model2.py

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session
import json
  
# Opening  JSON file
file = open('D:\coding_pranav\inheritance\chatbot\mentalhealth - Copy.json','r')
data = json.load(file)
df = pd.DataFrame(data['intents'])
df

dic = {"tag":[], "patterns":[], "responses":[]}
for i in range(len(df)):
    ptrns = df[df.index == i]['patterns'].values[0]
    rspns = df[df.index == i]['responses'].values[0]
    tag = df[df.index == i]['tag'].values[0]
    for j in range(len(ptrns)):
        dic['tag'].append(tag)
        dic['patterns'].append(ptrns[j])
        dic['responses'].append(rspns)
        
df = pd.DataFrame.from_dict(dic)
df

df['tag'].unique()

from tensorflow.keras.preprocessing.text import Tokenizer

tokenizer = Tokenizer(lower=True, split=' ')
tokenizer.fit_on_texts(df['patterns'])
tokenizer.get_config()

vacab_size = len(tokenizer.word_index)
print('number of unique words = ', vacab_size)

from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.preprocessing import LabelEncoder

ptrn2seq = tokenizer.texts_to_sequences(df['patterns'])
X = pad_sequences(ptrn2seq, padding='post')
print('X shape = ', X.shape)

lbl_enc = LabelEncoder()
y = lbl_enc.fit_transform(df['tag'])
print('y shape = ', y.shape)
print('num of classes = ', len(np.unique(y)))

import tensorflow
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Input, Embedding, LSTM, LayerNormalization, Dense, Dropout
from tensorflow.keras.utils import plot_model

model = Sequential()
model.add(Input(shape=(X.shape[1])))
model.add(Embedding(input_dim=vacab_size+1, output_dim=100, mask_zero=True))
model.add(LSTM(32, return_sequences=True))
model.add(LayerNormalization())
model.add(LSTM(32, return_sequences=True))
model.add(LayerNormalization())
model.add(LSTM(32))
model.add(LayerNormalization())
model.add(Dense(128, activation="relu"))
model.add(LayerNormalization())
model.add(Dropout(0.2))
model.add(Dense(128, activation="relu"))
model.add(LayerNormalization())
model.add(Dropout(0.2))
model.add(Dense(len(np.unique(y)), activation="softmax"))
model.compile(optimizer='adam', loss="sparse_categorical_crossentropy", metrics=['accuracy'])

model.summary()
#plot_model(model, show_shapes=True)

model_history = model.fit(x=X,
                          y=y,
                          batch_size=10,
                          callbacks=[tensorflow.keras.callbacks.EarlyStopping(monitor='accuracy', patience=3)],
                          epochs=50)

import re
import random

def generate_answer(pattern): 
    text = []
    txt = re.sub('[^a-zA-Z\']', ' ', pattern)
    txt = txt.lower()
    txt = txt.split()
    txt = " ".join(txt)
    text.append(txt)
        
    x_test = tokenizer.texts_to_sequences(text)
    x_test = np.array(x_test).squeeze()
    x_test = pad_sequences([x_test], padding='post', maxlen=X.shape[1])
    y_pred = model.predict(x_test)
    y_pred = y_pred.argmax()
    tag = lbl_enc.inverse_transform([y_pred])[0]
    responses = df[df['tag'] == tag]['responses'].values[0]

    #print("you: {}".format(pattern))
    print("{}".format(random.choice(responses)))
generate_answer('Well... I\'m feeling sad!')
generate_answer('Hi! How are you?')