Demo20220323
使用readr 讀取資料
library(readr)## Warning: 套件 'readr' 是用 R 版本 4.1.3 來建造的X03_17_2022 <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/03-17-2022.csv")## Rows: 4010 Columns: 14
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (4): Admin2, Province_State, Country_Region, Combined_Key
## dbl (7): FIPS, Lat, Long_, Confirmed, Deaths, Incident_Rate, Case_Fatality_...
## lgl (2): Recovered, Active
## dttm (1): Last_Update
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.View(X03_17_2022)使用dplyr 分析資料
library(dplyr)## Warning: 套件 'dplyr' 是用 R 版本 4.1.3 來建造的##
## 載入套件：'dplyr'## 下列物件被遮斷自 'package:stats':
##
## filter, lag## 下列物件被遮斷自 'package:base':
##
## intersect, setdiff, setequal, union# SELECT Country_Region, Confirmed FROM X03-17-2022 WHERE Confirmed > 1000000 ORDER BY Confirmed DESC limit 10
X03_17_2022 %>%
select(Country_Region, Confirmed) %>%
filter(Confirmed > 1000000) %>%
arrange(desc(Confirmed)) %>%
head(10)# SELECT Country_Region, sum(Confirmed) FROM x03_17_2022 GROUP BY Country_Region ORDER BY sum(Confirmed) DESC LIMIT 10
X03_17_2022 %>%
select(Country_Region, Confirmed) %>%
group_by(Country_Region) %>%
summarise(Confirmed_Total = sum(Confirmed) ) %>%
arrange(desc(Confirmed_Total))%>%
head(10)homework
請找出20220316 ~ 20220317 新增確診數最多的10個國家
library(readr)
X03_17_2022 <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/03-17-2022.csv")## Rows: 4010 Columns: 14
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (4): Admin2, Province_State, Country_Region, Combined_Key
## dbl (7): FIPS, Lat, Long_, Confirmed, Deaths, Incident_Rate, Case_Fatality_...
## lgl (2): Recovered, Active
## dttm (1): Last_Update
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.X03_16_2022 <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/03-16-2022.csv")## Rows: 4010 Columns: 14
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (4): Admin2, Province_State, Country_Region, Combined_Key
## dbl (7): FIPS, Lat, Long_, Confirmed, Deaths, Incident_Rate, Case_Fatality_...
## lgl (2): Recovered, Active
## dttm (1): Last_Update
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.covid19_0317_Confirmed <- X03_17_2022 %>%
select(Country_Region, Confirmed) %>%
group_by(Country_Region) %>%
summarise(Confirmed_Total = sum(Confirmed) )
covid19_0316_Confirmed <- X03_16_2022 %>%
select(Country_Region, Confirmed) %>%
group_by(Country_Region) %>%
summarise(Confirmed_Total = sum(Confirmed) )
# SELECT * FROM convid19_0317_confirmed INNER JOIN covid19_0316_confirmed ON convid19_0317_confirmed.Country_Region = convid19_0316_confirmed.Country_Region
covid19_0317_Confirmed %>%
inner_join(covid19_0316_Confirmed, by = 'Country_Region')covid19_0317_Confirmed %>%
inner_join(covid19_0316_Confirmed, by = 'Country_Region') %>%
mutate(Confirmed_Diff = Confirmed_Total.x - Confirmed_Total.y) %>%
arrange(desc(Confirmed_Diff)) %>%
head(10) #select(Country_Region,diff_Confirmed = Confirmed_Total.x - Confirmed_Total.y)資料視覺化
library(readr)
time_series_covid19_confirmed_global <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")## Rows: 284 Columns: 795
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (2): Province/State, Country/Region
## dbl (793): Lat, Long, 1/22/20, 1/23/20, 1/24/20, 1/25/20, 1/26/20, 1/27/20, ...
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.View(time_series_covid19_confirmed_global)
df <- time_series_covid19_confirmed_global
col_names <- colnames(df)
date_cols <- col_names[5:length(df)]
col_names[5:length(col_names)]## [1] "1/22/20" "1/23/20" "1/24/20" "1/25/20" "1/26/20" "1/27/20"
## [7] "1/28/20" "1/29/20" "1/30/20" "1/31/20" "2/1/20" "2/2/20"
## [13] "2/3/20" "2/4/20" "2/5/20" "2/6/20" "2/7/20" "2/8/20"
## [19] "2/9/20" "2/10/20" "2/11/20" "2/12/20" "2/13/20" "2/14/20"
## [25] "2/15/20" "2/16/20" "2/17/20" "2/18/20" "2/19/20" "2/20/20"
## [31] "2/21/20" "2/22/20" "2/23/20" "2/24/20" "2/25/20" "2/26/20"
## [37] "2/27/20" "2/28/20" "2/29/20" "3/1/20" "3/2/20" "3/3/20"
## [43] "3/4/20" "3/5/20" "3/6/20" "3/7/20" "3/8/20" "3/9/20"
## [49] "3/10/20" "3/11/20" "3/12/20" "3/13/20" "3/14/20" "3/15/20"
## [55] "3/16/20" "3/17/20" "3/18/20" "3/19/20" "3/20/20" "3/21/20"
## [61] "3/22/20" "3/23/20" "3/24/20" "3/25/20" "3/26/20" "3/27/20"
## [67] "3/28/20" "3/29/20" "3/30/20" "3/31/20" "4/1/20" "4/2/20"
## [73] "4/3/20" "4/4/20" "4/5/20" "4/6/20" "4/7/20" "4/8/20"
## [79] "4/9/20" "4/10/20" "4/11/20" "4/12/20" "4/13/20" "4/14/20"
## [85] "4/15/20" "4/16/20" "4/17/20" "4/18/20" "4/19/20" "4/20/20"
## [91] "4/21/20" "4/22/20" "4/23/20" "4/24/20" "4/25/20" "4/26/20"
## [97] "4/27/20" "4/28/20" "4/29/20" "4/30/20" "5/1/20" "5/2/20"
## [103] "5/3/20" "5/4/20" "5/5/20" "5/6/20" "5/7/20" "5/8/20"
## [109] "5/9/20" "5/10/20" "5/11/20" "5/12/20" "5/13/20" "5/14/20"
## [115] "5/15/20" "5/16/20" "5/17/20" "5/18/20" "5/19/20" "5/20/20"
## [121] "5/21/20" "5/22/20" "5/23/20" "5/24/20" "5/25/20" "5/26/20"
## [127] "5/27/20" "5/28/20" "5/29/20" "5/30/20" "5/31/20" "6/1/20"
## [133] "6/2/20" "6/3/20" "6/4/20" "6/5/20" "6/6/20" "6/7/20"
## [139] "6/8/20" "6/9/20" "6/10/20" "6/11/20" "6/12/20" "6/13/20"
## [145] "6/14/20" "6/15/20" "6/16/20" "6/17/20" "6/18/20" "6/19/20"
## [151] "6/20/20" "6/21/20" "6/22/20" "6/23/20" "6/24/20" "6/25/20"
## [157] "6/26/20" "6/27/20" "6/28/20" "6/29/20" "6/30/20" "7/1/20"
## [163] "7/2/20" "7/3/20" "7/4/20" "7/5/20" "7/6/20" "7/7/20"
## [169] "7/8/20" "7/9/20" "7/10/20" "7/11/20" "7/12/20" "7/13/20"
## [175] "7/14/20" "7/15/20" "7/16/20" "7/17/20" "7/18/20" "7/19/20"
## [181] "7/20/20" "7/21/20" "7/22/20" "7/23/20" "7/24/20" "7/25/20"
## [187] "7/26/20" "7/27/20" "7/28/20" "7/29/20" "7/30/20" "7/31/20"
## [193] "8/1/20" "8/2/20" "8/3/20" "8/4/20" "8/5/20" "8/6/20"
## [199] "8/7/20" "8/8/20" "8/9/20" "8/10/20" "8/11/20" "8/12/20"
## [205] "8/13/20" "8/14/20" "8/15/20" "8/16/20" "8/17/20" "8/18/20"
## [211] "8/19/20" "8/20/20" "8/21/20" "8/22/20" "8/23/20" "8/24/20"
## [217] "8/25/20" "8/26/20" "8/27/20" "8/28/20" "8/29/20" "8/30/20"
## [223] "8/31/20" "9/1/20" "9/2/20" "9/3/20" "9/4/20" "9/5/20"
## [229] "9/6/20" "9/7/20" "9/8/20" "9/9/20" "9/10/20" "9/11/20"
## [235] "9/12/20" "9/13/20" "9/14/20" "9/15/20" "9/16/20" "9/17/20"
## [241] "9/18/20" "9/19/20" "9/20/20" "9/21/20" "9/22/20" "9/23/20"
## [247] "9/24/20" "9/25/20" "9/26/20" "9/27/20" "9/28/20" "9/29/20"
## [253] "9/30/20" "10/1/20" "10/2/20" "10/3/20" "10/4/20" "10/5/20"
## [259] "10/6/20" "10/7/20" "10/8/20" "10/9/20" "10/10/20" "10/11/20"
## [265] "10/12/20" "10/13/20" "10/14/20" "10/15/20" "10/16/20" "10/17/20"
## [271] "10/18/20" "10/19/20" "10/20/20" "10/21/20" "10/22/20" "10/23/20"
## [277] "10/24/20" "10/25/20" "10/26/20" "10/27/20" "10/28/20" "10/29/20"
## [283] "10/30/20" "10/31/20" "11/1/20" "11/2/20" "11/3/20" "11/4/20"
## [289] "11/5/20" "11/6/20" "11/7/20" "11/8/20" "11/9/20" "11/10/20"
## [295] "11/11/20" "11/12/20" "11/13/20" "11/14/20" "11/15/20" "11/16/20"
## [301] "11/17/20" "11/18/20" "11/19/20" "11/20/20" "11/21/20" "11/22/20"
## [307] "11/23/20" "11/24/20" "11/25/20" "11/26/20" "11/27/20" "11/28/20"
## [313] "11/29/20" "11/30/20" "12/1/20" "12/2/20" "12/3/20" "12/4/20"
## [319] "12/5/20" "12/6/20" "12/7/20" "12/8/20" "12/9/20" "12/10/20"
## [325] "12/11/20" "12/12/20" "12/13/20" "12/14/20" "12/15/20" "12/16/20"
## [331] "12/17/20" "12/18/20" "12/19/20" "12/20/20" "12/21/20" "12/22/20"
## [337] "12/23/20" "12/24/20" "12/25/20" "12/26/20" "12/27/20" "12/28/20"
## [343] "12/29/20" "12/30/20" "12/31/20" "1/1/21" "1/2/21" "1/3/21"
## [349] "1/4/21" "1/5/21" "1/6/21" "1/7/21" "1/8/21" "1/9/21"
## [355] "1/10/21" "1/11/21" "1/12/21" "1/13/21" "1/14/21" "1/15/21"
## [361] "1/16/21" "1/17/21" "1/18/21" "1/19/21" "1/20/21" "1/21/21"
## [367] "1/22/21" "1/23/21" "1/24/21" "1/25/21" "1/26/21" "1/27/21"
## [373] "1/28/21" "1/29/21" "1/30/21" "1/31/21" "2/1/21" "2/2/21"
## [379] "2/3/21" "2/4/21" "2/5/21" "2/6/21" "2/7/21" "2/8/21"
## [385] "2/9/21" "2/10/21" "2/11/21" "2/12/21" "2/13/21" "2/14/21"
## [391] "2/15/21" "2/16/21" "2/17/21" "2/18/21" "2/19/21" "2/20/21"
## [397] "2/21/21" "2/22/21" "2/23/21" "2/24/21" "2/25/21" "2/26/21"
## [403] "2/27/21" "2/28/21" "3/1/21" "3/2/21" "3/3/21" "3/4/21"
## [409] "3/5/21" "3/6/21" "3/7/21" "3/8/21" "3/9/21" "3/10/21"
## [415] "3/11/21" "3/12/21" "3/13/21" "3/14/21" "3/15/21" "3/16/21"
## [421] "3/17/21" "3/18/21" "3/19/21" "3/20/21" "3/21/21" "3/22/21"
## [427] "3/23/21" "3/24/21" "3/25/21" "3/26/21" "3/27/21" "3/28/21"
## [433] "3/29/21" "3/30/21" "3/31/21" "4/1/21" "4/2/21" "4/3/21"
## [439] "4/4/21" "4/5/21" "4/6/21" "4/7/21" "4/8/21" "4/9/21"
## [445] "4/10/21" "4/11/21" "4/12/21" "4/13/21" "4/14/21" "4/15/21"
## [451] "4/16/21" "4/17/21" "4/18/21" "4/19/21" "4/20/21" "4/21/21"
## [457] "4/22/21" "4/23/21" "4/24/21" "4/25/21" "4/26/21" "4/27/21"
## [463] "4/28/21" "4/29/21" "4/30/21" "5/1/21" "5/2/21" "5/3/21"
## [469] "5/4/21" "5/5/21" "5/6/21" "5/7/21" "5/8/21" "5/9/21"
## [475] "5/10/21" "5/11/21" "5/12/21" "5/13/21" "5/14/21" "5/15/21"
## [481] "5/16/21" "5/17/21" "5/18/21" "5/19/21" "5/20/21" "5/21/21"
## [487] "5/22/21" "5/23/21" "5/24/21" "5/25/21" "5/26/21" "5/27/21"
## [493] "5/28/21" "5/29/21" "5/30/21" "5/31/21" "6/1/21" "6/2/21"
## [499] "6/3/21" "6/4/21" "6/5/21" "6/6/21" "6/7/21" "6/8/21"
## [505] "6/9/21" "6/10/21" "6/11/21" "6/12/21" "6/13/21" "6/14/21"
## [511] "6/15/21" "6/16/21" "6/17/21" "6/18/21" "6/19/21" "6/20/21"
## [517] "6/21/21" "6/22/21" "6/23/21" "6/24/21" "6/25/21" "6/26/21"
## [523] "6/27/21" "6/28/21" "6/29/21" "6/30/21" "7/1/21" "7/2/21"
## [529] "7/3/21" "7/4/21" "7/5/21" "7/6/21" "7/7/21" "7/8/21"
## [535] "7/9/21" "7/10/21" "7/11/21" "7/12/21" "7/13/21" "7/14/21"
## [541] "7/15/21" "7/16/21" "7/17/21" "7/18/21" "7/19/21" "7/20/21"
## [547] "7/21/21" "7/22/21" "7/23/21" "7/24/21" "7/25/21" "7/26/21"
## [553] "7/27/21" "7/28/21" "7/29/21" "7/30/21" "7/31/21" "8/1/21"
## [559] "8/2/21" "8/3/21" "8/4/21" "8/5/21" "8/6/21" "8/7/21"
## [565] "8/8/21" "8/9/21" "8/10/21" "8/11/21" "8/12/21" "8/13/21"
## [571] "8/14/21" "8/15/21" "8/16/21" "8/17/21" "8/18/21" "8/19/21"
## [577] "8/20/21" "8/21/21" "8/22/21" "8/23/21" "8/24/21" "8/25/21"
## [583] "8/26/21" "8/27/21" "8/28/21" "8/29/21" "8/30/21" "8/31/21"
## [589] "9/1/21" "9/2/21" "9/3/21" "9/4/21" "9/5/21" "9/6/21"
## [595] "9/7/21" "9/8/21" "9/9/21" "9/10/21" "9/11/21" "9/12/21"
## [601] "9/13/21" "9/14/21" "9/15/21" "9/16/21" "9/17/21" "9/18/21"
## [607] "9/19/21" "9/20/21" "9/21/21" "9/22/21" "9/23/21" "9/24/21"
## [613] "9/25/21" "9/26/21" "9/27/21" "9/28/21" "9/29/21" "9/30/21"
## [619] "10/1/21" "10/2/21" "10/3/21" "10/4/21" "10/5/21" "10/6/21"
## [625] "10/7/21" "10/8/21" "10/9/21" "10/10/21" "10/11/21" "10/12/21"
## [631] "10/13/21" "10/14/21" "10/15/21" "10/16/21" "10/17/21" "10/18/21"
## [637] "10/19/21" "10/20/21" "10/21/21" "10/22/21" "10/23/21" "10/24/21"
## [643] "10/25/21" "10/26/21" "10/27/21" "10/28/21" "10/29/21" "10/30/21"
## [649] "10/31/21" "11/1/21" "11/2/21" "11/3/21" "11/4/21" "11/5/21"
## [655] "11/6/21" "11/7/21" "11/8/21" "11/9/21" "11/10/21" "11/11/21"
## [661] "11/12/21" "11/13/21" "11/14/21" "11/15/21" "11/16/21" "11/17/21"
## [667] "11/18/21" "11/19/21" "11/20/21" "11/21/21" "11/22/21" "11/23/21"
## [673] "11/24/21" "11/25/21" "11/26/21" "11/27/21" "11/28/21" "11/29/21"
## [679] "11/30/21" "12/1/21" "12/2/21" "12/3/21" "12/4/21" "12/5/21"
## [685] "12/6/21" "12/7/21" "12/8/21" "12/9/21" "12/10/21" "12/11/21"
## [691] "12/12/21" "12/13/21" "12/14/21" "12/15/21" "12/16/21" "12/17/21"
## [697] "12/18/21" "12/19/21" "12/20/21" "12/21/21" "12/22/21" "12/23/21"
## [703] "12/24/21" "12/25/21" "12/26/21" "12/27/21" "12/28/21" "12/29/21"
## [709] "12/30/21" "12/31/21" "1/1/22" "1/2/22" "1/3/22" "1/4/22"
## [715] "1/5/22" "1/6/22" "1/7/22" "1/8/22" "1/9/22" "1/10/22"
## [721] "1/11/22" "1/12/22" "1/13/22" "1/14/22" "1/15/22" "1/16/22"
## [727] "1/17/22" "1/18/22" "1/19/22" "1/20/22" "1/21/22" "1/22/22"
## [733] "1/23/22" "1/24/22" "1/25/22" "1/26/22" "1/27/22" "1/28/22"
## [739] "1/29/22" "1/30/22" "1/31/22" "2/1/22" "2/2/22" "2/3/22"
## [745] "2/4/22" "2/5/22" "2/6/22" "2/7/22" "2/8/22" "2/9/22"
## [751] "2/10/22" "2/11/22" "2/12/22" "2/13/22" "2/14/22" "2/15/22"
## [757] "2/16/22" "2/17/22" "2/18/22" "2/19/22" "2/20/22" "2/21/22"
## [763] "2/22/22" "2/23/22" "2/24/22" "2/25/22" "2/26/22" "2/27/22"
## [769] "2/28/22" "3/1/22" "3/2/22" "3/3/22" "3/4/22" "3/5/22"
## [775] "3/6/22" "3/7/22" "3/8/22" "3/9/22" "3/10/22" "3/11/22"
## [781] "3/12/22" "3/13/22" "3/14/22" "3/15/22" "3/16/22" "3/17/22"
## [787] "3/18/22" "3/19/22" "3/20/22" "3/21/22" "3/22/22"library(tidyr)## Warning: 套件 'tidyr' 是用 R 版本 4.1.3 來建造的df_long <- df %>%
gather(Date, Confirmed, date_cols)## Note: Using an external vector in selections is ambiguous.
## i Use `all_of(date_cols)` instead of `date_cols` to silence this message.
## i See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This message is displayed once per session.df_stat <- df_long %>%
group_by(`Country/Region`, Date) %>%
summarise(Confirmed_Total = sum(Confirmed))## `summarise()` has grouped output by 'Country/Region'. You can override using
## the `.groups` argument.df_stat$Date <- as.Date(df_stat$Date, '%m/%d/%y')
df_taiwan <- df_stat %>%
filter(`Country/Region` == 'Taiwan*') %>%
arrange(desc(Date))
plot(df_taiwan$Date, df_taiwan$Confirmed_Total, type = 'o')
描述數據
curl::curl_download('https://raw.githubusercontent.com/ywchiu/fda_course/main/cdc.Rdata', 'cdc.Rdata')
load("cdc.Rdata")
head(cdc)names(cdc)## [1] "genhlth" "exerany" "hlthplan" "smoke100" "height" "weight" "wtdesire"
## [8] "age" "gender"hist(cdc$height, breaks = 10)
hist(cdc$height, breaks = 50)
hist(cdc$weight, breaks = 10)
stem(cdc$weight)##
## The decimal point is 1 digit(s) to the right of the |
##
## 6 | 80889
## 8 | 00223444555568888000000000000222222233333344455555555555555555555556+26
## 10 | 00000000000000000000000000000000000000000000000000000000000000000000+1166
## 12 | 00000000000000000000000000000000000000000000000000000000000000000000+3111
## 14 | 00000000000000000000000000000000000000000000000000000000000000000000+3751
## 16 | 00000000000000000000000000000000000000000000000000000000000000000000+4023
## 18 | 00000000000000000000000000000000000000000000000000000000000000000000+3155
## 20 | 00000000000000000000000000000000000000000000000000000000000000000000+1924
## 22 | 00000000000000000000000000000000000000000000000000000000000000000000+1027
## 24 | 00000000000000000000000000000000000000000000000000000000000000000000+501
## 26 | 00000000000000000000000000000000000000000000000000000000000000000000+192
## 28 | 00000000000000000000000000000000000000000000000000000000022335555555+66
## 30 | 00000000000000000000000000000000000000000000000000000000000000000000+18
## 32 | 000000000000455578000000
## 34 | 00000048000000000000000000000
## 36 | 0022401
## 38 | 0000550
## 40 | 000005
## 42 |
## 44 |
## 46 |
## 48 | 5
## 50 | 0summary(cdc)## genhlth exerany hlthplan smoke100
## excellent:4657 Min. :0.0000 Min. :0.0000 Min. :0.0000
## very good:6972 1st Qu.:0.0000 1st Qu.:1.0000 1st Qu.:0.0000
## good :5675 Median :1.0000 Median :1.0000 Median :0.0000
## fair :2019 Mean :0.7457 Mean :0.8738 Mean :0.4721
## poor : 677 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :1.0000 Max. :1.0000 Max. :1.0000
## height weight wtdesire age gender
## Min. :48.00 Min. : 68.0 Min. : 68.0 Min. :18.00 m: 9569
## 1st Qu.:64.00 1st Qu.:140.0 1st Qu.:130.0 1st Qu.:31.00 f:10431
## Median :67.00 Median :165.0 Median :150.0 Median :43.00
## Mean :67.18 Mean :169.7 Mean :155.1 Mean :45.07
## 3rd Qu.:70.00 3rd Qu.:190.0 3rd Qu.:175.0 3rd Qu.:57.00
## Max. :93.00 Max. :500.0 Max. :680.0 Max. :99.00數據中心
mean(cdc$weight)## [1] 169.683median(cdc$weight)## [1] 165table(cdc$genhlth)##
## excellent very good good fair poor
## 4657 6972 5675 2019 677table(cdc$smoke100)##
## 0 1
## 10559 9441pie(table(cdc$smoke100))
barplot(table(cdc$smoke100))
table(cdc$gender, cdc$smoke100)##
## 0 1
## m 4547 5022
## f 6012 4419mosaicplot(table(cdc$gender, cdc$smoke100))
離度計算
a <- c(150, 155, 160, 162, 168, 171, 173, 175, 178, 182, 185)
stem(a)##
## The decimal point is 1 digit(s) to the right of the |
##
## 15 | 05
## 16 | 028
## 17 | 1358
## 18 | 25median(a)## [1] 171quantile(a, 0.25)## 25%
## 161quantile(a, 0.75)## 75%
## 176.5176.5 - 161## [1] 15.5IQR(a)## [1] 15.5boxplot(cdc$weight)
temp <- c(20,30,10,15,20,32,18,19,22)
boxplot(temp)
temp2 <- c(20,30,10,15,20,32,18,19,22, 999,999)
boxplot(temp2)
boxplot(cdc$weight)
boxplot(cdc$weight ~ cdc$gender)
boxplot(cdc$height ~ cdc$gender)
bmi = (cdc$weight/cdc$height^2) * 703
boxplot(bmi ~ cdc$genhlth)
Standard deviation
sd(cdc$weight) ^ 2## [1] 1606.484var(cdc$weight)## [1] 1606.484contender1 <-
c(8.4,8.6,8.8,9,9,9.2,9.7,10.1,10.4,10.3,10.5,10.6,11.0,11.1,11.4,11.7,11.9,12.3,12.8,13,13,14.2,14.4,14.6)
contender2 <-
c(9.8,9.8,9.9,10.1,10.1,10.2,10.2,10.3,10.3,10.7,10.8,10.8,11,11.1,11.2,11.2,11.3,11.6,11.7,11.7,11.8,11.8,11.9,11.9)
summary(contender1)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 8.400 9.575 10.800 11.083 12.425 14.600summary(contender2)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 9.80 10.20 10.90 10.88 11.62 11.90IQR(contender1)## [1] 2.85IQR(contender2)## [1] 1.425combined <- cbind(contender1,contender2)
boxplot(combined)
sd(contender1)## [1] 1.880718sd(contender2)## [1] 0.7293038Cov, Cor
numeric_dataset <- cdc[,c('height', 'weight', 'wtdesire', 'age')]
cov(numeric_dataset)## height weight wtdesire age
## height 17.023499 91.834880 100.13654 -8.879927
## weight 91.834880 1606.484154 1026.56638 1.108694
## wtdesire 100.136542 1026.566383 1024.85178 -13.769994
## age -8.879927 1.108694 -13.76999 295.588571cor(numeric_dataset)## height weight wtdesire age
## height 1.0000000 0.555322192 0.75811946 -0.125181791
## weight 0.5553222 1.000000000 0.80005213 0.001608902
## wtdesire 0.7581195 0.800052128 1.00000000 -0.025018392
## age -0.1251818 0.001608902 -0.02501839 1.000000000plot(numeric_dataset$weight, numeric_dataset$wtdesire)
heatmap(cor(numeric_dataset))
## Probability
outcomes <- c("heads", "tails")
experiment <-sample(outcomes, size = 2000, replace=TRUE)
barplot(table(experiment))