diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..5b6a065
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
diff --git a/YQ class activity 1.Rmd b/YQ class activity 1.Rmd
new file mode 100644
index 0000000..0274a41
--- /dev/null
+++ b/YQ class activity 1.Rmd	
@@ -0,0 +1,49 @@
+---
+title: "activity 1"
+author: "YQ"
+date: "9/29/2019"
+output: html_document
+---
+
+
+## class activity 1
+
+```{r}
+library(tidyr)
+library(dplyr)
+
+DF1 <- read.csv("swirl-data.csv", header = TRUE)
+
+##5. Create a new data frame that only includes the variables `hash`, `lesson_name` and `attempt` called `DF2`
+DF2 <- select(DF1, hash, lesson_name, attempt)
+
+##6. Use the `group_by` function to create a data frame that sums all the attempts for each `hash` by each `lesson_name` called `DF3`
+DF3 <- DF2 %>% group_by(hash, lesson_name) %>% summarise(attempt = sum(attempt))
+## same as DF3 <- summarise(group_by(DF2, hash, lesson_name), attempt = sum(attempt))
+
+
+##8. Convert `DF3` to this format  
+DF3b <- spread(DF3, lesson_name, attempt)
+
+##9. Create a new data frame from `DF1` called `DF4` that only includes the variables `hash`, `lesson_name` and `correct`
+DF4 <- select(DF1, hash, lesson_name, correct)
+
+##10. Convert the `correct` variable so that `TRUE` is coded as the **number** `1` and `FALSE` is coded as `0` 
+DF4$correct <- ifelse(DF4$correct == TRUE, 1, 0)
+
+##11. Create a new data frame called `DF5` that provides a mean score for each student on each course
+DF5 <- 
+  ##summarise(group_by(DF4, hash, lesson_name), mean(correct, na.rm = TRUE))
+  DF4 %>% group_by(hash, lesson_name) %>% summarise(mean = mean(correct, na.rm = TRUE))
+
+##12. **Extra credit** Convert the `datetime` variable into month-day-year format and create a new data frame (`DF6`) that shows the average correct for each day
+DF6 <- select(DF1, correct, datetime)
+
+DF6$correct <- ifelse(DF6$correct == TRUE, 1, 0)
+
+DF6$datetime <- as.POSIXlt(DF6$datetime, origin = "1970-01-01 00:00.00 UTC")
+
+DF6$datetime <- strftime(DF6$datetime, format="%m-%d-%y")
+
+DF7 <- summarise(group_by(DF6, datetime), average = mean(correct, na.rm = TRUE))
+```
diff --git a/class activity 1.Rproj b/class activity 1.Rproj
new file mode 100644
index 0000000..8e3c2eb
--- /dev/null
+++ b/class activity 1.Rproj	
@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX