From ac744d672641e1cb793e25501ba7acf6db702770 Mon Sep 17 00:00:00 2001 From: Liying000888 Date: Sat, 14 Sep 2024 20:03:49 -0700 Subject: [PATCH] https://github.com/USCbiostats/PM566/issues/76 --- Lab 3.html | 8401 +++++++++++++++++++++++++++++++++++++++++++++++++++- Lab 3.qmd | 1 + 2 files changed, 8317 insertions(+), 85 deletions(-) diff --git a/Lab 3.html b/Lab 3.html index b91f816..fed32a8 100644 --- a/Lab 3.html +++ b/Lab 3.html @@ -16,11 +16,10 @@ div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;} ul.task-list{list-style: none;} ul.task-list li input[type="checkbox"] { - width: 0.8em; - margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */ - vertical-align: middle; +width: 0.8em; +margin: 0 0.8em 0.2em -1em; vertical-align: middle; } -/* CSS for syntax highlighting */ + pre > code.sourceCode { white-space: pre; position: relative; } pre > code.sourceCode > span { line-height: 1.25; } pre > code.sourceCode > span:empty { height: 1.2em; } @@ -36,49 +35,8281 @@ pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; } } pre.numberSource code - { counter-reset: source-line 0; } +{ counter-reset: source-line 0; } pre.numberSource code > span - { position: relative; left: -4em; counter-increment: source-line; } +{ position: relative; left: -4em; counter-increment: source-line; } pre.numberSource code > span > a:first-child::before - { content: counter(source-line); - position: relative; left: -1em; text-align: right; vertical-align: baseline; - border: none; display: inline-block; - -webkit-touch-callout: none; -webkit-user-select: none; - -khtml-user-select: none; -moz-user-select: none; - -ms-user-select: none; user-select: none; - padding: 0 4px; width: 4em; - } -pre.numberSource { margin-left: 3em; padding-left: 4px; } +{ content: counter(source-line); +position: relative; left: -1em; text-align: right; vertical-align: baseline; +border: none; display: inline-block; +-webkit-touch-callout: none; -webkit-user-select: none; +-khtml-user-select: none; -moz-user-select: none; +-ms-user-select: none; user-select: none; +padding: 0 4px; width: 4em; +} +pre.numberSource { margin-left: 3em; padding-left: 4px; } div.sourceCode - { } +{ } @media screen { pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } } - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + @@ -111,12 +8342,12 @@

Lab 3

#Question 1

download.file(
-  "https://raw.githubusercontent.com/USCbiostats/data-science-data/master/02_met/met_all.gz",
-  destfile = file.path("~", "Downloads", "met_all.gz"),
-  method   = "libcurl",
+  "https://raw.githubusercontent.com/USCbiostats/data-science-data/master/02_met/met_all.gz",
+  destfile = file.path("~", "Downloads", "met_all.gz"),
+  method   = "libcurl",
   timeout  = 60
 )
-met <- data.table::fread(file.path("~", "Downloads", "met_all.gz"))
+met <- data.table::fread(file.path("~", "Downloads", "met_all.gz"))
 met <- as.data.frame(met)

#Question 2

@@ -196,7 +8427,7 @@

Lab 3

str(met)
-
'data.frame':   2377343 obs. of  30 variables:
+
'data.frame':   2377343 obs. of  30 variables:
  $ USAFID           : int  690150 690150 690150 690150 690150 690150 690150 690150 690150 690150 ...
  $ WBAN             : int  93121 93121 93121 93121 93121 93121 93121 93121 93121 93121 ...
  $ year             : int  2019 2019 2019 2019 2019 2019 2019 2019 2019 2019 ...
@@ -208,22 +8439,22 @@ 
Lab 3

  $ lon              : num  -116 -116 -116 -116 -116 ...
  $ elev             : int  696 696 696 696 696 696 696 696 696 696 ...
  $ wind.dir         : int  220 230 230 210 120 NA 320 10 320 350 ...
- $ wind.dir.qc      : chr  "5" "5" "5" "5" ...
- $ wind.type.code   : chr  "N" "N" "N" "N" ...
+ $ wind.dir.qc      : chr  "5" "5" "5" "5" ...
+ $ wind.type.code   : chr  "N" "N" "N" "N" ...
  $ wind.sp          : num  5.7 8.2 6.7 5.1 2.1 0 1.5 2.1 2.6 1.5 ...
- $ wind.sp.qc       : chr  "5" "5" "5" "5" ...
+ $ wind.sp.qc       : chr  "5" "5" "5" "5" ...
  $ ceiling.ht       : int  22000 22000 22000 22000 22000 22000 22000 22000 22000 22000 ...
  $ ceiling.ht.qc    : int  5 5 5 5 5 5 5 5 5 5 ...
- $ ceiling.ht.method: chr  "9" "9" "9" "9" ...
- $ sky.cond         : chr  "N" "N" "N" "N" ...
+ $ ceiling.ht.method: chr  "9" "9" "9" "9" ...
+ $ sky.cond         : chr  "N" "N" "N" "N" ...
  $ vis.dist         : int  16093 16093 16093 16093 16093 16093 16093 16093 16093 16093 ...
- $ vis.dist.qc      : chr  "5" "5" "5" "5" ...
- $ vis.var          : chr  "N" "N" "N" "N" ...
- $ vis.var.qc       : chr  "5" "5" "5" "5" ...
+ $ vis.dist.qc      : chr  "5" "5" "5" "5" ...
+ $ vis.var          : chr  "N" "N" "N" "N" ...
+ $ vis.var.qc       : chr  "5" "5" "5" "5" ...
  $ temp             : num  37.2 35.6 34.4 33.3 32.8 31.1 29.4 28.9 27.2 26.7 ...
- $ temp.qc          : chr  "5" "5" "5" "5" ...
+ $ temp.qc          : chr  "5" "5" "5" "5" ...
  $ dew.point        : num  10.6 10.6 7.2 5 5 5.6 6.1 6.7 7.8 7.8 ...
- $ dew.point.qc     : chr  "5" "5" "5" "5" ...
+ $ dew.point.qc     : chr  "5" "5" "5" "5" ...
  $ atm.press        : num  1010 1010 1011 1012 1013 ...
  $ atm.press.qc     : int  5 5 5 5 5 5 5 5 5 5 ...
  $ rh               : num  19.9 21.8 18.5 16.9 17.4 ...

@@ -259,7 +8490,7 @@ 
Lab 3

 
summary(met$temp)
-
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
+
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  -40.00   19.60   23.50   23.59   27.80   56.00   60089 

 
summary(met$elev)
@@ -269,13 +8500,13 @@

Lab 3

summary(met$wind.sp)
-
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
+
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
    0.00    0.00    2.10    2.46    3.60   36.00   79693 

 
met[met$elev==9999.0, ] <- NA
 summary(met$elev)
-
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
+
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
     -13     101     252     413     400    4113     710 

 
met <- met[met$temp > -40, ]
@@ -379,7 +8610,7 @@ 
Lab 3

  Mean   :261.5                                         Mean   : 7.245  
  3rd Qu.:310.0                                         3rd Qu.: 9.800  
  Max.   :360.0                                         Max.   :21.100  
- NA's   :237                                           NA's   :168     
+ NA's   :237                                           NA's   :168     
   wind.sp.qc          ceiling.ht    ceiling.ht.qc   ceiling.ht.method 
  Length:2117        Min.   :   30   Min.   :5.000   Length:2117       
  Class :character   1st Qu.: 2591   1st Qu.:5.000   Class :character  
@@ -387,7 +8618,7 @@ 
Lab 3

                     Mean   :15145   Mean   :5.008                     
                     3rd Qu.:22000   3rd Qu.:5.000                     
                     Max.   :22000   Max.   :9.000                     
-                    NA's   :4                                         
+                    NA's   :4                                         
    sky.cond            vis.dist     vis.dist.qc          vis.var         
  Length:2117        Min.   :    0   Length:2117        Length:2117       
  Class :character   1st Qu.:16093   Class :character   Class :character  
@@ -395,7 +8626,7 @@ 
Lab 3

                     Mean   :15913                                        
                     3rd Qu.:16093                                        
                     Max.   :16093                                        
-                    NA's   :683                                          
+                    NA's   :683                                          
   vis.var.qc             temp         temp.qc            dew.point      
  Length:2117        Min.   : 1.00   Length:2117        Min.   :-6.0000  
  Class :character   1st Qu.: 6.00   Class :character   1st Qu.: 0.0000  
@@ -411,25 +8642,25 @@ 
Lab 3

                     Mean   :NaN    Mean   :9     Mean   :60.62  
                     3rd Qu.: NA    3rd Qu.:9     3rd Qu.:61.85  
                     Max.   : NA    Max.   :9     Max.   :70.01  
-                    NA's   :2117
+ NA's :2117
-
cor(elev$temp, elev$wind.sp, use="complete")
+
cor(elev$temp, elev$wind.sp, use="complete")
[1] -0.09373843
-
cor(elev$temp, elev$hour, use="complete")
+
cor(elev$temp, elev$hour, use="complete")
[1] 0.4397261
-
cor(elev$wind.sp, elev$day, use="complete")
+
cor(elev$wind.sp, elev$day, use="complete")
[1] 0.3643079
-
cor(elev$wind.sp, elev$hour, use="complete")
+
cor(elev$wind.sp, elev$hour, use="complete")
[1] 0.08807315
-
cor(elev$temp, elev$day, use="complete")
+
cor(elev$temp, elev$day, use="complete")
[1] -0.003857766
@@ -437,57 +8668,57 @@

Lab 3

Question 7

-
hist(met$elev, main= "Histogram of Elevation")
+
hist(met$elev, main= "Histogram of Elevation")
-

+

-
hist(met$temp,main= "Histogram of temperature")
+
hist(met$temp,main= "Histogram of temperature")
-

+

-
hist(met$wind.sp,main= "Histogram of wind speed")
+
hist(met$wind.sp,main= "Histogram of wind speed")
-

+

library(leaflet)
 leaflet(elev) %>%
-  addProviderTiles('OpenStreetMap') %>% 
+  addProviderTiles('OpenStreetMap') %>% 
   addCircles(lat=~lat,lng=~lon, opacity=1, fillOpacity=1, radius=100)
-
- +
+ 
library(lubridate)

-Attaching package: 'lubridate'
+Attaching package: 'lubridate'
-
The following objects are masked from 'package:base':
+
The following objects are masked from 'package:base':
 
     date, intersect, setdiff, union
-
elev$date <- with(elev, ymd_h(paste(year, month, day, hour, sep= ' ')))
+
elev$date <- with(elev, ymd_h(paste(year, month, day, hour, sep= ' ')))
 summary(elev$date)

 

 
                      Min.                    1st Qu. 
-"2019-08-01 00:00:00.0000" "2019-08-08 11:00:00.0000" 
+"2019-08-01 00:00:00.0000" "2019-08-08 11:00:00.0000" 
                     Median                       Mean 
-"2019-08-16 22:00:00.0000" "2019-08-16 14:09:56.8823" 
+"2019-08-16 22:00:00.0000" "2019-08-16 14:09:56.8823" 
                    3rd Qu.                       Max. 
-"2019-08-24 11:00:00.0000" "2019-08-31 22:00:00.0000" 

+"2019-08-24 11:00:00.0000" "2019-08-31 22:00:00.0000" 
elev <- elev[order(elev$date), ]
 head(elev)
@@ -528,19 +8759,19 @@

Question 7

221701 2019-08-01 01:00:00 221702 2019-08-01 02:00:00
-
plot(elev$date,elev$temp, type = "l")
+
plot(elev$date,elev$temp, type = "l")
-

+

-
plot(elev$date,elev$wind.sp, type = "l")
+
plot(elev$date,elev$wind.sp, type = "l")
-

+

@@ -639,7 +8870,7 @@

Question 8

return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href); } // Inspect non-navigation links and adorn them if external - var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool)'); + var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool)'); for (var i=0; i