bs_std function improvement

Trying to remove duplicated rows and merge rows of df_std_BS where applicable
gp1981 · Dec 3, 2023 · 99fa931 · 99fa931
1 parent 7ddd8f7
commit 99fa931
Show file tree

Hide file tree

Showing 8 changed files with 17,503 additions and 489 deletions.
diff --git a/code/Functions/data_retrieval.R b/code/Functions/data_retrieval.R
@@ -78,42 +78,123 @@ bs_std <- function(df_Facts) {
   # Read the standardized_balancesheet.xlsx file
   standardized_balancesheet <- read.xlsx(balancesheet_path, sheet = "Sheet1")
 
-  # Create a mapping between df_Facts_label and standardized_balancesheet_label
-  label_mapping <- df_Facts %>%
-    left_join(standardized_balancesheet, by = c("label" = "df_Facts_label")) %>%
-    select(label, standardized_balancesheet_label) %>%
+  # Rename standardized_balancesheet column df_Facts_label to perform left_join
+  standardized_balancesheet <- standardized_balancesheet %>% 
+    rename(label = df_Facts_label)
+
+  # Merge df_Facts with standardized_balancesheet
+  df_std_BS <- df_Facts %>%
+    left_join(standardized_balancesheet, by = "label") %>% 
+    select(standardized_balancesheet_label,everything(),-df_Fact_Description,)
+
+  # Filter out records not associated with standardized_balancesheet to create the mapping with df_Facts
+  df_std_BS_map <- df_std_BS %>%
+    filter(!is.na(standardized_balancesheet_label)) %>% 
+    select(standardized_balancesheet_label,label,description) %>% 
     distinct()
 
-  # Select relevant columns from df_Facts
-  df_Facts_subset <- df_Facts %>%
-    select(label, end, fy, fp, form, val) %>%
-    left_join(label_mapping, by = "label")
-
-  # Merge with standardized_balancesheet to get the corresponding df_Facts_label
-  df_std_BS <- df_Facts_subset %>%
-    left_join(standardized_balancesheet, by = "standardized_balancesheet_label")
-
-  # Filter out records not associated with standardized_balancesheet
+  # Filter out records not associated with standardized_balancesheet to create the pivot
   df_std_BS <- df_std_BS %>%
-    filter(!is.na(standardized_balancesheet_label)) %>%
-    select(-c(label,standardized_balancesheet_label, df_Fact_Description))
+    filter(!is.na(standardized_balancesheet_label)) %>% 
+    select(standardized_balancesheet_label,end,val,fy,fp,form,filed,start)
+
 
   # Pivot the data to the desired structure
-  df_std_BS <- df_std_BS %>%
+  # This function introduces a grouping by label, fy and fp and adds a logical column (has_form_A and has_form) to identify whether there is a row with /A and a row without /A for the same fy and fp. Rows without /A and with a corresponding row with /A will be filtered out. 
+  df_std_BS_test <- df_std_BS %>%
+    filter(!is.na(standardized_balancesheet_label)) %>% 
+    mutate(end = ymd(end), filed = ymd(filed)) %>%  # convert to date format
+    group_by(standardized_balancesheet_label, end) %>%
+    filter(filed == max(filed)) %>%  # filter rows with the most recent filing date
+    ungroup() %>%
+    select(standardized_balancesheet_label, end, val, fy, fp, form, filed, start) %>%
     pivot_wider(
-      names_from = df_Facts_label,
+      names_from = standardized_balancesheet_label,
       values_from = val
     ) %>%
     arrange(desc(end))
-
-  # Perform the calculation for "Other Current assets (to balance out the Total Current Assets)"
+  # <---- NEED TO CHECK STILL DUPLICATED ROW WITH 1 VARIABLE see 2020-12-31 NA ---->
+  # Perform the calculation for additional records in the balancesheet
   df_std_BS <- df_std_BS %>%
     mutate(
-      Other_Current_Assets = `Assets, Current` -
-        (`Cash and Cash Equivalents, at Carrying Value` +
-           `Marketable Securities, Current` +
-           `Accounts Receivable, after Allowance for Credit Loss, Current` +
-           `Inventory, Net`)
+      'Total Long Term Assets' = ifelse(
+        !is.na('Total Long Term Assets'),
+        'Total Assets' - 'Total Current Assets',
+        NA_real_
+      )
+    )
+
+      ,
+      'Other Current Assets' = ifelse(
+        !is.na('Total Current Assets') &
+          !is.na('Cash & Cash Equivalent') &
+          !is.na('Marketable Securities, Current') &
+          !is.na('Total Accounts Receivable') &
+          !is.na('Total Inventories'),
+        'Total Current Assets' - 
+          ('Cash & Cash Equivalent' + 
+             'Marketable Securities, Current' + 
+             'Total Accounts Receivable' + 
+             'Total Inventories'),
+        NA_real_
+      )
+
+  ,
+      'Other Long Term Assets' = ifelse(
+        !is.na('Total Long Term Assets') &
+          !is.na('Marketable Securities, Non Current') &
+          !is.na('Property, Plant and Equipment') &
+          !is.na('Intangible Assets (excl. goodwill)') &
+          !is.na('Goodwill'),
+        'Total Long Term Assets' - 
+          ('Marketable Securities, Non Current' + 
+             'Property, Plant and Equipment' +
+             'Intangible Assets (excl. goodwill)' + 
+             'Goodwill'),
+        NA_real_
+      ),
+      'Other Current Liabilities' = ifelse(
+        !is.na('Total Current Liabilities') &
+          !is.na('Accounts Payable') &
+          !is.na('Tax Payable') &
+          !is.na('Commercial papers') &
+          !is.na('Short-Term Debt') &
+          !is.na('Operating Lease, Liability, Current'),
+        'Total Current Liabilities' - 
+          ('Accounts Payable' + 'Tax Payable' + 
+             'Commercial papers' + 
+             'Short-Term Debt' +
+             'Operating Lease, Liability, Current'),
+        NA_real_
+      ),
+      'Other Long Term Liabilities' = ifelse(
+        !is.na('Total Long Term Liabilities') &
+          !is.na('Long Term Debts') &
+          !is.na('Operating Lease, Liability, Non Current') &
+          !is.na('Finance Lease, Liability, Non Current'),
+        'Total Long Term Liabilities' -
+          ('Long Term Debts' + 
+             'Operating Lease, Liability, Non Current' + 
+             'Finance Lease, Liability, Non Current'),
+        NA_real_
+      ),
+      'Other Company Stockholders Equity' = ifelse(
+        !is.na('Total Company Stockholders Equity') &
+          !is.na('Common Stock & Additional paid-in capital') &
+          !is.na('Common Stock, Value, Issued') &
+          !is.na('Additional Paid in Capital') &
+          !is.na('Preferred Stock') &
+          !is.na('Retained Earnings') &
+          !is.na('Accumulated other comprehensive income (loss)'),
+        'Total Company Stockholders Equity' -
+          ('Common Stock & Additional paid-in capital' + 
+             'Common Stock, Value, Issued' + 
+             'Additional Paid in Capital' + 
+             'Preferred Stock' + 
+             'Retained Earnings' +
+             'Accumulated other comprehensive income (loss)'),
+        NA_real_
+      )
     )
 
   # Reorder columns dynamically based on the order in standardized_balancesheet

diff --git a/code/Functions/data_visualization.R b/code/Functions/data_visualization.R
@@ -12,15 +12,11 @@ FactsList_to_Dataframe <- function(company_Facts_us_gaap) {
     unnest(cols = c(units)) %>%
     unnest(cols = c(units))
 
-  # Convert the val column to numeric
-  df_Facts$val <- as.numeric(df_Facts$val)
-
+  df_Facts <- as.data.frame(df_Facts)
+
   # Mutate to reduce values in millions by dividing by 1 million
   df_Facts <- df_Facts %>%
-    mutate(
-      val = val / 1e6,
-      formatted_val = scales::comma(val, accuracy = 0.1)
-    )
+    mutate(val = val / 1e6)
 
   return(df_Facts)
 }