most_common_from_train

2021-11-08 14:12:12 +01:00 · 2021-11-08 14:12:12 +01:00 · b4b1807c63
commit b4b1807c63
parent 8abd7178b4
3 changed files with 101856 additions and 101845 deletions
--- a/dev-0/out.tsv
+++ b/dev-0/out.tsv
--- a/most_common_from_train/a.py
+++ b/most_common_from_train/a.py
@ -0,0 +1,11 @@
+import pandas as pd
+
+r_out = pd.read_csv('../train/expected.tsv', names = ('class',))
+most_common = r_out['class'].value_counts().idxmax()
+
+
+for dataset in 'dev-0', 'test-A':
+    with open(f'../{dataset}/out.tsv', 'w') as f_out, open(f'../{dataset}/in.tsv', 'r') as f_in:
+        for line_in in f_in:
+            f_out.write(most_common + '\n')
+
--- a/test-A/out.tsv
+++ b/test-A/out.tsv