fixed #4

Author: usrbinr

R/data.R

@@ -4,7 +4,7 @@
 #' It provides insights into the transactions that have occurred, including order dates, delivery dates, customer and store information,
 #' as well as product details.
 #'
-#' @format A data frame with 17 columns:
+#' @format A data frame with sales columns:
 #' \describe{
 #'   \item{order_key}{\code{double} Unique identifier for each order.}
 #'   \item{line_number}{\code{double} Line number within the order (for multi-line orders).}
@@ -19,10 +19,13 @@
 #'   \item{unit_cost}{\code{double} The cost per unit of the product.}
 #'   \item{currency_code}{\code{character} The currency code used for the transaction (e.g., USD, EUR).}
 #'   \item{exchange_rate}{\code{double} The exchange rate applied to the currency, if applicable.}
-#'   \item{revenue}{\code{double} A product's unit_price multiplied by quantity.}
+#'   \item{gross_revenue}{\code{double} A product's unit_price multiplied by quantity.}
+#'   \item{net_revenue}{\code{double} A product's net_price multiplied by quantity.}
+#'   \item{unit_discount}{\code{double} A product's unit_price minute net_price.}
+#'   \item{discounts}{\code{double} A product's unit_discount multiplied by quantity.}
 #'   \item{cogs}{\code{double} A product's unit_cost multiplied by quantity.}
-#'   \item{margin}{\code{double} A product's revenue minus cogs.}
-#'   \item{unit_margin}{\code{double} A product unit_price minus unit_cost.}
+#'   \item{margin}{\code{double} A product's net_revenue minus cogs.}
+#'   \item{unit_margin}{\code{double} A product margin divided by quantity.}
 #' }
 #' @source https://github.com/sql-bi/Contoso-Data-Generator-V2-Data/releases/tag/ready-to-use-data
 "sales"
@@ -131,7 +134,7 @@
 #'   \item{currency_code}{\code{character} The currency code used for the order (e.g., USD, EUR).}
 #' }
 #' @source https://github.com/sql-bi/Contoso-Data-Generator-V2-Data/releases/tag/ready-to-use-data
-"order"
+"orders"
 
 
 

R/database.R

@@ -52,7 +52,7 @@ create_contoso_duckdb <- function(dir="temp"){
   duckdb::duckdb_register(con,"date"     ,contoso::date,overwrite = TRUE)
   duckdb::duckdb_register(con,"fx"       ,contoso::fx,overwrite = TRUE)
   duckdb::duckdb_register(con,"store"    ,contoso::store,overwrite = TRUE)
-  duckdb::duckdb_register(con,"order"    ,contoso::order,overwrite = TRUE)
+  duckdb::duckdb_register(con,"orders"    ,contoso::orders,overwrite = TRUE)
   duckdb::duckdb_register(con,"orderrows",contoso::orderrows,overwrite = TRUE)
 
 
@@ -61,6 +61,8 @@ create_contoso_duckdb <- function(dir="temp"){
   product_db <- dplyr::tbl(con,dplyr::sql("select * from product"))
   customer_db <- dplyr::tbl(con,dplyr::sql("select * from customer"))
   store_db <- dplyr::tbl(con,dplyr::sql("select * from store"))
+  orders_db <- dplyr::tbl(con,dplyr::sql("select * from orders"))
+  orderrows_db <- dplyr::tbl(con,dplyr::sql("select * from orderrows"))
   fx_db <- dplyr::tbl(con,dplyr::sql("select * from fx"))
   date_db <- dplyr::tbl(con,dplyr::sql("select * from date"))
 
@@ -72,6 +74,8 @@ create_contoso_duckdb <- function(dir="temp"){
     ,store=store_db
     ,fx=fx_db
     ,date=date_db
+    ,orders=orders_db
+    ,orderrows=orderrows_db
   )
 
   return(out)

README.md

@@ -47,6 +47,10 @@ processing techniques
 This dataset is perfect for practicing time series analysis, financial
 modeling, or any business intelligence-related tasks.
 
+Using view, you can see the columns’ label using the
+[labelled](https://larmarange.github.io/labelled/index.html)
+package.[^1]
+
 The data is sourced from the
 [sqlbi](https://github.com/sql-bi/Contoso-Data-Generator-V2-Data/releases/tag/ready-to-use-data)
 github site
@@ -77,7 +81,8 @@ pak::pak("alejandrohagan/contoso")
 
 ## Example
 
-Example of how to create a duckdb database with Conotoso tables loaded
+Example of how to create a duckdb database with Contoso tables loaded is
+below:
 
 ``` r
 library(contoso)
@@ -88,3 +93,6 @@ contoso_db <- create_contoso_duckdb(dir = "temp")
 # Access the sales dataset from the database
 sales_data <- contoso_db$sales
 ```
+
+[^1]: Inspiration from [Crystal
+    Lewis](https://cghlewis.com/blog/dict_clean/) excellent blog post

README.qmd

@@ -27,7 +27,7 @@ The package comes with the following datasets:
 - **date**:
   - Contains date-related information, including date, week, month, quarter, and year for use in time-based analysis.
 
-- **order**:
+- **orders**:
   - Contains information about individual orders, including order key, customer key, order date, and store information.
 
 - **orderrows**:
@@ -40,6 +40,8 @@ The package comes with the following datasets:
 
 This dataset is perfect for practicing time series analysis, financial modeling, or any business intelligence-related tasks.
 
+Using view, you can see the columns' label using the [labelled](https://larmarange.github.io/labelled/index.html) package.^[Inspiration from [Crystal Lewis](https://cghlewis.com/blog/dict_clean/) excellent blog post]
+
 The data is sourced from the [sqlbi](https://github.com/sql-bi/Contoso-Data-Generator-V2-Data/releases/tag/ready-to-use-data) github site 
 
 ## Dataset overview 
@@ -84,7 +86,7 @@ pak::pak("alejandrohagan/contoso")
 
 ## Example
 
-Example of how to create a duckdb database with Conotoso tables loaded
+Example of how to create a duckdb database with Contoso tables loaded is below:
 
 
 ```{r}

data-raw/customer.R

@@ -15,4 +15,37 @@ customer <- sales |>
 
 rm(sales)
 
+customer_labels <- list(
+    customer_key = "Unique customer identifier",
+    geo_area_key = "Geographical area identifier",
+    start_dt = "Start date of customer record",
+    end_dt = "End date of customer record",
+    continent = "Continent of the customer",
+    gender = "Gender of the customer",
+    title = "Title of the customer (e.g., Mr., Mrs., Dr.)",
+    given_name = "First name of the customer",
+    middle_initial = "Middle initial of the customer",
+    surname = "Last name of the customer",
+    street_address = "Street address of the customer",
+    city = "City where the customer resides",
+    state = "State or region where the customer resides",
+    state_full = "Full name of the state or region",
+    zip_code = "Postal code of the customer’s address",
+    country = "Country where the customer resides",
+    country_full = "Full name of the country",
+    birthday = "Birthday of the customer",
+    age = "Age of the customer",
+    occupation = "Occupation of the customer",
+    company = "Company where the customer works",
+    vehicle = "Vehicle owned by the customer",
+    latitude = "Latitude of the customer's location",
+    longitude = "Longitude of the customer's location"
+)
+
+# Example: Assuming 'customers' is your data frame
+var_labels(customer) <- customer_labels
+
+
+
+
 usethis::use_data(customer, overwrite = TRUE)

data-raw/date.R

@@ -6,5 +6,28 @@ dir <- "data-raw"
 
 date <- readr::read_csv(file.path(dir,"date.csv"),name_repair = janitor::make_clean_names,show_col_types = FALSE)
 
+date_labels <- list(
+    date = "Full date",
+    date_key = "Unique date identifier",
+    year = "Year of the date",
+    year_quarter = "Year and quarter of the date",
+    year_quarter_number = "Quarter number within the year",
+    quarter = "Quarter of the year (Q1, Q2, Q3, Q4)",
+    year_month = "Year and month of the date",
+    year_month_short = "Short year and month (e.g., 2023-05)",
+    year_month_number = "Numeric representation of the year and month",
+    month = "Month of the year (1-12)",
+    month_short = "Short month name (e.g., Jan, Feb)",
+    month_number = "Numeric month (1-12)",
+    dayof_week = "Day of the week (e.g., Monday, Tuesday)",
+    dayof_week_short = "Short form of the day of the week (e.g., Mon, Tue)",
+    dayof_week_number = "Numeric day of the week (1 = Sunday, 7 = Saturday)",
+    working_day = "Indicates if it's a working day (TRUE/FALSE)",
+    working_day_number = "Numeric representation of the working day only (1 = Monday, 2=Tuesday, 0 = weekend)"
+)
+
+# Example: Assuming 'dates' is your data frame
+labelled::var_labels(date) <- date_labels
+
 
 usethis::use_data(date, overwrite = TRUE)

data-raw/fx.R

@@ -5,4 +5,16 @@ dir <- "data-raw"
 
 fx <- readr::read_csv(file.path(dir,"currencyexchange.csv"),name_repair = janitor::make_clean_names,show_col_types = FALSE)
 
+
+fx_labels <- list(
+    date = "Date of the exchange rate",
+    from_currency = "Currency being exchanged from",
+    to_currency = "Currency being exchanged to",
+    exchange = "Exchange rate between the two currencies"
+)
+
+# Example: Assuming 'exchange_data' is your data frame
+var_labels(fx) <- fx_labels
+
+
 usethis::use_data(fx, overwrite = TRUE)

data-raw/order.R

@@ -6,4 +6,17 @@ dir <- "data-raw"
 orderrows <- readr::read_csv(file.path(dir,"orderrows.csv"),name_repair = janitor::make_clean_names,show_col_types = FALSE)
 
 
+orderrows_labels <- list(
+    order_key = "Unique order identifier",
+    line_number = "Line number of the order",
+    product_key = "Unique product identifier",
+    quantity = "Quantity of the product ordered",
+    unit_price = "Price per unit of the product",
+    net_price = "Total price for the line item after any discounts",
+    unit_cost = "Cost per unit of the product"
+)
+labelled::var_labels(orderrows) <- orderrows_labels
+
+
+
 usethis::use_data(orderrows, overwrite = TRUE)

data-raw/orderrows.R

@@ -0,0 +1,22 @@
+## code to prepare `order` dataset goes here
+fpaR::create_data_raw()
+
+dir <- "data-raw"
+
+orders <- readr::read_csv(file.path(dir,"orders.csv"),name_repair = janitor::make_clean_names,show_col_types = FALSE)
+
+
+order_labels <- list(
+    order_key = "Unique order identifier",
+    customer_key = "Unique customer identifier",
+    store_key = "Unique store identifier",
+    order_date = "Date when the order was placed",
+    delivery_date = "Actual delivery date",
+    currency_code = "Currency code (e.g., USD, EUR)"
+)
+
+# Example: Assuming 'orders' is your data frame
+
+labelled::var_labels(orders) <- order_labels
+
+usethis::use_data(orders, overwrite = TRUE)