backup

app.py

@@ -2,11 +2,6 @@
 from get_predictions import get_predictions
 import gradio
 
-"""
-@todo refactor code + fix nltk download
-@body change file directory, 
-"""
-
 
 if __name__ == "__main__":
     interface = gradio.Interface(

get_predictions.py

@@ -18,7 +18,3 @@ def get_predictions(text: str) -> tuple:
     pred_2 = model_2.predict(cleaned_data)[0]
 
     return (utils.TASK_1_MAP[pred_1], utils.TASK_2_MAP[pred_2])
-
-
-if __name__ == "__main__":
-    print(get_predictions("Hello"))

requirements.txt

@@ -1,53 +1,11 @@
-#
-# These requirements were autogenerated by pipenv
-# To regenerate from the project's Pipfile, run:
-#
-#    pipenv lock --requirements
-#
-
--i https://pypi.org/simple
-analytics-python==1.4.0
-backoff==1.10.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-bcrypt==3.2.0; python_version >= '3.6'
-certifi==2021.10.8
-cffi==1.15.0
-charset-normalizer==2.0.10; python_version >= '3'
-click==8.0.3; python_version >= '3.6'
-cryptography==36.0.1; python_version >= '3.6'
-cycler==0.11.0; python_version >= '3.6'
-ffmpy==0.3.0
-flask-cachebuster==1.0.0
-flask-cors==3.0.10
-flask-login==0.5.0
-flask==2.0.2; python_version >= '3.6'
-fonttools==4.28.5; python_version >= '3.7'
 gradio==2.7.0
-idna==3.3; python_version >= '3'
-itsdangerous==2.0.1; python_version >= '3.6'
-jinja2==3.0.3; python_version >= '3.6'
-joblib==1.0.1
-kiwisolver==1.3.2; python_version >= '3.7'
-markdown2==2.4.2; python_version >= '3.5' and python_version < '4'
-markupsafe==2.0.1; python_version >= '3.6'
-matplotlib==3.5.1; python_version >= '3.7'
-monotonic==1.6
-nltk==3.2.5
-numpy==1.19.5
-packaging==21.3; python_version >= '3.6'
-pandas==1.4.0rc0; python_version >= '3.8'
-paramiko==2.9.2
-pillow==9.0.0; python_version >= '3.7'
-pycparser==2.21
-pycryptodome==3.12.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-pydub==0.25.1
-pynacl==1.5.0; python_version >= '3.6'
-pyparsing==3.0.6; python_version >= '3.6'
-python-dateutil==2.8.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
-pytz==2021.3
-requests==2.27.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
-scikit-learn==0.22.2.post1
-scipy==1.8.0rc2; python_version < '3.11' and python_version >= '3.8'
-six==1.16.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
-urllib3==1.26.8; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
-werkzeug==2.0.2; python_version >= '3.6'
-xgboost==0.90
+xgboost==0.90
+numpy
+pandas
+matplotlib
+flask
+jinja2
+pillow
+nltk
+joblib
+sklearn

requirements.txt.bk

@@ -0,0 +1,53 @@
+#
+# These requirements were autogenerated by pipenv
+# To regenerate from the project's Pipfile, run:
+#
+#    pipenv lock --requirements
+#
+
+-i https://pypi.org/simple
+analytics-python==1.4.0
+backoff==1.10.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+bcrypt==3.2.0; python_version >= '3.6'
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.10; python_version >= '3'
+click==8.0.3; python_version >= '3.6'
+cryptography==36.0.1; python_version >= '3.6'
+cycler==0.11.0; python_version >= '3.6'
+ffmpy==0.3.0
+flask-cachebuster==1.0.0
+flask-cors==3.0.10
+flask-login==0.5.0
+flask==2.0.2; python_version >= '3.6'
+fonttools==4.28.5; python_version >= '3.7'
+gradio==2.7.0
+idna==3.3; python_version >= '3'
+itsdangerous==2.0.1; python_version >= '3.6'
+jinja2==3.0.3; python_version >= '3.6'
+joblib==1.0.1
+kiwisolver==1.3.2; python_version >= '3.7'
+markdown2==2.4.2; python_version >= '3.5' and python_version < '4'
+markupsafe==2.0.1; python_version >= '3.6'
+matplotlib==3.5.1; python_version >= '3.7'
+monotonic==1.6
+nltk==3.2.5
+numpy==1.19.5
+packaging==21.3; python_version >= '3.6'
+pandas==1.4.0rc0; python_version >= '3.8'
+paramiko==2.9.2
+pillow==9.0.0; python_version >= '3.7'
+pycparser==2.21
+pycryptodome==3.12.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+pydub==0.25.1
+pynacl==1.5.0; python_version >= '3.6'
+pyparsing==3.0.6; python_version >= '3.6'
+python-dateutil==2.8.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+pytz==2021.3
+requests==2.27.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
+scikit-learn==0.22.2.post1
+scipy==1.8.0rc2; python_version < '3.11' and python_version >= '3.8'
+six==1.16.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+urllib3==1.26.8; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
+werkzeug==2.0.2; python_version >= '3.6'
+xgboost==0.90

utils.py

@@ -3,7 +3,8 @@ import string
 import nltk
 import re
 
-nltk.download("stopwords")
+nltk.download("stopwords", download_dir="./nltk")
+
 # Constants
 TASK_1_MODEL = " models/TASK_A_model_final.pkl"
 TASK_2_MODEL = " models/TASK_B_model_final.pkl"
@@ -17,9 +18,19 @@ TASK_2_MAP = {
     1: "GEN - Misogynistic Content",
 }
 
+
 # Cleans one text
 def clean_one_text(text: str) -> str:
-    # Cleans one text and returns it
+    """
+    Cleans one text by removing punctuation, stopwords, and applying stemming.
+
+    Args:
+        text (str): The text to be cleaned.
+
+    Returns:
+        str: The cleaned text.
+
+    """
 
     # remove punctuation
     filter_str = string.punctuation.replace("'", "")