Yêu cầu đọc dữ liệu birthwt.csv vài R
bw = read.csv("/Volumes/PhD - NTTU/MÔN HỌC/PHAN TICH DU LIEU VOI R/DỮ LIỆU THỰC HÀNH (TS Thạch gửi)/birthwt.csv")
dim(bw)
## [1] 189 11
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 2622
tail(bw, 10)
## id low age lwt race smoke ptl ht ui ftv bwt
## 180 71 1 17 120 2 0 0 0 0 2 2438
## 181 75 1 26 154 3 0 1 1 0 1 2442
## 182 76 1 20 105 3 0 0 0 0 3 2450
## 183 77 1 26 190 1 1 0 0 0 0 2466
## 184 78 1 14 101 3 1 1 0 0 0 2466
## 185 79 1 28 95 1 1 0 0 0 2 2466
## 186 81 1 14 100 3 0 0 0 0 2 2495
## 187 82 1 23 94 3 1 0 0 0 0 2495
## 188 83 1 17 142 2 0 0 1 0 0 2495
## 189 84 1 21 130 1 1 0 1 0 3 2495
bw$mwt = bw$lwt*0.45
Nếu race = 1 thì ethnicity = “White” Nếu race = 2 thì ethnicity = “Black” Nếu race = 3 thì ethnicity = “Other”
bw$ethnicity[bw$race == 1] = "white"
bw$ethnicity[bw$race == 2] = "black"
bw$ethnicity[bw$race == 3] = "other"
table(bw$ethnicity, bw$race)
##
## 1 2 3
## black 0 26 0
## other 0 0 67
## white 96 0 0
bw1 = bw[, c("id", "low", "bwt")]
dim(bw1)
## [1] 189 3
bw3 = subset(bw, low == 1)
dim(bw3)
## [1] 59 13
bw4 = subset(bw, low == 1 & smoke == 1)
dim(bw4)
## [1] 30 13
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:base':
##
## sort_by
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(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
##
## black other white Total
## Frequencies: 26 67 96 189
## Proportions: 0.138 0.354 0.508 1.000
##
## Chi-squared test of null hypothesis of equal probabilities
## Chisq = 39.270, df = 2, p-value = 0.000
Plot(lwt, bwt, fit = "lm", data = bw)
##
##
## >>> Suggestions or enter: style(suggest=FALSE)
## Plot(lwt, bwt, enhance=TRUE) # many options
## Plot(lwt, bwt, color="red") # exterior edge 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
##
Plot(lwt, bwt, by = race, 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
##
## race: 1 Line: b0 = 2442.418 b1 = 5.000 Linear Model MSE = 514,065.615 Rsq = 0.040
##
## race: 2 Line: b0 = 2363.222 b1 = 2.428 Linear Model MSE = 415,263.548 Rsq = 0.023
##
## race: 3 Line: b0 = 2070.778 b1 = 6.120 Linear Model MSE = 505,570.324 Rsq = 0.045
##