library(readxl)
## Warning: package 'readxl' was built under R version 4.3.1
library(DescTools)
## Warning: package 'DescTools' was built under R version 4.3.1
library(gtsummary)
## Warning: package 'gtsummary' was built under R version 4.3.1
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.1
library(epitools)
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.1
## Warning: package 'tibble' was built under R version 4.3.1
## Warning: package 'tidyr' was built under R version 4.3.1
## Warning: package 'readr' was built under R version 4.3.1
## Warning: package 'purrr' was built under R version 4.3.1
## Warning: package 'dplyr' was built under R version 4.3.1
## Warning: package 'stringr' was built under R version 4.3.1
## Warning: package 'forcats' was built under R version 4.3.1
## Warning: package 'lubridate' was built under R version 4.3.1
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.2.1
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
Dữ liệu
a<-file.choose()
data <- read_xlsx(a)
## Warning: Expecting numeric in G3081 / R3081C7: got a date
## New names:
## • `` -> `...1`
str(data)
## tibble [153,430 × 15] (S3: tbl_df/tbl/data.frame)
## $ ...1 : num [1:153430] 0 1 2 3 4 5 6 7 8 9 ...
## $ property_type: chr [1:153430] "Flat" "Flat" "House" "House" ...
## $ price : num [1:153430] 10000000 6900000 16500000 43500000 7000000 34500000 27000000 7800000 50000000 40000000 ...
## $ location : chr [1:153430] "G-10" "E-11" "G-15" "Bani Gala" ...
## $ city : chr [1:153430] "Islamabad" "Islamabad" "Islamabad" "Islamabad" ...
## $ province_name: chr [1:153430] "Islamabad Capital" "Islamabad Capital" "Islamabad Capital" "Islamabad Capital" ...
## $ latitude : num [1:153430] 3.37e+06 3.37e+07 3.36e+16 3.37e+13 3.35e+07 ...
## $ longitude : num [1:153430] 7.30e+06 7.30e+07 7.29e+07 7.32e+12 7.33e+07 ...
## $ baths : num [1:153430] 2 3 6 4 3 8 8 2 7 5 ...
## $ purpose : chr [1:153430] "For Sale" "For Sale" "For Sale" "For Sale" ...
## $ bedrooms : num [1:153430] 2 3 5 4 3 8 8 2 7 5 ...
## $ date_added : POSIXct[1:153430], format: "2019-02-04" "2019-05-04" ...
## $ agency : chr [1:153430] "Self" "Self" "Self" "Self" ...
## $ agent : chr [1:153430] "Self" "Self" "Self" "Self" ...
## $ Area_in_Marla: num [1:153430] 4 5.6 8 40 8 32 20 6.2 20 20 ...
Thống kê mô tả các biến
pur1 <- table(data$purpose)
pur1
##
## For Rent For Sale
## 43183 110247
pur1a <- prop.table(pur1);pur1a
##
## For Rent For Sale
## 0.2814508 0.7185492
addmargins(pur1)
##
## For Rent For Sale Sum
## 43183 110247 153430
library(ggplot2)
data |> ggplot(aes(x = data$purpose, y = after_stat(count))) + geom_bar(fill = 'blue') + geom_text(aes(label = scales::percent(after_stat(count/sum(count)))), stat = 'count', color = 'black', vjust = - .5) + theme_classic() + labs(x = 'Purpose', y = 'Frequency')
## Warning: Use of `data$purpose` is discouraged.
## ℹ Use `purpose` instead.
## Use of `data$purpose` is discouraged.
## ℹ Use `purpose` instead.
Ước lượng tỷ lệ
m <- data[data$purpose == "For Rent",]
prop.test(length(m$purpose), length(data$purpose), p= 0.28)
##
## 1-sample proportions test with continuity correction
##
## data: length(m$purpose) out of length(data$purpose), null probability 0.28
## X-squared = 1.5948, df = 1, p-value = 0.2066
## alternative hypothesis: true p is not equal to 0.28
## 95 percent confidence interval:
## 0.2792029 0.2837097
## sample estimates:
## p
## 0.2814508
Mô hình hồi quy
Hồi quy logit
mh1 <- glm(formula = factor(data$purpose) ~ data$property_type + data$price + data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "logit"), data = data)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(mh1)
##
## Call:
## glm(formula = factor(data$purpose) ~ data$property_type + data$price +
## data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "logit"),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.798e+13 2.733e+06 1.756e+07 <2e-16 ***
## data$property_typeFlat 1.556e+15 2.752e+06 5.652e+08 <2e-16 ***
## data$property_typeHouse -5.182e+14 2.739e+06 -1.892e+08 <2e-16 ***
## data$property_typeLower Portion -3.930e+14 2.827e+06 -1.390e+08 <2e-16 ***
## data$property_typePenthouse -4.679e+14 4.388e+06 -1.066e+08 <2e-16 ***
## data$property_typeRoom -1.277e+15 3.774e+06 -3.384e+08 <2e-16 ***
## data$property_typeUpper Portion -2.953e+14 2.795e+06 -1.056e+08 <2e-16 ***
## data$price 6.576e+07 5.084e-03 1.294e+10 <2e-16 ***
## data$baths -4.013e+13 9.157e+04 -4.382e+08 <2e-16 ***
## data$bedrooms 6.753e+13 1.220e+05 5.535e+08 <2e-16 ***
## data$Area_in_Marla -2.979e+12 1.843e+03 -1.617e+09 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 182373 on 153429 degrees of freedom
## Residual deviance: 1385951 on 153419 degrees of freedom
## AIC: 1385973
##
## Number of Fisher Scoring iterations: 25
Hồi quy probit
mh2 <- glm(formula = factor(data$purpose) ~ data$property_type + data$price + data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "probit"), data = data)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(mh2)
##
## Call:
## glm(formula = factor(data$purpose) ~ data$property_type + data$price +
## data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "probit"),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 6.968e+14 2.733e+06 2.550e+08 <2e-16 ***
## data$property_typeFlat 1.917e+14 2.752e+06 6.964e+07 <2e-16 ***
## data$property_typeHouse 3.660e+14 2.739e+06 1.336e+08 <2e-16 ***
## data$property_typeLower Portion -4.624e+14 2.827e+06 -1.636e+08 <2e-16 ***
## data$property_typePenthouse -9.449e+14 4.388e+06 -2.153e+08 <2e-16 ***
## data$property_typeRoom -1.099e+15 3.774e+06 -2.911e+08 <2e-16 ***
## data$property_typeUpper Portion -3.249e+14 2.795e+06 -1.162e+08 <2e-16 ***
## data$price 5.401e+07 5.084e-03 1.062e+10 <2e-16 ***
## data$baths -5.222e+13 9.157e+04 -5.702e+08 <2e-16 ***
## data$bedrooms -1.233e+14 1.220e+05 -1.011e+09 <2e-16 ***
## data$Area_in_Marla -2.857e+12 1.843e+03 -1.551e+09 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 182373 on 153429 degrees of freedom
## Residual deviance: 1959910 on 153419 degrees of freedom
## AIC: 1959932
##
## Number of Fisher Scoring iterations: 25
Hồi quy cloglog
mh3 <- glm(formula = factor(data$purpose) ~ data$property_type + data$price + data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "cloglog"), data = data)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(mh3)
##
## Call:
## glm(formula = factor(data$purpose) ~ data$property_type + data$price +
## data$baths + data$bedrooms + data$Area_in_Marla, family = binomial(link = "cloglog"),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.014e+14 2.733e+06 3.711e+07 <2e-16 ***
## data$property_typeFlat 3.185e+14 2.752e+06 1.157e+08 <2e-16 ***
## data$property_typeHouse -9.156e+13 2.739e+06 -3.342e+07 <2e-16 ***
## data$property_typeLower Portion -6.761e+14 2.827e+06 -2.392e+08 <2e-16 ***
## data$property_typePenthouse 4.042e+14 4.388e+06 9.213e+07 <2e-16 ***
## data$property_typeRoom -2.253e+14 3.774e+06 -5.971e+07 <2e-16 ***
## data$property_typeUpper Portion -1.774e+15 2.795e+06 -6.346e+08 <2e-16 ***
## data$price 4.226e+07 5.084e-03 8.311e+09 <2e-16 ***
## data$baths -2.894e+13 9.157e+04 -3.160e+08 <2e-16 ***
## data$bedrooms -4.268e+13 1.220e+05 -3.498e+08 <2e-16 ***
## data$Area_in_Marla -1.871e+12 1.843e+03 -1.015e+09 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 182373 on 153429 degrees of freedom
## Residual deviance: 1345942 on 153419 degrees of freedom
## AIC: 1345964
##
## Number of Fisher Scoring iterations: 25