Analyses › Surface, excluding books 4 and 8, without rhetoric markers
Surface, excluding books 4 and 8, without rhetoric markers
This model drops sentences tagged other and fits a balanced TF-IDF logistic regression to the remaining mythic and historical tags.
Model Performance Metrics
The following metrics are from the logistic regression classifier's performance on the test set:
| Class |
Precision |
Recall |
F1-Score |
Support |
| Historical |
0.665 |
0.721 |
0.692 |
639 |
| Mythic |
0.732 |
0.676 |
0.703 |
717 |
| Overall Accuracy |
0.698 |
1356 |
Confusion Matrix
|
Predicted |
| Historical |
Mythic |
| Actual |
Historical |
461 |
178 |
| Mythic |
232 |
485 |
Counts
5,424mythic/historical sentences
2,867mythic
2,557historical
1,000features
Predictors of Mythic Sentences
Sort by:
| Word/Phrase |
English |
Coefficient |
Mythic Count |
Historical Count |
p-value |
q-value |
| εἶναι |
to be |
2.4003 |
345 |
106 |
3.41e-27 |
3.41e-24 |
| ἔπη |
words |
2.3966 |
38 |
1 |
6.67e-10 |
1.33e-07 |
| ἀφικέσθαι |
to arrive |
2.2922 |
34 |
3 |
4.08e-07 |
1.94e-05 |
| ἔχειν |
to have |
1.7922 |
29 |
9 |
0.00274 |
0.0194 |
| ἀνθρώπων |
of humans |
1.6954 |
44 |
16 |
0.00108 |
0.00979 |
| ἔνθα |
there; where; then |
1.5921 |
58 |
22 |
0.000292 |
0.00385 |
| γυναῖκα |
woman; wife |
1.5913 |
48 |
11 |
4.13e-06 |
0.000148 |
| ἐστὶν |
is |
1.5888 |
116 |
50 |
5.72e-06 |
0.000185 |
| ἐστιν |
is |
1.5620 |
214 |
96 |
2.48e-09 |
4.14e-07 |
| δʼ |
but; and |
1.5260 |
88 |
25 |
2.61e-08 |
2e-06 |
| ποταμὸν |
river |
1.5025 |
19 |
2 |
0.000319 |
0.00393 |
| αὐτόν |
him |
1.5006 |
43 |
17 |
0.00275 |
0.0194 |
| θυγατέρασ |
daughters |
1.4831 |
20 |
1 |
3.27e-05 |
0.000695 |
| ἔστι |
there is |
1.4574 |
81 |
33 |
6.14e-05 |
0.00108 |
| νομίζουσιν |
they think |
1.4353 |
23 |
2 |
5.43e-05 |
0.000996 |
| ἔχει |
he/she/it has |
1.4316 |
59 |
17 |
6.71e-06 |
0.000203 |
| γυναικῶν |
of women |
1.4117 |
24 |
8 |
0.00973 |
0.0455 |
| θυγατέρα |
daughter |
1.4115 |
55 |
8 |
4.13e-09 |
5.17e-07 |
| πεποίηται |
has been made |
1.4016 |
55 |
17 |
3.34e-05 |
0.000697 |
| ἔστιν |
there is |
1.3830 |
48 |
20 |
0.00269 |
0.0194 |
| ἔτοσ |
year |
1.3760 |
28 |
4 |
4.94e-05 |
0.000984 |
| καὶ εἶναι |
and to be |
1.3699 |
34 |
2 |
7.04e-08 |
4.69e-06 |
| θηρίον |
wild animal |
1.3654 |
12 |
0 |
0.000589 |
0.00608 |
| εἶναι καὶ |
also to be |
1.3614 |
63 |
7 |
1.27e-11 |
6.36e-09 |
| αὐτῶι |
to him |
1.3558 |
154 |
101 |
0.0131 |
0.0581 |
| θυγατέρων |
of daughters |
1.3389 |
14 |
1 |
0.00122 |
0.0102 |
| βωμὸσ |
altar |
1.3315 |
19 |
0 |
5.93e-06 |
0.000185 |
| καλεῖται |
is called |
1.3215 |
17 |
1 |
0.000201 |
0.00295 |
| γενέσθαι |
to become |
1.3203 |
155 |
63 |
2.02e-08 |
1.69e-06 |
| πρῶτον |
first; first of all |
1.2880 |
56 |
22 |
0.000574 |
0.00608 |
Predictors of Historical Sentences
Sort by:
| Word/Phrase |
English |
Coefficient |
Mythic Count |
Historical Count |
p-value |
q-value |
| ἐναντία |
opposite; contrary |
-2.3877 |
2 |
40 |
2.07e-11 |
6.91e-09 |
| αὖθισ |
again |
-2.2403 |
28 |
79 |
1.44e-08 |
1.31e-06 |
| πόλεμον |
war |
-2.0446 |
10 |
58 |
3.83e-11 |
9.58e-09 |
| εἰκόνα |
image |
-1.9911 |
5 |
29 |
3.15e-06 |
0.000117 |
| χρήματα |
money |
-1.9404 |
2 |
32 |
5.69e-09 |
6.33e-07 |
| ἀναστάτουσ |
expelled |
-1.7669 |
1 |
19 |
9.48e-06 |
0.000263 |
| πολέμου |
of war |
-1.7562 |
16 |
52 |
6.67e-07 |
3.03e-05 |
| ἔργου |
of work |
-1.7347 |
2 |
26 |
3.6e-07 |
1.8e-05 |
| πολέμωι |
in war; by/with war |
-1.6282 |
6 |
40 |
1.23e-08 |
1.23e-06 |
| ζημίαν |
a penalty |
-1.6010 |
0 |
16 |
5.8e-06 |
0.000185 |
| ἀνδρῶν |
of men; men's |
-1.5253 |
5 |
31 |
8.98e-07 |
3.74e-05 |
| ἑκατὸν |
one hundred |
-1.4888 |
0 |
13 |
5.59e-05 |
0.000998 |
| πυγμῆι |
with the fist |
-1.4624 |
1 |
14 |
0.00029 |
0.00385 |
| πολλά |
many; many things; often |
-1.4522 |
0 |
10 |
0.000537 |
0.0059 |
| ἐγένετο |
it happened |
-1.4501 |
43 |
90 |
1.35e-06 |
5.19e-05 |
| καὶ πρότερον |
and previously |
-1.4132 |
2 |
20 |
3.62e-05 |
0.000738 |
| ἐπίγραμμα |
epigram; inscription |
-1.3942 |
13 |
31 |
0.00168 |
0.0133 |
| χρημάτων |
of money; of goods |
-1.3440 |
5 |
27 |
1.09e-05 |
0.000286 |
| οὐδὲ |
nor |
-1.3438 |
28 |
43 |
0.0225 |
0.0814 |
| ἀνείλετο |
he/she/it killed |
-1.2783 |
1 |
19 |
9.48e-06 |
0.000263 |
| βαρβάρων |
of the barbarians |
-1.2591 |
7 |
27 |
0.000105 |
0.00178 |
| παγκρατίου |
of the pankration |
-1.2576 |
1 |
15 |
0.000147 |
0.0023 |
| σφῶν |
of them; their |
-1.2462 |
1 |
12 |
0.00112 |
0.00979 |
| οἰκίασ |
of the house; houses |
-1.2394 |
8 |
20 |
0.00905 |
0.0448 |
| στράτευμα |
army |
-1.2368 |
2 |
13 |
0.00287 |
0.0194 |
| χαλκοῦν |
of bronze; brazen |
-1.2343 |
7 |
21 |
0.00261 |
0.0189 |
| τυραννήσασ |
having become a tyrant |
-1.2273 |
0 |
9 |
0.00114 |
0.00984 |
| τάφοι |
tombs |
-1.2258 |
4 |
10 |
0.105 |
0.239 |
| πολεμίων |
of the enemies |
-1.2152 |
0 |
12 |
0.000119 |
0.00192 |
| τότε |
then; at that time |
-1.2125 |
60 |
119 |
1.17e-07 |
6.88e-06 |