Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
################
sgd + tf_idf
################
{'mean_fit_time': array([11.1112638 , 7.65372081]), 'std_fit_time': array([0.30272061, 0.68979293]), 'mean_score_time': array([0.10862832, 0.1094533 ]), 'std_score_time': array([0.01651967, 0.01454473]), 'param_loss': masked_array(data=['log', 'modified_huber'],
mask=[False, False],
fill_value='?',
dtype=object), 'params': [{'loss': 'log'}, {'loss': 'modified_huber'}], 'split0_test_score': array([0.69589831, 0.82364879]), 'split1_test_score': array([0.69899594, 0.82023072]), 'split2_test_score': array([0.69511804, 0.82234804]), 'split3_test_score': array([0.69757505, 0.81989104]), 'split4_test_score': array([0.70345049, 0.82480504]), 'mean_test_score': array([0.69820757, 0.82218473]), 'std_test_score': array([0.00294576, 0.00190344]), 'rank_test_score': array([2, 1], dtype=int32)}
SGDClassifier(loss='modified_huber')
################
lr + tf_idf
################
{'mean_fit_time': array([123.9822535 , 136.45079255, 257.74739246, 308.11041398,
311.64957185, 322.79306488, 305.09573908]), 'std_fit_time': array([ 3.76680984, 8.42099004, 9.91248406, 4.83509197, 16.14945534,
14.52110241, 21.5707605 ]), 'mean_score_time': array([0.13736248, 0.15582333, 0.1767817 , 0.16810074, 0.18395748,
0.18684502, 0.18736963]), 'std_score_time': array([0.01582882, 0.0185194 , 0.04162888, 0.01046594, 0.00640279,
0.03858243, 0.10977951]), 'param_C': masked_array(data=[0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0],
mask=[False, False, False, False, False, False, False],
fill_value='?',
dtype=object), 'params': [{'C': 0.001}, {'C': 0.01}, {'C': 0.1}, {'C': 1.0}, {'C': 10.0}, {'C': 100.0}, {'C': 1000.0}], 'split0_test_score': array([0.22388379, 0.28797266, 0.59378338, 0.78914762, 0.81595813,
0.81189917, 0.80677206]), 'split1_test_score': array([0.22388379, 0.28978851, 0.59506516, 0.78498184, 0.81456954,
0.81019013, 0.80378124]), 'split2_test_score': array([0.22401453, 0.28928533, 0.59427412, 0.78378378, 0.81038351,
0.80931524, 0.7964961 ]), 'split3_test_score': array([0.22401453, 0.2883239 , 0.59309903, 0.78827048, 0.81134494,
0.81070398, 0.8030125 ]), 'split4_test_score': array([0.22401453, 0.28800342, 0.59363316, 0.79051383, 0.81390877,
0.81177225, 0.80760602]), 'mean_test_score': array([0.22396223, 0.28867476, 0.59397097, 0.78733951, 0.81323298,
0.81077615, 0.80353359]), 'std_test_score': array([6.40506523e-05, 7.32118303e-04, 6.63133820e-04, 2.54613785e-03,
2.06657692e-03, 9.73267502e-04, 3.92253793e-03]), 'rank_test_score': array([7, 6, 5, 4, 1, 2, 3], dtype=int32)}
LogisticRegression(C=10.0)
################
rfc + tf_idf
{'mean_fit_time': array([ 7.13981152, 2.20858259, 8.44964633, 2.15034537, 9.95642118,
2.37193513, 11.87502141, 2.5397316 , 13.33019848, 2.6721931 ]), 'std_fit_time': array([0.39802958, 0.16057515, 0.09037486, 0.04216271, 0.25096427,
0.07728006, 0.13315339, 0.09627813, 0.67575281, 0.19097522]), 'mean_score_time': array([1.01170306, 1.04494491, 0.87090235, 1.33797326, 1.25466337,
1.85760932, 1.73018894, 0.91106348, 1.23974652, 1.24655042]), 'std_score_time': array([0.11756533, 0.17492892, 0.15125138, 0.92002164, 0.86968069,
1.7114886 , 1.81341711, 0.11803296, 0.98138169, 0.98342632]), 'param_max_depth': masked_array(data=[4, 4, 5, 5, 6, 6, 7, 7, 8, 8],
mask=[False, False, False, False, False, False, False, False,
False, False],
fill_value='?',
dtype=object), 'param_max_features': masked_array(data=['sqrt', 'log2', 'sqrt', 'log2', 'sqrt', 'log2', 'sqrt',
'log2', 'sqrt', 'log2'],
mask=[False, False, False, False, False, False, False, False,
False, False],
fill_value='?',
dtype=object), 'params': [{'max_depth': 4, 'max_features': 'sqrt'}, {'max_depth': 4, 'max_features': 'log2'}, {'max_depth': 5, 'max_features': 'sqrt'}, {'max_depth': 5, 'max_features': 'log2'}, {'max_depth': 6, 'max_features': 'sqrt'}, {'max_depth': 6, 'max_features': 'log2'}, {'max_depth': 7, 'max_features': 'sqrt'}, {'max_depth': 7, 'max_features': 'log2'}, {'max_depth': 8, 'max_features': 'sqrt'}, {'max_depth': 8, 'max_features': 'log2'}], 'split0_test_score': array([0.24193548, 0.22388379, 0.254326 , 0.22388379, 0.26169622,
0.22388379, 0.26842555, 0.22420423, 0.27878658, 0.22441786]), 'split1_test_score': array([0.23894467, 0.22388379, 0.24727622, 0.22388379, 0.25891903,
0.22388379, 0.26201666, 0.22388379, 0.27846614, 0.22420423]), 'split2_test_score': array([0.24452516, 0.22401453, 0.24698216, 0.22401453, 0.26332657,
0.22401453, 0.2683474 , 0.22401453, 0.27208632, 0.22422818]), 'split3_test_score': array([0.24698216, 0.22401453, 0.24901186, 0.22401453, 0.26492896,
0.22401453, 0.2703771 , 0.22444183, 0.27710715, 0.22433501]), 'split4_test_score': array([0.24206816, 0.22401453, 0.25360538, 0.22401453, 0.2614037 ,
0.22401453, 0.27347506, 0.22412135, 0.27625254, 0.22444183]), 'mean_test_score': array([0.24289113, 0.22396223, 0.25024032, 0.22396223, 0.2620549 ,
0.22396223, 0.26852835, 0.22413315, 0.27653974, 0.22432542]), 'std_test_score': array([2.70450243e-03, 6.40506523e-05, 3.12816315e-03, 6.40506523e-05,
2.01314354e-03, 6.40506523e-05, 3.75055041e-03, 1.88005584e-04,
2.40818393e-03, 9.62616196e-05]), 'rank_test_score': array([5, 8, 4, 8, 3, 8, 2, 7, 1, 6], dtype=int32)}
RandomForestClassifier(max_depth=8, max_features='sqrt')