Updating the non-hierarchical worksheets to make sure they run

construct_longsynth_onehier_pnbd_models.qmd

@@ -115,6 +115,7 @@ customer_transactions_tbl |> glimpse()
 
 ## Load Derived Data
 
+<<<<<<< Updated upstream
 ```{r write_data_disk}
 #| echo: TRUE
 
@@ -126,12 +127,40 @@ fit_1000_data_tbl  <- read_rds("data/fit_1000_longframe_data_tbl.rds")
 fit_10000_data_tbl <- read_rds("data/fit_10000_longframe_data_tbl.rds")
 
 customer_summarystats_tbl <- read_rds("data/customer_summarystats_longframe_tbl.rds")
+=======
+```{r load_modelling_data}
+#| echo: TRUE
+
+id_1000  <- read_rds("data/longsynth_id_1000.rds")
+id_5000  <- read_rds("data/longsynth_id_5000.rds")
+id_10000 <- read_rds("data/longsynth_id_10000.rds")
+
+fit_1000_data_tbl  <- read_rds("data/longsynth_fit_1000_data_tbl.rds")
+fit_10000_data_tbl <- read_rds("data/longsynth_fit_10000_data_tbl.rds")
+
+customer_fit_stats_tbl    <- fit_1000_data_tbl
+customer_summarystats_tbl <- read_rds("data/longsynth_customer_summarystats_tbl.rds")
+>>>>>>> Stashed changes
 
 obs_fitdata_tbl   <- read_rds("data/longsynth_obs_fitdata_tbl.rds")
 obs_validdata_tbl <- read_rds("data/longsynth_obs_validdata_tbl.rds")
 ```
 
 
+<<<<<<< Updated upstream
+=======
+Finally, we need to set our directories where we save our Stan code and the
+model outputs.
+
+```{r setup_workbook_parameters}
+#| echo: TRUE
+
+stan_modeldir <- "stan_models"
+stan_codedir  <-   "stan_code"
+```
+
+
+>>>>>>> Stashed changes
 
 # Fit First Hierarchical Lambda Model
 

construct_onlineretail_fixed_pnbd_models.qmd

@@ -133,7 +133,6 @@ ggplot(plot_tbl, aes(x = tnx_timestamp, y = customer_id)) +
 ```
 
 
-
 ## Construct Datasets
 
 Having loaded the synthetic data we need to construct a number of datasets of
@@ -980,19 +979,19 @@ calculate_simulation_statistics <- function(file_rds) {
 ```{r load_model_assessment_data}
 #| echo: TRUE
 
-obs_fit_customer_count <- customer_fit_stats_tbl |>
-  filter(x > 0) |>
+obs_fit_customer_count <- obs_fitdata_tbl |>
+  filter(tnx_count > 0) |>
   nrow()
 
-obs_valid_customer_count <- customer_valid_stats_tbl |>
+obs_valid_customer_count <- obs_validdata_tbl |>
   filter(tnx_count > 0) |>
   nrow()
 
-obs_fit_total_count <- customer_fit_stats_tbl |>
-  pull(x) |>
+obs_fit_total_count <- obs_fitdata_tbl |>
+  pull(tnx_count) |>
   sum()
 
-obs_valid_total_count <- customer_valid_stats_tbl |>
+obs_valid_total_count <- obs_validdata_tbl |>
   pull(tnx_count) |>
   sum()
 
@@ -1004,19 +1003,30 @@ obs_stats_tbl <- tribble(
   "valid",      "simtnx_count",      obs_valid_total_count
   )
 
-
-
-
 model_assess_tbl <- dir_ls("data", regexp = "pnbd_onlineretail_.*_assess") |>
   enframe(name = NULL, value = "file_path") |>
   filter(str_detect(file_path, "_assess_model_", negate = TRUE)) |>
   mutate(
     model_label = str_replace(file_path, "data/pnbd_onlineretail_(.*?)_assess_.*", "\\1"),
     assess_type = if_else(str_detect(file_path, "_assess_fit_"), "fit", "valid"),
     
-    sim_data = map(file_path, calculate_simulation_statistics)
+    sim_data = map(
+      file_path, calculate_simulation_statistics,
+      
+      .progress = "calculate_simulation_statistics"
+      )
     )
 
+model_assess_tbl |> glimpse()
+```
+
+We have now constructed the simulation summary statistics and now reshape our
+data to aid in our model assessment.
+
+
+```{r calculate_model_assess_summary_stats}
+#| echo: TRUE
+
 model_assess_summstat_tbl <- model_assess_tbl |>
   select(model_label, assess_type, sim_data) |>
   unnest(sim_data) |>
@@ -1034,9 +1044,15 @@ model_assess_summstat_tbl <- model_assess_tbl |>
     p75 = quantile(value, 0.75),
     p90 = quantile(value, 0.90)
     )
+
+model_assess_summstat_tbl |> glimpse()
 ```
 
 
+We now use this data to construct model comparison plots for the different
+models we have fit.
+
+
 ```{r construct_model_comparison_plot}
 #! echo: TRUE
 

exploring_online_retail_transactions.html

@@ -7,9 +7,9 @@
 <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
 
 <meta name="author" content="Mick Cooney [email protected]">
-<meta name="dcterms.date" content="2023-05-18">
+<meta name="dcterms.date" content="2023-06-06">
 
-<title>Construct Non-Hierarchical P/NBD Model for Long Timeframe Synthetic Data</title>
+<title>Exploring the Online Retail Transaction Data</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -5331,7 +5331,7 @@ <h2 id="toc-title">Table of contents</h2>
 
 <header id="title-block-header" class="quarto-title-block default">
 <div class="quarto-title">
-<h1 class="title">Construct Non-Hierarchical P/NBD Model for Long Timeframe Synthetic Data</h1>
+<h1 class="title">Exploring the Online Retail Transaction Data</h1>
 </div>
 
 
@@ -5348,7 +5348,7 @@ <h1 class="title">Construct Non-Hierarchical P/NBD Model for Long Timeframe Synt
     <div>
     <div class="quarto-title-meta-heading">Published</div>
     <div class="quarto-title-meta-contents">
-      <p class="date">May 18, 2023</p>
+      <p class="date">June 6, 2023</p>
     </div>
   </div>
 
@@ -7702,7 +7702,7 @@ <h1 data-number="11"><span class="header-section-number">11</span> R Environment
  collate  en_US.UTF-8
  ctype    en_US.UTF-8
  tz       Europe/Dublin
- date     2023-05-18
+ date     2023-06-06
  pandoc   2.19.2 @ /usr/local/bin/ (via rmarkdown)
 
 ─ Packages ───────────────────────────────────────────────────────────────────

exploring_online_retail_transactions.qmd

@@ -1,5 +1,5 @@
 ---
-title: "Construct Non-Hierarchical P/NBD Model for Long Timeframe Synthetic Data"
+title: "Exploring the Online Retail Transaction Data"
 author: "Mick Cooney <[email protected]>"
 date: "Last updated: `r format(Sys.time(), '%B %d, %Y')`"
 editor: source