debugging, removed unnecessary files

Author: neagualexa

.github/workflows/ai-version-deploy.yml

@@ -37,11 +37,6 @@ jobs:
           python -m pip install --upgrade pip
           python -m pip install flake8 pytest
           python -m pip install -r requirements.txt
-          # python -m nltk.downloader wordnet
-          # python -m nltk.downloader word2vec_sample
-          # python -m nltk.downloader brown
-          # python -m nltk.downloader punkt
-          # python -m nltk.downloader stopwords
 
       - name: Lint with flake8
         run: |

app/Dockerfile

@@ -6,53 +6,10 @@ FROM rabidsheep55/python-base-eval-layer
 
 WORKDIR /app
 
-# RUN mkdir /usr/share/nltk_data
-# RUN mkdir -p /usr/share/nltk_data/corpora /usr/share/nltk_data/models /usr/share/nltk_data/tokenizers
-
-# ARG NLTK_DATA=/usr/share/nltk_data
-
-# ENV NLTK_DATA=/usr/share/nltk_data
 # Copy and install any packages/modules needed for your evaluation script.
 COPY requirements.txt .
-# COPY brown_length .
-# COPY word_freqs .
-# COPY w2v .
-# RUN yum install -y wget unzip
 RUN pip3 install -r requirements.txt
 
-# # Download NLTK data files
-# RUN wget -O /usr/share/nltk_data/corpora/wordnet.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/wordnet.zip
-# RUN wget -O /usr/share/nltk_data/models/word2vec_sample.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/models/word2vec_sample.zip
-# RUN wget -O /usr/share/nltk_data/corpora/brown.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/brown.zip
-# RUN wget -O /usr/share/nltk_data/corpora/stopwords.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/stopwords.zip
-# RUN wget -O /usr/share/nltk_data/tokenizers/punkt.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/tokenizers/punkt.zip
-# RUN wget -O /usr/share/nltk_data/tokenizers/punkt_tab.zip https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/tokenizers/punkt_tab.zip
-
-# # Unzip the downloaded files into the correct subfolders corresponsing to NLTK requirements
-# RUN unzip /usr/share/nltk_data/corpora/wordnet.zip -d /usr/share/nltk_data/corpora/
-# RUN unzip /usr/share/nltk_data/models/word2vec_sample.zip -d /usr/share/nltk_data/models/
-# RUN unzip /usr/share/nltk_data/corpora/brown.zip -d /usr/share/nltk_data/corpora/
-# RUN unzip /usr/share/nltk_data/corpora/stopwords.zip -d /usr/share/nltk_data/corpora/
-# RUN unzip /usr/share/nltk_data/tokenizers/punkt.zip -d /usr/share/nltk_data/tokenizers/
-# RUN unzip /usr/share/nltk_data/tokenizers/punkt_tab.zip -d /usr/share/nltk_data/tokenizers/
-
-# # Clean up zip files to reduce image size
-# RUN rm /usr/share/nltk_data/corpora/*.zip
-# RUN rm /usr/share/nltk_data/models/*.zip
-# RUN rm /usr/share/nltk_data/tokenizers/*.zip
-
-# Warnings: those commands sometimes download corrupted zips, so it is better to wget each package from the main site
-# RUN python -m nltk.downloader wordnet
-# RUN python -m nltk.downloader word2vec_sample
-# RUN python -m nltk.downloader brown
-# RUN python -m nltk.downloader stopwords
-# RUN python -m nltk.downloader punkt
-# RUN python -m nltk.downloader punkt_tab
-
-# Copy the evaluation and testing scripts
-# COPY brown_length ./app/
-# COPY word_freqs ./app/
-# COPY w2v ./app/
 COPY evaluation.py ./app/
 COPY evaluation_tests.py ./app/
 

app/brown_length

@@ -79,6 +79,8 @@ def recursive_evaluation(responses, answers, chain, parser):
             eval_result = chain.invoke({"word": res, "target": ans})
             eval_result_content = eval_result.content
             similarity_result = parser.invoke(eval_result_content)
+
+            print("eval_result_content: ", eval_result_content, "; similarity_result: ", similarity_result, "; res: ", res, "; ans: ", ans) #TODO: debugging
 
             if similarity_result == "True":
                 matched_word = ans
@@ -105,7 +107,7 @@ def evaluation_function(response, answer, param=None):
     response = parse_input(response)
     answer = parse_input(answer)
 
-
+    print("response: ", response, "; answer: ", answer) #TODO: debugging
 
 
     # Ensure config is provided
@@ -174,6 +176,8 @@ def evaluation_function(response, answer, param=None):
         return {"is_correct": False, "error": "Invalid input: response and answer must be lists of strings."}
 
     is_correct, correct_answers, incorrect_answers = recursive_evaluation(response, answer, chain, parser)
+    print("correct_answers: ", correct_answers, "; incorrect_answers: ", incorrect_answers) #TODO: debugging
+
     #check if student is inputting enough answers
     if len(response) < param.response_num_required:
         is_correct = False