kuhyx/WUT_Computer_Science
1
0
Fork 0
mirror of https://github.com/kuhyx/WUT_Computer_Science.git synced 2026-07-04 15:03:08 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

quick fix

Browse Source
This commit is contained in:
mati9456 2024-01-10 23:12:16 +01:00
parent 581cb90466
commit 56650422d8
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
format_alignments.py
View File

@ -3,19 +3,22 @@ import processing
import re import re
import copy import copy
# output file name # input file name
file_path = "headlines_fixed_format.wa" file_path = "alignments_unformatted_headlines.txt"
# paths to students andsewrs database # output file path
#chunked_path1 = "test_goldStandard/student/STSint.testinput.answers-students.sent1.chunk.txt" output_file_path = "headlines_fixed_format.wa"
#chunked_path2 = "test_goldStandard/student/STSint.testinput.answers-students.sent2.chunk.txt"
#alignment_path = "test_goldStandard/student/STSint.testinput.answers-students.wa"
# paths to headlines database # paths to headlines database
chunked_path1 = "test_goldStandard/headlines/STSint.testinput.headlines.sent1.chunk.txt" chunked_path1 = "test_goldStandard/headlines/STSint.testinput.headlines.sent1.chunk.txt"
chunked_path2 = "test_goldStandard/headlines/STSint.testinput.headlines.sent1.chunk.txt" chunked_path2 = "test_goldStandard/headlines/STSint.testinput.headlines.sent1.chunk.txt"
alignment_path = "test_goldStandard/headlines/STSint.testinput.headlines.wa" alignment_path = "test_goldStandard/headlines/STSint.testinput.headlines.wa"
# paths to students andsewrs database
#chunked_path1 = "test_goldStandard/student/STSint.testinput.answers-students.sent1.chunk.txt"
#chunked_path2 = "test_goldStandard/student/STSint.testinput.answers-students.sent2.chunk.txt"
#alignment_path = "test_goldStandard/student/STSint.testinput.answers-students.wa"
# load data # load data
goldstandard_chunked = processing.load_chunked(chunked_path1, chunked_path2) goldstandard_chunked = processing.load_chunked(chunked_path1, chunked_path2)
goldstandard_alignment = processing.load_alignment(alignment_path) goldstandard_alignment = processing.load_alignment(alignment_path)
@ -23,8 +26,6 @@ goldstandard_alignment = processing.load_alignment(alignment_path)
# get a nice table # get a nice table
data = pd.merge(goldstandard_chunked, goldstandard_alignment, left_index=True, right_index=True) data = pd.merge(goldstandard_chunked, goldstandard_alignment, left_index=True, right_index=True)
file_path = "alignments_unformatted_headlines.txt"
# open generated alignments # open generated alignments
with open(file_path, 'r') as file: with open(file_path, 'r') as file:
responses = [eval(line.strip()) for line in file.readlines()] responses = [eval(line.strip()) for line in file.readlines()]
@ -141,7 +142,7 @@ for n, r in enumerate(responses):
print("rejected indexes:") print("rejected indexes:")
print(rejected_indexes) print(rejected_indexes)
with open(file_path, 'w') as file: with open(output_file_path, 'w') as file:
for i, r in zip(indexes, responses_final): for i, r in zip(indexes, responses_final):
file.write("<sentence id=\"" + str(i+1) + "\" status=\"\">\n") file.write("<sentence id=\"" + str(i+1) + "\" status=\"\">\n")
file.write("<alignment>\n") file.write("<alignment>\n")