\TAP HUAN UNG DUNG AI TRONG PT DU LIEU SU DUNG R\\THUC HANH TAI LOP\\hocRngay2\\bt1.html"bw=read.csv("D:\\HOC TAP\\TAP HUAN UNG DUNG AI TRONG PT DU LIEU SU DUNG R\\thuc hanh\\birthwt.csv")head (bw)## id low age lwt race smoke ptl ht ui ftv bwt
## 1 85 0 19 182 2 0 0 0 1 0 2523
## 2 86 0 33 155 3 0 0 0 0 3 2551
## 3 87 0 20 105 1 1 0 0 0 1 2557
## 4 88 0 21 108 1 1 0 0 1 2 2594
## 5 89 0 18 107 1 1 0 0 1 0 2600
## 6 91 0 21 124 3 0 0 0 0 0 2622dim(bw)## [1] 189 11#5.1 Tạo biến số mới mwt là cân nặng của mẹ tính bằng kg #lwt có đơn vị là pound # Mục tiêu: hoán chuyển sang kg + lưu lại trong một biến mới mwt
bw$mwt = bw$lwt* 0.453592head(bw)## id low age lwt race smoke ptl ht ui ftv bwt mwt
## 1 85 0 19 182 2 0 0 0 1 0 2523 82.55374
## 2 86 0 33 155 3 0 0 0 0 3 2551 70.30676
## 3 87 0 20 105 1 1 0 0 0 1 2557 47.62716
## 4 88 0 21 108 1 1 0 0 1 2 2594 48.98794
## 5 89 0 18 107 1 1 0 0 1 0 2600 48.53434
## 6 91 0 21 124 3 0 0 0 0 0 2622 56.24541#5.2 Tạo biến số mới ethnicity là biến factor với điều kiện sau:Nếu race = 1 thì ethnicity = “White” #Nếu race = 2 thì ethnicity = “Black” #Nếu race = 3 thì ethnicity = “Other”
library(dplyr)## Warning: package 'dplyr' was built under R version 4.4.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionbw$ethnicity <- factor(bw$race,
levels = c(1, 2, 3),
labels = c("White","Black", "Other"))
head(bw)## id low age lwt race smoke ptl ht ui ftv bwt mwt ethnicity
## 1 85 0 19 182 2 0 0 0 1 0 2523 82.55374 Black
## 2 86 0 33 155 3 0 0 0 0 3 2551 70.30676 Other
## 3 87 0 20 105 1 1 0 0 0 1 2557 47.62716 White
## 4 88 0 21 108 1 1 0 0 1 2 2594 48.98794 White
## 5 89 0 18 107 1 1 0 0 1 0 2600 48.53434 White
## 6 91 0 21 124 3 0 0 0 0 0 2622 56.24541 Other#5.3 Tạo 1 tập dữ liệu bw1 chỉ gồm 3 biến số id, low và bwt. Dữ liệu này có bao nhiêu biến số và quan sát?
bw1 = bw[, c("id", "low", "bwt")]
head(bw1)## id low bwt
## 1 85 0 2523
## 2 86 0 2551
## 3 87 0 2557
## 4 88 0 2594
## 5 89 0 2600
## 6 91 0 2622#5.4 Tạo 1 tập dữ liệu bw2 chỉ gồm những thai phụ có cân nặng thấp (low = 1). Dữ liệ ucó bao nhiêu biến số và quan sát?
bw2 = subset (bw, low == 1)
head(bw2)## id low age lwt race smoke ptl ht ui ftv bwt mwt ethnicity
## 131 4 1 28 120 3 1 1 0 1 0 709 54.43104 Other
## 132 10 1 29 130 1 0 0 0 1 2 1021 58.96696 White
## 133 11 1 34 187 2 1 0 1 0 0 1135 84.82170 Black
## 134 13 1 25 105 3 0 1 1 0 0 1330 47.62716 Other
## 135 15 1 25 85 3 0 0 0 1 0 1474 38.55532 Other
## 136 16 1 27 150 3 0 0 0 0 0 1588 68.03880 Otherdim(bw2)## [1] 59 13#5.5 Tạo 1 tập dữ liệu bw3 chỉ gồm những thai phụ có cân nặng thấp (low = 1) và có hú thuốc trong lúc mang thai (smoke = 1). Dữ liệu này có bao nhiêu biến số và quan sát?
bw3 = subset(bw, low ==1 & smoke ==1)
head(bw3)## id low age lwt race smoke ptl ht ui ftv bwt mwt ethnicity
## 131 4 1 28 120 3 1 1 0 1 0 709 54.43104 Other
## 133 11 1 34 187 2 1 0 1 0 0 1135 84.82170 Black
## 140 20 1 21 165 1 1 0 1 0 1 1790 74.84268 White
## 141 22 1 32 105 1 1 0 0 0 0 1818 47.62716 White
## 142 23 1 19 91 1 1 2 0 1 0 1885 41.27687 White
## 145 26 1 25 92 1 1 0 0 0 0 1928 41.73046 Whitedim(bw3)## [1] 30 13#————————–Việc 6. Phân tích mô tả: ————————————— #6.1 Mô tả đặc điểm tuổi của mẹ (age), cân nặng của mẹ (lwt) và cân nặng của con (bwt)
library(table1)## Warning: package 'table1' was built under R version 4.4.3##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~age + lwt + bwt, data=bw)| Overall (N=189) |
|
|---|---|
| age | |
| Mean (SD) | 23.2 (5.30) |
| Median [Min, Max] | 23.0 [14.0, 45.0] |
| lwt | |
| Mean (SD) | 130 (30.6) |
| Median [Min, Max] | 121 [80.0, 250] |
| bwt | |
| Mean (SD) | 2940 (729) |
| Median [Min, Max] | 2980 [709, 4990] |
#6.2 Mô tả đặc điểm tuổi của mẹ (age), cân nặng của mẹ (lwt), tình trạng hút thuốc trong nthai kỳ (smoke) , chủng tộc (race), và cân nặng của con (bwt) theo tình trạng trẻ thiếu cân (low)
table1(~age + lwt + bwt | low, data=bw)## Warning in table1.formula(~age + lwt + bwt | low, data = bw): Terms to the
## right of '|' in formula 'x' define table columns and are expected to be factors
## with meaningful labels.| 0 (N=130) |
1 (N=59) |
Overall (N=189) |
|
|---|---|---|---|
| age | |||
| Mean (SD) | 23.7 (5.58) | 22.3 (4.51) | 23.2 (5.30) |
| Median [Min, Max] | 23.0 [14.0, 45.0] | 22.0 [14.0, 34.0] | 23.0 [14.0, 45.0] |
| lwt | |||
| Mean (SD) | 133 (31.7) | 122 (26.6) | 130 (30.6) |
| Median [Min, Max] | 124 [85.0, 250] | 120 [80.0, 200] | 121 [80.0, 250] |
| bwt | |||
| Mean (SD) | 3330 (478) | 2100 (391) | 2940 (729) |
| Median [Min, Max] | 3270 [2520, 4990] | 2210 [709, 2500] | 2980 [709, 4990] |
Chuyển thành biến factor
bw$low <- factor(bw$low, levels = c(0, 1), labels = c("Normal weight", "Low birth weight"))
bw$smoke <- factor(bw$smoke, levels = c(0, 1), labels = c("Non-smoker", "Smoker"))
bw$race <- factor(bw$race, levels = c(1, 2, 3), labels = c("White", "Black", "Other"))
head(bw)## id low age lwt race smoke ptl ht ui ftv bwt mwt
## 1 85 Normal weight 19 182 Black Non-smoker 0 0 1 0 2523 82.55374
## 2 86 Normal weight 33 155 Other Non-smoker 0 0 0 3 2551 70.30676
## 3 87 Normal weight 20 105 White Smoker 0 0 0 1 2557 47.62716
## 4 88 Normal weight 21 108 White Smoker 0 0 1 2 2594 48.98794
## 5 89 Normal weight 18 107 White Smoker 0 0 1 0 2600 48.53434
## 6 91 Normal weight 21 124 Other Non-smoker 0 0 0 0 2622 56.24541
## ethnicity
## 1 Black
## 2 Other
## 3 White
## 4 White
## 5 White
## 6 Othertable1(~ age + lwt + smoke + race + bwt | low, data = bw)| Normal weight (N=130) |
Low birth weight (N=59) |
Overall (N=189) |
|
|---|---|---|---|
| age | |||
| Mean (SD) | 23.7 (5.58) | 22.3 (4.51) | 23.2 (5.30) |
| Median [Min, Max] | 23.0 [14.0, 45.0] | 22.0 [14.0, 34.0] | 23.0 [14.0, 45.0] |
| lwt | |||
| Mean (SD) | 133 (31.7) | 122 (26.6) | 130 (30.6) |
| Median [Min, Max] | 124 [85.0, 250] | 120 [80.0, 200] | 121 [80.0, 250] |
| smoke | |||
| Non-smoker | 86 (66.2%) | 29 (49.2%) | 115 (60.8%) |
| Smoker | 44 (33.8%) | 30 (50.8%) | 74 (39.2%) |
| race | |||
| White | 73 (56.2%) | 23 (39.0%) | 96 (50.8%) |
| Black | 15 (11.5%) | 11 (18.6%) | 26 (13.8%) |
| Other | 42 (32.3%) | 25 (42.4%) | 67 (35.4%) |
| bwt | |||
| Mean (SD) | 3330 (478) | 2100 (391) | 2940 (729) |
| Median [Min, Max] | 3270 [2520, 4990] | 2210 [709, 2500] | 2980 [709, 4990] |
#smoking
bw$smoking = ifelse(bw$smoke=="Yes", 1, 0)
head(bw)## id low age lwt race smoke ptl ht ui ftv bwt mwt
## 1 85 Normal weight 19 182 Black Non-smoker 0 0 1 0 2523 82.55374
## 2 86 Normal weight 33 155 Other Non-smoker 0 0 0 3 2551 70.30676
## 3 87 Normal weight 20 105 White Smoker 0 0 0 1 2557 47.62716
## 4 88 Normal weight 21 108 White Smoker 0 0 1 2 2594 48.98794
## 5 89 Normal weight 18 107 White Smoker 0 0 1 0 2600 48.53434
## 6 91 Normal weight 21 124 Other Non-smoker 0 0 0 0 2622 56.24541
## ethnicity smoking
## 1 Black 0
## 2 Other 0
## 3 White 0
## 4 White 0
## 5 White 0
## 6 Other 0biểu đồ phân bố
library(lessR)## Warning: package 'lessR' was built under R version 4.4.3##
## lessR 4.4.3 feedback: gerbing@pdx.edu
## --------------------------------------------------------------
## > d <- Read("") Read data file, many formats available, e.g., Excel
## d is default data frame, data= in analysis routines optional
##
## Many examples of reading, writing, and manipulating data,
## graphics, testing means and proportions, regression, factor analysis,
## customization, forecasting, and aggregation from pivot tables
## Enter: browseVignettes("lessR")
##
## View lessR updates, now including time series forecasting
## Enter: news(package="lessR")
##
## Interactive data analysis
## Enter: interact()##
## Attaching package: 'lessR'## The following object is masked from 'package:table1':
##
## label## The following objects are masked from 'package:dplyr':
##
## order_by, recode, rename## The following object is masked from 'package:base':
##
## sort_byHistogram(bwt, data=bw)
## >>> Suggestions
## bin_width: set the width of each bin
## bin_start: set the start of the first bin
## bin_end: set the end of the last bin
## Histogram(bwt, density=TRUE) # smoothed curve + histogram
## Plot(bwt) # Violin/Box/Scatterplot (VBS) plot
##
## --- bwt ---
##
## n miss mean sd min mdn max
## 189 0 2944.59 729.21 709.00 2977.00 4990.00
##
##
##
## --- Outliers --- from the box plot: 1
##
## Small Large
## ----- -----
## 709.0
##
##
## Bin Width: 500
## Number of Bins: 9
##
## Bin Midpnt Count Prop Cumul.c Cumul.p
## -----------------------------------------------------
## 500 > 1000 750 1 0.01 1 0.01
## 1000 > 1500 1250 4 0.02 5 0.03
## 1500 > 2000 1750 14 0.07 19 0.10
## 2000 > 2500 2250 40 0.21 59 0.31
## 2500 > 3000 2750 38 0.20 97 0.51
## 3000 > 3500 3250 45 0.24 142 0.75
## 3500 > 4000 3750 38 0.20 180 0.95
## 4000 > 4500 4250 7 0.04 187 0.99
## 4500 > 5000 4750 2 0.01 189 1.00
## Histogram(bwt, fill="blue", xlab="Birthweight (g)",
ylab="Frequency", data=bw)
## >>> Suggestions
## bin_width: set the width of each bin
## bin_start: set the start of the first bin
## bin_end: set the end of the last bin
## Histogram(bwt, density=TRUE) # smoothed curve + histogram
## Plot(bwt) # Violin/Box/Scatterplot (VBS) plot
##
## --- bwt ---
##
## n miss mean sd min mdn max
## 189 0 2944.59 729.21 709.00 2977.00 4990.00
##
##
##
## --- Outliers --- from the box plot: 1
##
## Small Large
## ----- -----
## 709.0
##
##
## Bin Width: 500
## Number of Bins: 9
##
## Bin Midpnt Count Prop Cumul.c Cumul.p
## -----------------------------------------------------
## 500 > 1000 750 1 0.01 1 0.01
## 1000 > 1500 1250 4 0.02 5 0.03
## 1500 > 2000 1750 14 0.07 19 0.10
## 2000 > 2500 2250 40 0.21 59 0.31
## 2500 > 3000 2750 38 0.20 97 0.51
## 3000 > 3500 3250 45 0.24 142 0.75
## 3500 > 4000 3750 38 0.20 180 0.95
## 4000 > 4500 4250 7 0.04 187 0.99
## 4500 > 5000 4750 2 0.01 189 1.00
## BarChart(race, data=bw)
## >>> Suggestions
## BarChart(race, horiz=TRUE) # horizontal bar chart
## BarChart(race, fill="reds") # red bars of varying lightness
## PieChart(race) # doughnut (ring) chart
## Plot(race) # bubble plot
## Plot(race, stat="count") # lollipop plot
##
## --- race ---
##
## Missing Values: 0
##
## White Black Other Total
## Frequencies: 96 26 67 189
## Proportions: 0.508 0.138 0.354 1.000
##
## Chi-squared test of null hypothesis of equal probabilities
## Chisq = 39.270, df = 2, p-value = 0.000#Biểu đồ tương quan: Plot(x, y)
Plot(lwt, bwt, data=bw)
##
## >>> Suggestions or enter: style(suggest=FALSE)
## Plot(lwt, bwt, enhance=TRUE) # many options
## Plot(lwt, bwt, fill="skyblue") # interior fill color of points
## Plot(lwt, bwt, fit="lm", fit_se=c(.90,.99)) # fit line, stnd errors
## Plot(lwt, bwt, MD_cut=6) # Mahalanobis distance from center > 6 is an outlier
##
##
## >>> Pearson's product-moment correlation
##
## Number of paired values with neither missing, n = 189
## Sample Correlation of lwt and bwt: r = 0.186
##
## Hypothesis Test of 0 Correlation: t = 2.585, df = 187, p-value = 0.011
## 95% Confidence Interval for Correlation: 0.044 to 0.320
## Plot(lwt, bwt, fit="lm", data=bw)
##
##
## >>> Suggestions or enter: style(suggest=FALSE)
## Plot(lwt, bwt, enhance=TRUE) # many options
## Plot(lwt, bwt, fill="skyblue") # interior fill color of points
## Plot(lwt, bwt, out_cut=.10) # label top 10% from center as outliers
##
##
## >>> Pearson's product-moment correlation
##
## Number of paired values with neither missing, n = 189
## Sample Correlation of lwt and bwt: r = 0.186
##
## Hypothesis Test of 0 Correlation: t = 2.585, df = 187, p-value = 0.011
## 95% Confidence Interval for Correlation: 0.044 to 0.320
##
##
## Line: b0 = 2369.624 b1 = 4.429 Linear Model MSE = 516,155.173 Rsq = 0.034
## bw$ethnicity[bw$race==1]<-"White"
bw$ethnicity [bw$race==2] <- "Black"
bw$ethnicity [bw$race==3] <- "Other"
Plot(lwt, bwt, by= ethnicity, fit="lm", data=bw)
##
##
## >>> Suggestions or enter: style(suggest=FALSE)
## Plot(lwt, bwt, enhance=TRUE) # many options
## Plot(lwt, bwt, fill="skyblue") # interior fill color of points
## Plot(lwt, bwt, out_cut=.10) # label top 10% from center as outliers
##
## ethnicity: White Line: b0 = 2442.418 b1 = 5.000 Linear Model MSE = 514,065.615 Rsq = 0.040
##
## ethnicity: Black Line: b0 = 2363.222 b1 = 2.428 Linear Model MSE = 415,263.548 Rsq = 0.023
##
## ethnicity: Other Line: b0 = 2070.778 b1 = 6.120 Linear Model MSE = 505,570.324 Rsq = 0.045
## #———————–using table1 thống kê mô tả————————————————- # phân tích mô tả theo low
bw$low <- factor(bw$low, levels = c(0, 1), labels = c("Normal weight", "Low birth weight"))