| import nltk |
| import numpy as np |
| import tensorflow as tf |
| from keras.models import Sequential, load_model |
| from keras.layers import Dense |
| import random |
| import json |
| import pickle |
|
|
| |
|
|
|
|
| nltk.download('punkt') |
|
|
|
|
| stemmer = nltk.stem.lancaster.LancasterStemmer() |
|
|
| |
| with open("/home/mrdev/Ollama_testes/tutorial_IA/intents.json") as file: |
| data = json.load(file) |
|
|
| |
| try: |
| with open("/home/mrdev/Ollama_testes/tutorial_IA/data.pickle", "rb") as f: |
| words, labels, training, output = pickle.load(f) |
| except: |
| words = [] |
| labels = [] |
| docs_y = [] |
| docs_x = [] |
|
|
| |
| for intent in data["intents"]: |
| for pattern in intent["pattern"]: |
| wrds = nltk.word_tokenize(pattern) |
| words.extend(wrds) |
| docs_x.append(wrds) |
| docs_y.append(intent["tag"]) |
|
|
| if intent["tag"] not in labels: |
| labels.append(intent["tag"]) |
|
|
| |
| words = [stemmer.stem(w.lower()) for w in words if w != "?"] |
| words = sorted(list(set(words))) |
|
|
| labels = sorted(labels) |
|
|
| |
| training = [] |
| output = [] |
|
|
| out_empty = [0 for _ in range(len(labels))] |
|
|
| for x, doc in enumerate(docs_x): |
| bag = [] |
|
|
| wrds = [stemmer.stem(w) for w in doc] |
|
|
| for w in words: |
| if w in wrds: |
| bag.append(1) |
| else: |
| bag.append(0) |
| output_row = out_empty[:] |
| output_row[labels.index(docs_y[x])] = 1 |
|
|
| training.append(bag) |
| output.append(output_row) |
|
|
| training = np.array(training) |
| output = np.array(output) |
|
|
| with open("/home/mrdev/Ollama_testes/tutorial_IA/data.pickle", "wb") as f: |
| pickle.dump((words, labels, training, output), f) |
|
|
| |
|
|
| |
| tf.keras.backend.clear_session() |
| model = Sequential() |
| model.add(Dense(8, input_shape=(len(training[0]),), activation='relu')) |
| model.add(Dense(8, activation='relu')) |
| model.add(Dense(len(output[0]), activation='softmax')) |
|
|
| |
| model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) |
|
|
| |
| try: |
| model = load_model("/home/mrdev/Ollama_testes/tutorial_IA/model_keras.h5") |
| except: |
| |
| model.fit(training, output, epochs=1000, batch_size=8, verbose=1) |
| |
| model.save("/home/mrdev/Ollama_testes/tutorial_IA/model_keras.h5") |
|
|
|
|
| def bag_of_words(s, words): |
| bag = [0 for _ in range(len(words))] |
| s_words = nltk.word_tokenize(s) |
| s_words = [stemmer.stem(word.lower()) for word in s_words] |
|
|
| for se in s_words: |
| for i, w in enumerate(words): |
| if w == se: |
| bag[i] = 1 |
| return np.array(bag) |
|
|
|
|
| |
| def chat(): |
| print("__start__") |
| while True: |
| inp = input("Você: ") |
| if inp.lower() == "sair": |
| print("Saindo") |
| break |
| else: |
| results = model.predict(np.array([bag_of_words(inp, words)])) |
| results_index = np.argmax(results) |
| tag = labels[results_index] |
|
|
| for tg in data["intents"]: |
| if tg["tag"] == tag: |
| responses = tg["responses"] |
|
|
| print(random.choice(responses)) |
|
|
|
|
| chat() |
|
|
