⛑️

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 1 - 10

2021/11/21に公開

Top

R-001

df_receipt %>% head(10)

R-002

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        amount
    ) %>%
    head(10)

R-003

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        amount
    ) %>%
    rename(
	sales_date = sales_ymd
    ) %>%
    head(10)

R-004

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        amount
    ) %>%
    rename(
        sales_date = sales_ymd
    ) %>%
    dplyr::filter(
        customer_id == "CS018205000001"
    )

R-005

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        amount
    ) %>%
    rename(
        sales_date = sales_ymd
    ) %>%
    dplyr::filter(
        customer_id == "CS018205000001",
        amount >= 1000
    )

R-006

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        quantity,
        amount
    ) %>%
    rename(
        sales_date = sales_ymd
    ) %>%
    dplyr::filter(
        customer_id == "CS018205000001",
        {amount >= 1000} | {quantity >= 5}
    )

R-007

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        quantity,
        amount
    ) %>%
    rename(
        sales_date = sales_ymd
    ) %>%
    dplyr::filter(
        customer_id == "CS018205000001",
        {amount >= 1000} & {amount <= 2000}
    )

R-008

df_receipt %>%
    select(
        sales_ymd,
        customer_id,
        product_cd,
        quantity,
        amount
    ) %>%
    rename(
        sales_date = sales_ymd
    ) %>%
    dplyr::filter(
        customer_id == "CS018205000001",
        product_cd != "P071401019"
    )

R-009

df_store %>%
    dplyr::filter(
        !(prefecture_cd == "13" & floor_area > 900)
    )

R-010

df_store %>%
    dplyr::filter(
        str_starts(store_cd, "S14")
    ) %>%
    head(10)

次の問題:11-20

Discussion