Trying to execute Logistic Regression In R- Predicting Customer Conversions

[AyomideA]

Hello All,

I am trying to set up logistic regression in R for a customer conversion dataset. Can anyone assist with debugging this? Sorry, I am new to R.

Heres what I have so far:

install.packages("tidyverse")
install.packages("tidymodels")
library(tidymodels)

#Read the dataset and convert the variable to a factor
dataset2 <- read_csv("Bike_Trips_2019.csv")
dataset2$y = as.factor(dataset2$y)

plot the gender and birth year against the target variable
ggplot(dataset2, aes(gender, fill = y))+
geom_bar(x=gender,y=user_type)
coord_flip()

The error message is <error/tibble_error_assign_incompatible_size>
Error in $<-:
! Assigned data as.factor(dataset2$y) must be compatible with existing data.
Existing data has 365069 rows.
Assigned data has 0 rows.
Only vectors of size 1 are recycled.
Caused by error in vectbl_recycle_rhs_rows():
! Can't recycle input of size 0 to size 365069.

Backtrace:
▆

1. ├─base::$<-(*tmp*, y, value = <fct>)
2. └─tibble:::$<-.tbl_df(*tmp*, y, value = <fct>)
3. └─tibble:::tbl_subassign(...)

4. └─tibble:::vectbl_recycle_rhs_rows(value, fast_nrow(xo), i_arg = NULL, value_arg, call)
   

View(data2)
View(dataset2)
Error in View : object 'dataset2' not found

[FJCC]

It seems the first of the following lines works but the second throws an error.

dataset2 <- read_csv("Bike_Trips_2019.csv")
dataset2$y = as.factor(dataset2$y)

After running the first line what is the result of running

colnames(dataset2)

Is there a column named y?

[AyomideA]

Nope , the column I am trying to reference is 'user_type'

I am confused because the tutorial I am following said to write the code that way ?

https://www.datacamp.com/tutorial/logistic-regression-R

[AyomideA]

Wait one moment. after running the first line as you suggested:

Blockquote dataset2 <- read_csv("Bike_Trips_2019.csv")
Rows: 365069 Columns: 14
── Column specification ────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (7): start_time, end_time, from_station_name, to_station_name, user_type, gender, ride_length
dbl (6): trip_id, bikeid, from_station_id, to_station_id, birthyear, day_of_week
num (1): tripduration

Use spec() to retrieve the full column specification for this data.
Specify the column types or set show_col_types = FALSE to quiet this message.

colnames(dataset2)
[1] "trip_id" "start_time" "end_time" "bikeid" "tripduration"
[6] "from_station_id" "from_station_name" "to_station_id" "to_station_name" "user_type"
[11] "gender" "birthyear" "ride_length" "day_of_week"

Blockquote

[AyomideA]

Hi I see that you replied but it looks like the system temporarily hid the message. I wanted to give an update. I since plugged in the y value as:

dataset2$user_type =as.factor(dataset2$user_type)

So it now reads:

#Read the dataset and convert the variable to a factor
dataset2 <- read_csv("Bike_Trips_2019.csv")
dataset2$user_type =as.factor(dataset2$user_type)

install.packages("ggplot2")
library(ggplot2)

plot the gender and birth year against the target variable
ggplot(dataset2, aes(dataset2$gender, fill = y))+
geom_bar(x=dataset2$gender,y=dataset2$user_type)
coord_flip()

The error message states it still 'y' cannot be found.

Here is a screenshot if that also helps

[FJCC]

You wrote ggplot(dataset2, aes(dataset2$gender, fill = y))but there is no column named y. Do you mean ggplot(dataset2, aes(gender, fill = user_type))?
Note that you should not use the syntax like dataset2$gender. Just write gender. ggplot() knows to look in the dataset2 data frame because you set that as the data argument of the function. Try

ggplot(dataset2,  aes(x = gender, y = user_type, fill = user_type))+
geom_bar() +
coord_flip()

[AyomideA]

I tried that:

plot the gender and birth year against the target variable
ggplot(data = dataset2,aes(x = gender, y = user_type, fill = user_type))+

• geom_bar()+
• coord_flip()
  Error in geom_bar():
  ! Problem while computing stat.
  Error occurred in the 1st layer.
  Caused by error in setup_params():
  ! stat_count() must only have an x or y aesthetic.
  Run rlang::last_trace() to see where the error occurred.

So I tried this instead:

plot the gender and birth year against the target variable
ggplot(data = dataset2,aes( y = user_type, fill = user_type))+
geom_bar()+
coord_flip()

And I did get a plot but what does the count mean? It is not exactly clear/
Please see attached screenshot of graph

[AyomideA]

To clarify I need the graph to show a break down in count (x-axis) by customer attributes on the y axis. with a yes and no for whether the customer is a casual riders "no" or membership holder "yes"

It was supposed to look like the graph Data Camp shows here:

[FJCC]

I understand that you want to fill by the user_type and you want to plot by gender or some other column. This should get you roughly what you want.

ggplot(data = dataset2,aes( y = gender, fill = user_type))+ geom_bar()

The geom_bar() will count how many rows have each combination of gender and user_type.
To get the yes/no labels for user_type, run

dataset2$user_type <- factor(dataset2$user_type, levels = c("customer", "subscriber"), labels = c("no","yes"))

[AyomideA]

I tried to plug that in to get the graph but the plot went blank. Here I have attached a screenshot for you to see.

I even tried to use the absolute '$' symbol for the gender and user_type but that isn't working either

[AyomideA]

Do you think we have to insert a pipeline?

[FJCC]

This will be easier if I have a little data. Please post the output of

dput(head(dataset2, 15))

[AyomideA]

Sure here it returned:

dput(head(dataset2,15))
structure(list(trip_id = c(21742443, 21742444, 21742445, 21742446,
21742447, 21742448, 21742449, 21742450, 21742451, 21742452, 21742453,
21742454, 21742455, 21742456, 21742457), start_time = c("2019-01-01 0:04:37",
"2019-01-01 0:08:13", "2019-01-01 0:13:23", "2019-01-01 0:13:45",
"2019-01-01 0:14:52", "2019-01-01 0:15:33", "2019-01-01 0:16:06",
"2019-01-01 0:18:41", "2019-01-01 0:18:43", "2019-01-01 0:19:18",
"2019-01-01 0:20:34", "2019-01-01 0:21:52", "2019-01-01 0:23:04",
"2019-01-01 0:23:43", "2019-01-01 0:23:54"), end_time = c("2019-01-01 0:11:07",
"2019-01-01 0:15:34", "2019-01-01 0:27:12", "2019-01-01 0:43:28",
"2019-01-01 0:20:56", "2019-01-01 0:19:09", "2019-01-01 0:19:03",
"2019-01-01 0:20:21", "2019-01-01 0:47:30", "2019-01-01 0:24:54",
"2019-01-01 0:35:20", "2019-01-01 0:32:45", "2019-01-01 0:33:05",
"2019-01-01 0:33:05", "2019-01-01 0:39:00"), bikeid = c(2167,
4386, 1524, 252, 1170, 2437, 2708, 2796, 6205, 3939, 6243, 6300,
3029, 84, 5019), tripduration = c(390, 441, 829, 1783, 364, 216,
177, 100, 1727, 336, 886, 653, 601, 562, 906), from_station_id = c(199,
44, 15, 123, 173, 98, 98, 211, 150, 268, 299, 204, 90, 90, 289
), from_station_name = c("Wabash Ave & Grand Ave", "State St & Randolph St",
"Racine Ave & 18th St", "California Ave & Milwaukee Ave", "Mies van der Rohe Way & Chicago Ave",
"LaSalle St & Washington St", "LaSalle St & Washington St", "St. Clair St & Erie St",
"Fort Dearborn Dr & 31st St", "Lake Shore Dr & North Blvd", "Halsted St & Roscoe St",
"Prairie Ave & Garfield Blvd", "Millennium Park", "Millennium Park",
"Wells St & Concord Ln"), to_station_id = c(84, 624, 644, 176,
35, 49, 49, 142, 148, 141, 295, 420, 255, 255, 324), to_station_name = c("Milwaukee Ave & Grand Ave",
"Dearborn St & Van Buren St ()", "Western Ave & Fillmore St ()",
"Clark St & Elm St", "Streeter Dr & Grand Ave", "Dearborn St & Monroe St",
"Dearborn St & Monroe St", "McClurg Ct & Erie St", "State St & 33rd St",
"Clark St & Lincoln Ave", "Broadway & Argyle St", "Ellis Ave & 55th St",
"Indiana Ave & Roosevelt Rd", "Indiana Ave & Roosevelt Rd", "Stockton Dr & Wrightwood Ave"
), user_type = structure(c(NA_integer_, NA_integer_, NA_integer_,
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_,
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_,
NA_integer_, NA_integer_), levels = c("customer", "subscriber"
), class = "factor"), gender = c("Male", "Female", "Female",
"Male", "Male", "Female", "Male", "Male", "Male", "Male", "Male",
"Female", "Male", "Female", "Female"), birthyear = c(1989, 1990,
1994, 1993, 1994, 1983, 1984, 1990, 1995, 1996, 1994, 1994, 1986,
1990, 1989), ride_length = c("0:06:30", "0:07:21", "0:13:49",
"0:29:43", "0:06:04", "0:03:36", "0:02:57", "0:01:40", "0:28:47",
"0:05:36", "0:14:46", "0:10:53", "0:10:01", "0:09:22", "0:15:06"
), day_of_week = c(3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3)), row.names = c(NA, -15L), class = c("tbl_df", "tbl", "data.frame"

[AyomideA]

Does that code ask for the 1st 15 rows per variable?

[FJCC]

The user_type column has all NA values in the data you posted to I manually filled it. Here is the plot I get.

dataset2 <- structure(list(trip_id = c(21742443, 21742444, 21742445, 21742446,
                           21742447, 21742448, 21742449, 21742450, 21742451, 21742452, 21742453,
                           21742454, 21742455, 21742456, 21742457), start_time = c("2019-01-01 0:04:37",
                                                                                   "2019-01-01 0:08:13", "2019-01-01 0:13:23", "2019-01-01 0:13:45",
                                                                                   "2019-01-01 0:14:52", "2019-01-01 0:15:33", "2019-01-01 0:16:06",
                                                                                   "2019-01-01 0:18:41", "2019-01-01 0:18:43", "2019-01-01 0:19:18",
                                                                                   "2019-01-01 0:20:34", "2019-01-01 0:21:52", "2019-01-01 0:23:04",
                                                                                   "2019-01-01 0:23:43", "2019-01-01 0:23:54"), end_time = c("2019-01-01 0:11:07",
                                                                                                                                             "2019-01-01 0:15:34", "2019-01-01 0:27:12", "2019-01-01 0:43:28",
                                                                                                                                             "2019-01-01 0:20:56", "2019-01-01 0:19:09", "2019-01-01 0:19:03",
                                                                                                                                             "2019-01-01 0:20:21", "2019-01-01 0:47:30", "2019-01-01 0:24:54",
                                                                                                                                             "2019-01-01 0:35:20", "2019-01-01 0:32:45", "2019-01-01 0:33:05",
                                                                                                                                             "2019-01-01 0:33:05", "2019-01-01 0:39:00"), bikeid = c(2167,
                                                                                                                                                                                                     4386, 1524, 252, 1170, 2437, 2708, 2796, 6205, 3939, 6243, 6300,
                                                                                                                                                                                                     3029, 84, 5019), tripduration = c(390, 441, 829, 1783, 364, 216,
                                                                                                                                                                                                                                       177, 100, 1727, 336, 886, 653, 601, 562, 906), from_station_id = c(199,
                                                                                                                                                                                                                                                                                                          44, 15, 123, 173, 98, 98, 211, 150, 268, 299, 204, 90, 90, 289
                                                                                                                                                                                                                                       ), from_station_name = c("Wabash Ave & Grand Ave", "State St & Randolph St",
                                                                                                                                                                                                                                                                "Racine Ave & 18th St", "California Ave & Milwaukee Ave", "Mies van der Rohe Way & Chicago Ave",
                                                                                                                                                                                                                                                                "LaSalle St & Washington St", "LaSalle St & Washington St", "St. Clair St & Erie St",
                                                                                                                                                                                                                                                                "Fort Dearborn Dr & 31st St", "Lake Shore Dr & North Blvd", "Halsted St & Roscoe St",
                                                                                                                                                                                                                                                                "Prairie Ave & Garfield Blvd", "Millennium Park", "Millennium Park",
                                                                                                                                                                                                                                                                "Wells St & Concord Ln"), to_station_id = c(84, 624, 644, 176,
                                                                                                                                                                                                                                                                                                            35, 49, 49, 142, 148, 141, 295, 420, 255, 255, 324), to_station_name = c("Milwaukee Ave & Grand Ave",
                                                                                                                                                                                                                                                                                                                                                                                     "Dearborn St & Van Buren St ()", "Western Ave & Fillmore St ()",
                                                                                                                                                                                                                                                                                                                                                                                     "Clark St & Elm St", "Streeter Dr & Grand Ave", "Dearborn St & Monroe St",
                                                                                                                                                                                                                                                                                                                                                                                     "Dearborn St & Monroe St", "McClurg Ct & Erie St", "State St & 33rd St",
                                                                                                                                                                                                                                                                                                                                                                                     "Clark St & Lincoln Ave", "Broadway & Argyle St", "Ellis Ave & 55th St",
                                                                                                                                                                                                                                                                                                                                                                                     "Indiana Ave & Roosevelt Rd", "Indiana Ave & Roosevelt Rd", "Stockton Dr & Wrightwood Ave"
                                                                                                                                                                                                                                                                                                            ), user_type = structure(c(NA_integer_, NA_integer_, NA_integer_,
                                                                                                                                                                                                                                                                                                                                       NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_,
                                                                                                                                                                                                                                                                                                                                       NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_,
                                                                                                                                                                                                                                                                                                                                       NA_integer_, NA_integer_), levels = c("customer", "subscriber"
                                                                                                                                                                                                                                                                                                                                       ), class = "factor"), gender = c("Male", "Female", "Female",
                                                                                                                                                                                                                                                                                                                                                                        "Male", "Male", "Female", "Male", "Male", "Male", "Male", "Male",
                                                                                                                                                                                                                                                                                                                                                                        "Female", "Male", "Female", "Female"), birthyear = c(1989, 1990,
                                                                                                                                                                                                                                                                                                                                                                                                                             1994, 1993, 1994, 1983, 1984, 1990, 1995, 1996, 1994, 1994, 1986,
                                                                                                                                                                                                                                                                                                                                                                                                                             1990, 1989), ride_length = c("0:06:30", "0:07:21", "0:13:49",
                                                                                                                                                                                                                                                                                                                                                                                                                                                          "0:29:43", "0:06:04", "0:03:36", "0:02:57", "0:01:40", "0:28:47",
                                                                                                                                                                                                                                                                                                                                                                                                                                                          "0:05:36", "0:14:46", "0:10:53", "0:10:01", "0:09:22", "0:15:06"
                                                                                                                                                                                                                                                                                                                                                                                                                             ), day_of_week = c(3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
                                                                                                                                                                                                                                                                                                                                                                                                                                                3)), row.names = c(NA, -15L), class = c("tbl_df", "tbl", "data.frame"))

library(ggplot2)
dataset2$user_type <- sample(c("customer","subscriber"),15,replace = TRUE)
dataset2$user_type <- factor(dataset2$user_type, levels = c("customer", "subscriber"), labels = c("no","yes"))
ggplot(data = dataset2,aes( y = gender, fill = user_type))+ geom_bar()

^{Created on 2024-03-09 with reprex v2.0.2}
The image in the last post where you were getting and error shows that you set dataset2=aes() within the ggplot function. That's why you weren't getting a plot.

[AyomideA]

I tried to copy the format for the sample size and apply it to my original dataset and still I am bit confused.

There seems to be errors although its the same?

[FJCC]

You should not use the two lines of code, quoted below, where I manually filled user_type with values. That was done only to allow me to use the data you posted.

dataset2$user_type <- sample(c("customer","subscriber"),15,replace = TRUE)
dataset2$user_type <- factor(dataset2$user_type, levels = c("customer", "subscriber"), labels = c("no","yes"))

Does the user_type column contain values in the full data set, or are they mostly or totally NA. Have you changed that column?

[AyomideA]

One moment I can do a summary or head of the dataset

Thank you for all of your help, I appreciate it

[AyomideA]

oh yes it looks like all of the user_types are 'NA'

summary(dataset2$user_type)
no yes NA's
0 0 365069

I had suspected they were and that's why I tried to replace it as you did with 2 lines of code, that is not the correct way to manually enter the values?

[FJCC]

Read in the data again and don't try to change that column. We can do that later.