remove aggregate data

Author: wvictor14

index.qmd

@@ -105,7 +105,22 @@ import re
 
 ```{python}
 labour = read_labourcan(LABOUR_DATA_FILE)
-labour_processed = calculate_centered_rank(labour)
+
+# Remove Aggregated Rows
+labour_filtered = labour.filter(
+    ~pl.col("Industry").is_in(
+        [
+            "Total employed, all industries",
+            "Goods-producing sector",
+            "Services-producing sector",
+        ]
+    )
+)
+
+# Calculate ranking based on monthly % change
+labour_processed = calculate_centered_rank(labour_filtered)
+
+# Bin % difference
 labour_processed_cutted = cut_pdiff(labour_processed, DEFAULT_CUTS)
 plot_data = labour_processed_cutted.filter(
     pl.col("YEAR") >= FILTER_YEAR[0], pl.col("YEAR") <= FILTER_YEAR[1]
@@ -143,7 +158,6 @@ LEGEND_LABELS = [
 ]
 ```
 
-
 # Sector Shifts: Where Canada's Jobs Are Moving
 
 Track the number of industries gaining or losing jobs each month. Boxes are shaded based on percentage change from previous month in each industry's employment levels.
@@ -198,7 +212,7 @@ plot
 ```{python}
 # | output: asis
 ALL_INDUSTRIES = (
-    labour_processed_cutted.select("Industry").unique().to_series().to_list()
+    labour_filtered.select("Industry").unique(maintain_order=True).to_series().to_list()
 )
 
 for INDUSTRY in ALL_INDUSTRIES: