INT104-lab4

python 统计频率

import csv
import numpy as np


# the method for parse data into a matrix
def input_data_to_matrix():
    csv_file = open('binary_data.csv')
    csv_reader = csv.reader(csv_file, delimiter=',')
    Matrix = []
    N = 0
    for row in csv_reader:
        Matrix.append([int(i) for i in row])
        N += 1
    print("
Showing the matrix:
")
    print(np.array(Matrix))
    return Matrix, N


# the method to compute p(ai=?|l=?)
def p(i: int, ai: int, l: int, Matrix: list):
    n = N = 0
    for a in Matrix:
        if a[5] == l:
            if a[i] == ai:
                n += 1
            N += 1
    print("p(a[{}]={}|l={})={}".format(i, ai, l, n / N))


if __name__ == '__main__':
    # part 1
    # Reading data and parse its content into a matrix
    # (20 scores)
    Matrix, N = input_data_to_matrix()

    # part 2
    # Compute the prior probabilities p(l = 0) and p(l = 1)
    # (20 scores)
    print("
Result of p(l=0) and p(l=1)
")
    n = [0, 0]
    for a in Matrix:
        if a[5] == 0:
            n[0] += 1
        else:
            n[1] += 1
    for i in range(2):
        print("p(l={})={}".format(i, n[i] / N))

    # part 3
    # Compute the conditional probabilities
    # p(ai=0|l=0),i=0,1,2,3,4 and p(ai=1|l=0),i=0,1,2,3,4,
    # p(ai=0|l=1),i=0,1,2,3,4 and p(ai=1|l=1),i=0,1,2,3,4
    # (60 scores)
    No = 1
    for l in range(2):
        for ai in range(2):
            print("
Result Group_{} of: p(ai={}|l={}),i=0,1,2,3,4
".format(No, ai, l))
            No += 1
            for i in range(5):
                p(i, ai, l, Matrix)