👏
データサイエンス100本ノック(構造化データ加工編)をRで解く 11 - 20
R-011
df_customer %>%
dplyr::filter(
str_ends(customer_id, "1")
) %>%
head(10)
R-012
df_store %>%
dplyr::filter(
str_detect(address, "神奈川県横浜市")
) %>%
head(10)
R-013
df_customer %>%
dplyr::filter(
str_detect(status_cd, regex("^[ABCDEF].*", dotall=TRUE))
) %>%
head(10)
R-014
df_customer %>%
dplyr::filter(
str_detect(status_cd, regex(".*[1-9]$", dotall=TRUE))
) %>%
head(10)
R-015
df_customer %>%
dplyr::filter(
str_detect(status_cd, regex("^[ABCDEF].*[1-9]$", dotall=TRUE))
) %>%
head(10)
R-016
df_store %>%
dplyr::filter(
str_detect(tel_no, regex("[0-9]{3}-[0-9]{3}-[0-9]{4}"))
)
R-017
df_customer %>%
arrange(birth_day) %>%
head(10)
R-018
df_customer %>%
arrange(desc(birth_day)) %>%
head(10)
R-019
df_receipt %>%
mutate(
amount_rank = rank(-amount)
) %>%
select(
customer_id,
amount,
amount_rank
) %>%
# arrange(amount_rank) %>%
head(10)
R-020
df_receipt %>%
mutate(
amount_rank = rank(-amount, ties.method = "first")
) %>%
select(
customer_id,
amount,
amount_rank
) %>%
# arrange() %>%
head(10)
Discussion