Bai1_Dung chatGPT
Kim Dung
2025-06-16
#prom cho chat gpt
#Tôi có 1 file về cân nặng của trẻ em tên là “birthwt.csv”
#Hãy viết R codes cho R Markdown để làm những thao tác sau đây:
#1.Đọc dữ liệu vào R và gọi tên là “bw”
#2.Coding biến race={1,2,3} thành ethnicity={“White”,”Black”,”Others”}
#3.Coding biến smoke={1,2} thành smoking={“Yes”,”No”}
#4.Coding biến low={0,1} thành low.bw={“Normal”,”Low BW”}
#5.Tạo ra biến mới mwt=lwt*0.45
#6.Dùng package table 1 để mô tả các biến số sau đây theo low.bw, age, ethnicity, smoking, mother.wt, bwt
#7.Dùng package less R để vẽ biểu đồ histogram cho biến số bwt
#8.Dùng package less R để vẽ biểu đồ phân bố cho biến số ethnicity
#9.Dùng package less R để vẽ biểu đồ tương quan giữa mwt và bwt# 1. Đọc dữ liệu vào R
pathfile="D:\\CuDiHoc\\TaiLieuHoc\\ThucHanh\\Data\\birthwt.csv"
bw <- read.csv(pathfile)
# 2. Coding biến race {1, 2, 3} thành ethnicity {"White","Black","Others"}
bw$ethnicity <- factor(bw$race,
levels = c(1, 2, 3),
labels = c("White", "Black", "Others"))
# 3. Coding biến smoke {1, 2} thành smoking {"Yes","No"}
bw$smoking <- factor(bw$smoke,
levels = c(1, 0),
labels = c("Yes", "No"))
# 4. Coding biến low {0, 1} thành low.bw {"Normal","Low BW"}
bw$low.bw <- factor(bw$low,
levels = c(0, 1),
labels = c("Normal", "Low BW"))
# 5. Tạo biến mwt = lwt * 0.45
bw$mwt <- bw$lwt * 0.45
# 6. Dùng table1 để mô tả các biến theo low.bw
#install.packages("table1")
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-head(bw)## id low age lwt race smoke ptl ht ui ftv bwt ethnicity smoking low.bw mwt
## 1 85 0 19 182 2 0 0 0 1 0 2523 Black No Normal 81.90
## 2 86 0 33 155 3 0 0 0 0 3 2551 Others No Normal 69.75
## 3 87 0 20 105 1 1 0 0 0 1 2557 White Yes Normal 47.25
## 4 88 0 21 108 1 1 0 0 1 2 2594 White Yes Normal 48.60
## 5 89 0 18 107 1 1 0 0 1 0 2600 White Yes Normal 48.15
## 6 91 0 21 124 3 0 0 0 0 0 2622 Others No Normal 55.80table1(~ age + ethnicity + smoking + mwt + bwt | low.bw, data=bw)| Normal (N=130) |
Low BW (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] |
| ethnicity | |||
| White | 73 (56.2%) | 23 (39.0%) | 96 (50.8%) |
| Black | 15 (11.5%) | 11 (18.6%) | 26 (13.8%) |
| Others | 42 (32.3%) | 25 (42.4%) | 67 (35.4%) |
| smoking | |||
| Yes | 44 (33.8%) | 30 (50.8%) | 74 (39.2%) |
| No | 86 (66.2%) | 29 (49.2%) | 115 (60.8%) |
| mwt | |||
| Mean (SD) | 60.0 (14.3) | 55.0 (12.0) | 58.4 (13.8) |
| Median [Min, Max] | 55.6 [38.3, 113] | 54.0 [36.0, 90.0] | 54.5 [36.0, 113] |
| bwt | |||
| Mean (SD) | 3330 (478) | 2100 (391) | 2940 (729) |
| Median [Min, Max] | 3270 [2520, 4990] | 2210 [709, 2500] | 2980 [709, 4990] |
# 7, 8, 9. Sử dụng lessR để vẽ Histogram, BarChart, Plot
#install.packages("lessR")
library(lessR)##
## 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 object is masked from 'package:base':
##
## sort_by# 7. Histogram bwt bằng lessR
Histogram(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
## # 8. Bar chart phân bố ethnicity bằng lessR
BarChart(ethnicity, data=bw)
## >>> Suggestions
## BarChart(ethnicity, horiz=TRUE) # horizontal bar chart
## BarChart(ethnicity, fill="reds") # red bars of varying lightness
## PieChart(ethnicity) # doughnut (ring) chart
## Plot(ethnicity) # bubble plot
## Plot(ethnicity, stat="count") # lollipop plot
##
## --- ethnicity ---
##
## Missing Values: 0
##
## White Black Others 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# 9. Scatterplot mwt và bwt bằng lessR
Plot(bwt, mwt, data=bw)
##
## >>> Suggestions or enter: style(suggest=FALSE)
## Plot(bwt, mwt, enhance=TRUE) # many options
## Plot(bwt, mwt, fill="skyblue") # interior fill color of points
## Plot(bwt, mwt, fit="lm", fit_se=c(.90,.99)) # fit line, stnd errors
## Plot(bwt, mwt, 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 bwt and mwt: 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
##