File size: 9,191 Bytes
f2b1250 628908b f2b1250 b8c19dd f2b1250 e34a42b f2b1250 e34a42b f2b1250 e34a42b f2b1250 96c3f1b f2b1250 e34a42b f2b1250 8960a6d f2b1250 89c38bf f2b1250 89c38bf f2b1250 89c38bf f2b1250 89c38bf f2b1250 89c38bf f2b1250 e34a42b f2b1250 89c38bf 8960a6d f2b1250 628908b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 |
# -*- coding: utf-8 -*-
"""app.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1Z_cMyllUfHf2lYtUtdS1ggVMpLCLg0-j
"""
import gradio as gr
########### 1 ###########
#https://www.youtube.com/watch?v=RpWeNzfSUHw&list=PLqnslRFeH2UrFW4AUgn-eY37qOAWQpJyg
#intents.json --> nltk_utils.py --> model.py --> train.ipynb --> chat.ipynb
import numpy as np
import nltk
nltk.download('punkt')
from nltk.stem.porter import PorterStemmer
stemmer = PorterStemmer()
def tokenize(sentence):
"""
split sentence into array of words/tokens
a token can be a word or punctuation character, or number
"""
return nltk.word_tokenize(sentence)
# print(tokenize('Hello how are you'))
def stem(word):
"""
stemming = find the root form of the word
examples:
words = ["organize", "organizes", "organizing"]
words = [stem(w) for w in words]
-> ["organ", "organ", "organ"]
"""
return stemmer.stem(word.lower())
# print(stem('organize'))
def bag_of_words(tokenized_sentence, words):
"""
return bag of words array:
1 for each known word that exists in the sentence, 0 otherwise
example:
sentence = ["hello", "how", "are", "you"]
words = ["hi", "hello", "I", "you", "bye", "thank", "cool"]
bog = [ 0 , 1 , 0 , 1 , 0 , 0 , 0]
"""
# stem each word
sentence_words = [stem(word) for word in tokenized_sentence]
# initialize bag with 0 for each word
bag = np.zeros(len(words), dtype=np.float32)
for idx, w in enumerate(words):
if w in sentence_words:
bag[idx] = 1
return bag
# print(bag_of_words('Hello how are you', 'hi'))
########### 2 ###########
import torch
import torch.nn as nn
class NeuralNet(nn.Module):
def __init__(self, input_size, hidden_size, num_classes):
super(NeuralNet, self).__init__()
self.l1 = nn.Linear(input_size, hidden_size)
self.l2 = nn.Linear(hidden_size, hidden_size)
self.l3 = nn.Linear(hidden_size, num_classes)
self.relu = nn.ReLU()
def forward(self, x):
out = self.l1(x)
out = self.relu(out)
out = self.l2(out)
out = self.relu(out)
out = self.l3(out)
# no activation and no softmax at the end
return out
########### 3 ###########
import numpy as np
import random
import json
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
#2. Loading our JSON Data
#from google.colab import drive #commented
#drive.mount('/content/drive') #commented
# Commented out IPython magic to ensure Python compatibility.
# %cd '/content/drive/My Drive/Colab Notebooks/NLP/ChatBot/'
#path = '/content/drive/My Drive/Colab Notebooks/NLP/ChatBot/intents.json'
#!pwd
import json
path = 'intents.json'
with open(path, 'r') as f:
intents = json.load(f)
# print(intents)
# Commented out IPython magic to ensure Python compatibility.
# %cd '/content/drive/My Drive/Colab Notebooks/NLP/ChatBot/intents.json'
# Commented out IPython magic to ensure Python compatibility.
# %pwd
#!ls
import nltk
nltk.download('punkt')
#from nltk_utils import bag_of_words, tokenize, stem
all_words = []
tags = []
xy = []
# loop through each sentence in our intents patterns
for intent in intents['intents']:
tag = intent['tag']
# add to tag list
tags.append(tag)
for pattern in intent['patterns']:
# tokenize each word in the sentence
w = tokenize(pattern)
# add to our words list
all_words.extend(w)
# add to xy pair
xy.append((w, tag))
# stem and lower each word
# ignore_words = ['?', '.', '!']
ignore_words = ['(',')','-',':',',',"'s",'!',':',"'","''",'--','.',':','?',';''[',']','``','o','’','“','”','”','[',';']
all_words = [stem(w) for w in all_words if w not in ignore_words]
# remove duplicates and sort
all_words = sorted(set(all_words))
tags = sorted(set(tags))
#print(len(xy), "patterns") #commented
#print(len(tags), "tags:", tags) #commented
#print(len(all_words), "unique stemmed words:", all_words) #commented
# create training data
X_train = []
y_train = []
for (pattern_sentence, tag) in xy:
# X: bag of words for each pattern_sentence
bag = bag_of_words(pattern_sentence, all_words)
X_train.append(bag)
# y: PyTorch CrossEntropyLoss needs only class labels, not one-hot
label = tags.index(tag)
y_train.append(label)
X_train = np.array(X_train)
y_train = np.array(y_train)
# Hyper-parameters
num_epochs = 1000
batch_size = 8
learning_rate = 0.001
input_size = len(X_train[0])
hidden_size = 8
output_size = len(tags)
#print(input_size, output_size) #commented
class ChatDataset(Dataset):
def __init__(self):
self.n_samples = len(X_train)
self.x_data = X_train
self.y_data = y_train
# support indexing such that dataset[i] can be used to get i-th sample
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
# we can call len(dataset) to return the size
def __len__(self):
return self.n_samples
import torch
import torch.nn as nn
#from model import NeuralNet
dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset,batch_size=batch_size,shuffle=True,num_workers=2)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = NeuralNet(input_size, hidden_size, output_size).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
for epoch in range(num_epochs):
for (words, labels) in train_loader:
words = words.to(device)
labels = labels.to(dtype=torch.long).to(device)
# Forward pass
outputs = model(words)
# if y would be one-hot, we must apply
# labels = torch.max(labels, 1)[1]
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch+1) % 100 == 0:
print (f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')
#print(f'final loss: {loss.item():.4f}')#commented
data = {
"model_state": model.state_dict(),
"input_size": input_size,
"hidden_size": hidden_size,
"output_size": output_size,
"all_words": all_words,
"tags": tags
}
FILE = "data.pth"
torch.save(data, FILE)
#print(f'training complete. file saved to {FILE}') #commented
# !nvidia-smi
#https://github.com/python-engineer/pytorch-chatbot
import random
import string # to process standard python strings
import warnings # Hide the warnings
warnings.filterwarnings('ignore')
import torch
import nltk
nltk.download('punkt')
#from google.colab import drive #commented
#drive.mount("/content/drive") #commented
# Commented out IPython magic to ensure Python compatibility.
# %cd "/content/drive/My Drive/Colab Notebooks/NLP/ChatBot/"
# !ls
import random
import json
import torch
#from model import NeuralNet
#from nltk_utils import bag_of_words, tokenize
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
with open('intents.json', 'r') as json_data:
intents = json.load(json_data)
FILE = "data.pth"
data = torch.load(FILE, map_location=torch.device('cpu'))
input_size = data["input_size"]
hidden_size = data["hidden_size"]
output_size = data["output_size"]
all_words = data['all_words']
tags = data['tags']
model_state = data["model_state"]
model = NeuralNet(input_size, hidden_size, output_size).to(device)
model.load_state_dict(model_state)
model.eval()
bot_name = "Sam"
def get_response(msg):
sentence = tokenize(msg)
X = bag_of_words(sentence, all_words)
X = X.reshape(1, X.shape[0])
X = torch.from_numpy(X).to(device)
output = model(X)
_, predicted = torch.max(output, dim=1)
tag = tags[predicted.item()]
probs = torch.softmax(output, dim=1)
prob = probs[0][predicted.item()]
if prob.item() > 0.75:
for intent in intents['intents']:
if tag == intent["tag"]:
return random.choice(intent['responses'])
return "I do not understand..."
print("Let's chat! (type 'quit' to exit)")
while True:
# sentence = "do you use credit cards?"
sentence = input("You: ")
if sentence == "quit":
break
sentence = tokenize(sentence)
X = bag_of_words(sentence, all_words)
X = X.reshape(1, X.shape[0])
X = torch.from_numpy(X).to(device)
output = model(X)
_, predicted = torch.max(output, dim=1)
tag = tags[predicted.item()]
probs = torch.softmax(output, dim=1)
prob = probs[0][predicted.item()]
if prob.item() > 0.75:
for intent in intents['intents']:
if tag == intent["tag"]:
print(f"{bot_name}: {random.choice(intent['responses'])}")
else:
print(f"{bot_name}: I do not understand...")
#def get_chatbot(input_text):
#return classifier(input_text)
title = "ChatBOT"
chatbot_demo = gr.Interface(fn=get_response, inputs = 'text',outputs='text',title = title,description = 'Chat BOT')
chatbot_demo .launch() |