remove(list=ls())
Vegetable.Prices.2022 <- read.csv("~/Downloads/Vegetable-Prices-2022.csv")GlobalScholars_PovertyProject
Importing the Dataset
Installing Packages
library(visdat)
library(stargazer)
Please cite as: Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables. R package version 5.2.3. https://CRAN.R-project.org/package=stargazer library(stargazer)
library(psych)
#install.packages("nanair")
library(naniar)
library(ggplot2)
Attaching package: 'ggplot2'The following objects are masked from 'package:psych':
%+%, alphalibrary(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, union# install.packages("Hmisc")
library("Hmisc")
Attaching package: 'Hmisc'The following objects are masked from 'package:dplyr':
src, summarizeThe following object is masked from 'package:psych':
describeThe following objects are masked from 'package:base':
format.pval, unitslibrary(MASS)
Attaching package: 'MASS'The following object is masked from 'package:dplyr':
selectCleaning the data / Checking for missing data
vis_dat(Vegetable.Prices.2022)
vis_miss(Vegetable.Prices.2022)
missing_values_count <- sapply(Vegetable.Prices.2022, function(x) sum(is.na(x)))
print(missing_values_count) Vegetable Form RetailPrice RetailPriceUnit
0 0 0 0
Yield CupEquivalentSize CupEquivalentUnit CupEquivalentPrice
0 0 0 0 # Vegetable.Prices.2022$TIDAL.Popularity <- NULL#Renaming Variables in Dataset
head(Vegetable.Prices.2022, n=10) Vegetable Form RetailPrice RetailPriceUnit Yield CupEquivalentSize
1 Acorn squash Fresh 1.2136 per pound 0.4586 0.4519
2 Artichoke Fresh 2.4703 per pound 0.3750 0.3858
3 Artichoke Canned 3.4498 per pound 0.6500 0.3858
4 Asparagus Fresh 2.9531 per pound 0.4938 0.3968
5 Asparagus Canned 3.4328 per pound 0.6500 0.3968
6 Asparagus Frozen 6.8212 per pound 1.0335 0.3968
7 Avocados Fresh 2.6737 per pound 0.7408 0.3197
8 Beets Canned 1.1431 per pound 0.6500 0.3748
9 Black beans Canned 1.2387 per pound 0.6500 0.3858
10 Black beans Dried 1.5250 per pound 2.4692 0.3858
CupEquivalentUnit CupEquivalentPrice
1 pounds 1.1961
2 pounds 2.5415
3 pounds 2.0476
4 pounds 2.3731
5 pounds 2.0958
6 pounds 2.6191
7 pounds 1.1538
8 pounds 0.6591
9 pounds 0.7352
10 pounds 0.2383print(Vegetable.Prices.2022$Vegetable['Asparagus'])[1] NASummary Statistics
stargazer(Vegetable.Prices.2022,
type = "text",
title = "Summary statistics",
digits = 2)
Summary statistics
=============================================
Statistic N Mean St. Dev. Min Max
---------------------------------------------
RetailPrice 93 2.11 1.08 0.80 6.82
Yield 93 0.96 0.49 0.38 2.54
CupEquivalentSize 93 0.34 0.07 0.15 0.54
CupEquivalentPrice 93 0.83 0.51 0.22 2.62
---------------------------------------------ggplots
ggplot(data = Vegetable.Prices.2022,
mapping = aes(x = RetailPrice, y = Yield)) + geom_point(colour = "lightblue") + ggtitle("2022 Vegetable Prices; Retail Price by Yeild")
ggplot(data = Vegetable.Prices.2022,
mapping = aes(x = Vegetable, y = RetailPrice)) + geom_point(colour = "lightblue") + ggtitle("2022 Vegetable Prices; Retail Price by Yeild")
Mass Food Access Dataset
Food.Access.Research.Atlas <- read.csv("~/Downloads/2019 Food Access Research Atlas Data/Food Access Research Atlas.csv", header=FALSE)
#sub_data <- Food.Access.Research.Atlas[Food.Access.Research.Atlas$V2 ==S Massachusetts, ]
#vis_dat(Food.Access.Research.Atlas)
#vis_miss(Food.Access.Research.Atlas)
#missing_values_count <- sapply(Food.Access.Research.Atlas, function(x) sum(is.na(x)))
#print(missing_values_count)
str(Food.Access.Research.Atlas)'data.frame': 72532 obs. of 147 variables:
$ V1 : chr "CensusTract" "1001020100" "1001020200" "1001020300" ...
$ V2 : chr "State" "Alabama" "Alabama" "Alabama" ...
$ V3 : chr "County" "Autauga County" "Autauga County" "Autauga County" ...
$ V4 : chr "Urban" "1" "1" "1" ...
$ V5 : chr "Pop2010" "1912" "2170" "3373" ...
$ V6 : chr "OHU2010" "693" "743" "1256" ...
$ V7 : chr "GroupQuartersFlag" "0" "0" "0" ...
$ V8 : chr "NUMGQTRS" "0" "181" "0" ...
$ V9 : chr "PCTGQTRS" "0" "8.34" "0" ...
$ V10 : chr "LILATracts_1And10" "0" "1" "0" ...
$ V11 : chr "LILATracts_halfAnd10" "0" "1" "0" ...
$ V12 : chr "LILATracts_1And20" "0" "1" "0" ...
$ V13 : chr "LILATracts_Vehicle" "0" "0" "0" ...
$ V14 : chr "HUNVFlag" "0" "0" "0" ...
$ V15 : chr "LowIncomeTracts" "0" "1" "0" ...
$ V16 : chr "PovertyRate" "11.3" "17.9" "15" ...
$ V17 : chr "MedianFamilyIncome" "81250" "49000" "62609" ...
$ V18 : chr "LA1and10" "1" "1" "1" ...
$ V19 : chr "LAhalfand10" "1" "1" "1" ...
$ V20 : chr "LA1and20" "1" "1" "1" ...
$ V21 : chr "LATracts_half" "1" "1" "1" ...
$ V22 : chr "LATracts1" "1" "1" "1" ...
$ V23 : chr "LATracts10" "0" "0" "0" ...
$ V24 : chr "LATracts20" "0" "0" "0" ...
$ V25 : chr "LATractsVehicle_20" "0" "0" "0" ...
$ V26 : chr "LAPOP1_10" "1896" "1261" "1552" ...
$ V27 : chr "LAPOP05_10" "1912" "2170" "2857" ...
$ V28 : chr "LAPOP1_20" "1896" "1261" "1552" ...
$ V29 : chr "LALOWI1_10" "461" "604" "478" ...
$ V30 : chr "LALOWI05_10" "467" "962" "971" ...
$ V31 : chr "LALOWI1_20" "461" "604" "478" ...
$ V32 : chr "lapophalf" "1912" "2170" "2857" ...
$ V33 : chr "lapophalfshare" "100" "100" "84.7" ...
$ V34 : chr "lalowihalf" "467" "962" "971" ...
$ V35 : chr "lalowihalfshare" "24.42" "44.34" "28.79" ...
$ V36 : chr "lakidshalf" "507" "606" "771" ...
$ V37 : chr "lakidshalfshare" "26.52" "27.93" "22.86" ...
$ V38 : chr "laseniorshalf" "221" "214" "358" ...
$ V39 : chr "laseniorshalfshare" "11.56" "9.86" "10.6" ...
$ V40 : chr "lawhitehalf" "1622" "888" "2177" ...
$ V41 : chr "lawhitehalfshare" "84.83" "40.92" "64.53" ...
$ V42 : chr "lablackhalf" "217" "1217" "554" ...
$ V43 : chr "lablackhalfshare" "11.35" "56.08" "16.43" ...
$ V44 : chr "laasianhalf" "14" "5" "10" ...
$ V45 : chr "laasianhalfshare" "0.73" "0.23" "0.3" ...
$ V46 : chr "lanhopihalf" "0" "0" "1" ...
$ V47 : chr "lanhopihalfshare" "0" "0" "0.03" ...
$ V48 : chr "laaianhalf" "14" "5" "10" ...
$ V49 : chr "laaianhalfshare" "0.73" "0.23" "0.3" ...
$ V50 : chr "laomultirhalf" "45" "55" "105" ...
$ V51 : chr "laomultirhalfshare" "2.35" "2.53" "3.1" ...
$ V52 : chr "lahisphalf" "44" "75" "78" ...
$ V53 : chr "lahisphalfshare" "2.3" "3.46" "2.3" ...
$ V54 : chr "lahunvhalf" "5" "93" "39" ...
$ V55 : chr "lahunvhalfshare" "0.79" "12.47" "3.09" ...
$ V56 : chr "lasnaphalf" "92" "161" "139" ...
$ V57 : chr "lasnaphalfshare" "13.33" "21.7" "11.05" ...
$ V58 : chr "lapop1" "1896" "1261" "1552" ...
$ V59 : chr "lapop1share" "99.19" "58.11" "46" ...
$ V60 : chr "lalowi1" "461" "604" "478" ...
$ V61 : chr "lalowi1share" "24.11" "27.83" "14.18" ...
$ V62 : chr "lakids1" "504" "406" "416" ...
$ V63 : chr "lakids1share" "26.33" "18.69" "12.34" ...
$ V64 : chr "laseniors1" "219" "127" "201" ...
$ V65 : chr "laseniors1share" "11.44" "5.83" "5.96" ...
$ V66 : chr "lawhite1" "1611" "357" "1242" ...
$ V67 : chr "lawhite1share" "84.26" "16.43" "36.81" ...
$ V68 : chr "lablack1" "214" "854" "255" ...
$ V69 : chr "lablack1share" "11.17" "39.36" "7.56" ...
$ V70 : chr "laasian1" "14" "4" "8" ...
$ V71 : chr "laasian1share" "0.72" "0.18" "0.24" ...
$ V72 : chr "lanhopi1" "0" "0" "0" ...
$ V73 : chr "lanhopi1share" "0" "0" "0" ...
$ V74 : chr "laaian1" "14" "4" "2" ...
$ V75 : chr "laaian1share" "0.73" "0.2" "0.06" ...
$ V76 : chr "laomultir1" "44" "42" "45" ...
$ V77 : chr "laomultir1share" "2.31" "1.93" "1.33" ...
$ V78 : chr "lahisp1" "43" "33" "36" ...
$ V79 : chr "lahisp1share" "2.27" "1.52" "1.08" ...
$ V80 : chr "lahunv1" "5" "67" "0" ...
$ V81 : chr "lahunv1share" "0.79" "9" "0" ...
$ V82 : chr "lasnap1" "92" "96" "74" ...
$ V83 : chr "lasnap1share" "13.22" "12.95" "5.87" ...
$ V84 : chr "lapop10" "NULL" "NULL" "NULL" ...
$ V85 : chr "lapop10share" "NULL" "NULL" "NULL" ...
$ V86 : chr "lalowi10" "NULL" "NULL" "NULL" ...
$ V87 : chr "lalowi10share" "NULL" "NULL" "NULL" ...
$ V88 : chr "lakids10" "NULL" "NULL" "NULL" ...
$ V89 : chr "lakids10share" "NULL" "NULL" "NULL" ...
$ V90 : chr "laseniors10" "NULL" "NULL" "NULL" ...
$ V91 : chr "laseniors10share" "NULL" "NULL" "NULL" ...
$ V92 : chr "lawhite10" "NULL" "NULL" "NULL" ...
$ V93 : chr "lawhite10share" "NULL" "NULL" "NULL" ...
$ V94 : chr "lablack10" "NULL" "NULL" "NULL" ...
$ V95 : chr "lablack10share" "NULL" "NULL" "NULL" ...
$ V96 : chr "laasian10" "NULL" "NULL" "NULL" ...
$ V97 : chr "laasian10share" "NULL" "NULL" "NULL" ...
$ V98 : chr "lanhopi10" "NULL" "NULL" "NULL" ...
$ V99 : chr "lanhopi10share" "NULL" "NULL" "NULL" ...
[list output truncated]df_clean <- na.omit(Food.Access.Research.Atlas)
#Food.Access.Research.Atlas$TIDAL.Popularity <- NULL