chi_squared.py

from stats_collector import StatsCollector

LETTER_PROBABILITIES = {"A": 0.0856, "B": 0.0139, "C": 0.0279, "D": 0.0378,
                        "E": 0.1304, "F": 0.0289, "G": 0.0199, "H": 0.0528,
                        "I": 0.0627, "J": 0.0013, "K": 0.0042, "L": 0.0339,
                        "M": 0.0249, "N": 0.0707, "O": 0.0797, "P": 0.0199,
                        "Q": 0.0012, "R": 0.0677, "S": 0.0607, "T": 0.1045,
                        "U": 0.0249, "V": 0.0092, "W": 0.0149, "X": 0.0017,
                        "Y": 0.0199, "Z": 0.0008}


class ChiSquared:
    def __init__(self, data):
        self.data = data
        self.val = 0
        self._calculate()

    def _calculate(self):
        stats_collector = StatsCollector(self.data)
        for c, f in stats_collector.freq_dict.items():
            expected_c = LETTER_PROBABILITIES[c] * stats_collector.total_chars
            self.val += (f - expected_c) ** 2 / expected_c