Hi Matt, Thanks for the great tutorial. I hope you can help with my query. I am stuck with the step_dummy function. The script is running fine for me (see below) up until this point but it does not convert the categorical data into binary. I still only have 17 columns with 45k rows after running this. I have checked that my libraries are all the required versions and seem to have no issue there. Do you have any suggestions? Thanks Matt, John. recipe_obj % step_rm(ID) %>% step_discretize(all_numeric(), options = list(min_unique = 1)) %>% step_dummy(all_nominal(), one_hot = TRUE, naming = partial(dummy_names, sep = "__")) %>% prep()
Could you guys do something about the video's blurriness? After running each line of code, this error message comes up? Can you explain this error message? > # 3.0 PERFORM VLOOKUP EQUIVALENT ---- Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) : invalid first argument > data_joined_tbl % Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) : invalid first argument + map(~ read_excel(path = path, sheet = .)) %>% Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) : invalid first argument + reduce(left_join) Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) : invalid first argument
Hello all, Thanks a lot for this tutorial. Please I have a question. I tried: map(sheets~ read_excel(path = path, sheet = .)) But got an error> Why is this so? I imagine thw "%>%"(pipe) just supplies the data to the nested function. How come it gives an error when applied directly?
Hi Onimisi, Please double-check the verified code against your code. You can see it here: github.com/business-science/presentations/blob/master/2019_02_13_Learning_Lab_Marketing_Analytics/marketing_analysis.R
Hello, I am getting the following error for the one_hot=TRUE parameter in step_dummies: `TRUE` must evaluate to column positions or names, not a logical vector .
Did you check against the verified code? github.com/business-science/presentations/blob/master/2019_02_13_Learning_Lab_Marketing_Analytics/marketing_analysis.R
Hey Matt, Yeah I copied and paste the code and it gives me that error. I don't know if someone else has had this error. However, if I just use the code like this, recipe_obj % step_rm(ID) %>% step_discretize(all_numeric(), options = list(min_unique = 1)) %>% step_dummy(all_nominal())%>% prep() It works, the only thing I have less variables as you do because it is not using the one-hot encoding parameter. I'll try and find what possible error it could be.
Great course Matt, Can't wait to start taking this course. I find R to be a really good platform especially for business analysis. Thanks for providing this video.
@@janiobachmann5029 Awesome!! The courses are great. You will be amazed where you go with it. This is just one example of what you can do. And, for business analysis, R will change your life.
Excellent material, thanks a lot for sharing!
You are welcome
Excellent video! How can we download the data set?
It’s a learning lab. Everything is included here: university.business-science.io/p/learning-labs-pro?el=website
Interesting research. Thanks 4 all
Thanks for the video! Can you tell me the name of the company that this case study are taken place from?
The company is fictional. It’s a demo based on real world.
Hi Matt,
Thanks for the great tutorial.
I hope you can help with my query.
I am stuck with the step_dummy function.
The script is running fine for me (see below) up until this point but it does not convert the categorical data into binary.
I still only have 17 columns with 45k rows after running this.
I have checked that my libraries are all the required versions and seem to have no issue there.
Do you have any suggestions?
Thanks Matt, John.
recipe_obj %
step_rm(ID) %>%
step_discretize(all_numeric(), options = list(min_unique = 1)) %>%
step_dummy(all_nominal(), one_hot = TRUE, naming = partial(dummy_names, sep = "__")) %>%
prep()
Same issue here. PDAYS variable values is being collated into just one bin with one level. How'd you resolve this please?
Same problem
Hi...have you got solution to this? I am also stuck here
we could tableau too right
37:18 good man
Could you guys do something about the video's blurriness? After running each line of code, this error message comes up? Can you explain this error message?
> # 3.0 PERFORM VLOOKUP EQUIVALENT ----
Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) :
invalid first argument
> data_joined_tbl %
Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) :
invalid first argument
+ map(~ read_excel(path = path, sheet = .)) %>%
Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) :
invalid first argument
+ reduce(left_join)
Error in exists(cacheKey, where = .rs.WorkingDataEnv, inherits = FALSE) :
invalid first argument
Try changing your quality from auto to a higher setting. RUclips defaults to lower resolution.
Hello all,
Thanks a lot for this tutorial. Please I have a question.
I tried:
map(sheets~ read_excel(path = path, sheet = .))
But got an error> Why is this so? I imagine thw "%>%"(pipe) just supplies the data to the nested function. How come it gives an error when applied directly?
Hi Onimisi, Please double-check the verified code against your code. You can see it here: github.com/business-science/presentations/blob/master/2019_02_13_Learning_Lab_Marketing_Analytics/marketing_analysis.R
Great job
Thanks!!
Hello,
27:10 code is not running. It gives me an error "Could not find function %>%"
Make sure you load the tidyverse library - library(tidyverse) You will need to install all of the packages with install.packages("package_name")
Hello,
I am getting the following error for the one_hot=TRUE parameter in step_dummies:
`TRUE` must evaluate to column positions or names, not a logical vector .
Did you check against the verified code? github.com/business-science/presentations/blob/master/2019_02_13_Learning_Lab_Marketing_Analytics/marketing_analysis.R
Hey Matt, Yeah I copied and paste the code and it gives me that error. I don't know if someone else has had this error. However, if I just use the code like this,
recipe_obj %
step_rm(ID) %>%
step_discretize(all_numeric(), options = list(min_unique = 1)) %>%
step_dummy(all_nominal())%>%
prep()
It works, the only thing I have less variables as you do because it is not using the one-hot encoding parameter. I'll try and find what possible error it could be.
Great course Matt, Can't wait to start taking this course. I find R to be a really good platform especially for business analysis. Thanks for providing this video.
@@janiobachmann5029 Awesome!! The courses are great. You will be amazed where you go with it. This is just one example of what you can do. And, for business analysis, R will change your life.
We have a good Learning Lab coming up - H2O unleashed - zoom.us/webinar/register/WN_IuKxXfp6TVeixKAPRrr0-Q
There is nothing...