state-soc-cross/analysis.py
2025-05-03 20:26:10 +02:00

85 lines
2.2 KiB
Python

from typing import List
import scipy.stats as stats
import numpy as np
import matplotlib.pyplot as plt
counties = [
"BA",
"TN",
"TT",
"NR",
"BB",
"ZA",
"PO",
"KE"
]
counties_c = len(counties) # how many counties
categories = [
"Problematika voľného času",
"Matematika, fyzika",
"Chémia, potravinárstvo",
"Biológia",
"Životné prostredie, geografia, geológia",
"Zdravotníctvo, farmakológia",
"Pôdohospodárstvo (poľnohospodárstvo, lesné a vodné hospodárstvo)",
"Cestovný ruch, hotelierstvo, gastronómia",
"Strojárstvo, hutníctvo, doprava",
"Stavebníctvo, geodézia, kartografia",
"Informatika",
"Elektrotechnika, hardware, mechatronika",
"História, filozofia, právne vedy",
"Tvorba učebných pomôcok, didaktické technológie",
"Ekonomika a riadenie",
"Teória kultúry, umenie, umelecká, odevná tvorba",
"Pedagogika, psychológia, sociológia"
]
categories_c = 17 # how many categories
def map_counties(arr: List[str]) -> List[int]:
ret = []
for county in arr:
ret.append(counties.index(county))
return ret
raw_data = []
with open("dataset.txt") as stream:
for line in stream.readlines():
if not line:
continue
split = line.strip().split(" ")
year = int(split[0])
category = int(split[1])
wins_raw = split[2].split(",")
raw_data.append([year, category, *map_counties(wins_raw)])
# 0 - year
# 1 - abteilung (category) id (starts at 1)
# 2-7 - first to last place county ids
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))
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
print(data)