sklearn_broken_test.py

import numpy as np
from os import listdir
from os.path import isfile, join
from PIL import Image
from sklearn.datasets.base import Bunch
from sklearn import svm
from sklearn.naive_bayes import MultinomialNB



def prepare_dataset():
    data_list = []
    target_list = np.array([])
    mypath = r"./test_data/"
    onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
    onlyfiles = [f for f in onlyfiles if f.endswith("txt")] # we only want the txt files
    for f in onlyfiles:
        output_array = np.fromfile(join(mypath, f), np.uint32)#.reshape((16,16)) # target
        # output_file = open(join(mypath, f), "rb")
        input_array = np.asarray(Image.open(join(mypath, f.split(".")[0] + ".png")).convert("L")).flatten() # data
        # print(len(input_array))
        #input_file = 
        
        #data_list = np.append(data_list, input_array)
        data_list.append(input_array)
        target_list = np.append(target_list, output_array)
        #target_list.append(output_array)
    return Bunch(data=np.array(data_list), target=target_list)
    
def main():
    ascii_data = prepare_dataset()
    #print(ascii_data.target)
    print(ascii_data.data[0].reshape(1,-1) )
    # print(ascii_data.target[0])
    # print(prepare_dataset())
    # clf = svm.SVC(gamma=0.001, C=100.)
    #clf = svm.SVC(gamma=0.001)
    clf = MultinomialNB()
    
    clf.fit(ascii_data.data[0].reshape(1,-1) , ascii_data.target[0])
    print(ascii_data.data[0])
    print(clf.predict(ascii_data.data[0]))
    
    
if __name__ == "__main__":
    main()