r_week3_hw
karmaGyatso
2022-08-01
# the csv is stored in my github and below is the link
path <- ('https://raw.githubusercontent.com/karmaggyatso/CUNY_SPS/main/week3/CigarettesB.csv')
cigData= read.csv(path)#1 Data Exploration: This should include summary statistics, means, medians, quartiles, or any other relevant information about the data set. Please include some conclusions in the R Markdown text.
summary(cigData)## X packs price income
## Length:46 Min. :4.409 Min. :-0.0326 Min. :4.529
## Class :character 1st Qu.:4.712 1st Qu.: 0.1405 1st Qu.:4.679
## Mode :character Median :4.815 Median : 0.2002 Median :4.759
## Mean :4.848 Mean : 0.2055 Mean :4.775
## 3rd Qu.:4.984 3rd Qu.: 0.2735 3rd Qu.:4.853
## Max. :5.379 Max. : 0.3640 Max. :5.103#means for column packs
mean(cigData$packs)## [1] 4.847844#median for column packs
median(cigData$packs) ## [1] 4.81495#SD for column packs
sd(cigData$packs)## [1] 0.1914581#range for column packs
range(cigData$packs) ## [1] 4.40859 5.37906#mean for column price
mean(cigData$price)## [1] 0.2055087#median for column price
median(cigData$price) ## [1] 0.200205#SD for column price
sd(cigData$price) ## [1] 0.08623038#range for column price
range(cigData$price) ## [1] -0.03260 0.36399#mean for column income
#income
mean(cigData$income)## [1] 4.775455#median for column income
median(cigData$income) ## [1] 4.758505#SD for column income
sd(cigData$income)## [1] 0.1422612#range for column income
range(cigData$income) ## [1] 4.52938 5.102682. Data wrangling: Please perform some basic transformations. They will need to make sense but could include column renaming, creating a subset of the data, replacing values, or creating new columns with derived data (for example – if it makes sense you could sum two columns together)
dataDf <- data.frame(cigData$packs,cigData$price,cigData$income)
dataDf## cigData.packs cigData.price cigData.income
## 1 4.96213 0.20487 4.64039
## 2 4.66312 0.16640 4.68389
## 3 5.10709 0.23406 4.59435
## 4 4.50449 0.36399 4.88147
## 5 4.66983 0.32149 5.09472
## 6 5.04705 0.21929 4.87087
## 7 4.65637 0.28946 5.05960
## 8 4.80081 0.28733 4.81155
## 9 4.97974 0.12826 4.73299
## 10 4.74902 0.17541 4.64307
## 11 4.81445 0.24806 4.90387
## 12 5.11129 0.08992 4.72916
## 13 4.80857 0.24081 4.74211
## 14 4.79263 0.21642 4.79613
## 15 5.37906 -0.03260 4.64937
## 16 4.98602 0.23856 4.61461
## 17 4.98722 0.29106 4.75501
## 18 4.77751 0.12575 4.94692
## 19 4.73877 0.22613 4.99998
## 20 4.94744 0.23067 4.80620
## 21 4.69589 0.34297 4.81207
## 22 4.93990 0.13638 4.52938
## 23 5.06430 0.08731 4.78189
## 24 4.73313 0.15303 4.70417
## 25 4.77558 0.18907 4.79671
## 26 4.96642 0.32304 4.83816
## 27 5.10990 0.15852 5.00319
## 28 4.70633 0.30901 5.10268
## 29 4.58107 0.16458 4.58202
## 30 4.66496 0.34701 4.96075
## 31 4.58237 0.18197 4.69163
## 32 4.97952 0.12889 4.75875
## 33 4.72720 0.19554 4.62730
## 34 4.80363 0.22784 4.83516
## 35 4.84693 0.30324 4.84670
## 36 5.07801 0.07944 4.62549
## 37 4.81545 0.13139 4.67747
## 38 5.04939 0.15547 4.72525
## 39 4.65398 0.28196 4.73437
## 40 4.40859 0.19260 4.55586
## 41 5.08799 0.18018 4.77578
## 42 4.93065 0.11818 4.85490
## 43 4.66134 0.35053 4.85645
## 44 4.82454 0.12008 4.56859
## 45 4.83026 0.22954 4.75826
## 46 5.00087 0.10029 4.71169colnames(dataDf) <- c("total_number_of_cig_packs", "price_per_pack", "grossIncome")
dataDf['totalCost'] <- dataDf$total_number_of_cig_packs * dataDf$price_per_pack
dataDf['netIncome'] <- abs(dataDf$grossIncome - dataDf$totalCost)
dataDf## total_number_of_cig_packs price_per_pack grossIncome totalCost netIncome
## 1 4.96213 0.20487 4.64039 1.0165916 3.623798
## 2 4.66312 0.16640 4.68389 0.7759432 3.907947
## 3 5.10709 0.23406 4.59435 1.1953655 3.398985
## 4 4.50449 0.36399 4.88147 1.6395893 3.241881
## 5 4.66983 0.32149 5.09472 1.5013036 3.593416
## 6 5.04705 0.21929 4.87087 1.1067676 3.764102
## 7 4.65637 0.28946 5.05960 1.3478329 3.711767
## 8 4.80081 0.28733 4.81155 1.3794167 3.432133
## 9 4.97974 0.12826 4.73299 0.6387015 4.094289
## 10 4.74902 0.17541 4.64307 0.8330256 3.810044
## 11 4.81445 0.24806 4.90387 1.1942725 3.709598
## 12 5.11129 0.08992 4.72916 0.4596072 4.269553
## 13 4.80857 0.24081 4.74211 1.1579517 3.584158
## 14 4.79263 0.21642 4.79613 1.0372210 3.758909
## 15 5.37906 -0.03260 4.64937 -0.1753574 4.824727
## 16 4.98602 0.23856 4.61461 1.1894649 3.425145
## 17 4.98722 0.29106 4.75501 1.4515803 3.303430
## 18 4.77751 0.12575 4.94692 0.6007719 4.346148
## 19 4.73877 0.22613 4.99998 1.0715781 3.928402
## 20 4.94744 0.23067 4.80620 1.1412260 3.664974
## 21 4.69589 0.34297 4.81207 1.6105494 3.201521
## 22 4.93990 0.13638 4.52938 0.6737036 3.855676
## 23 5.06430 0.08731 4.78189 0.4421640 4.339726
## 24 4.73313 0.15303 4.70417 0.7243109 3.979859
## 25 4.77558 0.18907 4.79671 0.9029189 3.893791
## 26 4.96642 0.32304 4.83816 1.6043523 3.233808
## 27 5.10990 0.15852 5.00319 0.8100213 4.193169
## 28 4.70633 0.30901 5.10268 1.4543030 3.648377
## 29 4.58107 0.16458 4.58202 0.7539525 3.828067
## 30 4.66496 0.34701 4.96075 1.6187878 3.341962
## 31 4.58237 0.18197 4.69163 0.8338539 3.857776
## 32 4.97952 0.12889 4.75875 0.6418103 4.116940
## 33 4.72720 0.19554 4.62730 0.9243567 3.702943
## 34 4.80363 0.22784 4.83516 1.0944591 3.740701
## 35 4.84693 0.30324 4.84670 1.4697831 3.376917
## 36 5.07801 0.07944 4.62549 0.4033971 4.222093
## 37 4.81545 0.13139 4.67747 0.6327020 4.044768
## 38 5.04939 0.15547 4.72525 0.7850287 3.940221
## 39 4.65398 0.28196 4.73437 1.3122362 3.422134
## 40 4.40859 0.19260 4.55586 0.8490944 3.706766
## 41 5.08799 0.18018 4.77578 0.9167540 3.859026
## 42 4.93065 0.11818 4.85490 0.5827042 4.272196
## 43 4.66134 0.35053 4.85645 1.6339395 3.222510
## 44 4.82454 0.12008 4.56859 0.5793308 3.989259
## 45 4.83026 0.22954 4.75826 1.1087379 3.649522
## 46 5.00087 0.10029 4.71169 0.5015373 4.2101533. Graphics: Please make sure to display at least one scatter plot, box plot and histogram. Don’t be limited to this. Please explore the many other options in R packages such as ggplot2
#scatterplot
plot(x=dataDf$grossIncome,y=dataDf$totalCost)
#histogram
hist(dataDf$total_number_of_cig_packs)
4. Meaningful question for analysis: Please state at the beginning a meaningful question for analysis. Use the first three steps and anything else that would be helpful to answer the question you are posing from the data set you chose. Please write a brief conclusion paragraph in R markdown at the end.
cor(dataDf$grossIncome,dataDf$totalCost)## [1] 0.4878801