Spaces:
Sleeping
Sleeping
File size: 9,793 Bytes
6b4dab8 |
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 |
#!/usr/bin/env python
"""The chatbot model training app is the "Train the chatbot model page" in the main page"""
# the code for the page
def run_app():
"""
Application code for the Chatbot Training app
"""
############################
# :: IMPORTS AND CONSTANTS #
############################
# machine learning modules
import numpy as np
import random
# Deep Learning modules
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import SGD
import streamlit as st
# suppress warnings
import warnings
warnings.filterwarnings('ignore')
# for file processing
import json
import pickle
# natural language processiong modules
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
# Load NLTK dependencies
nltk.download('punkt')
nltk.download('wordnet')
######################################
# :: HELPER FUNCTIONS FOR PROCESSING #
######################################
def read_json_file(uploaded_file):
"""
Reads a JSON file and returns its contents.
Args:
uploaded_file (_UploadedFile): The uploaded JSON file.
Returns:
dict: The contents of the JSON file.
"""
data = json.loads(uploaded_file.read().decode("utf-8"))
return data
def preprocess_data(data):
"""
Preprocesses the JSON data.
Args:
data (dict): The JSON data.
Returns:
tuple: The pre-processed data (words, classes, documents).
"""
# creating lists for NLP
words=[]
classes = []
documents = []
ignore_words = ['?', '!']
lemmatizer = WordNetLemmatizer()
for command in data['intents']:
for pattern in command['patterns']:
# Tokenize each word
w = nltk.word_tokenize(pattern)
words.extend(w)
# Add documents to the corpus
documents.append((w, command['tag']))
# Add to classes list
if command['tag'] not in classes:
classes.append(command['tag'])
# Lemmatize, convert to lowercase, and remove duplicates
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)))
return words, classes, documents
def load_pickle_data():
"""
Loads the pickle data.
Returns:
tuple: The loaded pickle data (words, classes, documents).
"""
with open('words.pkl', 'rb') as f:
words = pickle.load(f)
with open('classes.pkl', 'rb') as f:
classes = pickle.load(f)
with open('documents.pkl', 'rb') as f:
documents = pickle.load(f)
return words, classes, documents
def create_training_data(words, classes, documents):
"""
Create the training data for the chatbot model.
Args:
words (list): List of words in the vocabulary.
classes (list): List of classes/intents.
documents (list): List of (pattern, intent) pairs.
Returns:
tuple: Tuple containing the training data as NumPy arrays (train_x, train_y).
"""
training = []
output_empty = np.zeros(len(classes), dtype=int)
for doc in documents:
bag = np.zeros(len(words), dtype=int)
pattern_words = doc[0]
pattern_words = [lemmatizer.lemmatize(word.lower()) for word in pattern_words]
for i, w in enumerate(words):
if w in pattern_words:
bag[i] = 1
output_row = np.copy(output_empty)
output_row[classes.index(doc[1])] = 1
training.append([bag, output_row])
random.shuffle(training)
training = np.array(training)
train_x = list(training[:, 0])
train_y = list(training[:, 1])
return np.array(train_x), np.array(train_y)
###############
# :: MAIN APP #
###############
st.markdown("<h1 style='text-align: left;'>Train the chatbot model ⚙️</h1>", unsafe_allow_html=True)
st.subheader(
"""
Let's train the chatbot model by following the sequence of steps provided below:
"""
)
# Summary of steps
st.markdown(
"""
**Summary of Steps:**
- Upload the `commands.json` file for processing. The file should contain the commands and their corresponding tags.
- Load the preprocessed data from pickle files (optional if you have already processed the data previously).
- Create the training data by converting the commands into numerical vectors.
- Build the model by specifying the number of layers, epochs, batch size, and activation function.
Once the model is built, the training loss and accuracy will be displayed.
"""
)
st.write("---")
if st.checkbox("Upload the commands.json file for processing"):
st.subheader("JSON File Uploader")
uploaded_file = st.file_uploader("Upload JSON file", type="json")
if uploaded_file is not None:
try:
data = read_json_file(uploaded_file)
st.json(data)
# Preprocess the data
words, classes, documents = preprocess_data(data)
# Save the preprocessed data as pickle files
with open('words.pkl', 'wb') as f:
pickle.dump(words, f)
with open('classes.pkl', 'wb') as f:
pickle.dump(classes, f)
with open('documents.pkl', 'wb') as f:
pickle.dump(documents, f)
# Display the processed data
st.write("Preprocessing Results:")
st.write(len(documents), "documents")
st.write(len(classes), "classes", classes)
st.write(len(words), "unique lemmatized words", words)
except json.JSONDecodeError:
st.error("Invalid JSON file.")
if st.checkbox("Load pickle data"):
# Initialize the progress bar
progress_bar = st.progress(0)
with st.spinner("Creating training data ..."):
words, classes, documents = load_pickle_data()
# Update the progress bar
progress_bar.progress(100)
st.write("Words:")
st.write(words)
st.write("Classes:")
st.write(classes)
st.write("Documents:")
st.write(documents)
if st.checkbox("Create training data"):
try:
# Initialize the progress bar
progress_bar = st.progress(0)
with st.spinner("Creating training data ..."):
train_x, train_y = create_training_data(words, classes, documents)
# Update the progress bar
progress_bar.progress(100)
st.success("Training data created")
st.write(f"Training data (train_x): {len(train_x)} samples")
st.write(f"Training data (train_y): {len(train_y)} samples")
except Exception as e:
st.error("An error occurred during training data creation.")
st.error(str(e))
if st.checkbox("Build the model"):
# Get user inputs
num_layers = st.number_input("Number of layers", min_value=1, max_value=10, value=3)
epochs = st.number_input("Number of epochs", min_value=1, max_value=1000, value=200)
batch_size = st.number_input("Batch size", min_value=1, max_value=100, value=5)
activation_functions = ['relu', 'sigmoid', 'softmax']
activation_function = st.selectbox("Activation function", options=activation_functions)
try:
# Initialize the progress bar
progress_bar = st.progress(0)
with st.spinner("Building the model ..."):
# Create model
model = Sequential()
# Add layers to the model based on user input
for i in range(num_layers):
if i == 0:
# Input layer
model.add(Dense(128, input_shape=(len(train_x[0]),), activation=activation_function))
else:
# Hidden layers
model.add(Dense(64, activation=activation_function))
model.add(Dropout(0.5))
# Output layer
model.add(Dense(len(train_y[0]), activation='softmax'))
# Compile model
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
# Fit the model
hist = model.fit(np.array(train_x), np.array(train_y), epochs=epochs, batch_size=batch_size, verbose=1)
# Save the model
model.save('chatbot_model.h5', hist)
# Update the progress bar
progress_bar.progress(100)
st.success("The chatbot model is created")
# Display training loss and accuracy summary
st.subheader("Training Summary")
st.write("Training Loss:", hist.history['loss'][-1])
st.write("Training Accuracy:", hist.history['accuracy'][-1])
except Exception as e:
st.error("An error occurred during model building.")
st.error(str(e))
# End of app
if __name__ == "__main__":
run_app() |