Fix review issues: len() commas, math errors, 2020 ACS skip

- Remove comma formatting from len() output blocks (len() returns plain
  ints, not comma-separated)
- Fix moe_sum output: 2746.0 → 2746.4 (sqrt(1500² + 2300²))
- Fix moe_ratio output: 0.063 → 0.065 (correct formula application)
- Fix multi-year.md inflation example to skip 2020 ACS 1-year (not
  released due to COVID-19)
- Fix DATE_DESC values in multi-year.md to match population-estimates.md
- Fix housing WGTP column count: 80 → 81 (WGTP + WGTP1–WGTP80)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: chekos

docs/getting-started/census-101.md

@@ -226,7 +226,7 @@ print(f"{len(la_tracts)} tracts in Los Angeles County")
 ```
 
 ```
-2,495 tracts in Los Angeles County
+2495 tracts in Los Angeles County
 ```
 
 ---

docs/guides/acs-data.md

@@ -234,7 +234,7 @@ print(f"{len(la_tracts)} tracts in LA County")
 ```
 
 ```
-2,495 tracts in LA County
+2495 tracts in LA County
 ```
 
 !!! tip "County FIPS codes"
@@ -257,7 +257,7 @@ print(f"{len(cook_bgs)} block groups in Cook County")
 ```
 
 ```
-4,010 block groups in Cook County
+4010 block groups in Cook County
 ```
 
 **All places in a state:**
@@ -274,7 +274,7 @@ print(tx_places.head(3))
 ```
 
 ```
-1,834 places in Texas
+1834 places in Texas
      GEOID                    NAME    variable  estimate     moe
 0  4800100  Abernathy city, Texas  B01003_001      2846   229.0
 1  4800484     Addison town, Texas  B01003_001     16661  1031.0
@@ -684,7 +684,7 @@ print(f"Statistically significant: {is_sig}")
 ```
 
 ```
-Combined MOE: 2746.0
+Combined MOE: 2746.4
 Proportion MOE: 0.0305
 Statistically significant: True
 ```

docs/guides/geography.md

@@ -133,7 +133,7 @@ optionally which county) you want tracts for.
     ```
     52 states/territories
     939 metro/micro areas
-    33,120 ZCTAs
+    33120 ZCTAs
     ```
 
 === "State required"
@@ -160,7 +160,7 @@ optionally which county) you want tracts for.
 
     ```
     58 counties in CA
-    1,834 places in TX
+    1834 places in TX
     ```
 
 === "State + county required"
@@ -188,8 +188,8 @@ optionally which county) you want tracts for.
     ```
 
     ```
-    2,495 tracts in LA County
-    4,010 block groups in Cook County
+    2495 tracts in LA County
+    4010 block groups in Cook County
     ```
 
 ## FIPS codes explained

docs/guides/margins-of-error.md

@@ -308,7 +308,7 @@ print(f"Renter-to-owner ratio: {ratio_est:.3f} +/- {ratio_moe:.3f}")
 ```
 
 ```
-Renter-to-owner ratio: 0.429 +/- 0.063
+Renter-to-owner ratio: 0.429 +/- 0.065
 ```
 
 ### `moe_prop()` --- margins of error for proportions

docs/guides/migration-flows.md

@@ -141,7 +141,7 @@ print(f"{len(age_flows)} flow records with age breakdowns")
 ```
 
 ```
-45,210 flow records with age breakdowns
+45210 flow records with age breakdowns
 ```
 
 ### Adding human-readable labels

docs/guides/multi-year.md

@@ -227,7 +227,7 @@ critical for multi-year analysis.
     ```
 
     ```
-    2,495 tracts in Los Angeles County
+    2495 tracts in Los Angeles County
     ```
 
 ### Year interpretation for ACS 5-year
@@ -358,14 +358,13 @@ import pypums
 cpi = {
     2018: 251.1,
     2019: 255.7,
-    2020: 258.8,
     2021: 270.9,
     2022: 292.7,
 }
 target_year = 2022
 
 frames = []
-for year in range(2018, 2023):
+for year in [2018, 2019, 2021, 2022]:  # skip 2020 (no standard ACS 1-year)
     df = pypums.get_acs(
         geography="state",
         variables="B19013_001",  # Median household income
@@ -387,9 +386,8 @@ print(trend[["year", "estimate", "estimate_real"]])
    year    estimate  estimate_real
 0  2018    75277.0      87760.6
 1  2019    78672.0      90046.7
-2  2020    78672.0      89005.4
-3  2021    80440.0      86906.3
-4  2022    84097.0      84097.0
+2  2021    80440.0      86906.3
+3  2022    84097.0      84097.0
 ```
 
 !!! note
@@ -420,12 +418,12 @@ print(df[["NAME", "DATE_CODE", "DATE_DESC", "value"]].head(10))
 ```
 
 ```
-         NAME  DATE_CODE              DATE_DESC      value
-0  California          1  4/1/2020 Census pop.  39538223
-1  California          2     7/1/2020 pop. est.  39499738
-2  California          3     7/1/2021 pop. est.  39142991
-3  California          4     7/1/2022 pop. est.  38965193
-4  California          5     7/1/2023 pop. est.  38965193
+         NAME  DATE_CODE                    DATE_DESC      value
+0  California          1  4/1/2020 Census population  39538223
+1  California          2  7/1/2020 population estimate  39499738
+2  California          3  7/1/2021 population estimate  39142991
+3  California          4  7/1/2022 population estimate  38965193
+4  California          5  7/1/2023 population estimate  38965193
 ```
 
 This is more efficient than looping over individual years and avoids the need

docs/guides/population-estimates.md

@@ -174,7 +174,7 @@ print(f"{len(by_age_sex)} rows (states × age groups × sexes)")
 ```
 
 ```
-4,992 rows (states × age groups × sexes)
+4992 rows (states × age groups × sexes)
 ```
 
 ---
@@ -672,7 +672,7 @@ print(race_data[["NAME", "RACE_label", "HISP_label", "value"]].head(4))
 ```
 
 ```
-7,620 rows
+7620 rows
                          NAME          RACE_label           HISP_label      value
 0  Anderson County, Texas       All races   Both Hispanic Origins      57245
 1  Anderson County, Texas       All races         Non-Hispanic      43210

docs/guides/pums-microdata.md

@@ -117,7 +117,7 @@ print(females[["AGEP", "SEX", "SCHL"]].head())
 ```
 
 ```
-198,412 records (all SEX == 2)
+198412 records (all SEX == 2)
    AGEP SEX SCHL
 0    35   2   21
 1    33   2   16
@@ -140,7 +140,7 @@ print(f"{len(grad_degrees)} records with Bachelor's, Master's, or Doctorate")
 ```
 
 ```
-98,245 records with Bachelor's, Master's, or Doctorate
+98245 records with Bachelor's, Master's, or Doctorate
 ```
 
 !!! tip "Server-side vs. client-side filtering"
@@ -168,7 +168,7 @@ print(employed_male_ba[["AGEP", "SEX", "SCHL", "ESR", "WAGP"]].head())
 ```
 
 ```
-12,843 employed males with BA in New York
+12843 employed males with BA in New York
    AGEP SEX SCHL ESR   WAGP
 0    34   1   21   1  65000
 1    28   1   21   1  52000
@@ -264,10 +264,11 @@ are included.
     ```
 
     ```
-    80 WGTP columns: ['WGTP1', 'WGTP2', 'WGTP3', 'WGTP4'] ... ['WGTP79', 'WGTP80']
+    81 WGTP columns: ['WGTP', 'WGTP1', 'WGTP2', 'WGTP3'] ... ['WGTP79', 'WGTP80']
     ```
 
-    Adds 80 housing replicate weight columns (`WGTP1` through `WGTP80`).
+    Adds 80 housing replicate weight columns (`WGTP1` through `WGTP80`)
+    alongside the main weight `WGTP`.
 
 === "Both"
 
@@ -347,7 +348,7 @@ print(f"{len(dtla)} records in PUMA 03710 (Downtown LA)")
 ```
 
 ```
-2,841 records in PUMA 03710 (Downtown LA)
+2841 records in PUMA 03710 (Downtown LA)
 ```
 
 ### Multiple PUMAs

docs/migration/from-tidycensus.md

@@ -140,7 +140,7 @@ If you've used Kyle Walker's [tidycensus](https://walker-data.com/tidycensus/) R
     ```
 
     ```
-    2,495 tracts
+    2495 tracts
          GEOID                           NAME  estimate                  geometry
     0  06037101110  Census Tract 1011.10, ...   85714.0  POLYGON ((-118.24 34.05...
     1  06037101122  Census Tract 1011.22, ...   62500.0  POLYGON ((-118.25 34.04...