Analyses › Surface, excluding books 4 and 8, with rhetoric markers
Surface, excluding books 4 and 8, with 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 |
0.673 |
0.754 |
0.711 |
639 |
| Mythic |
0.755 |
0.674 |
0.712 |
717 |
| Overall Accuracy |
0.712 |
1356 |
Confusion Matrix
|
Predicted |
| Historical |
Mythic |
| Actual |
Historical |
482 |
157 |
| Mythic |
234 |
483 |
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 |
| λέγουσιν |
they say |
2.9979 |
194 |
38 |
6.93e-24 |
3.46e-21 |
| ἔπη |
words |
2.3688 |
38 |
1 |
6.67e-10 |
6.67e-08 |
| ἀφικέσθαι |
to arrive |
2.0120 |
34 |
3 |
4.08e-07 |
1.57e-05 |
| εἶναι |
to be |
1.9473 |
345 |
106 |
3.41e-27 |
3.41e-24 |
| ὄνομα |
name |
1.8765 |
136 |
42 |
4.41e-11 |
6.31e-09 |
| φασιν |
they say |
1.8469 |
143 |
28 |
7.43e-18 |
2.48e-15 |
| φασὶν |
they say |
1.8207 |
79 |
15 |
1.23e-10 |
1.54e-08 |
| ἔχειν |
to have |
1.7533 |
29 |
9 |
0.00274 |
0.018 |
| ἀνθρώπων |
of humans |
1.7115 |
44 |
16 |
0.00108 |
0.00901 |
| ἐστιν |
is |
1.7013 |
214 |
96 |
2.48e-09 |
2.26e-07 |
| ἐστὶν |
is |
1.6222 |
116 |
50 |
5.72e-06 |
0.000156 |
| γυναῖκα |
woman; wife |
1.6092 |
48 |
11 |
4.13e-06 |
0.000122 |
| δʼ |
but; and |
1.5856 |
88 |
25 |
2.61e-08 |
1.45e-06 |
| ἔστι |
there is |
1.5322 |
81 |
33 |
6.14e-05 |
0.000944 |
| αὐτόν |
him |
1.5263 |
43 |
17 |
0.00275 |
0.018 |
| πεποίηται |
has been made |
1.5146 |
55 |
17 |
3.34e-05 |
0.000597 |
| λόγοσ |
word; speech; account; reason; argument |
1.4935 |
42 |
9 |
8.93e-06 |
0.000218 |
| ἔνθα |
there; where; then |
1.4738 |
58 |
22 |
0.000292 |
0.00349 |
| νομίζουσιν |
they think |
1.4630 |
23 |
2 |
5.43e-05 |
0.000869 |
| θυγατέρασ |
daughters |
1.4287 |
20 |
1 |
3.27e-05 |
0.000594 |
| ποταμὸν |
river |
1.4211 |
19 |
2 |
0.000319 |
0.00358 |
| θυγατέρων |
of daughters |
1.3987 |
14 |
1 |
0.00122 |
0.00952 |
| θηρίον |
wild animal |
1.3705 |
12 |
0 |
0.000589 |
0.00567 |
| καὶ εἶναι |
and to be |
1.3625 |
31 |
1 |
5.95e-08 |
3.13e-06 |
| καλεῖται |
is called |
1.3513 |
17 |
1 |
0.000201 |
0.00264 |
| θυγατέρα |
daughter |
1.3504 |
55 |
8 |
4.13e-09 |
3.18e-07 |
| λέγουσι |
they say |
1.3496 |
101 |
24 |
4.17e-11 |
6.31e-09 |
| ἔχων |
having |
1.3430 |
31 |
11 |
0.00515 |
0.0276 |
| βωμὸσ |
altar |
1.3389 |
19 |
0 |
5.93e-06 |
0.000156 |
| ἔχει |
he/she/it has |
1.3283 |
59 |
17 |
6.71e-06 |
0.000172 |
Predictors of Historical Sentences
Sort by:
| Word/Phrase |
English |
Coefficient |
Mythic Count |
Historical Count |
p-value |
q-value |
| ἐναντία |
opposite; contrary |
-2.3060 |
2 |
40 |
2.07e-11 |
5.19e-09 |
| αὖθισ |
again |
-2.2017 |
28 |
79 |
1.44e-08 |
9.03e-07 |
| πόλεμον |
war |
-1.9910 |
10 |
58 |
3.83e-11 |
6.31e-09 |
| εἰκόνα |
image |
-1.9428 |
5 |
29 |
3.15e-06 |
9.55e-05 |
| χρήματα |
money |
-1.8374 |
2 |
32 |
5.69e-09 |
4.07e-07 |
| ἀναστάτουσ |
expelled |
-1.7127 |
1 |
19 |
9.48e-06 |
0.00022 |
| πολέμου |
of war |
-1.7091 |
16 |
52 |
6.67e-07 |
2.38e-05 |
| ἔργου |
of work |
-1.6303 |
2 |
26 |
3.6e-07 |
1.44e-05 |
| πολέμωι |
in war; by/with war |
-1.5844 |
6 |
40 |
1.23e-08 |
8.21e-07 |
| ἑκατὸν |
one hundred |
-1.5310 |
0 |
13 |
5.59e-05 |
0.000873 |
| ζημίαν |
a penalty |
-1.5090 |
0 |
16 |
5.8e-06 |
0.000156 |
| ἀνδρῶν |
of men; men's |
-1.4760 |
5 |
31 |
8.98e-07 |
2.99e-05 |
| πολλά |
many; many things; often |
-1.4732 |
0 |
10 |
0.000537 |
0.00548 |
| πυγμῆι |
with the fist |
-1.3985 |
1 |
14 |
0.00029 |
0.00349 |
| καὶ πρότερον |
and previously |
-1.3867 |
2 |
20 |
3.62e-05 |
0.000634 |
| ἐγένετο |
it happened |
-1.3623 |
43 |
90 |
1.35e-06 |
4.22e-05 |
| σφῶν |
of them; their |
-1.3067 |
1 |
12 |
0.00112 |
0.00901 |
| παγκρατίου |
of the pankration |
-1.2879 |
1 |
15 |
0.000147 |
0.00204 |
| ἄνδρασ |
men |
-1.2865 |
15 |
39 |
0.000173 |
0.00233 |
| ἐπίγραμμα |
epigram; inscription |
-1.2803 |
13 |
31 |
0.00168 |
0.0124 |
| τότε |
then; at that time |
-1.2669 |
60 |
119 |
1.17e-07 |
5.32e-06 |
| ἀνείλετο |
he/she/it killed |
-1.2591 |
1 |
19 |
9.48e-06 |
0.00022 |
| οὐδὲ |
nor |
-1.2441 |
28 |
43 |
0.0225 |
0.0767 |
| ὃσ |
who; which; that |
-1.2419 |
48 |
75 |
0.00186 |
0.0133 |
| χρημάτων |
of money; of goods |
-1.2414 |
5 |
27 |
1.09e-05 |
0.000242 |
| βαρβάρων |
of the barbarians |
-1.2390 |
7 |
27 |
0.000105 |
0.00156 |
| τάφοι |
tombs |
-1.2176 |
4 |
10 |
0.105 |
0.232 |
| αὐτῶν |
of them; their |
-1.2128 |
71 |
116 |
3.21e-05 |
0.000594 |
| πολεμίων |
of the enemies |
-1.2021 |
0 |
12 |
0.000119 |
0.0017 |
| ἐπʼ αὐτοῖσ |
on them |
-1.1968 |
3 |
12 |
0.0167 |
0.0628 |