Create app.py

app.py

@@ -0,0 +1,105 @@
+import gradio as gr
+import numpy as np
+import numpy as np
+import pickle
+import pandas as pd
+from PRNN import PRNN
+
+from PRNN_utils import   batch_calculate_grads, check_conditions, check_all_conditions, train_and_val, prepare_folds, process_CVresults, tags2sentence
+import nltk
+from nltk.tokenize import word_tokenize
+
+def tokens_and_tags(sentence):
+    # Sample sentence
+    #sentence = "The quick brown fox jumps over the lazy dog"
+
+    # Tokenize the sentence
+    tokens = word_tokenize(sentence)
+
+    # Tag the tokens with POS
+    tagged_words = nltk.pos_tag(tokens)
+
+    # Define the set of desired POS tags
+    desired_tags = {'JJ', 'NN', 'DT'}
+
+    # Initialize lists to store words and tags separately
+    words = []
+    tags = []
+
+    # Iterate over tagged words and filter them
+    for word, tag in tagged_words:
+        if tag in desired_tags:
+            words.append(word)
+            tags.append(tag)
+        else:
+            words.append(word)
+            tags.append('OT')
+
+    # Print the lists of words and tags
+    # print("Words:", words)
+    # print("Tags:", tags)
+
+    return words, tags
+
+def create_pos_tags(tags = ['NN', 'JJ', 'DT', 'OT']):
+
+    liss = []
+    pos_dict = {'NN':1, 'DT':2, 'JJ':3, 'OT':4}
+
+    for tag in tags:
+        liss.append(pos_dict[tag])
+    
+    return liss
+
+def predict_for_example(sentence, tags, model):
+
+    sent_pos_tags = create_pos_tags(tags)
+    x = tags2sentence(sent_pos_tags)
+
+    return model.predict_tags(x)
+
+def find_chunks(sentence, preds):
+    chunks = []
+    chunk = []
+    for i in range(len(preds)):
+        if preds[i] == 1:
+            if len(chunk) > 1:
+                chunks.append(" ".join(chunk))
+            chunk = [sentence[i]]
+        elif preds[i] == 0 and chunk:
+            chunk.append(sentence[i])
+    if len(chunk) > 1:
+        chunks.append(" ".join(chunk))
+    return chunks
+
+
+model2 = PRNN()  # Instantiate a model
+
+# Loading the dictionary from the file using pickle
+with open('CVresults_con_data.pkl', 'rb') as f:
+    model_dict2 = pickle.load(f)
+
+P_best2, W_best2 = process_CVresults(CVresults_dict=model_dict2, summarize=False)
+model2.params = P_best2
+model2.w = W_best2
+
+model4 = PRNN()  # Instantiate a model
+
+# Loading the dictionary from the file using pickle
+with open('CVresults_con_data_sigmoid.pkl', 'rb') as f:
+    model_dict4 = pickle.load(f)
+
+P_best4, W_best4 = process_CVresults(CVresults_dict=model_dict4, summarize=False)
+model4.params = P_best4
+model4.w = W_best4
+
+def demo_(sentence):
+  sentence, tags = tokens_and_tags(sentence)
+  preds2=predict_for_example(sentence=sentence, tags=tags, model=model2)
+  preds4=predict_for_example(sentence=sentence, tags=tags, model=model4)
+  return str(preds2),str(preds4),str(find_chunks(sentence=sentence, preds=preds2)),str(find_chunks(sentence=sentence, preds=preds4))
+
+title="POS-Tagged Corpus Analysis: Training a Recurrent Perceptron for Noun Chunk Identification"
+demo = gr.Interface(fn=demo_, inputs=gr.Textbox(label="sentence for which you want noun chunks"), outputs=[gr.Textbox(label="predicted chunk label with step activation function"),gr.Textbox(label="predicted chunk label with sigmoid activation function"),gr.Textbox(label="predicted Noun chunk with step activation function"),gr.Textbox(label="predicted Noun chunk with sigmoid activation function")],title=title)
+
+demo.launch(share=True)