weASK / app.py
ipvikas's picture
Upload app.py
f2b1250
raw
history blame
8.83 kB
# -*- coding: utf-8 -*-
"""app.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1Z_cMyllUfHf2lYtUtdS1ggVMpLCLg0-j
"""
########### 5 ###########
########### 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
drive.mount('/content/drive')
# 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
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','’','β€œ','”','”','[',';']
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")
print(len(tags), "tags:", tags)
print(len(all_words), "unique stemmed words:", all_words)
# 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)
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}')
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}')
# !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
drive.mount("/content/drive")
# 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...")