Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -7,78 +7,56 @@ from spacy.tokens import Span
|
|
7 |
|
8 |
nlp = spacy.load("en_core_web_md")
|
9 |
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
for
|
18 |
-
|
19 |
|
20 |
-
|
21 |
-
for ent in doc1.ents:
|
22 |
-
print(ent.label_, spacy.explain(ent.label_))
|
23 |
-
|
24 |
-
Use PhraseMatcher to find all references of interest
|
25 |
-
Define the different references to Covid
|
26 |
-
user_entries = input(str("")) #gradio text box here to enter sample terms
|
27 |
-
pattern_list = []
|
28 |
-
|
29 |
-
for i in user_entries.strip().split():
|
30 |
-
pattern_list.append(i)
|
31 |
-
|
32 |
-
patterns = list(nlp.pipe(pattern_list))
|
33 |
-
print("patterns:", patterns)
|
34 |
-
|
35 |
-
#Instantiate PhraseMatcher
|
36 |
-
matcher = PhraseMatcher(nlp.vocab)
|
37 |
-
|
38 |
-
#Create label for pattern
|
39 |
-
user_named = input(str("").strip()) #gradio text box here to enter pattern label
|
40 |
-
matcher.add(user_named, patterns)
|
41 |
-
|
42 |
-
# Define the custom component
|
43 |
-
@Language.component("covid_component")
|
44 |
-
def covid_component_function(doc):
|
45 |
-
#Apply the matcher to the doc
|
46 |
-
matches = matcher(doc)
|
47 |
-
#Create a Span for each match and assign the label
|
48 |
-
spans = [Span(doc, start, end, label=user_named) for match_id, start, end in matches]
|
49 |
-
# Overwrite the doc.ents with the matched spans
|
50 |
-
doc.ents = spans
|
51 |
-
return doc
|
52 |
-
|
53 |
-
# Add the component to the pipeline after the "ner" component
|
54 |
-
nlp.add_pipe((user_named + "component"), after="ner")
|
55 |
-
print(nlp.pipe_names)
|
56 |
-
|
57 |
-
|
58 |
-
#Verify that your model now detects all specified mentions of Covid on another text
|
59 |
-
user_doc = input(str("").strip())
|
60 |
-
apply_doc = nlp(user_doc)
|
61 |
-
print([(ent.text, ent.label_) for ent in apply_doc.ents])
|
62 |
-
|
63 |
-
#Count total mentions of label COVID in the 3rd document
|
64 |
-
from collections import Counter
|
65 |
-
labels = [ent.label_ for ent in apply_doc.ents]
|
66 |
-
Counter(labels)
|
67 |
-
|
68 |
-
iface = gr.Interface(
|
69 |
-
process_text,
|
70 |
-
[gr.inputs.Textbox(lines=10, default="The coronavirus disease 2019 (COVID-19) pandemic is the result of widespread infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).", label="Text to Run through Entity Recognition")],
|
71 |
|
72 |
-
|
73 |
-
|
|
|
74 |
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
|
80 |
-
|
81 |
-
|
82 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
)
|
84 |
-
iface.launch()
|
|
|
7 |
|
8 |
nlp = spacy.load("en_core_web_md")
|
9 |
|
10 |
+
def load(txt1, txt2, txt3, txt4):
|
11 |
+
user_input = str(txt1.strip())
|
12 |
+
doc1 = nlp(user_input)
|
13 |
+
entities = [(ent.text, ent.label_) for ent in doc1.ents]
|
14 |
+
|
15 |
+
|
16 |
+
pattern_list = []
|
17 |
+
for i in txt2.strip().split():
|
18 |
+
pattern_list.append(i)
|
19 |
|
20 |
+
patterns = list(nlp.pipe(pattern_list))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
+
matcher = PhraseMatcher(nlp.vocab)
|
23 |
+
user_named = str(txt3.strip())
|
24 |
+
matcher.add(user_named, patterns)
|
25 |
|
26 |
+
@Language.component("added_component")
|
27 |
+
def component_function(doc):
|
28 |
+
matches = matcher(doc)
|
29 |
+
spans = [Span(doc, start, end, label=user_named) for match_id, start, end in matches]
|
30 |
+
doc.ents = spans
|
31 |
+
return doc
|
32 |
+
|
33 |
+
if "added_component" not in nlp.pipe_names:
|
34 |
+
nlp.add_pipe(("added_component"), after="ner")
|
35 |
+
|
36 |
+
user_input4 = str(txt4.strip())
|
37 |
+
apply_doc = nlp(user_input4)
|
38 |
+
entities2 = [(ent.text, ent.label_) for ent in apply_doc.ents]
|
39 |
+
|
40 |
+
from collections import Counter
|
41 |
+
labels = [ent.label_ for ent in apply_doc.ents]
|
42 |
+
lab_counts = Counter(labels)
|
43 |
+
|
44 |
+
return(entities, entities2, lab_counts)
|
45 |
+
|
46 |
+
|
47 |
+
|
48 |
+
description = "Use this space to produce and test your own customized NER"
|
49 |
|
50 |
+
|
51 |
+
iface = gr.Interface(
|
52 |
+
title = "Customized Named Entity Recognition",
|
53 |
+
description = description,
|
54 |
+
fn = load,
|
55 |
+
interpretation = "shap",
|
56 |
+
inputs = [gr.inputs.Textbox(lines=10, default="The coronavirus disease 2019 (COVID-19) pandemic is the result of widespread infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).", label="Text to Run through Entity Recognition"), gr.inputs.Textbox(lines=3, default= "Coronavirus, coronavirus, COVID-19, SARS-CoV-2, SARS‐CoV‐2", label="Enter entity references"), gr.inputs.Textbox(lines=1, default="COVID", label="Enter entity label"), gr.inputs.Textbox(lines=10, default="The tissue distribution of the virus-targeted receptor protein, angiotensin converting enzyme II (ACE2), determines which organs will be attacked by SARS‐CoV‐2.", label="Enter new sentence containing named entity")],
|
57 |
+
outputs = [gr.outputs.Textbox(type="str", label="Entities recognized before"),
|
58 |
+
gr.outputs.Textbox(type="str", label="Entites recognized after"),
|
59 |
+
gr.outputs.Textbox(type="str", label="Count of entities captured for new label")],
|
60 |
+
theme = "dark"
|
61 |
)
|
62 |
+
iface.launch()
|