Update app.py

app.py

@@ -5,10 +5,10 @@ import spacy
 import subprocess
 
 # Download the spaCy model if it is not already downloaded
-subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
+subprocess.run(["python", "-m", "spacy", "download", "en_core_web_md"])
 
-# Load the spaCy model for POS tagging
-nlp = spacy.load("en_core_web_sm")
+# Load the spaCy model for POS tagging and similarity
+nlp = spacy.load("en_core_web_md")
 
 def identify_nouns_verbs(text):
     # Process the text with spaCy
@@ -20,14 +20,47 @@ def identify_nouns_verbs(text):
     
     return {"Nouns": nouns, "Verbs": verbs}
 
+def calculate_similarity(nouns_verbs, input_list):
+    similarities = {"Nouns": {}, "Verbs": {}}
+    
+    for noun in nouns_verbs["Nouns"]:
+        noun_token = nlp(noun)
+        for word in input_list["Nouns"]:
+            word_token = nlp(word)
+            similarity = noun_token.similarity(word_token)
+            if similarity > 0.7:  # Adjust threshold as needed
+                if noun not in similarities["Nouns"]:
+                    similarities["Nouns"][noun] = []
+                similarities["Nouns"][noun].append((word, similarity))
+    
+    for verb in nouns_verbs["Verbs"]:
+        verb_token = nlp(verb)
+        for word in input_list["Verbs"]:
+            word_token = nlp(word)
+            similarity = verb_token.similarity(word_token)
+            if similarity > 0.7:  # Adjust threshold as needed
+                if verb not in similarities["Verbs"]:
+                    similarities["Verbs"][verb] = []
+                similarities["Verbs"][verb].append((word, similarity))
+    
+    return similarities
+
+def process_inputs(text, input_list):
+    nouns_verbs = identify_nouns_verbs(text)
+    similarities = calculate_similarity(nouns_verbs, input_list)
+    return {"Nouns and Verbs": nouns_verbs, "Similarities": similarities}
+
 # Create the Gradio interface
 iface = gr.Interface(
-    fn=identify_nouns_verbs,
-    inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."),
-    outputs=gr.JSON(),
-    title="Noun and Verb Identifier",
-    description="Enter a document or text to identify the nouns and verbs."
+    fn=process_inputs,
+    inputs=[
+        gr.inputs.Textbox(lines=10, placeholder="Enter your text here..."),
+        gr.inputs.JSON(label="Input List", placeholder='{"Nouns": ["word1", "word2"], "Verbs": ["word1", "word2"]}')
+    ],
+    outputs=gr.outputs.JSON(),
+    title="Noun and Verb Identifier with Similarity Check",
+    description="Enter a document or text to identify the nouns and verbs, and check for similarities with a given list of words."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()