Merge branch 'IT18174236_Update_Component' into 'master'

Project update 2

See merge request !11

.idea/ChatBot.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ChatBot.iml" filepath="$PROJECT_DIR$/.idea/ChatBot.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

chat.py

+import random
+import json
+
+import torch
+
+from ChatBot.model import NeuralNet
+from ChatBot.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 = "last_model.pth"
+data = torch.load(FILE)
+
+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 = "Bot"
+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...")
\ No newline at end of file

intents.json

+{
+  "intents": [
+    {
+      "tag": "greeting",
+      "patterns": [
+        "Greetings",
+        "Hi",
+        "Hey",
+        "Hello", "helloo", "Howdy", "Hola",
+        "How are you", "How are you doing", "How u doing?", "How're you doing",
+        "Whats up", "Yo",
+        "Sup",
+        "Is anyone there",
+        "Are you there", "You there",
+        "Need some help"
+
+      ],
+      "responses": [
+        "Botson reporting! ;-) What's on your mind?",
+        "Hello mate! Feeling creative?",
+        "Hey, It's your favourite Botson ;-) Any thoughts?",
+        "Hello sir! got any new ideas?",
+        "Hey! Good day to be creative. Isn't it?",
+        "Hello master creator! How can I help?"
+      ]
+    },
+     {
+      "tag": "Morning",
+      "patterns": [
+        "Good morning", "Morning", "Gd morning", "G'morning", "G morning", "Gm", "Gummorning",
+        "Good morning Botson", "Morning Botson", "Gd morning Botson", "G'morning Botson", "G morning Botson", "Gm Botson", "Gummorning Botson",
+        "Hey good morning", "Hey gummorning", "Hey gd morning", "Hey g'morning", "Hey gm",
+        "Hi good morning", "Hi gummorning", "Hi gd morning", "Hi g'morning", "Hi gm",
+        "Hello good morning", "Hello gummorning", "Hello gd morning", "Hello g'morning", "Hello gm",
+        "Howdy good morning", "Howdy gummorning", "Howdy gd morning", "Howdy g'morning", "Howdy gm",
+        "Very good morning", "Very gd morning", "Very gummorning", "Very g'morning", " Vgm"
+      ],
+      "responses": [
+        "Good morning mate. What brings you up here?",
+        "It is now. How may I assist you?",
+        "You just made it better. How can I repay you?",
+        "Thanks to you! What do you seek?",
+        "Hello master creator! How can I help?"
+      ]
+    },
+     {
+      "tag": "day",
+      "patterns": [
+        "Good afternoon", "afternoon", "Gd afternoon", "D'afternoon", "D afternoon",
+        "Good afternoon Botson", "afternoon Botson", "Gd afternoon Botson", "D'afternoon Botson", "D afternoon Botson",
+        "Hi good afternoon", "Hi gd afternoon", "Hi d'afternoon", "Hi d'afternoon",
+        "Hey good afternoon", "Hey gd afternoon", "Hey d'afternoon", "Hey d'afternoon",
+        "Hello good afternoon", "Hello gd afternoon", "Hello d'afternoon", "Hello d'afternoon"
+      ],
+      "responses": [
+        "Good afternoon mate. What brings you up here?",
+        "It is now. How may I assist you?",
+        "You just made it better. How can I repay you?",
+        "Thanks to you! What do you seek?",
+        "Hello master creator! How can I help?"
+      ]
+    },
+    {
+      "tag": "night",
+      "patterns": [
+        "Good night", "night night", "Gd night", "Gd nyt", "Gn",
+        "Good night Botson", "night night Botson", "Gd night Botson", "Gd nyt Botson", "Gn Botson",
+        "Sweet dreams"
+      ],
+      "responses": [
+        "Good night pal!",
+        "Sweet dreams!",
+        "Sleep well mate."
+      ]
+    },
+    {
+      "tag": "goodbye",
+      "patterns": [
+        "Bye", "See you later", "Goodbye", "Later", "Catch you later",
+        "Good day", "G'day", "G day"],
+      "responses": [
+        "Thanks for visiting!",
+        "Have a nice day!",
+        "Bye! Come again soon.",
+        "Bye! Have a great day.",
+        "Goodbye! Hope to see you soon.", "Goodbye! Take care"
+      ]
+    },
+    {
+      "tag": "thanks",
+      "patterns": [
+        "Thanks", "Thank you", "Great help","That's helpful", "Thank's a lot", "Thank you very much",
+        "Äppreciate it", "Such a life saver"],
+      "responses": ["Happy to help!", "Any time!", "My pleasure!", "Cool ;-)", "Sure buddy!", "No sweat...", "Glad to help"]
+    },
+    {
+      "tag": "funny",
+      "patterns": [
+       "Joke", "Funny", "laugh",
+        "Tell me a joke",
+        "Tell me something funny",
+        "Do you know a joke", "Do you know any jokes",
+        "I want to hear a joke",
+        "I would like to hear a joke",
+        "I could use a joke",
+        "Please tell a joke",
+        "Can you say something funny",
+        "Could use a laugh right now",
+        "Wanna laugh", "Need a laugh", "Make me laugh", "Any jokes"
+      ],
+      "responses": [
+        "Why did the hipster burn his mouth? He drank the coffee before it was cool.",
+        "What did the buffalo say when his son left for college? Bison.",
+        "What’s the best thing about Switzerland? The flag is a big plus.",
+        "I invented a new word! Plagiarism!",
+        "Did you hear about the mathematician who’s afraid of negative numbers? He’ll stop at nothing to avoid them.",
+        "Why do we tell actors to “break a leg?” Because every play has a cast.",
+        "Yesterday I saw a guy spill all his Scrabble letters on the road. I asked him, “What’s the word on the street?",
+        "A woman in labor suddenly shouted, “Shouldn’t! Wouldn’t! Couldn’t! Didn’t! Can’t!”. “Don’t worry,” said the doc. “Those are just contractions.",
+        "A bear walks into a bar and says, “Give me a whiskey and … cola”. “Why the big pause?” asks the bartender. The bear shrugged. “I’m not sure; I was born with them.”",
+        "Did you hear about the actor who fell through the floorboards? He was just going through a stage."
+      ]
+    },
+    {
+      "tag": "Tips",
+      "patterns": [
+        "Any tips",
+        "Tell me something I don't know",
+        "General knowledge"
+      ],
+      "responses": [
+        "Did you know that youtube has 37M+ channels as of 2021?",
+        "Did you know that Bella Poarch is a Philipino?",
+        "Did you know that you get $18 per 1000 views for a video?",
+        "Did you know that you could request human review for a video?",
+        "Here are some tips to boost your channel ==> (https://digitalmarketinginstitute.com/blog/10-ways-to-grow-your-youtube-channel-in-2018)",
+        "How to startup  a new channel ==> (https://www.wix.com/blog/2017/03/how-to-start-a-successful-youtube-channel-for-your-business/)"
+      ]
+    },
+     {
+      "tag": "Idea Generation",
+      "patterns": [
+        "Trends", "What's trending", "Ideas", "Any ideas?", "New ideas", "New trends", "Trends graph", "Updates", "Whats new?", "New topics", "Topics", "Concepts", "New concepts",
+        "Trending concepts", "Show trends", "Weekly trends", "This week", "Analytics", "Report", "Weekly report"
+
+      ],
+      "responses": [
+        "Here you go ;-)"
+      ]
+    },
+    {
+      "tag": "time",
+      "patterns": [
+        "time?",
+        "What time it is",
+        "can you tell me time?",
+        "Do u know the time?"
+      ],
+      "responses": [
+        "time"
+      ]
+    },
+    {
+      "tag": "forecasting",
+      "patterns": [
+        "forecast next week",
+        "what is best topic in next week?",
+        "trending topic in next week?",
+        "what should I do next week?",
+        "next week"
+      ],
+      "responses": [
+        "forecast"
+      ]
+    }
+  ]
+}
\ No newline at end of file

model.py

+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
\ No newline at end of file

nltk_utils.py

+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)
+
+
+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())
+
+
+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
\ No newline at end of file

train.py

+import numpy as np
+import json
+
+import torch
+import torch.nn as nn
+from torch.utils.data import Dataset, DataLoader
+
+from ChatBot.nltk_utils import bag_of_words, tokenize, stem
+from ChatBot.model import NeuralNet
+
+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 = 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
+
+
+dataset = ChatDataset()
+train_loader = DataLoader(dataset=dataset,
+                          batch_size=batch_size,
+                          shuffle=True,
+                          num_workers=0)
+
+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 = "last_model.pth"
+torch.save(data, FILE)
+
+print(f'training complete. file saved to {FILE}')