Feat:Spans

app.py

@@ -7,72 +7,83 @@ import gradio as gr
 DEFAULT_MODEL = "en_core_web_sm"
 DEFAULT_TEXT = "David Bowie moved to the US in 1974, initially staying in New York City before settling in Los Angeles."
 DEFAULT_TOK_ATTR = ['idx', 'text', 'pos_', 'lemma_', 'shape_', 'dep_']
-DEFAULT_ENTS = ['CARDINAL', 'DATE', 'EVENT', 'FAC', 'GPE', 'LANGUAGE', 'LAW', 'LOC', 'MONEY', 'NORP', 'ORDINAL', 'ORG', 'PERCENT', 'PERSON', 'PRODUCT', 'QUANTITY', 'TIME', 'WORK_OF_ART']
+DEFAULT_ENTS = ['CARDINAL', 'DATE', 'EVENT', 'FAC', 'GPE', 'LANGUAGE', 'LAW', 'LOC', 'MONEY',
+                'NORP', 'ORDINAL', 'ORG', 'PERCENT', 'PERSON', 'PRODUCT', 'QUANTITY', 'TIME', 'WORK_OF_ART']
 
 nlp = spacy.load("en_core_web_sm")
 nlp2 = spacy.load("en_core_web_md")
 
+
 def dependency(text, col_punct, col_phrase, compact):
-  doc = nlp(text)
-  options = {"compact": compact, "collapse_phrases": col_phrase, "collapse_punct": col_punct}
-  html = displacy.render(doc, style="dep", options=options)
-  return html
+    doc = nlp(text)
+    options = {"compact": compact, "collapse_phrases": col_phrase,
+               "collapse_punct": col_punct}
+    html = displacy.render(doc, style="dep", options=options)
+    return html
+
 
 def entity(text, ents):
-  doc = nlp(text)
-  options = {"ents": ents}
-  html = displacy.render(doc, style="ent", options=options)
-  return html
+    doc = nlp(text)
+    options = {"ents": ents}
+    html = displacy.render(doc, style="ent", options=options)
+    return html
 
-def text(default):
-  if default:
-    return default
 
-def token(text, attributes):
-  data = []
-  doc = nlp(text)
-  for tok in doc:
-    tok_data = []
-    for attr in attributes:
-      tok_data.append(getattr(tok, attr))
-    data.append(tok_data)
-  return data
+def text(default):
+    if default:
+        return default
 
-def vectors(text):
-  doc = nlp2(text)
-  n_chunks = [chunk for chunk in 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
 
-def span(text, span1, span2, label1, label2):
-  doc = nlp(text)
-  idx1_1 = 0
-  idx1_2 = 0
-  idx2_1 = 0
-  idx2_2 = 0
+def token(text, attributes):
+    data = []
+    doc = nlp(text)
+    for tok in doc:
+        tok_data = []
+        for attr in attributes:
+            tok_data.append(getattr(tok, attr))
+        data.append(tok_data)
+    return data
 
-  for tok in doc:
-    if span1[0] == tok.text:
-      idx1_1 = tok.idx
-    if span1[-1] == tok.text:
-      idx1_2 = tok.idx
-    if span2[0] == tok.text:
-      idx2_1 = tok.idx
-    if span2[-1] == tok.text:
-      idx2_2 = tok.idx
 
+def vectors(text):
+    doc = nlp2(text)
+    n_chunks = [chunk for chunk in 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
 
-  doc.spans["sc"] = [
-      Span(doc, idx1_1, idx1_2, label1), 
-      Span(doc, idx2_1, idx2_2, label2),
-  ]
 
-  html = displacy.render(doc, style="span")
-  return html
+def span(text, span1, span2, label1, label2):
+    doc = nlp(text)
+    idx1_1 = 0
+    idx1_2 = 0
+    idx2_1 = 0
+    idx2_2 = 0
+
+    span1 = span1.split(" ")
+    span2 = span2.split(" ")
+
+    for i in range(len(list(doc))):
+        tok = list(doc)[i]
+        if span1[0] == tok.text:
+            idx1_1 = i
+        if span1[-1] == tok.text:
+            idx1_2 = i + 1
+        if span2[0] == tok.text:
+            idx2_1 = i
+        if span2[-1] == tok.text:
+            idx2_2 = i + 1
+
+    doc.spans["sc"] = [
+        Span(doc, idx1_1, idx1_2, label1),
+        Span(doc, idx2_1, idx2_2, label2),
+    ]
+
+    html = displacy.render(doc, style="span")
+    return html
 
-list_chunks = [chunk.text for chunk in nlp(DEFAULT_TEXT).noun_chunks]
 
 demo = gr.Blocks()
 
@@ -82,7 +93,7 @@ with demo:
     with gr.Tabs():
         with gr.TabItem("Dependency"):
             col_punct = gr.Checkbox(label="Collapse Punctuation", value=True)
-            col_phrase = gr.Checkbox(label="Collapse Phrases", value=True) 
+            col_phrase = gr.Checkbox(label="Collapse Phrases", value=True)
             compact = gr.Checkbox(label="Compact", value=True)
             depen_output = gr.HTML()
             depen_button = gr.Button("Generate")
@@ -91,18 +102,31 @@ with demo:
             entity_output = gr.HTML()
             entity_button = gr.Button("Generate")
         with gr.TabItem("Tokens"):
-            tok_input = gr.CheckboxGroup(DEFAULT_TOK_ATTR, value=DEFAULT_TOK_ATTR)
+            tok_input = gr.CheckboxGroup(
+                DEFAULT_TOK_ATTR, value=DEFAULT_TOK_ATTR)
             tok_output = gr.Dataframe()
             tok_button = gr.Button("Generate")
         with gr.TabItem("Similarity"):
-            sim_text1 = gr.Textbox(label="Chosen")
-            sim_text2 = gr.Textbox(label="Chosen")
-            sim_output = gr.Textbox(label="Similarity Score")
+            sim_text1 = gr.Textbox(value="David Bowie", label="Chosen")
+            sim_text2 = gr.Textbox(value="the US", label="Chosen")
+            sim_output = gr.Textbox(value="0.09", label="Similarity Score")
             sim_button = gr.Button("Generate")
-
-    depen_button.click(dependency, inputs=[text_input, col_punct, col_phrase, compact], outputs=depen_output)
-    entity_button.click(entity, inputs=[text_input, entity_input], outputs=entity_output)
+        with gr.TabItem("Spans"):
+            span1 = gr.Textbox(value="David Bowie", label="Span 1")
+            label1 = gr.Textbox(value="Full Name", label="Label for Span 1")
+            span2 = gr.Textbox(value="David", label="Span 2")
+            label2 = gr.Textbox(value="First Name", label="Label for Span 2")
+            span_output = gr.HTML()
+            span_button = gr.Button("Generate")
+
+    depen_button.click(dependency, inputs=[
+                       text_input, col_punct, col_phrase, compact], outputs=depen_output)
+    entity_button.click(
+        entity, inputs=[text_input, entity_input], outputs=entity_output)
     tok_button.click(token, inputs=[text_input, tok_input], outputs=tok_output)
-    sim_button.click(vectors, inputs=[text_input], outputs=[sim_output, sim_text1, sim_text2])
+    sim_button.click(vectors, inputs=[text_input], outputs=[
+                     sim_output, sim_text1, sim_text2])
+    span_button.click(
+        span, inputs=[text_input, span1, span2, label1, label2], outputs=span_output)
 
-demo.launch()
+demo.launch()