Data import from local storage, i download data from kaggle
Data wrangling is the process from raw data to usable data | resource
df_nyc_ab <- read.csv("data_input/AB_NYC_2019.csv")
summary(df_nyc_ab)
## id name host_id host_name
## Min. : 2539 Length:48895 Min. : 2438 Length:48895
## 1st Qu.: 9471945 Class :character 1st Qu.: 7822033 Class :character
## Median :19677284 Mode :character Median : 30793816 Mode :character
## Mean :19017143 Mean : 67620011
## 3rd Qu.:29152178 3rd Qu.:107434423
## Max. :36487245 Max. :274321313
##
## neighbourhood_group neighbourhood latitude longitude
## Length:48895 Length:48895 Min. :40.50 Min. :-74.24
## Class :character Class :character 1st Qu.:40.69 1st Qu.:-73.98
## Mode :character Mode :character Median :40.72 Median :-73.96
## Mean :40.73 Mean :-73.95
## 3rd Qu.:40.76 3rd Qu.:-73.94
## Max. :40.91 Max. :-73.71
##
## room_type price minimum_nights number_of_reviews
## Length:48895 Min. : 0.0 Min. : 1.00 Min. : 0.00
## Class :character 1st Qu.: 69.0 1st Qu.: 1.00 1st Qu.: 1.00
## Mode :character Median : 106.0 Median : 3.00 Median : 5.00
## Mean : 152.7 Mean : 7.03 Mean : 23.27
## 3rd Qu.: 175.0 3rd Qu.: 5.00 3rd Qu.: 24.00
## Max. :10000.0 Max. :1250.00 Max. :629.00
##
## last_review reviews_per_month calculated_host_listings_count
## Length:48895 Min. : 0.010 Min. : 1.000
## Class :character 1st Qu.: 0.190 1st Qu.: 1.000
## Mode :character Median : 0.720 Median : 1.000
## Mean : 1.373 Mean : 7.144
## 3rd Qu.: 2.020 3rd Qu.: 2.000
## Max. :58.500 Max. :327.000
## NA's :10052
## availability_365
## Min. : 0.0
## 1st Qu.: 0.0
## Median : 45.0
## Mean :112.8
## 3rd Qu.:227.0
## Max. :365.0
##
colSums(is.na(df_nyc_ab))
## id name
## 0 0
## host_id host_name
## 0 0
## neighbourhood_group neighbourhood
## 0 0
## latitude longitude
## 0 0
## room_type price
## 0 0
## minimum_nights number_of_reviews
## 0 0
## last_review reviews_per_month
## 0 10052
## calculated_host_listings_count availability_365
## 0 0
sapply(df_nyc_ab, function(x) sum(duplicated(x)))
## id name
## 0 989
## host_id host_name
## 11438 37442
## neighbourhood_group neighbourhood
## 48890 48674
## latitude longitude
## 29847 34177
## room_type price
## 48892 48221
## minimum_nights number_of_reviews
## 48786 48501
## last_review reviews_per_month
## 47130 47957
## calculated_host_listings_count availability_365
## 48848 48529
boxplot(df_nyc_ab$price ~ df_nyc_ab$neighbourhood_group, main="Boxplot of Price by City", xlab="City", ylab="Price")
str(df_nyc_ab)
## 'data.frame': 48895 obs. of 16 variables:
## $ id : int 2539 2595 3647 3831 5022 5099 5121 5178 5203 5238 ...
## $ name : chr "Clean & quiet apt home by the park" "Skylit Midtown Castle" "THE VILLAGE OF HARLEM....NEW YORK !" "Cozy Entire Floor of Brownstone" ...
## $ host_id : int 2787 2845 4632 4869 7192 7322 7356 8967 7490 7549 ...
## $ host_name : chr "John" "Jennifer" "Elisabeth" "LisaRoxanne" ...
## $ neighbourhood_group : chr "Brooklyn" "Manhattan" "Manhattan" "Brooklyn" ...
## $ neighbourhood : chr "Kensington" "Midtown" "Harlem" "Clinton Hill" ...
## $ latitude : num 40.6 40.8 40.8 40.7 40.8 ...
## $ longitude : num -74 -74 -73.9 -74 -73.9 ...
## $ room_type : chr "Private room" "Entire home/apt" "Private room" "Entire home/apt" ...
## $ price : int 149 225 150 89 80 200 60 79 79 150 ...
## $ minimum_nights : int 1 1 3 1 10 3 45 2 2 1 ...
## $ number_of_reviews : int 9 45 0 270 9 74 49 430 118 160 ...
## $ last_review : chr "2018-10-19" "2019-05-21" "" "2019-07-05" ...
## $ reviews_per_month : num 0.21 0.38 NA 4.64 0.1 0.59 0.4 3.47 0.99 1.33 ...
## $ calculated_host_listings_count: int 6 2 1 1 1 1 1 1 1 4 ...
## $ availability_365 : int 365 355 365 194 0 129 0 220 0 188 ...