⚡ Adds chi2 and fisher exact tests

analysis.py

@@ -59,26 +59,38 @@ with open("dataset.txt") as stream:
 
 
 # 0 - year
-# 1 - abteilung (category) id (starts at 1)
-# 2-7 - first to last place county ids
+# 1 - abteilung (category) idx (starts at 1)
+# 2-7 - first to last place county idxs
 data_original = np.array(raw_data)
 
-# table where counties are rows and category-scores are columnes
-#      01 | 02 | 03 | ...
-# BA |  5 |  2 |  1 | ...
-# TT |  0 |  3 |  4 | ...
-# KE |  4 |  1 |  5 | ...
-# ...
-# as a row-first 2d numpy array (first dimension will represent counties, second category-scores)
-data = np.zeros((counties_c, categories_c))
+# table where counties are rows and counts of placements are columnes
+#      #1 | #2 | ...
+# BA |  5 |  4 | ...
+# ZA |  9 |  8 | ...
+# KE |  4 |  6 | ...
+# as a row-first 2d numpy array (first dimension will represent counties, second counts of placements)
+data = np.zeros((counties_c, 5))  # 5 because top five
 for sample in data_original:
-    category_id = sample[1] - 1  # because they start at 1
     results = sample[2:7]
-    for i, county_id in enumerate(results):
-        # first  -> 5
-        # second -> 4
-        # ... (formula is 6 - i)
-        data[county_id, category_id] += 6 - i
+    for placement_idx, county_idx in enumerate(results):
+        data[county_idx, placement_idx] += 1
 
 
+print("Data:")
 print(data)
+
+# H0: county and placement are independent
+# H1: county and placement are not independent
+print("\nAttempting Chi-Square test")
+chi2, p, dof, expected = stats.chi2_contingency(data)
+
+print(f"Chi-Square Statistic: {chi2}")
+print(f"p-value: {p}")
+print(f"Degrees of Freedom: {dof}")
+#print("Expected Frequencies:\n", expected)
+
+print("\nAttempting Fisher's Exact test")
+oddsratio, p_value = stats.fisher_exact(data)
+
+print(f"Odds Ratio: {oddsratio}")
+print(f"p-value: {p_value}")