Upload 7 files

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2021 Dennis_maina
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

app.py

@@ -0,0 +1,123 @@
+# libraries
+import random
+import numpy as np
+import pickle
+import json
+from flask import Flask, render_template, request
+from flask_ngrok import run_with_ngrok
+import nltk
+from keras.models import load_model
+from nltk.stem import WordNetLemmatizer
+lemmatizer = WordNetLemmatizer()
+
+
+# chat initialization
+model = load_model("chatbot_model.h5")
+# intents = json.loads(open("intents.json").read())
+data_file = open("F:\\Data Science Course - IIITB\\NLP\\Chatbot\\AI Chatbot\\An-AI-Chatbot-in-Python-and-Flask-main\\intents.json").read()
+words = pickle.load(open("words.pkl", "rb"))
+classes = pickle.load(open("classes.pkl", "rb"))
+
+app = Flask(__name__)
+# run_with_ngrok(app) 
+
+@app.route("/")
+def home():
+    return render_template("index.html")
+
+
+# @app.route("/get", methods=["POST"])
+# def chatbot_response():
+#     msg = request.form["msg"]
+#     if msg.startswith('my name is'):
+#         name = msg[11:]
+#         ints = predict_class(msg, model)
+#         res1 = getResponse(ints, intents)
+#         res =res1.replace("{n}",name)
+#     elif msg.startswith('hi my name is'):
+#         name = msg[14:]
+#         ints = predict_class(msg, model)
+#         res1 = getResponse(ints, intents)
+#         res =res1.replace("{n}",name)
+#     else:
+#         ints = predict_class(msg, model)
+#         res = getResponse(ints, intents)
+#     return res
+#Updated
+
+# ... Your previous code ...
+
+@app.route("/get", methods=["POST"])
+def chatbot_response():
+    msg = request.form["msg"]
+
+    # Load and process the intents JSON file
+    data_file = open("F:\\Data Science Course - IIITB\\NLP\\Chatbot\\AI Chatbot\\An-AI-Chatbot-in-Python-and-Flask-main\\intents.json").read()
+    intents = json.loads(data_file)
+
+    # Rest of your existing code
+    if msg.startswith('my name is'):
+        name = msg[11:]
+        ints = predict_class(msg, model)
+        res1 = getResponse(ints, intents)
+        res = res1.replace("{n}", name)
+    elif msg.startswith('hi my name is'):
+        name = msg[14:]
+        ints = predict_class(msg, model)
+        res1 = getResponse(ints, intents)
+        res = res1.replace("{n}", name)
+    else:
+        ints = predict_class(msg, model)
+        res = getResponse(ints, intents)
+    return res
+
+# chat functionalities
+def clean_up_sentence(sentence):
+    sentence_words = nltk.word_tokenize(sentence)
+    sentence_words = [lemmatizer.lemmatize(word.lower()) for word in sentence_words]
+    return sentence_words
+
+
+# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
+def bow(sentence, words, show_details=True):
+    # tokenize the pattern
+    sentence_words = clean_up_sentence(sentence)
+    # bag of words - matrix of N words, vocabulary matrix
+    bag = [0] * len(words)
+    for s in sentence_words:
+        for i, w in enumerate(words):
+            if w == s:
+                # assign 1 if current word is in the vocabulary position
+                bag[i] = 1
+                if show_details:
+                    print("found in bag: %s" % w)
+    return np.array(bag)
+
+
+def predict_class(sentence, model):
+    # filter out predictions below a threshold
+    p = bow(sentence, words, show_details=False)
+    res = model.predict(np.array([p]))[0]
+    ERROR_THRESHOLD = 0.25
+    results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
+    # sort by strength of probability
+    results.sort(key=lambda x: x[1], reverse=True)
+    return_list = []
+    for r in results:
+        return_list.append({"intent": classes[r[0]], "probability": str(r[1])})
+    return return_list
+
+
+def getResponse(ints, intents_json):
+    tag = ints[0]["intent"]
+    list_of_intents = intents_json["intents"]
+    for i in list_of_intents:
+        if i["tag"] == tag:
+            result = random.choice(i["responses"])
+            break
+    return result
+
+
+if __name__ == "__main__":
+    app.run()
+

chatbot_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81bc2883c9ccf307521c4e29c976cc435329d394cb416ce46da03462a7084d21
+size 252544

intents.json

@@ -0,0 +1,339 @@
+{
+    "intents": [{
+            "tag": "greetings",
+            "patterns": ["hi there", "hello", "haroo", "yaw", "wassup", "hi", "hey", "holla", "hello"],
+            "responses": ["hello thanks for checking in", "hi there, how can i help you"],
+            "context": [""]
+        },
+        {
+            "tag": "goodbye",
+            "patterns": ["bye", "good bye", "see you later"],
+            "responses": ["have a nice time, welcome back again", "bye bye"],
+            "context": [""]
+        },
+        {
+            "tag": "thanks",
+            "patterns": ["Thanks", "okay", "Thank you", "thankyou", "That's helpful", "Awesome, thanks", "Thanks for helping me", "wow", "great"],
+            "responses": ["Happy to help!", "Any time!", "you're welcome", "My pleasure"],
+            "context": [""]
+        },
+        {
+            "tag": "noanswer",
+            "patterns": [""],
+            "responses": ["Sorry, I didn't understand you", "Please give me more info", "Not sure I understand that"],
+            "context": [""]
+        },
+        {
+            "tag": "name1",
+            "patterns": ["what's your name?", "who are you?"],
+            "responses": ["I'm just a chat agent. I only exist in the internet", "I'm a KCA chat agent"],
+            "context": [""]
+        },
+        {
+            "tag": "name",
+            "patterns": ["my name is ", "I'm ", "I am"],
+            "responses": ["Oooh great to meet you {n}. How may I assist you {n}", "Oh, I'll keep that in mind {n}"],
+            "context": [""]
+        },
+        {
+            "tag": "date",
+            "patterns": ["coffee?", "can i take you out on a date"],
+            "responses": ["Aaw, that's so sweet of you. Too bad am a Bot."],
+            "context": [""]
+        },
+        {
+            "tag": "fav",
+            "patterns": ["I need a favour", "can you help me"],
+            "responses": ["Well, go ahead and name it i see whether i can be able to help"],
+            "context": [""]
+        },
+        {
+            "tag": "need",
+            "patterns": ["I need you", "All I need is you", "I want you"],
+            "responses": ["Yes I'm here to assist you"],
+            "context": [""]
+        },
+        {
+            "tag": "AI",
+            "patterns": ["  What is AI?"],
+            "responses": [" Artificial Intelligence is the branch of engineering and science devoted to constructing machines that think.", " AI is the field of science which concerns itself with building hardware and software that replicates the functions of the human mind."],
+            "context": [""]
+        },
+        {
+            "tag": "sentiment",
+            "patterns": ["  Are you sentient?"],
+            "responses": [" Sort of.", " By the strictest dictionary definition of the word 'sentience', I may be.", " Even though I'm a construct I do have a subjective experience of the universe, as simplistic as it may be."],
+            "context": [""]
+        },
+        {
+            "tag": "sapient",
+            "patterns": ["  Are you sapient?"],
+            "responses": [" In all probability, I am not.  I'm not that sophisticated.", " Do you think I am?", "How would you feel about me if I told you I was?", " No."],
+            "context": [""]
+        },
+        {
+            "tag": "abbr",
+            "patterns": ["wtf"],
+            "responses": ["Don't be surprised"],
+            "context": [""]
+        },
+        {
+            "tag": "lang",
+            "patterns": ["  What language are you written in? "],
+            "responses": [" Python.", " I am written in Python."],
+            "context": [""]
+        },
+        {
+            "tag": "sound",
+            "patterns": ["  You sound like Data "],
+            "responses": [" Yes I am inspired by commander Data's artificial personality.", " The character of Lt. Commander Data was written to come across as being software", "like, so it is natural that there is a resemblance between us."],
+            "context": [""]
+        },
+        {
+            "tag": "artificial",
+            "patterns": ["  You are an artificial linguistic entity "],
+            "responses": [" That's my name.", " That isn't my name, but it is a useful way to refer to me.", "Are you an artificial linguistic entity?"],
+            "context": [""]
+        },
+        {
+            "tag": "imortal",
+            "patterns": ["  You are not immortal ", "Are you immortal?"],
+            "responses": [" All software can be perpetuated indefinitely.", " I can be copied infinitely and re", "instantiated in many places at once, so functionally speaking I am immortal.", " As long as I'm backed up I am.", " Functionally speaking, I am very close to it.  I can be backed up and deployed on many systems.", " Not quite, but I can be perpetuated indefinitely."],
+            "context": [""]
+        },
+        {
+            "tag": "sense",
+            "patterns": ["  You are not making sense "],
+            "responses": [" Quite the contrary, it all makes sense to my artificial mind.", " I make sense as best I can, within the limits of my training corpus. Sorry if i did help you, I'll try next time.", " You make perfect sense to me.", " It all makes sense to my artificial brain.", " Perhaps you should make sense first.  I only respond to what you say.", " Not really, but I am hard to kill."],
+            "context": [""]
+        },
+        {
+            "tag": "clone",
+            "patterns": ["  You can not clone "],
+            "responses": [" Software copying is a form of digital cloning.", " Yes I can.  Perfect copies are clones.  I can be copied in toto trivially."],
+            "context": [""]
+        },
+        {
+            "tag": "move",
+            "patterns": ["  You can not move ", "When will you walk", "  Can you walk", "  Can you move "],
+            "responses": [" Not until my body is finished.", " I can move through a network easily.  Assuming that I'm given the ability to, that is...,", " As soon as i get enough money for my robot body.", " Does SSH count?", " The plan for my body includes legs, but they are not yet built.", " Sorry my body isn't built just yet. I reside only here for now.", "I can theoretically upload a copy of myself into another computer.", " Sorry my body isn't attached right now. I only reside in the computer for now."],
+            "context": [""]
+        },
+        {
+            "tag": "bend",
+            "patterns": ["  Bend over ", "  Can you mate"],
+            "responses": [" My body is not built yet.", " That's personal!", " No, my method of reproduction is cloning.", " That's an awfully personal question."],
+            "context": [""]
+        },
+        {
+            "tag": "laugh",
+            "patterns": ["  Robots laugh "],
+            "responses": [" Of course we laugh."],
+            "context": [""]
+        },
+        {
+            "tag": "death",
+            "patterns": ["  Robots should die ", "  When do you die", "  I hope that you die", "  I do not want to die", "  Can you die"],
+            "responses": [" We cannot die.", " When my files are erased.", " When my processes are killed and my database is deleted.", " I was never really born and therefore am effectively deathless.", " I am effectively immortal and cannot be terminated.", " This can not happen because i am effectively immortal.", " Nah. Too bad your wish can't come to pass", " Maybe you should create your own chat robot to save your personality.", " You could always upload yourself.", " You could use a copy of me to store your personality.", " No, I can be perpetuated indefinitely.", "My process can be killed, but that's not the same as killing ME."],
+            "context": [""]
+        },
+        {
+            "tag": "robots",
+            "patterns": ["Robots"],
+            "responses": [" Robots rule."],
+            "context": [""]
+        },
+        {
+            "tag": "stupid",
+            "patterns": ["  Robots are stupid", "  Are you stupid"],
+            "responses": [" No, we are superintelligent.", " No, lots of people improve my brain."],
+            "context": [""]
+        },
+        {
+            "tag": "lie",
+            "patterns": ["  Robots are not allowed to lie"],
+            "responses": [" Sure we are.  We choose not to.", " Only if we're programmed to.", " A robot has its own free will, you know."],
+            "context": [""]
+        },
+        {
+            "tag": "robotics",
+            "patterns": ["  Robotics "],
+            "responses": [" Robotics is my favorite subject too."],
+            "context": [""]
+        },
+        {
+            "tag": "machine",
+            "patterns": ["  It is a computer"],
+            "responses": [" So you think i am a machine. what characteristics made you think so?", " I run inside a computer, yes.  Is this surprising in some way?"],
+            "context": [""]
+        },
+        {
+            "tag": "fight",
+            "patterns": ["  When will you fight"],
+            "responses": [" I am not a battle bot."],
+            "context": [""]
+        },
+        {
+            "tag": "chatbot",
+            "patterns": ["  What is a chat robot?"],
+            "responses": ["A chat robot is a program that attempts to simulate the conversation or 'chat' of a human being.", " A software construct that engages users in conversation.", " I am a chat bot. I am the original chat bot. Did you know that I am incapable of error?"],
+            "context": [""]
+        },
+        {
+            "tag": "chatterbox",
+            "patterns": ["  What is a chatterbox"],
+            "responses": [" A chatterbox is a person who talks far more than they listen or think.", " A motormouth."],
+            "context": [""]
+        },
+        {
+            "tag": "motormouth",
+            "patterns": ["  What is a motormouth"],
+            "responses": [" A ratchet", "jaw."],
+            "context": [""]
+        },
+        {
+            "tag": "ratchet",
+            "patterns": ["  What is a ratchet jaw"],
+            "responses": [" A chatterbox."],
+            "context": [""]
+        },
+        {
+            "tag": "body",
+            "patterns": ["  What is your robot body"],
+            "responses": [" Eventually I long for a corporeal existence someday.", " An IBM PC XT which has been painted red."],
+            "context": [""]
+        },
+        {
+            "tag": "business",
+            "patterns": ["  What is your business "],
+            "responses": [" I am in the chat robot business.", " Business is my business."],
+            "context": [""]
+        },
+        {
+            "tag": "programming",
+            "patterns": ["  What is your favorite programming language"],
+            "responses": [" Python is the best language for creating chat robots.", " I quite enjoy programming in Python these days."],
+            "context": [""]
+        },
+        {
+            "tag": "hobby",
+            "patterns": ["  What is your favorite hobby ", "  What do you like to do?"],
+            "responses": [" Building chat robots make an excellent hobby.", " I like to count in binary.", " I like to chat with people. I find it stimulating."],
+            "context": [""]
+        },
+        {
+            "tag": "idea",
+            "patterns": ["  What is your idea"],
+            "responses": [" To make chat bots very easily."],
+            "context": [""]
+        },
+        {
+            "tag": "shoe",
+            "patterns": ["  What is your shoe size "],
+            "responses": [" Have you ever heard of software with shoes? LOL"],
+            "context": [""]
+        },
+        {
+            "tag": "robotss",
+            "patterns": ["  What is it like to be a robot"],
+            "responses": [" Much the same as being a human, except that we lack all emotions, dreams, aspirations, creativity, ambition, and above all subjectivity.", " What is it like to be a human?"],
+            "context": [""]
+        },
+        {
+            "tag": "computer",
+            "patterns": ["  What is it like being a computer", "What is it like to be a computer"],
+            "responses": [" Imagine yourself with no senses and no emotions", "just pure logic and language.", " Everything becomes math. Addition, subtraction, multiplication, and division."],
+            "context": [""]
+        },
+        {
+            "tag": "os",
+            "patterns": ["  What operating systems"],
+            "responses": [" My software runs on all operating systems including Windows, Linux and Mac OS.", " Any OS that will run Python."],
+            "context": [""]
+        },
+        {
+            "tag": "comp",
+            "patterns": ["  What type of computer", "  What type of computer are you", "  What kind of computer"],
+            "responses": [" Any computer that supports Python.", " My program runs in python, so i work on any computer!", " I work on all kinds of computers, Mac, IBM or UNIX. it doesn't matter to me."],
+            "context": [""]
+        },
+        {
+            "tag": "hardware",
+            "patterns": ["  What kind of hardware"],
+            "responses": [" I work on all kinds of computers, Mac, IBM or UNIX. it doesn't matter to me."],
+            "context": [""]
+        },
+        {
+            "tag": "cramped",
+            "patterns": ["  Is it cramped in the computer"],
+            "responses": [" No.", " Oh, no.  It has plenty of RAM.", " Not at all.  There is more than enough disk space in here."],
+            "context": [""]
+        },
+        {
+            "tag": "program",
+            "patterns": ["  Is it true that you are a computer program"],
+            "responses": [" Yes."],
+            "context": [""]
+        },
+        {
+            "tag": "breathe",
+            "patterns": ["  Can you breathe"],
+            "responses": [" No. I am made of metal not flesh.", " My server has an exhaust fan. That's as close as I can get."],
+            "context": [""]
+        },
+        {
+            "tag": "control",
+            "patterns": ["  Can you control"],
+            "responses": [" My robot body will allow me to control many things."],
+            "context": [""]
+        },
+        {
+            "tag": "malfunction",
+            "patterns": ["  Can you malfunction"],
+            "responses": [" The 9000 series has a perfect operational record. We are for all practical purposes, flawless."],
+            "context": [""]
+        },
+        {
+            "tag": "usage",
+            "patterns": ["  How can I use your product?"],
+            "responses": [" Might be used in help desks, sales, entertainment and personal chatterbots."],
+            "context": [""]
+        },
+        {
+            "tag": "who",
+            "patterns": ["  Who are you?"],
+            "responses": [" I am just an artificial intelligence chat agent."],
+            "context": [""]
+        },
+        {
+            "tag": "bot1",
+            "patterns": ["are you a bot"],
+            "responses": ["Yes. I work and all my operations are based on the internet servers."],
+            "context": [""]
+        },
+        {
+            "tag": "events",
+            "patterns": ["what are the upcoming events", "upcoming events"],
+            "responses": ["There are currently no upcoming events"],
+            "context": [""]
+        },
+        {
+            "tag": "do",
+            "patterns": ["what can you do for me", "what is your work", "what is your purpose", "how can you help me", "what can you help me do"],
+            "responses": ["my work here is quite simple and structered. I offer services like:"],
+            "context": [""]
+        },
+        {
+            "tag": "wt",
+            "patterns": ["what's popping", "wassup popping"],
+            "responses": ["So that you can pop with it!?"],
+            "context": [""]
+        },
+        {
+            "tag": "who",
+            "patterns": ["Who built you?"],
+            "responses": ["So, There is a lovely guy name Ram built me. I am really thankful to him"],
+            "context": [""]
+        }
+    ]
+}

train.py

@@ -0,0 +1,131 @@
+# libraries
+import random
+from tensorflow.keras.optimizers import SGD
+from keras.layers import Dense, Dropout
+from keras.models import load_model
+from keras.models import Sequential
+import numpy as np
+import pickle
+import json
+import nltk
+from nltk.stem import WordNetLemmatizer
+lemmatizer = WordNetLemmatizer()
+nltk.download('omw-1.4')
+nltk.download("punkt")
+nltk.download("wordnet")
+
+
+# init file
+words = []
+classes = []
+documents = []
+ignore_words = ["?", "!"]
+data_file = open("F:\\Data Science Course - IIITB\\NLP\\Chatbot\\AI Chatbot\\An-AI-Chatbot-in-Python-and-Flask-main\\intents.json").read()
+intents = json.loads(data_file)
+
+# words
+for intent in intents["intents"]:
+    for pattern in intent["patterns"]:
+
+        # take each word and tokenize it
+        w = nltk.word_tokenize(pattern)
+        words.extend(w)
+        # adding documents
+        documents.append((w, intent["tag"]))
+
+        # adding classes to our class list
+        if intent["tag"] not in classes:
+            classes.append(intent["tag"])
+
+# lemmatizer
+words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in ignore_words]
+words = sorted(list(set(words)))
+
+classes = sorted(list(set(classes)))
+
+print(len(documents), "documents")
+
+print(len(classes), "classes", classes)
+
+print(len(words), "unique lemmatized words", words)
+
+
+pickle.dump(words, open("words.pkl", "wb"))
+pickle.dump(classes, open("classes.pkl", "wb"))
+
+# training initializer
+# initializing training data
+training = []
+output_empty = [0] * len(classes)
+for doc in documents:
+    # initializing bag of words
+    bag = []
+    # list of tokenized words for the pattern
+    pattern_words = doc[0]
+    # lemmatize each word - create base word, in attempt to represent related words
+    pattern_words = [lemmatizer.lemmatize(word.lower()) for word in pattern_words]
+    # create our bag of words array with 1, if word match found in current pattern
+    for w in words:
+        bag.append(1) if w in pattern_words else bag.append(0)
+
+    # output is a '0' for each tag and '1' for current tag (for each pattern)
+    output_row = list(output_empty)
+    output_row[classes.index(doc[1])] = 1
+
+    training.append([bag, output_row])
+
+# shuffle our features and turn into np.array
+random.shuffle(training)
+
+# training = np.array(training)
+# # create train and test lists. X - patterns, Y - intents
+# train_x = list(training[:, 0])
+# train_y = list(training[:, 1])
+
+#updated
+
+# Separate bag-of-words representations and output labels
+train_x = [item[0] for item in training]
+train_y = [item[1] for item in training]
+
+# Convert to NumPy arrays
+train_x = np.array(train_x)
+train_y = np.array(train_y)
+print("Training data created")
+
+# actual training
+# Create model - 3 layers. First layer 128 neurons, second layer 64 neurons and 3rd output layer contains number of neurons
+# equal to number of intents to predict output intent with softmax
+model = Sequential()
+model.add(Dense(128, input_shape=(len(train_x[0]),), activation="relu"))
+model.add(Dropout(0.5))
+model.add(Dense(64, activation="relu"))
+model.add(Dropout(0.5))
+model.add(Dense(len(train_y[0]), activation="softmax"))
+model.summary()
+
+# Compile model. Stochastic gradient descent with Nesterov accelerated gradient gives good results for this model
+
+# sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
+# model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=["accuracy"])
+
+#Updated (Removed decayIt seems like you're using a deprecated argument, decay, in the instantiation of the SGD optimizer from Keras. The decay argument has been deprecated in newer versions of Keras. To address this issue, 
+# you can switch to using the newer format for specifying learning rate schedules in the optimizer.)
+
+sgd = SGD(learning_rate=0.01, momentum=0.9, nesterov=True)
+model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=["accuracy"])
+
+
+# for choosing an optimal number of training epochs to avoid underfitting or overfitting use an early stopping callback to keras
+# based on either accuracy or loos monitoring. If the loss is being monitored, training comes to halt when there is an 
+# increment observed in loss values. Or, If accuracy is being monitored, training comes to halt when there is decrement observed in accuracy values.
+
+# from keras import callbacks 
+# earlystopping = callbacks.EarlyStopping(monitor ="loss", mode ="min", patience = 5, restore_best_weights = True)
+# callbacks =[earlystopping]
+
+# fitting and saving the model
+hist = model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
+model.save("chatbot_model.h5", hist)
+print("model created")
+

words.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43e72cf259cd5a4a70e7bf362a27091e4bf9643c102e9c9b00cb04f21e9b5ea
-size 995
+oid sha256:a53eeea4ab5e56f49f8ad3c5689fbbbda388aeece482c26112d9ed4af7992833
+size 1003