Update: Add model type

README.md

@@ -1,5 +1,5 @@
 ---
-title: spaCy Pipeline Visualizer
+title: Gradio Pipeline Visualizer
 emoji: 👀
 colorFrom: green
 colorTo: gray

app.py

@@ -41,42 +41,29 @@ def download_svg(svg):
     html = f'<a download="displacy.svg" href="{img}" style="{button_css}">Download as SVG</a>'
     return html
 
-# def download_png(svg):
-#     encode = base64.b64encode(bytes(svg, 'utf-8'))
-#     svg_uri = 'data:image/svg+xml;base64,' + str(encode)[2:-1]
-#     output = cairosvg.svg2png(url=svg_uri)
-#     encoded = base64.b64encode(output)
-#     img = 'data:image/png;base64,' + str(encoded)[2:-1]
-#     html = f'<a download="displacy.png" href="{img}" style="{button_css}">Download as PNG</a>'
-#     return html
-
-# def download(type, svg):
-#     if type == 'png':
-#         return download_png(svg)
-#     elif type == 'svg':
-#         return download_svg(svg)
-
 def dependency(text, col_punct, col_phrase, compact, bg, font, model):
-    nlp = spacy.load(model + "_sm")
+    model_name = model + "_sm"
+    nlp = spacy.load(model_name)
     doc = nlp(text)
     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)
-    return svg, download
+    return svg, download, model_name
 
 
 def entity(text, ents, model):
-    nlp = spacy.load(model + "_sm")
+    model_name = model + "_sm"
+    nlp = spacy.load(model_name)    
     doc = nlp(text)
     options = {"ents": ents}
     svg = displacy.render(doc, style="ent", options=options)
-    # download = download_svg('<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" xml:lang="en" id="97e9d3ac65344f2bb6e6ce517bd13b1e-0" class="displacy" width="1800" height="399.5" direction="ltr" style="max-width: none; height: 399.5px; color: black; font-family: Arial; direction: ltr">' + svg + "</svg>")
-    return svg
+    return svg, model_name
 
 
 def token(text, attributes, model):
-    nlp = spacy.load(model + "_sm")
+    model_name = model + "_sm"
+    nlp = spacy.load(model_name)
     data = []
     doc = nlp(text)
     for tok in doc:
@@ -85,11 +72,12 @@ def token(text, attributes, model):
             tok_data.append(getattr(tok, attr))
         data.append(tok_data)
     data = pd.DataFrame(data, columns=attributes)
-    return data
+    return data, model_name
 
 
 def default_token(text, attributes, model):
-    nlp = spacy.load(model + "_sm")
+    model_name = model + "_sm"
+    nlp = spacy.load(model_name)
     data = []
     doc = nlp(text)
     for tok in doc:
@@ -97,27 +85,30 @@ def default_token(text, attributes, model):
         for attr in attributes:
             tok_data.append(getattr(tok, attr))
         data.append(tok_data)
-    return data
+    return data, model_name
 
 
 def random_vectors(text, model):
-    nlp = spacy.load(model + "_md")
+    model_name = model + "_md"
+    nlp = spacy.load(model_name)
     doc = nlp(text)
     n_chunks = [chunk for chunk in doc.noun_chunks if doc.noun_chunks]
     words = [tok for tok in doc if not tok.is_stop and tok.pos_ not in [
         'PUNCT', "PROPN"]]
     str_list = n_chunks + words
     choice = random.choices(str_list, k=2)
-    return round(choice[0].similarity(choice[1]), 2), choice[0].text, choice[1].text
+    return round(choice[0].similarity(choice[1]), 2), choice[0].text, choice[1].text, model_name
 
 
 def vectors(input1, input2, model):
-    nlp = spacy.load(model + "_md")
-    return round(nlp(input1).similarity(nlp(input2)), 2)
+    model_name = model + "_md"
+    nlp = spacy.load(model_name)
+    return round(nlp(input1).similarity(nlp(input2)), 2), model_name
 
 
 def span(text, span1, span2, label1, label2, model):
-    nlp = spacy.load(model + "_sm")
+    model_name = model + "_sm"
+    nlp = spacy.load(model_name)
     doc = nlp(text)
     if span1:
         idx1_1 = 0
@@ -155,8 +146,7 @@ def span(text, span1, span2, label1, label2, model):
         ]
 
     svg = displacy.render(doc, style="span")
-    # download = download_svg(svg)
-    return svg
+    return svg, model_name
 
 
 def get_text(model):
@@ -200,13 +190,21 @@ with demo:
                 with gr.Column():
                     gr.Markdown("")
 
-            button = gr.Button("Generate", variant="primary")
+            button = gr.Button("Update", variant="primary")
     with gr.Box():
         with gr.Column():
-            gr.Markdown(
-                "## [Dependency Parser](https://spacy.io/usage/visualizers#dep)")
-            gr.Markdown(
-                "The dependency visualizer shows part-of-speech tags and syntactic dependencies")
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown(
+                        "## [Dependency Parser](https://spacy.io/usage/visualizers#dep)")
+                    gr.Markdown(
+                        "The dependency visualizer shows part-of-speech tags and syntactic dependencies")
+                with gr.Column():
+                    with gr.Row():
+                        with gr.Column():
+                            gr.Markdown(" ")
+                        with gr.Column():
+                            dep_model = gr.Textbox(label="Model", value="en_core_web_sm")
             with gr.Row():
                 with gr.Column():
                     col_punct = gr.Checkbox(
@@ -221,43 +219,47 @@ with demo:
                     text = gr.Textbox(
                         label="Text Color", value="black")
             
-            depen_output = gr.HTML(value=dependency(
+            dep_output = gr.HTML(value=dependency(
                 DEFAULT_TEXT, True, True, False, DEFAULT_COLOR, "black", DEFAULT_MODEL)[0])
             with gr.Row():
                 with gr.Column():
-                    dep_button = gr.Button("Generate Dependency Parser", variant="primary")
+                    dep_button = gr.Button("Update Dependency Parser", variant="primary")
                 with gr.Column():
-                    dep_download_button = gr.HTML(value=download_svg(depen_output.value))
-                    
-                
-                
+                    dep_download_button = gr.HTML(value=download_svg(dep_output.value))
                 gr.Markdown(" ")
     with gr.Box():
         with gr.Column():
-            gr.Markdown(
-                "## [Entity Recognizer](https://spacy.io/usage/visualizers#ent)")
-            gr.Markdown(
-                "The entity visualizer highlights named entities and their labels in a text")
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown(
+                        "## [Entity Recognizer](https://spacy.io/usage/visualizers#ent)")
+                    gr.Markdown(
+                        "The entity visualizer highlights named entities and their labels in a text")
+                with gr.Column():
+                    with gr.Row():
+                        with gr.Column():
+                            gr.Markdown(" ")
+                        with gr.Column():
+                            ent_model = gr.Textbox(label="Model", value="en_core_web_sm")  
             ent_input = gr.CheckboxGroup(
                 DEFAULT_ENTS, value=DEFAULT_ENTS)
             ent_output = gr.HTML(value=entity(
-                DEFAULT_TEXT, DEFAULT_ENTS, DEFAULT_MODEL))
-            ent_button = gr.Button("Generate Entity Recognizer", variant="primary")
-            # with gr.Row():
-            #         with gr.Column():
-            #             ent_button = gr.Button("Generate Entity Recognizer", variant="primary")
-            #         with gr.Column():
-            #             ent_download_button = gr.HTML(value=download_svg(ent_output.value))
-            #         with gr.Column():
-            #             gr.Markdown(" ")
-            #         with gr.Column():
-            #             gr.Markdown(" ")
+                DEFAULT_TEXT, DEFAULT_ENTS, DEFAULT_MODEL)[0])
+            ent_button = gr.Button("Update Entity Recognizer", variant="primary")
     with gr.Box():
         with gr.Column():
-            gr.Markdown(
-                "## [Token Properties](https://spacy.io/usage/linguistic-features)")
-            gr.Markdown(
-                "When you put in raw text to spaCy, it returns a Doc object with different linguistic features")
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown(
+                        "## [Token Properties](https://spacy.io/usage/linguistic-features)")
+                    gr.Markdown(
+                        "When you put in raw text to spaCy, it returns a Doc object with different linguistic features")
+                with gr.Column():
+                    with gr.Row():
+                        with gr.Column():
+                            gr.Markdown(" ")
+                        with gr.Column():
+                            tok_model = gr.Textbox(label="Model", value="en_core_web_sm")  
             with gr.Row():
                 with gr.Column():
                     tok_input = gr.CheckboxGroup(
@@ -265,14 +267,22 @@ with demo:
                 with gr.Column():
                     gr.Markdown("")
             tok_output = gr.Dataframe(headers=DEFAULT_TOK_ATTR, value=default_token(
-                DEFAULT_TEXT, DEFAULT_TOK_ATTR, DEFAULT_MODEL), overflow_row_behaviour="paginate")
-            tok_button = gr.Button("Generate Token Properties", variant="primary")
+                DEFAULT_TEXT, DEFAULT_TOK_ATTR, DEFAULT_MODEL)[0], overflow_row_behaviour="paginate")
+            tok_button = gr.Button("Update Token Properties", variant="primary")
     with gr.Box():
         with gr.Column():
-            gr.Markdown(
-                "## [Word and Phrase Similarity](https://spacy.io/usage/linguistic-features#vectors-similarity)")
-            gr.Markdown(
-                "Words and spans have similarity ratings based off of their word vectors, or word embeddings")
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown(
+                        "## [Word and Phrase Similarity](https://spacy.io/usage/linguistic-features#vectors-similarity)")
+                    gr.Markdown(
+                        "Words and spans have similarity ratings based off of their word vectors, or word embeddings")
+                with gr.Column():
+                    with gr.Row():
+                        with gr.Column():
+                            gr.Markdown(" ")
+                        with gr.Column():
+                            sim_model = gr.Textbox(label="Model", value="en_core_web_md")
             with gr.Row():
                 with gr.Column():
                     sim_text1 = gr.Textbox(
@@ -285,15 +295,22 @@ with demo:
                         label="Similarity Score", value="0.12")
                 with gr.Column():
                     gr.Markdown("")
-            sim_random_button = gr.Button("Generate random words")
-            sim_button = gr.Button("Generate similarity", variant="primary")
+            sim_random_button = gr.Button("Update random words")
+            sim_button = gr.Button("Update similarity", variant="primary")
     with gr.Box():
         with gr.Column():
-            gr.Markdown(
-                "## [Spans](https://spacy.io/usage/visualizers#span)")
-            gr.Markdown(
-                "The span visualizer highlights overlapping spans in a text")
-            
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown(
+                        "## [Spans](https://spacy.io/usage/visualizers#span)")
+                    gr.Markdown(
+                        "The span visualizer highlights overlapping spans in a text")
+                with gr.Column():
+                    with gr.Row():
+                        with gr.Column():
+                            gr.Markdown(" ")
+                        with gr.Column():
+                            span_model = gr.Textbox(label="Model", value="en_core_web_sm")
             with gr.Row():
                 with gr.Column():
                     span1 = gr.Textbox(
@@ -317,39 +334,30 @@ with demo:
                 with gr.Column():
                     gr.Markdown("")
             span_output = gr.HTML(value=span(
-                DEFAULT_TEXT, "U.K. startup", "U.K.", "ORG", "GPE", DEFAULT_MODEL))
-            span_button = gr.Button("Generate Spans", variant="primary")
-            # with gr.Row():
-            #         with gr.Column():
-            #             span_button = gr.Button("Generate Spans", variant="primary")
-            #         with gr.Column():
-            #             span_download_button = gr.HTML(value=download_svg(span_output.value))
-            #         with gr.Column():
-            #             gr.Markdown(" ")
-            #         with gr.Column():
-            #             gr.Markdown(" ")
+                DEFAULT_TEXT, "U.K. startup", "U.K.", "ORG", "GPE", DEFAULT_MODEL)[0])
+            span_button = gr.Button("Update Spans", variant="primary")
 
     model_input.change(get_text, inputs=[model_input], outputs=text_input)
     button.click(dependency, inputs=[
-        text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[depen_output, dep_download_button])
+        text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[dep_output, dep_download_button, dep_model])
     button.click(
-        entity, inputs=[text_input, ent_input, model_input], outputs=[ent_output])
+        entity, inputs=[text_input, ent_input, model_input], outputs=[ent_output, ent_model])
     button.click(
-        token, inputs=[text_input, tok_input, model_input], outputs=tok_output)
+        token, inputs=[text_input, tok_input, model_input], outputs=[tok_output, tok_model])
     button.click(vectors, inputs=[sim_text1,
-                 sim_text2, model_input], outputs=sim_output)
+                 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, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=[span_output, span_model])
     dep_button.click(dependency, inputs=[
-        text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[depen_output, dep_download_button])
+        text_input, col_punct, col_phrase, compact, bg, text, model_input], outputs=[dep_output, dep_download_button, dep_model])
     ent_button.click(
-        entity, inputs=[text_input, ent_input, model_input], outputs=[ent_output])
+        entity, inputs=[text_input, ent_input, model_input], outputs=[ent_output, ent_model])
     tok_button.click(
-        token, inputs=[text_input, tok_input, model_input], outputs=[tok_output])
+        token, inputs=[text_input, tok_input, model_input], outputs=[tok_output, tok_model])
     sim_button.click(vectors, inputs=[
-                     sim_text1, sim_text2, model_input], outputs=sim_output)
+                     sim_text1, sim_text2, model_input], outputs=[sim_output, sim_model])
     span_button.click(
-        span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=[span_output])
+        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_output, sim_text1, sim_text2, sim_model])
 demo.launch()

requirements.txt

@@ -1,6 +1,6 @@
 pandas==1.4.2
 gradio==3.0.18
-spacy==3.4.0
+spacy==3.3.1
 
 https://huggingface.co/spacy/ca_core_news_md/resolve/main/ca_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ca_core_news_sm/resolve/main/ca_core_news_sm-any-py3-none-any.whl