Commit
•
addbb21
1
Parent(s):
790f6dd
Update app.py
Browse files
app.py
CHANGED
@@ -5,10 +5,10 @@ import spacy
|
|
5 |
import subprocess
|
6 |
|
7 |
# Download the spaCy model if it is not already downloaded
|
8 |
-
subprocess.run(["python", "-m", "spacy", "download", "
|
9 |
|
10 |
-
# Load the spaCy model for POS tagging
|
11 |
-
nlp = spacy.load("
|
12 |
|
13 |
def identify_nouns_verbs(text):
|
14 |
# Process the text with spaCy
|
@@ -20,14 +20,47 @@ def identify_nouns_verbs(text):
|
|
20 |
|
21 |
return {"Nouns": nouns, "Verbs": verbs}
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
# Create the Gradio interface
|
24 |
iface = gr.Interface(
|
25 |
-
fn=
|
26 |
-
inputs=
|
27 |
-
|
28 |
-
|
29 |
-
|
|
|
|
|
|
|
30 |
)
|
31 |
|
32 |
if __name__ == "__main__":
|
33 |
-
iface.launch()
|
|
|
5 |
import subprocess
|
6 |
|
7 |
# Download the spaCy model if it is not already downloaded
|
8 |
+
subprocess.run(["python", "-m", "spacy", "download", "en_core_web_md"])
|
9 |
|
10 |
+
# Load the spaCy model for POS tagging and similarity
|
11 |
+
nlp = spacy.load("en_core_web_md")
|
12 |
|
13 |
def identify_nouns_verbs(text):
|
14 |
# Process the text with spaCy
|
|
|
20 |
|
21 |
return {"Nouns": nouns, "Verbs": verbs}
|
22 |
|
23 |
+
def calculate_similarity(nouns_verbs, input_list):
|
24 |
+
similarities = {"Nouns": {}, "Verbs": {}}
|
25 |
+
|
26 |
+
for noun in nouns_verbs["Nouns"]:
|
27 |
+
noun_token = nlp(noun)
|
28 |
+
for word in input_list["Nouns"]:
|
29 |
+
word_token = nlp(word)
|
30 |
+
similarity = noun_token.similarity(word_token)
|
31 |
+
if similarity > 0.7: # Adjust threshold as needed
|
32 |
+
if noun not in similarities["Nouns"]:
|
33 |
+
similarities["Nouns"][noun] = []
|
34 |
+
similarities["Nouns"][noun].append((word, similarity))
|
35 |
+
|
36 |
+
for verb in nouns_verbs["Verbs"]:
|
37 |
+
verb_token = nlp(verb)
|
38 |
+
for word in input_list["Verbs"]:
|
39 |
+
word_token = nlp(word)
|
40 |
+
similarity = verb_token.similarity(word_token)
|
41 |
+
if similarity > 0.7: # Adjust threshold as needed
|
42 |
+
if verb not in similarities["Verbs"]:
|
43 |
+
similarities["Verbs"][verb] = []
|
44 |
+
similarities["Verbs"][verb].append((word, similarity))
|
45 |
+
|
46 |
+
return similarities
|
47 |
+
|
48 |
+
def process_inputs(text, input_list):
|
49 |
+
nouns_verbs = identify_nouns_verbs(text)
|
50 |
+
similarities = calculate_similarity(nouns_verbs, input_list)
|
51 |
+
return {"Nouns and Verbs": nouns_verbs, "Similarities": similarities}
|
52 |
+
|
53 |
# Create the Gradio interface
|
54 |
iface = gr.Interface(
|
55 |
+
fn=process_inputs,
|
56 |
+
inputs=[
|
57 |
+
gr.inputs.Textbox(lines=10, placeholder="Enter your text here..."),
|
58 |
+
gr.inputs.JSON(label="Input List", placeholder='{"Nouns": ["word1", "word2"], "Verbs": ["word1", "word2"]}')
|
59 |
+
],
|
60 |
+
outputs=gr.outputs.JSON(),
|
61 |
+
title="Noun and Verb Identifier with Similarity Check",
|
62 |
+
description="Enter a document or text to identify the nouns and verbs, and check for similarities with a given list of words."
|
63 |
)
|
64 |
|
65 |
if __name__ == "__main__":
|
66 |
+
iface.launch()
|