update_sentence_input

app.py

@@ -1,60 +1,99 @@
-import streamlit as st
-# st.title("Neural Network Prediction")
-from mygrad import Layer, Value
+# -*- coding: utf-8 -*-
+"""usemodel.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1c8Qtf9TWr3apElEv2uDgCD_MQwHnmw0B
+"""
+
 import pickle
+from mygrad import Neuron, Value
+import streamlit as st 
+def convertToOneHotEncode(tags):
+    tag1 = tags[0]
+    tag2 = tags[1]
+    vec1 = [0]*5
+    vec2 = [0]*4
+    vec1[tag1] = 1
+    vec2[tag2-1] = 1
+    vec1.extend(vec2)
 
-# Define the predict function
-def predict(x):
-    x1 = hiddenLayer1(x)    
-    final = outputLayer([x1] + x)
-    return final.data
 
-# Load model
+
+    return vec1
 def loadModel():
-    neuron1weightsbias, outputneuronweightsbias = [], []
-    with open(f'parameters/neuron1weightsbias_fn_reLu.pckl', 'rb') as file:
+    neuron1weightsbias = []
+    with open(f'weights.pkl', 'rb') as file:
         neuron1weightsbias = pickle.load(file)
-    with open('parameters/outputneuronweightsbias_fn_reLu.pckl', 'rb') as file:
-        outputneuronweightsbias = pickle.load(file)
-    hiddenLayer1_ = Layer(10, 1, 'reLu')
-    outputLayer_ = Layer(11, 1, 'sigmoid')
-
-    hiddenLayer1_.neurons[0].w = [Value(i) for i in neuron1weightsbias[:-1]]
-    hiddenLayer1_.neurons[0].b = Value(neuron1weightsbias[-1])
-
-    outputLayer_.neurons[0].w = [Value(i) for i in outputneuronweightsbias[:-1]]
-    outputLayer_.neurons[0].b = Value(outputneuronweightsbias[-1])
-    return hiddenLayer1_, outputLayer_
-
-hiddenLayer1, outputLayer = loadModel()
-
-st.title("Neural Network Prediction")
-
-st.header("Input")
-inputs = st.text_input("Input 10 digits Binary no")
-input = []
-flag = 0
-if len(inputs)!=10:
-    st.write("Error: Input not equal to 10 bits")
-    flag =1
-for i in inputs:
-    if i!='0' and i!='1':
-        st.write("Please input Binary number only")
-        flag = 1
+    neuron = Neuron(10)
+
+    neuron.w = [Value(i) for i in neuron1weightsbias[:-1]]
+    neuron.b = Value(neuron1weightsbias[-1])
+    return neuron
+
+import json
+def loadjson(filepath):
+    data = []
+    with open(filepath, 'rb') as file:
+        for line in file:
+            data.append(json.loads(line))
+    return data
+
+data = loadjson('data/train.jsonl')
+data2 = loadjson('data/test.jsonl')
+X = [element['pos_tags'] for element in data] + [element['pos_tags'] for element in data2]
+Y = [element['chunk_tags'] for element in data] + [element['chunk_tags'] for element in data2]
+
+n = loadModel()
+
+def predictsentence(postagsOfSentence):
+    if postagsOfSentence:
+        postagsOfSentence = [0] + postagsOfSentence
     else:
-        input.append(int(i))
-
-# Prediction
-if st.button("Predict"):
-    if flag:
-        st.stop()
-    try:
-        result = predict(input)
-        st.success(f"The prediction is: {result}")
-        if result>0.5:
-            st.success("It is Palindrome")
+        return
+    xnew = []
+    for ix in range(1, len(postagsOfSentence)):
+        xnew.append([ postagsOfSentence[ix-1], postagsOfSentence[ix]])
+    for ix, pair in enumerate(xnew):
+        xnew[ix] = convertToOneHotEncode(pair)
+    w = Value(0)
+    chunks = []
+    for ix2, wordpair in enumerate(xnew):
+        xinput = [w] + wordpair
+        w = n(xinput)
+        if w.data > 0.5:
+            chunks.append(1)
         else:
-            st.success("It is not Palindrome")
-    except Exception as e:
-        st.error(f"An error occurred: {e}")
+            chunks.append(0)
+    return chunks
+def input_(input):
+    if not input:
+        return
+    result = word_tokenize(input)
+    word_pos=  nltk.pos_tag(result)
+    pos = [ i[1] for i in word_pos]
+    for i in range(len(pos)):
+        if pos[i] =='NN':
+            pos[i] = 1
+        elif pos[i] =='DT':
+            pos[i] = 2
+        elif pos[i] =='JJ':
+            pos[i] = 3
+        else:
+            pos[i]= 4
+    return pos
+st.title('Chunk tagging')
+input = st.text_input('Input the pos tags')
+
+import nltk
+from nltk.tokenize import word_tokenize
+
+inputs = input_(input)
+output = predictsentence(inputs)
+st.write(output)
 
+# import pandas as pd
+# data = output
+# df = pd.DataFrame.from_dict(data)
+# st.dataframe(df)