From cb8a96579fefb6a3c9ef225e892b309a18149eb4 Mon Sep 17 00:00:00 2001
From: Jakub Konieczny <jakkon6@st.amu.edu.pl>
Date: Sun, 23 Jan 2022 15:39:11 +0000
Subject: [PATCH] adapt to vm

---
 do_inject.sh                  |  6 +-----
 scripts/do_inject_helper.sh   |  9 +++++++++
 scripts/inject.py             | 11 ++++++-----
 scripts/lemmatize_glossary.py |  7 +++++--
 scripts/lemmatize_in.py       | 10 ++++++----
 5 files changed, 27 insertions(+), 16 deletions(-)
 mode change 100644 => 100755 do_inject.sh
 create mode 100755 scripts/do_inject_helper.sh

diff --git a/do_inject.sh b/do_inject.sh
old mode 100644
new mode 100755
index f74cbdf..f4a0f4e
--- a/do_inject.sh
+++ b/do_inject.sh
@@ -1,7 +1,3 @@
 #!/bin/bash
 
-source gpu/bin/activate
-
-python scripts/lemmatize_glossary.py
-python scripts/lemmatize_in.py
-python scripts/inject.py
+. ./scripts/do_inject_helper.sh
diff --git a/scripts/do_inject_helper.sh b/scripts/do_inject_helper.sh
new file mode 100755
index 0000000..f2d62d3
--- /dev/null
+++ b/scripts/do_inject_helper.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+source ~/gpu/bin/activate
+
+cd ~/transfix-mt/scripts
+
+python lemmatize_glossary.py
+python lemmatize_in.py
+python inject.py
diff --git a/scripts/inject.py b/scripts/inject.py
index f118357..368d261 100644
--- a/scripts/inject.py
+++ b/scripts/inject.py
@@ -1,3 +1,4 @@
+import os
 import pandas as pd
 import rapidfuzz
 
@@ -40,13 +41,13 @@ def get_injected(sentence, sentence_en, sequence, inject):
 
 THRESHOLD = 70
 
-# train_in_path = 'mt-summit-corpora/train/in.tsv'
-# train_expected_path = 'mt-summit-corpora/train/expected.tsv'
+# train_in_path = '~/mt-summit-corpora/train/in.tsv'
+# train_expected_path = '~/mt-summit-corpora/train/expected.tsv'
 
-train_in_path = 'mt-summit-corpora/dev-0/in.tsv'
-train_expected_path = 'mt-summit-corpora/dev-0/expected.tsv'
+train_in_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/dev-0/in.tsv')
+train_expected_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/dev-0/expected.tsv')
 
-glossary = pd.read_csv('mt-summit-corpora/glossary_lem.tsv', sep='\t')
+glossary = pd.read_csv('~/mt-summit-corpora/glossary.tsv.lemmatized', sep='\t')
 glossary['source_lem'] = [str(default_process(x)) for x in glossary['source_lem']]
 
 file_pl = pd.read_csv(train_expected_path, sep='\t', header=None, names=['text'])
diff --git a/scripts/lemmatize_glossary.py b/scripts/lemmatize_glossary.py
index a62cb5f..5325c09 100644
--- a/scripts/lemmatize_glossary.py
+++ b/scripts/lemmatize_glossary.py
@@ -6,7 +6,10 @@ from nltk.stem import WordNetLemmatizer
 nltk.download('wordnet')
 
 wl = WordNetLemmatizer()
-glossary = pd.read_csv('mt-summit-corpora/glossary.tsv', sep='\t', header=None, names=['source', 'result'])
+
+glossary_path = '~/mt-summit-corpora/glossary.tsv'
+
+glossary = pd.read_csv(glossary_path, sep='\t', header=None, names=['source', 'result'])
 source_lemmatized = []
 for word in glossary['source']:
     word = nltk.word_tokenize(word)
@@ -16,4 +19,4 @@ glossary['source_lem'] = source_lemmatized
 glossary = glossary[['source', 'source_lem', 'result']]
 glossary.set_index('source_lem')
 
-glossary.to_csv('mt-summit-corpora/glossary_lem.tsv', sep='\t', index=False)
+glossary.to_csv(glossary_path + '.lemmatized', sep='\t', index=False)
diff --git a/scripts/lemmatize_in.py b/scripts/lemmatize_in.py
index 190d7c6..2232f07 100644
--- a/scripts/lemmatize_in.py
+++ b/scripts/lemmatize_in.py
@@ -1,14 +1,16 @@
 import nltk
+import os
+
 from nltk.stem import WordNetLemmatizer
 
 
 wl = WordNetLemmatizer()
 
-# train_in_path = 'mt-summit-corpora/train/in.tsv'
-# train_expected_path = 'mt-summit-corpora/train/expected.tsv'
+# train_in_path = '~/mt-summit-corpora/train/in.tsv'
+# train_expected_path = '~/mt-summit-corpora/train/expected.tsv'
 
-train_in_path = 'mt-summit-corpora/dev-0/in.tsv'
-train_expected_path = 'mt-summit-corpora/dev-0/expected.tsv'
+train_in_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/dev-0/in.tsv')
+train_expected_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/dev-0/expected.tsv')
 
 file_lemmatized = []
 with open(train_in_path, 'r') as file: