From 48b1ac4753e687e07eab3930afbc41c7ff91085f Mon Sep 17 00:00:00 2001
From: Daniel Svitan <daniel.svitan.team7274dev@gmail.com>
Date: Wed, 21 May 2025 19:49:10 +0200
Subject: [PATCH] :bulb: Adjusts for population

---
 analysis.py | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/analysis.py b/analysis.py
index a6e8e99..cc008ae 100644
--- a/analysis.py
+++ b/analysis.py
@@ -14,6 +14,17 @@ counties = [
     "KE"
 ]
 counties_c = len(counties)  # how many counties
+counties_population = [
+    736_385,  # BA
+    565_900,  # TN
+    565_572,  # TT
+    665_600,  # NR
+    611_124,  # BB
+    686_063,  # ZA
+    810_008,  # PO
+    778_799  # KE
+]  # source: https://sk.wikipedia.org/wiki/Zoznam_krajov_na_Slovensku
+total_population = sum(counties_population)
 
 categories = [
     "Problematika voľného času",
@@ -96,10 +107,19 @@ for sample in data_original:
     for i in results:
         observed[i] += 1
 
+print("Observed before adjusting for population:")
+print(observed)
+
+# micro-wins per capita (because wins would be a tiny number)
+for i in range(len(observed)):
+    observed[i] = observed[i] / counties_population[i] * 1_000_000
+
+print("Observed after adjusting for population:")
+print(observed)
+
 expected = np.ones_like(observed) * (sum(observed) / len(observed))
 
-print("Data:")
-print(observed)
+print("Expected after adjusting for population:")
 print(expected)
 
 chi2, p = stats.chisquare(f_obs=observed, f_exp=expected)