Individual slides

Author: rdpeng

03_GettingData/dplyr/dplyr.Rmd

@@ -1,5 +1,4 @@
 % Managing Data Frames with `dplyr`
-% Biostatistics 140.776
 %
 
 ```{r, echo=FALSE, results="hide"}
@@ -177,12 +176,12 @@ Generating summary statistics by stratum
 
 ```{r, tidy=FALSE}
 chicago <- mutate(chicago, 
-                  tempcat = factor(1 * (tmpd > 90), 
+                  tempcat = factor(1 * (tmpd > 80), 
                                    labels = c("cold", "hot")))
 hotcold <- group_by(chicago, tempcat)
 summarize(hotcold, pm25 = mean(pm25, na.rm = TRUE), 
-          o3 = max(o3tmean2, na.rm = TRUE), 
-          no2 = median(no2tmean2, na.rm = TRUE))
+          o3 = max(o3tmean2), 
+          no2 = median(no2tmean2))
 ```
 
 
@@ -207,15 +206,15 @@ chicago$year <- NULL  ## Can't use mutate to create an existing variable
 # `%>%`
 
 ```{r,tidy=FALSE,eval=FALSE}
-chicago %>% mutate(year = as.POSIXlt(date)$year + 1900) 
-	%>% group_by(year) 
+chicago %>% mutate(month = as.POSIXlt(date)$mon + 1) 
+	%>% group_by(month) 
 	%>% summarize(pm25 = mean(pm25, na.rm = TRUE), 
           o3 = max(o3tmean2, na.rm = TRUE), 
           no2 = median(no2tmean2, na.rm = TRUE))
 ```
 
 ```{r,echo=FALSE}
-chicago %>% mutate(year = as.POSIXlt(date)$year + 1900) %>% group_by(year) %>% 
+chicago %>% mutate(month = as.POSIXlt(date)$mon + 1) %>% group_by(month) %>% 
 summarize(pm25 = mean(pm25, na.rm = TRUE), o3 = max(o3tmean2, na.rm = TRUE), no2 = median(no2tmean2, na.rm = TRUE))
 
 ```

03_GettingData/dplyr/dplyr.md

@@ -1,5 +1,4 @@
 % Managing Data Frames with `dplyr`
-% Biostatistics 140.776
 %
 
 
@@ -323,20 +322,20 @@ Generating summary statistics by stratum
 
 ```r
 chicago <- mutate(chicago, 
-                  tempcat = factor(1 * (tmpd > 90), 
+                  tempcat = factor(1 * (tmpd > 80), 
                                    labels = c("cold", "hot")))
 hotcold <- group_by(chicago, tempcat)
 summarize(hotcold, pm25 = mean(pm25, na.rm = TRUE), 
-          o3 = max(o3tmean2, na.rm = TRUE), 
-          no2 = median(no2tmean2, na.rm = TRUE))
+          o3 = max(o3tmean2), 
+          no2 = median(no2tmean2))
 ```
 
 ```
 ## Source: local data frame [3 x 4]
 ## 
 ##   tempcat     pm25        o3      no2
-## 1    cold 16.21831 66.587500 24.55492
-## 2     hot      NaN 58.549524 26.04565
+## 1    cold 15.97807 66.587500 24.54924
+## 2     hot 26.48118 62.969656 24.93870
 ## 3      NA 47.73750  9.416667 37.44444
 ```
 
@@ -387,37 +386,30 @@ summarize(years, pm25 = mean(pm25, na.rm = TRUE),
 
 
 ```r
-chicago %>% mutate(year = as.POSIXlt(date)$year + 1900) 
-	%>% group_by(year) 
+chicago %>% mutate(month = as.POSIXlt(date)$mon + 1) 
+	%>% group_by(month) 
 	%>% summarize(pm25 = mean(pm25, na.rm = TRUE), 
           o3 = max(o3tmean2, na.rm = TRUE), 
           no2 = median(no2tmean2, na.rm = TRUE))
 ```
 
 
 ```
-## Source: local data frame [19 x 4]
+## Source: local data frame [12 x 4]
 ## 
-##    year     pm25       o3      no2
-## 1  1987      NaN 62.96966 23.49369
-## 2  1988      NaN 61.67708 24.52296
-## 3  1989      NaN 59.72727 26.14062
-## 4  1990      NaN 52.22917 22.59583
-## 5  1991      NaN 63.10417 21.38194
-## 6  1992      NaN 50.82870 24.78921
-## 7  1993      NaN 44.30093 25.76993
-## 8  1994      NaN 52.17844 28.47500
-## 9  1995      NaN 66.58750 27.26042
-## 10 1996      NaN 58.39583 26.38715
-## 11 1997      NaN 56.54167 25.48143
-## 12 1998 18.26467 50.66250 24.58649
-## 13 1999 18.49646 57.48864 24.66667
-## 14 2000 16.93806 55.76103 23.46082
-## 15 2001 16.92632 51.81984 25.06522
-## 16 2002 15.27335 54.88043 22.73750
-## 17 2003 15.23183 56.16608 24.62500
-## 18 2004 14.62864 44.48240 23.39130
-## 19 2005 16.18556 58.84126 22.62387
+##    month     pm25       o3      no2
+## 1      1 17.76996 28.22222 25.35417
+## 2      2 20.37513 37.37500 26.78034
+## 3      3 17.40818 39.05000 26.76984
+## 4      4 13.85879 47.94907 25.03125
+## 5      5 14.07420 52.75000 24.22222
+## 6      6 15.86461 66.58750 25.01140
+## 7      7 16.57087 59.54167 22.38442
+## 8      8 16.93380 53.96701 22.98333
+## 9      9 15.91279 57.48864 24.47917
+## 10    10 14.23557 47.09275 24.15217
+## 11    11 15.15794 29.45833 23.56537
+## 12    12 17.52221 27.70833 24.45773
 ```