add comments

app.py

@@ -22,28 +22,30 @@ texts = {"en": DEFAULT_TEXT, "ca": "Apple està buscant comprar una startup del
 button_css = "float: right; --tw-border-opacity: 1; border-color: rgb(229 231 235 / var(--tw-border-opacity)); --tw-gradient-from: rgb(243 244 246 / 0.7); --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to, rgb(243 244 246 / 0)); --tw-gradient-to: rgb(229 231 235 / 0.8); --tw-text-opacity: 1; color: rgb(55 65 81 / var(--tw-text-opacity));    border-width: 1px; --tw-bg-opacity: 1; background-color: rgb(255 255 255 / var(--tw-bg-opacity)); background-image: linear-gradient(to bottom right, var(--tw-gradient-stops)); display: inline-flex; flex: 1 1 0%; align-items: center; justify-content: center;    --tw-shadow: 0 1px 2px 0 rgb(0 0 0 / 0.05); --tw-shadow-colored: 0 1px 2px 0 var(--tw-shadow-color); box-shadow: var(--tw-ring-offset-shadow, 0 0 #0000), var(--tw-ring-shadow, 0 0 #0000), var(--tw-shadow); -webkit-appearance: button; border-radius: 0.5rem; padding-top: 0.5rem; padding-bottom: 0.5rem; padding-left: 1rem; padding-right: 1rem; font-size: 1rem; line-height: 1.5rem; font-weight: 600;"
 NOUN_ATTR = ['text', 'root.text', 'root.dep_', 'root.head.text']
 
+# get the huggingface models specified in the requirements.txt file
 def get_all_models():
     with open("requirements.txt") as f:
         content = f.readlines()
         models = []
         for line in content:
             if "huggingface.co" in line:
+                # the first three tokens in model, ex. en_core_web
                 model = "_".join(line.split("/")[4].split("_")[:3])
                 if model not in models:
                     models.append(model)
         return models
 
-
 models = get_all_models()
 
-
+# when clicked, download as SVG. Rendered as HTML on the page
 def download_svg(svg):
     encode = base64.b64encode(bytes(svg, 'utf-8'))
     img = 'data:image/svg+xml;base64,' + str(encode)[2:-1]
     html = f'<a download="displacy.svg" href="{img}" style="{button_css}">Download as SVG</a>'
     return html
 
-
+# create dependency graph, inputs are text, collapse punctuation, 
+# collapse phrases, compact, background color, font color, and model
 def dependency(text, col_punct, col_phrase, compact, bg, font, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -51,10 +53,10 @@ def dependency(text, col_punct, col_phrase, compact, bg, font, model):
     options = {"compact": compact, "collapse_phrases": col_phrase,
                "collapse_punct": col_punct, "bg": bg, "color": font}
     svg = displacy.render(doc, style="dep", options=options)
-    download = download_svg(svg)
+    download = download_svg(svg) # download button for SVG
     return svg, download, model_name
 
-
+# returns the NER displacy, inputs are text, checked ents, and model
 def entity(text, ents, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -63,7 +65,7 @@ def entity(text, ents, model):
     svg = displacy.render(doc, style="ent", options=options)
     return svg, model_name
 
-
+# returns token attributes for the user inputs
 def token(text, attributes, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -77,7 +79,8 @@ def token(text, attributes, model):
     data = pd.DataFrame(data, columns=attributes)
     return data, model_name
 
-
+# returns token attributtes in the default state
+# the return value is not a pandas DataFrame
 def default_token(text, attributes, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -90,7 +93,7 @@ def default_token(text, attributes, model):
         data.append(tok_data)
     return data, model_name
 
-
+# returns noun chunks in text
 def noun_chunks(text, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -102,7 +105,8 @@ def noun_chunks(text, model):
     data = pd.DataFrame(data, columns=NOUN_ATTR)
     return data, model_name
 
-
+# returns noun chuncks for the default value
+# the return value is not a pandas DataFrame
 def default_noun_chunks(text, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -113,7 +117,7 @@ def default_noun_chunks(text, model):
             chunk.root.head.text])
     return data, model_name
 
-
+# Get similarity of two random generated vectors
 def random_vectors(text, model):
     model_name = model + "_md"
     nlp = spacy.load(model_name)
@@ -125,13 +129,13 @@ def random_vectors(text, model):
     choice = random.choices(str_list, k=2)
     return round(choice[0].similarity(choice[1]), 2), choice[0].text, choice[1].text, model_name
 
-
+# Get similarity of two inputted vectors
 def vectors(input1, input2, model):
     model_name = model + "_md"
     nlp = spacy.load(model_name)
     return round(nlp(input1).similarity(nlp(input2)), 2), model_name
 
-
+# display spans, inputs are text, spans, labels, and model
 def span(text, span1, span2, label1, label2, model):
     model_name = model + "_sm"
     nlp = spacy.load(model_name)
@@ -174,20 +178,17 @@ def span(text, span1, span2, label1, label2, model):
     svg = displacy.render(doc, style="span")
     return svg, model_name
 
-
+# get default text based on language model
 def get_text(model):
     for i in range(len(models)):
         model = model.split("_")[0]
         new_text = texts[model]
-
     return new_text
 
-
 demo = gr.Blocks(css="scrollbar.css")
 
 with demo:
     with gr.Box():
-
         with gr.Row():
             with gr.Column():
                 gr.Markdown("# Pipeline Visualizer")
@@ -208,14 +209,12 @@ with demo:
                     gr.Markdown("")
                 with gr.Column():
                     gr.Markdown("")
-
             with gr.Row():
                 with gr.Column():
                     text_input = gr.Textbox(
                         value=DEFAULT_TEXT, interactive=True, label="Input Text")
                 with gr.Column():
                     gr.Markdown("")
-
             button = gr.Button("Update", variant="primary")
     with gr.Box():
         with gr.Column():
@@ -349,7 +348,7 @@ with demo:
                 with gr.Column():
                     gr.Markdown("")
             sim_random_button = gr.Button("Update random words")
-            sim_button = gr.Button("Update similarity", variant="primary")
+            sim_button = gr.Button("Update similarity", variant="primary")       
     with gr.Box():
         with gr.Column():
             with gr.Row():
@@ -391,7 +390,10 @@ with demo:
                 DEFAULT_TEXT, "U.K. startup", "U.K.", "ORG", "GPE", DEFAULT_MODEL)[0])
             span_button = gr.Button("Update Spans", variant="primary")
 
+    # change text based on model input
     model_input.change(get_text, inputs=[model_input], outputs=text_input)
+
+    # main button - update all components
     button.click(dependency, inputs=[
         text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[dep_output, dep_download_button, dep_model])
     button.click(
@@ -404,6 +406,8 @@ with demo:
                  sim_text2, model_input], outputs=[sim_output, sim_model])
     button.click(
         span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=[span_output, span_model])
+    
+    # individual component buttons
     dep_button.click(dependency, inputs=[
         text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[dep_output, dep_download_button, dep_model])
     ent_button.click(
@@ -418,4 +422,5 @@ with demo:
         span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=[span_output, span_model])
     sim_random_button.click(random_vectors, inputs=[text_input, model_input], outputs=[
                             sim_output, sim_text1, sim_text2, sim_model])
+
 demo.launch()