#Assignment 2#
#####################################################################################################################
# Session 3
#####################################################################################################################
# Task 1.1 - Check working directory and import the following files :
## "cities.csv"
## "movehubcostofliving.csv"
## "movehubqualityoflife.csv"
library(tidyr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(Hmisc)
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## Loading required package: ggplot2
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:dplyr':
##
## src, summarize
## The following objects are masked from 'package:base':
##
## format.pval, units
library(tidyverse)
## -- Attaching packages -------------------------------------------------------------------------- tidyverse 1.2.1 --
## v tibble 2.1.1 v purrr 0.3.2
## v readr 1.3.1 v stringr 1.4.0
## v tibble 2.1.1 v forcats 0.4.0
## -- Conflicts ----------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x Hmisc::src() masks dplyr::src()
## x Hmisc::summarize() masks dplyr::summarize()
library(plyr)
## -------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## -------------------------------------------------------------------------
##
## Attaching package: 'plyr'
## The following object is masked from 'package:purrr':
##
## compact
## The following objects are masked from 'package:Hmisc':
##
## is.discrete, summarize
## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
library(forecast)
setwd("E:\\Assignment R\\city_rankings_elons_tweets_dataset")
cities <- read.csv("E:\\Assignment R\\city_rankings_elons_tweets_dataset\\cities.csv")
cost_of_living <- read.csv("E:\\Assignment R\\city_rankings_elons_tweets_dataset\\movehubcostofliving.csv")
quality_of_life <- read.csv("E:\\Assignment R\\city_rankings_elons_tweets_dataset\\movehubqualityoflife.csv")
# Task 1.2 - Find the country with the highest mean of Avg Rent
cities_data <- cities %>% inner_join(cost_of_living, by = "City")
## Warning: Column `City` joining factors with different levels, coercing to
## character vector
cities_data2 <- cities_data %>% inner_join(quality_of_life, by = "City")
## Warning: Column `City` joining character vector and factor, coercing into
## character vector
max(cities_data2$Avg.Rent)
## [1] 5052.31
# Task 1.3 - Find the countries where Health.Care >60 and Crime.Rating < 40
Countries <- count(cities_data2%>%filter(cities_data2$Health.Care>60,cities_data2$Crime.Rating<40))
count(Countries)
## Using freq as weighting variable
## City Country Cappuccino Cinema Wine Gasoline
## 1 Oslo Norway 3.36 11.20 12.32 1.57
## 2 Ottawa Canada 2.39 7.65 9.56 0.80
## 3 Oxford United Kingdom 2.49 7.97 7.97 1.36
## 4 Madrid Spain 1.70 6.82 3.92 1.24
## 5 Manama Bahrain 2.60 5.20 19.61 0.17
## 6 Manchester United Kingdom 2.40 8.00 6.00 1.15
## 7 Montreal Canada 1.91 7.65 9.56 0.89
## 8 Munich Germany 2.30 7.67 5.11 1.36
## 9 Seoul South Korea 2.59 5.25 11.67 1.17
## 10 Shanghai China 2.96 8.46 8.46 0.85
## 11 Stavanger Norway 4.48 10.65 13.44 1.68
## 12 Stockholm Sweden 3.00 11.01 7.91 1.46
## 13 Stuttgart Germany 2.13 6.82 4.26 1.32
## 14 Sydney Australia 2.35 12.10 10.75 1.00
## 15 Nashville United States 3.84 12.00 13.50 0.65
## 16 Newark United States 2.45 7.19 10.46 0.67
## 17 Nicosia Cyprus 3.41 6.82 4.69 1.20
## 18 Warsaw Poland 1.66 5.19 5.19 1.18
## 19 Wellington New Zealand 2.20 8.82 8.27 1.17
## 20 Calgary Canada 2.55 8.29 9.56 0.74
## 21 Cambridge United States 1.99 8.22 7.97 1.39
## 22 Cambridge Canada 1.99 8.22 7.97 1.39
## 23 Cambridge United Kingdom 1.99 8.22 7.97 1.39
## 24 Charlotte United States 2.15 5.23 7.19 0.60
## 25 Chennai India 0.66 1.81 4.83 0.87
## 26 Chiang Mai Thailand 1.05 3.53 11.40 0.82
## 27 Cologne Germany 1.92 7.25 3.62 1.32
## 28 Copenhagen Denmark 3.66 9.15 5.72 1.40
## 29 Cork Ireland 2.13 7.08 8.52 1.36
## 30 Vadodara India 0.72 2.17 6.03 0.84
## 31 Valencia Spain 1.28 6.82 4.26 1.24
## 32 Valencia Philippines 1.28 6.82 4.26 1.24
## 33 Valencia Venezuela 1.28 6.82 4.26 1.24
## 34 Vancouver United States 2.55 7.97 12.75 0.89
## 35 Vancouver Canada 2.55 7.97 12.75 0.89
## 36 Venice Italy 1.28 6.82 3.41 1.40
## 37 Vienna Austria 2.13 7.67 4.26 1.25
## 38 Vilnius Lithuania 1.23 4.44 4.44 1.19
## 39 Porto Portugal 0.68 4.26 3.41 1.37
## 40 Prague Czech Republic 1.32 5.08 3.29 1.18
## 41 Kochi India 0.60 1.81 3.62 0.84
## 42 Taipei Taiwan 1.75 6.01 8.14 0.77
## 43 The Hague Netherlands 2.26 8.10 4.05 1.52
## 44 Tokyo Japan 2.30 11.80 8.52 0.98
## 45 Toronto Canada 2.23 8.29 9.50 0.83
## 46 Trondheim Norway 3.81 12.32 13.44 1.57
## 47 Florence Italy 1.02 6.82 4.26 1.53
## 48 Utrecht Netherlands 2.13 6.82 4.26 1.45
## 49 Gothenburg Sweden 3.30 10.76 8.01 1.44
## 50 Edinburgh United Kingdom 2.09 7.97 6.73 1.35
## 51 Edmonton Canada 2.55 8.29 11.16 0.69
## 52 Bangkok Thailand 1.37 4.10 13.68 0.91
## 53 Basel Switzerland 3.50 11.89 7.35 1.25
## 54 Bergen Norway 3.92 12.32 12.32 1.57
## 55 Berlin Germany 1.88 6.82 3.84 1.36
## 56 Braga Portugal 1.02 4.48 2.13 1.39
## 57 Budapest Hungary 1.00 4.27 2.85 1.20
## 58 Hamburg Germany 1.83 9.38 3.41 1.36
## 59 Hamilton New Zealand 1.91 7.01 8.29 0.80
## 60 Hamilton Canada 1.91 7.01 8.29 0.80
## 61 Hong Kong Hong Kong 2.78 5.89 10.10 1.52
## 62 Hyderabad India 0.72 1.81 4.83 0.91
## 63 Hyderabad Pakistan 0.72 1.81 4.83 0.91
## 64 Lausanne Switzerland 3.15 12.59 8.40 1.32
## 65 Leeds United Kingdom 1.99 7.60 6.33 1.38
## 66 Leicester United Kingdom 2.49 7.22 5.27 1.43
## 67 Limassol Cyprus 2.98 6.82 4.26 1.15
## 68 Liverpool United Kingdom 1.99 7.67 5.98 1.35
## 69 Ljubljana Slovenia 1.28 4.69 4.26 1.27
## 70 Darwin Australia 3.36 10.08 10.08 1.04
## 71 Doha Qatar 2.78 6.28 14.32 0.18
## 72 Dresden Germany 2.13 6.82 3.84 1.33
## 73 Dubai United Arab Emirates 2.62 6.23 12.77 0.31
## 74 Aachen Germany 2.05 6.88 4.26 1.33
## 75 Aberdeen United Kingdom 1.99 6.98 5.98 1.37
## 76 Addis Ababa Ethiopia 0.46 2.29 4.18 0.72
## 77 Ahmedabad India 0.72 2.11 4.22 0.85
## 78 Amsterdam Netherlands 2.09 8.52 4.26 1.45
## Avg.Rent Avg.Disposable.Income Movehub.Rating Purchase.Power
## 1 2016.66 2800.92 82.09 52.51
## 2 1020.02 2900.68 87.69 91.85
## 3 1494.67 1693.96 80.94 50.33
## 4 1193.48 1278.72 85.37 54.07
## 5 1078.72 1176.78 77.56 40.26
## 6 1200.00 1388.55 81.89 62.31
## 7 956.27 1785.03 89.28 66.99
## 8 1278.72 2045.96 86.00 63.28
## 9 1458.20 1458.20 82.43 54.30
## 10 1533.38 592.20 75.69 26.74
## 11 2240.74 2957.77 79.41 46.59
## 12 1501.88 2002.51 82.85 51.03
## 13 980.35 1943.66 82.48 65.82
## 14 2788.71 2755.12 94.53 54.82
## 15 2257.14 3089.75 80.61 80.30
## 16 980.65 2402.60 84.97 84.39
## 17 639.36 1065.60 78.76 39.03
## 18 726.59 664.31 76.76 35.77
## 19 1515.65 1763.67 81.06 49.11
## 20 1115.65 2231.29 85.77 63.90
## 21 1345.20 2730.26 82.15 54.76
## 22 1345.20 2730.26 82.15 54.76
## 23 1345.20 2730.26 82.15 54.76
## 24 915.28 2073.10 84.46 77.18
## 25 301.69 301.69 78.12 32.91
## 26 426.24 227.95 68.64 15.89
## 27 980.35 1704.96 82.18 59.18
## 28 1658.01 2001.04 82.85 49.33
## 29 1022.98 1633.36 83.55 47.98
## 30 120.68 307.73 76.54 36.37
## 31 596.74 1193.48 81.06 49.11
## 32 596.74 1193.48 81.06 49.11
## 33 596.74 1193.48 81.06 49.11
## 34 1848.79 1657.53 82.59 48.06
## 35 1848.79 1657.53 82.59 48.06
## 36 1278.72 1875.46 78.82 45.69
## 37 1248.90 1619.72 81.84 51.21
## 38 493.78 457.29 72.45 24.17
## 39 596.74 664.94 76.17 31.28
## 40 821.94 723.30 76.64 35.32
## 41 181.02 271.52 74.27 28.98
## 42 784.52 942.66 77.42 38.19
## 43 1363.97 2386.95 83.23 68.28
## 44 1967.31 2065.67 80.00 47.57
## 45 1593.78 1912.54 88.42 61.44
## 46 1680.55 2800.92 80.36 51.22
## 47 1278.72 1278.72 76.63 35.31
## 48 1193.48 1611.19 79.70 49.87
## 49 1001.25 2302.88 74.63 26.95
## 50 996.45 1992.89 83.92 58.77
## 51 1147.52 2199.42 85.94 67.19
## 52 1139.76 455.91 74.21 20.82
## 53 1649.29 3847.76 84.20 78.17
## 54 1725.37 3002.59 80.74 51.24
## 55 916.42 1772.57 89.54 68.72
## 56 383.62 596.74 75.07 30.21
## 57 341.97 414.64 74.13 24.59
## 58 1534.47 1747.59 84.66 61.13
## 59 605.64 1593.78 81.34 56.52
## 60 605.64 1593.78 81.34 56.52
## 61 5052.31 2210.39 86.37 50.07
## 62 241.35 301.69 79.35 39.93
## 63 241.35 301.69 79.35 39.93
## 64 1714.00 4266.11 87.21 90.77
## 65 797.16 1992.89 82.57 63.88
## 66 787.19 1793.60 83.36 71.88
## 67 618.05 937.73 78.30 40.13
## 68 896.80 1534.47 81.23 53.78
## 69 767.23 809.86 75.35 32.28
## 70 2015.94 2435.93 79.63 49.51
## 71 2221.74 2775.58 90.73 81.96
## 72 1193.48 2088.58 84.75 82.60
## 73 1981.57 2313.91 98.44 69.64
## 74 767.23 1619.72 81.64 60.55
## 75 1195.74 1743.78 81.89 49.70
## 76 653.77 124.22 59.88 6.38
## 77 193.08 301.69 76.16 33.69
## 78 1513.16 1747.59 84.00 47.18
## Health.Care Pollution Quality.of.Life Crime.Rating freq freq.1
## 1 88.19 29.39 71.27 35.53 1 1
## 2 66.02 33.55 86.11 22.25 1 1
## 3 66.20 11.48 72.09 24.22 1 1
## 4 73.51 55.77 59.87 39.34 1 1
## 5 72.22 17.06 63.85 19.79 1 1
## 6 61.42 0.00 73.00 24.20 1 1
## 7 66.77 6.27 78.55 31.63 1 1
## 8 88.43 43.08 90.08 15.34 1 1
## 9 75.00 85.59 60.28 21.35 1 1
## 10 78.70 61.74 31.66 16.51 1 1
## 11 62.48 29.13 76.50 20.83 1 1
## 12 82.50 13.93 78.58 25.62 1 1
## 13 80.38 16.89 90.40 23.96 1 1
## 14 71.27 18.48 74.32 32.80 1 1
## 15 60.30 0.00 80.50 25.50 1 1
## 16 79.72 62.14 73.21 30.21 1 1
## 17 72.04 6.27 57.58 38.22 1 1
## 18 63.33 86.16 51.82 32.03 1 1
## 19 73.72 30.55 79.83 27.38 1 1
## 20 75.33 23.53 87.57 29.53 1 1
## 21 81.48 57.18 70.61 24.22 1 1
## 22 81.48 57.18 70.61 24.22 1 1
## 23 81.48 57.18 70.61 24.22 1 1
## 24 72.08 67.05 84.39 30.21 1 1
## 25 67.49 78.07 43.89 33.22 1 1
## 26 85.91 30.55 37.50 37.78 1 1
## 27 67.88 68.41 82.82 27.08 1 1
## 28 85.14 30.54 75.23 32.39 1 1
## 29 64.32 18.48 76.37 35.83 1 1
## 30 77.87 92.42 54.98 32.03 1 1
## 31 72.07 35.24 64.89 26.04 1 1
## 32 72.07 35.24 64.89 26.04 1 1
## 33 72.07 35.24 64.89 26.04 1 1
## 34 83.73 18.48 71.89 30.03 1 1
## 35 83.73 18.48 71.89 30.03 1 1
## 36 72.67 11.48 70.34 21.48 1 1
## 37 79.86 22.39 77.21 27.45 1 1
## 38 77.31 82.08 64.19 27.93 1 1
## 39 61.51 67.64 58.95 37.51 1 1
## 40 64.15 41.53 58.85 34.54 1 1
## 41 70.23 71.78 45.13 16.93 1 1
## 42 88.89 87.62 52.35 15.71 1 1
## 43 66.74 37.21 79.99 29.76 1 1
## 44 71.53 30.54 69.29 13.91 1 1
## 45 66.11 8.95 77.02 27.40 1 1
## 46 81.67 14.53 82.67 19.80 1 1
## 47 67.11 29.44 53.73 39.58 1 1
## 48 70.90 18.27 72.61 29.76 1 1
## 49 68.24 92.42 71.51 25.62 1 1
## 50 60.64 13.94 75.03 30.51 1 1
## 51 78.83 22.79 89.58 31.14 1 1
## 52 95.96 60.39 37.54 36.10 1 1
## 53 79.74 59.18 88.27 28.12 1 1
## 54 84.95 18.40 83.76 16.67 1 1
## 55 65.48 16.05 91.17 24.18 1 1
## 56 69.71 14.54 69.91 18.12 1 1
## 57 60.42 68.38 46.58 34.18 1 1
## 58 82.41 67.78 87.18 25.52 1 1
## 59 86.67 81.68 84.83 35.68 1 1
## 60 86.67 81.68 84.83 35.68 1 1
## 61 67.59 14.88 59.50 16.31 1 1
## 62 63.89 89.72 54.97 36.90 1 1
## 63 63.89 89.72 54.97 36.90 1 1
## 64 65.85 87.62 73.21 35.55 1 1
## 65 81.48 18.48 78.06 28.91 1 1
## 66 60.64 18.04 76.19 24.22 1 1
## 67 77.60 26.74 74.83 23.75 1 1
## 68 82.86 55.35 83.14 28.70 1 1
## 69 71.76 85.59 61.87 32.94 1 1
## 70 75.28 6.78 78.52 32.80 1 1
## 71 68.06 83.45 80.28 27.17 1 1
## 72 78.29 16.89 90.21 15.34 1 1
## 73 67.78 30.81 85.16 19.36 1 1
## 74 73.25 11.69 90.52 15.34 1 1
## 75 82.86 34.31 76.77 24.22 1 1
## 76 63.89 85.59 28.41 26.04 1 1
## 77 61.67 68.21 57.01 18.18 1 1
## 78 68.06 53.42 72.85 29.76 1 1
# Task 1.4 - Rank the Countries by average Quality of Life, where average pollution
# and average Crime Rating are less than the mean (for all cities of all countries combined),
# and mean of Avg Disposable Income > 2000
# Task 1.5 - Rank the countries separetly based on mean of Gasoline price, Health care, Pollution, Avg Rent and
# Avg Disposable Income. Then find mean of these ranks for each country and order the countries by it.
#####################################################################################################################
# Session 4
#####################################################################################################################
# Task 1.1 - Check working directory and import the following files :
# "elonmusk_tweets.csv"
setwd("E:\\Assignment R\\city_rankings_elons_tweets_dataset")
# Task 1.2 - Find count of Elon's tweets by Session of the week
tweets <- read.csv("elonmusk_tweets.csv")
tweets<-Sys.time()
p<-as.POSIXlt(tweets)
p
## [1] "2020-01-26 21:27:18 IST"
names(unclass(p))
## [1] "sec" "min" "hour" "mday" "mon" "year" "wday"
## [8] "yday" "isdst" "zone" "gmtoff"
p$hour
## [1] 21
p$sec
## [1] 18.67306
count1 <- strftime(tweets,"%W")
count1
## [1] "03"
# Task 1.3 - Find count of Elon's tweets by Hour of Session
count2 <- strftime(tweets,"%H")
count2
## [1] "21"
# TAsk 1.4 - Find count of Elon's tweets by By year and Month
count3 <- strftime(tweets,"%B")
count3
## [1] "January"
# Task 1.5 - Fid the weekSessions with the word 'u' in them
# Task 1.6 - Find tweets with the word tesla in it
# Task 1.7 - Find the number of times the word 'human' has been mentioned in his tweets.
# Then find the % of times it was mentioned on a 'WednesSession'