Как интерпретировать большое отрицательное значение _joint_log_likelihood.Допустим, переменная класса данных только для газа T / F.
# Programming assignment 2
import pickle
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import BernoulliNB
import numpy as np
print("Loading datasets...")
Xs = pickle.load(open('binarized_xs.pkl', 'rb'))
ys = pickle.load(open('binarized_ys.pkl', 'rb'))
print("Done Loading...")
alphaValues = list(map(lambda pow: 10 ** pow, range(-7, 8)))
print(alphaValues)
train_jll = np.zeros((10,15))
test_jll = np.zeros((10,15))
for i in range(len(Xs)):
X_train, X_test, y_train, y_test = train_test_split(Xs[i], ys[i], test_size=1./3, random_state=3922) # CWID - A 20413922
for alpha in range(len(alphaValues)):
model = BernoulliNB(alpha=alphaValues[alpha], binarize=0.0, class_prior=None, fit_prior=True)
sum_train = sum_test = 0
model.fit(X_train, y_train)
jll_xtrain = model._joint_log_likelihood(X_train)
jll_xtest = model._joint_log_likelihood(X_test)
for k in range(0, len(jll_xtrain)):
if y_train[k] is True:
sum_train += jll_xtrain[k][1]
else:
sum_train += jll_xtrain[k][0]
for l in range(0, len(jll_xtest)):
if y_train[l] is True:
sum_test += jll_xtest[l][1]
else:
sum_test += jll_xtest[l][0]
train_jll[i][alpha] = sum_train
test_jll[i][alpha] = sum_test
print("Train set accuracies")
for x in range(len(train_jll)):
print("\t".join("{0:.4f}".format(n) for n in train_jll[x]))
print("\nTest set accuracies")
for y in range(len(test_jll)):
print("\t".join("{0:.4f}".format(n) for n in test_jll[y]))
pickle.dump((train_jll, test_jll), open('result.pkl', 'wb'))
Вывод -
Загрузка наборов данных ... Готово Загрузка ... [1e-07, 1e-06, 1e-05,0,0001, 0,001, 0,01, 0,1, 1, 10, 100, 1000, 10000, 100000, 1000000, 10000000] Точность набора поездов -2076,9291 -1865.0913 -1653.2535 -1441.4161 -1229.5828 -1017.7904 -806.4090 -599.2828 -433.6816 -393.9880 -39394.3349 -394.3729 -394.3767 -394.3771 -32191,9825 -32125,2076 -32058,4325 -31991,6569 -31924,8758 -31858,0396 -31790,7286 -31723,9835 -31809,0404 -34359,6845 -44846,6500 -50567,2306 -51394,1834 -51480,5729 -51489,2505 -9399,8784 -8674,5640 -7949,2493 -7223,9305 -6498,5714 -5772,8111 -5043.1794 -4285.4285 -3557.9619 -4441.6394 -7156.1042 -7949.3959 -8043.5842 -8053.1794 -8054.1407 -353033,8920 -353017,7734 -353001,6555 -352985,5397 -352969,4446 -352953,5568 -352939,8490 -352954,5902 -353374,1657 -358382,4072 -409460,4788 -733413,0483 -1191967,4850 -1306874,0175 -1320147,6708 -3180,1231 -3180.1231 -3180.1231 -3180.1227 -3180.1193 -3180.0847 -3179.7394 -3176.3400 -3147.0704 -3059.4605 -3189.5939 -3280.1913 -3292.5986 -3293.8829 -3294.0118 -4574.8093 -4574.8093 -4574.8092 -4574.8085 -4574.8016016018676018016016015255255256255456456255456456255255255255255256255456456455256455256456455256456456456456456456456456456456456456456456456456456456456456456456456-RU-RU-RU-RU-RU-RU 847 -3179.7394 -3176.3400 -317-808-808 -7-RU12062.2160 -11525,7137 -10989,2111 -10452,7065 -9916,1810 -9379,4479 -8840,6448 -8281,8848 -7575,0972 -6582,4242 -6736,2181 -7272,9840 -7364,0583 -7373,7458 -7374,7206 -5259,2360 -5259,2360 -5259,2360 -5259,2361 -5259,2374 -5259,2503 -5259,3793 -5260,7374 -5279,3215 -5554,7885 -6477.3544 -6868.2764 -6919.7250 -6925.0321 -6925.5645 -3514.5228 -3489.1943 -3463.8658 -3438.5362 -3413.1960 -3387.7507 -3361.3059 -3328.3483 -3321.7284 -4067.7458 -5939.6312 -6559.4446 -6635.7135 -6643.5165 -6644.2986 -16439,2193 -16439,2192 -16439,2186 -16439,2126 -16439,1520 -16438,5472 -16432.5838 -16380.1945 -16158.3379 -16977.7163 -21690.7497 -23938.6506 -24244.2920 -24275.9518 -24279.1292
Точность тестового набора -1053.7924 -945.5709-837.3494 -729.1282 -620.9093 -512.7138 -404.7524 -299.1838 -215.8272 -196.2691 -196.9655 -197.1646 -197.1862 -197.1883 -197.1886 -15989,8827 -15957,6465 -15925,4103 -15893,1734 -15860,9307 -15828,6299 -15795,8012 -15761,3437 -15802,3473 -17104,9942 -22402,1020 -25280,9583-25696,8189 -25740,2591 -25744,6225 -4534,7085 -4177,8078 -3820,9070 -3464,0050 -3107,0909 -2750,0567 -2391,8688 -2025,7431 -1695,5868 -2189,5685 -3580,8558 -3984,4531 -4032,3297 -4037,2065 -4037,6951 -177068,0250 -177042,6961 -177017,3678 -176992,0408 -176966,7274 -176941,5493 -176917,7628-176910,2919 -177109,2109 -179594,7458 -205083,1285 -366890,6006 -596016,9983 -653440,6438 -660074,2024 -1620,5941 -1620,5941 -1620,5940 -1620,5938 -1620,5919 -1620,5727 -1620,3805 -1618,4869 -1602,0804 -1548,8017 -1601,9069 -1644,1081 -1649,9448 -1650,5496 -1650,6103 -2300,3443 -2300,3443-2300.3443 -2300.3440 -2300.3405 -2300.3063 -2299.9661 -2296.7773 -2280.6516 -2426.8969 -2874.4986 -3004.2282 -3019.4848 -3021.0371 -3021.1926-6679.6097 -6357.2478 -6034.8857 -5712.5225 -5390.1476 -5067.6560 -4744.0017 -4409.1390 -3991.1972 -3405.6240 -3400.4154 -3643.0063 -3685.1813 -3689.6778 -3690.1304 -2566.8863 -2566.8863 -2566.8863 -2566.8864 -2566.8872 -2566.8959 -2566.9826 -2567.8859 -2579.5423 -2735.3703-3228.0735 -3432.8776 -3459.7340 -3462.5032 -3462.7809 -1767.5406 -1758.3303 -1749.1199 -1739.9090 -1730.6931 -1721.4272 -1711.6835 -1698.6756 -1696.0342 -2056.3261 -2977.0952 -3223253233232322322322325-8463.1185 -8460.8158 -8458.5130 -8456.2073 -8453.8744 -8451.2691 -8445.9788 -8417.2311 -8295.8823 -8635.8290 -10888.2128 -11982.1214 -12131.2829 -12146.73898 -12148.2