Streamer272/state-soc-cross
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

⚡ Adds chi2 and fisher exact tests

Browse Source
This commit is contained in:
Daniel Svitan 2025-05-03 20:55:55 +02:00
parent feed2387c8
commit 465f56146a
1 changed files with 28 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
analysis.py
View File

@ -59,26 +59,38 @@ with open("dataset.txt") as stream:
# 0 - year # 0 - year
# 1 - abteilung (category) id (starts at 1) # 1 - abteilung (category) idx (starts at 1)
# 2-7 - first to last place county ids # 2-7 - first to last place county idxs
data_original = np.array(raw_data) data_original = np.array(raw_data)
# table where counties are rows and category-scores are columnes # table where counties are rows and counts of placements are columnes
# 01 | 02 | 03 | ... # #1 | #2 | ...
# BA | 5 | 2 | 1 | ... # BA | 5 | 4 | ...
# TT | 0 | 3 | 4 | ... # ZA | 9 | 8 | ...
# KE | 4 | 1 | 5 | ... # KE | 4 | 6 | ...
# ... # as a row-first 2d numpy array (first dimension will represent counties, second counts of placements)
# as a row-first 2d numpy array (first dimension will represent counties, second category-scores) data = np.zeros((counties_c, 5)) # 5 because top five
data = np.zeros((counties_c, categories_c))
for sample in data_original: for sample in data_original:
category_id = sample[1] - 1 # because they start at 1
results = sample[2:7] results = sample[2:7]
for i, county_id in enumerate(results): for placement_idx, county_idx in enumerate(results):
# first -> 5 data[county_idx, placement_idx] += 1
# second -> 4
# ... (formula is 6 - i)
data[county_id, category_id] += 6 - i
print("Data:")
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}")