Try embedding document classifier inside main block

projects/01_Document_Classifier.py

@@ -72,34 +72,35 @@ def autoclassifier(images):
             # Delete image file
             os.remove(image.name)
 
-st.header('Document Classifier', divider='green')
-
-st.warning("Work in Progress")
-
-st.markdown("#### What is OCR?")
-st.markdown("OCR stands for Optical Character Recognition, and the technology for it has been around for over 30 years.")
-st.markdown("In this project, we leverage the extraction of the text from an image to classify the document. I am using EasyOCR as the OCR Engine, and I do some pre-processing of the raw OCR text to improve the quality of the words used to classify the documents.")
-st.markdown("After an investigation I settled on a Random Forest classifier for this project, since it had the best classification accuracy of the different models I investigated.")
-st.markdown("This project makes use of the [Real World Documents Collections](https://www.kaggle.com/datasets/shaz13/real-world-documents-collections) found at `Kaggle`")
-st.markdown("*This project is based off the tutorial by Animesh Giri [Intelligent Document Classification](https://www.kaggle.com/code/animeshgiri/intelligent-document-classification)*")
-st.markdown("*N.B. I created a similar document classifier in my first ML project, but that relied on IBM's Datacap for the OCR Engine. I also used a Support Vector Machine (SVM) classifier library (libsvm) at the time, but it was slow to train. I tried to re-create that document classifier again, using open source tools and modern techniques outlined in the referenced tutorial.*")
-st.divider()
-
-# Load the Spacy tokenizer
-nlp = load_nlp()
-
-# Initialze the OCR Engine
-ocr_engine = load_ocr_engine()
-
-# Load the Model
-stopwords, punctuations, model_pipe = load_model()
-
-# Fetch uploaded images
-images = st.file_uploader(
-    "Choose an image to classify",
-    type=['png','jpg','jpeg'],
-    accept_multiple_files=True
-)
-
-# Process and predict document classification
-autoclassifier(images)
+if __name__ == "__main__":
+    st.header('Document Classifier', divider='green')
+
+    st.warning("Work in Progress")
+
+    st.markdown("#### What is OCR?")
+    st.markdown("OCR stands for Optical Character Recognition, and the technology for it has been around for over 30 years.")
+    st.markdown("In this project, we leverage the extraction of the text from an image to classify the document. I am using EasyOCR as the OCR Engine, and I do some pre-processing of the raw OCR text to improve the quality of the words used to classify the documents.")
+    st.markdown("After an investigation I settled on a Random Forest classifier for this project, since it had the best classification accuracy of the different models I investigated.")
+    st.markdown("This project makes use of the [Real World Documents Collections](https://www.kaggle.com/datasets/shaz13/real-world-documents-collections) found at `Kaggle`")
+    st.markdown("*This project is based off the tutorial by Animesh Giri [Intelligent Document Classification](https://www.kaggle.com/code/animeshgiri/intelligent-document-classification)*")
+    st.markdown("*N.B. I created a similar document classifier in my first ML project, but that relied on IBM's Datacap for the OCR Engine. I also used a Support Vector Machine (SVM) classifier library (libsvm) at the time, but it was slow to train. I tried to re-create that document classifier again, using open source tools and modern techniques outlined in the referenced tutorial.*")
+    st.divider()
+
+    # Load the Spacy tokenizer
+    nlp = load_nlp()
+
+    # Initialze the OCR Engine
+    ocr_engine = load_ocr_engine()
+
+    # Load the Model
+    stopwords, punctuations, model_pipe = load_model()
+
+    # Fetch uploaded images
+    images = st.file_uploader(
+        "Choose an image to classify",
+        type=['png','jpg','jpeg'],
+        accept_multiple_files=True
+    )
+
+    # Process and predict document classification
+    autoclassifier(images)