Create streamlit_app.py

streamlit_app.py

@@ -0,0 +1,125 @@
+import json
+import string
+import random
+import nltk
+import numpy as np
+import tensorflow as tf
+from nltk.stem import WordNetLemmatizer
+from tensorflow.keras import Sequential
+from tensorflow.keras.layers import Dense, Dropout
+from tensorflow.keras.optimizers.schedules import ExponentialDecay
+import streamlit as st
+
+# Download NLTK resources
+nltk.download("punkt")
+nltk.download("wordnet")
+
+# Load the intents JSON file
+with open('intents.json', 'r') as file:
+    data = json.load(file)
+
+# Preprocess and prepare data
+lemmatizer = WordNetLemmatizer()
+words = []
+classes = []
+data_X = []
+data_Y = []
+
+for intent in data["intents"]:
+    for pattern in intent["patterns"]:
+        tokens = nltk.word_tokenize(pattern)
+        words.extend(tokens)
+        data_X.append(pattern)
+        data_Y.append(intent["tag"])
+    if intent["tag"] not in classes:
+        classes.append(intent["tag"])
+
+words = [lemmatizer.lemmatize(word.lower()) for word in words if word not in string.punctuation]
+words = sorted(set(words))
+classes = sorted(set(classes))
+
+# Bag of Words model
+training = []
+out_empty = [0] * len(classes)
+
+for idx, doc in enumerate(data_X):
+    bow = []
+    text = lemmatizer.lemmatize(doc.lower())
+    for word in words:
+        bow.append(1) if word in text else bow.append(0)
+    output_row = list(out_empty)
+    output_row[classes.index(data_Y[idx])] = 1
+    training.append([bow, output_row])
+
+random.shuffle(training)
+training = np.array(training, dtype=object)
+train_X = np.array(list(training[:, 0]), dtype=np.float32)
+train_Y = np.array(list(training[:, 1]), dtype=np.float32)
+
+# Define learning rate schedule
+initial_learning_rate = 0.01
+lr_schedule = ExponentialDecay(
+    initial_learning_rate=initial_learning_rate,
+    decay_steps=1000,
+    decay_rate=0.9,
+    staircase=True
+)
+
+# Build the neural network model
+model = Sequential([
+    Dense(128, input_shape=(len(train_X[0]),), activation="relu"),
+    Dropout(0.5),
+    Dense(64, activation="relu"),
+    Dropout(0.5),
+    Dense(len(train_Y[0]), activation="softmax")
+])
+
+adam = tf.keras.optimizers.Adam(learning_rate=lr_schedule)
+model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=["accuracy"])
+model.fit(x=train_X, y=train_Y, epochs=150, verbose=1)
+
+# Define the helper functions
+def clean_text(text):
+    tokens = nltk.word_tokenize(text)
+    tokens = (lemmatizer.lemmatize(word) for word in tokens)
+    return tokens
+
+def bag_of_words(text, vocab):
+    tokens = clean_text(text)
+    bow = [0] * len(vocab)
+    for w in tokens:
+        if w in vocab:
+            bow[vocab.index(w)] = 1
+    return np.array(bow, dtype=np.float32)
+
+def pred_class(text, vocab, labels):
+    bow = bag_of_words(text, vocab)
+    result = model.predict(np.array([bow]))[0]
+    thresh = 0.5
+    y_pred = [[indx, res] for indx, res in enumerate(result) if res > thresh]
+    y_pred.sort(key=lambda x: x[1], reverse=True)
+    return_list = [labels[r[0]] for r in y_pred]
+    return return_list
+
+def get_response(intents_list, intents_json):
+    if len(intents_list) == 0:
+        return "Sorry! I didn't understand."
+    else:
+        tag = intents_list[0]
+        list_of_intents = intents_json["intents"]
+        for i in list_of_intents:
+            if i["tag"] == tag:
+                return random.choice(i["responses"])
+
+def chatbot_response(message):
+    intents = pred_class(message, words, classes)
+    result = get_response(intents, data)
+    return result
+
+# Streamlit app interface
+st.title("ChatBot")
+user_input = st.text_input("You:")
+
+if user_input:
+    response = chatbot_response(user_input)
+    st.text_area("ChatBot:", value=response, height=100, max_chars=None, key=None)