bot_function.py

import nltk
from nltk.stem.porter import PorterStemmer
import json
import pickle
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import numpy as np
import random
stemmer = PorterStemmer()
def tokenize(sentence):
    return nltk.word_tokenize(sentence)

def stem(word):
    return stemmer.stem(word.lower())

def bag_of_words(tokenized_sentence, all_words):
    tokenized = [stem(w) for w in tokenized_sentence]
    bag = np.zeros(len(all_words), dtype = np.float32)
    for idx,w in enumerate(all_words):
        if w in tokenized:
            bag[idx] = 1.0
    return bag
with open('intents.json', 'r') as f:
    intents = json.load(f)
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 = ['?', '.', '!']
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 = 10
learning_rate = 0.01
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

dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset,
                          batch_size=batch_size,
                          shuffle=True)
class Neturalnet(nn.Module):
    def __init__(self,input_size,hidden_size,num_classes):
        super(Neturalnet,self).__init__()
        self.l1 = nn.Linear(input_size,hidden_size)
        self.l2 = nn.Linear(hidden_size,hidden_size)
        self.l3 = nn.Linear(hidden_size,hidden_size)
        self.l4 = 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)
        out = self.relu(out)
        out = self.l4(out)
        return out
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = Neturalnet(input_size,hidden_size,output_size).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for epoch in range(num_epochs):
    for (words,labels) in train_loader:
        words = words.to(device)
        labels = labels.to(dtype=torch.long).to(device)
        outputs = model(words)
        loss = criterion(outputs,labels)
        optimizer .zero_grad()
        loss.backward()
        optimizer.step()
    if (epoch+1) %100 == 0:
        print(f'epoch{epoch+1}/num_epochs, loss={loss.item():.5f}')
print(f'final loss, loss={loss.item():.5f}')
data={
    "input_size":input_size,
    "output_size": output_size,
    "hidden_size": hidden_size,
    "model_state": model.state_dict(),
    "all_words": all_words,
    "tags" : tags
}
FILE = "data1.pth"
torch.save(data,FILE)
print("Traing completed! Save file complete")

print("model created")