machine_learning.py

import en_core_web_md
nlp = en_core_web_md.load()


#import spacy
import re
import numpy
import tflearn
import tensorflow
import os

def convert_txt_to_DataFrame(textFile):
    with open(textFile) as f:
        lines = f.readlines()
    # remove all '\n' characters in all lines
    lines = list(map(lambda x: x.strip('\n'), lines))
    
    temp_dict = {}
    for x in lines:
        if '- -' in x:
            # add new key to dict
            temp_dict[x.strip('- -')] = []

    for i, x in enumerate(lines):
        if '- -' in x:
            # '- -' = the question
            # ' -' = the answers, there could be multiple answers for 1 question
            # add the values(answers) to the question(key) of the dictionaries
            temp_dict[x.strip('- -')].append(lines[i+1].strip(' -'))
    
    return temp_dict

#npl = spacy.load('en_core_web_md')

def convert_to_list(file):
    data = convert_txt_to_DataFrame(file)

    question = []
    temp_bag = []
    ans = []

    for x in data:
        ans.append(data[x])
        x = re.sub(r'[^\w\s]', '', x)
        temp_bag.append(x)
            
    for x in temp_bag:
        x1 = nlp(x)       
        temp = []
        for z in x1:
            temp.append(z.lemma_)
        question.append(temp)

    return question,ans

def addQuestion(file):

    name = str(file).strip('.txt')
    # print(f"\n\n{name}\n\n")

    temp_ques = {}
    temp_ans = {}
    
    ques, ans = convert_to_list(file)
    
    temp_ques[name] = ques
    temp_ans[name] = ans
    
    return (ml_data.update(temp_ques), ans_data.update(temp_ans))

ml_data = {}
ans_data = {}


addQuestion('hello.txt')
addQuestion('how are you.txt')
addQuestion('interest.txt')
addQuestion('who are you.txt')
addQuestion('you a robot.txt')
addQuestion('tell me about yourself.txt')
addQuestion('what language python.txt')
addQuestion('What is AI.txt')
addQuestion('Tell me a joke.txt')
addQuestion('you are stupid.txt')
addQuestion('Pollak Library.txt')
addQuestion('Where is the building.txt')
addQuestion('hungry.txt')
addQuestion('What is your major.txt')
addQuestion('free time.txt')
addQuestion('I need help.txt')
addQuestion('your food.txt')
addQuestion('what time.txt')
addQuestion('weather.txt')
addQuestion('your job.txt')
addQuestion('old.txt')
addQuestion('love you.txt')
addQuestion('shut up.txt')
addQuestion('where is csuf.txt')
addQuestion('csuf mascot.txt')
addQuestion('school start.txt')
addQuestion('golden gate.txt')
addQuestion('trc.txt')
addQuestion('gwpac.txt')
addQuestion('lovelace.txt')
addQuestion('bathroom.txt')
addQuestion('starbucks.txt')
addQuestion('workout.txt')
addQuestion('tuffy.txt')
addQuestion('mccarthy.txt')
addQuestion('sgmh.txt')
addQuestion('david.txt')
addQuestion('microwave.txt')
addQuestion('arboretum.txt')
addQuestion('langdor.txt')
addQuestion('restroom.txt')
addQuestion('burger.txt')
addQuestion('tsu.txt')
addQuestion('park.txt')
addQuestion('dan.txt')



labels = []
for x in ml_data:
    labels.append(x)
    
labels = sorted(labels)
# labels

words = []
for x in ml_data:
    for z in ml_data[x]:
        words.extend(z)
        
words = sorted(list(set(words)))

#source: https://www.techwithtim.net/tutorials/ai-chatbot/part-2/
out_empty = [0 for _ in range(len(labels))]
training = []
output = []

for x, ques in enumerate(ml_data):
    print(f"question: {ques}\n\n")
    bag = []
    wrds = []
    
    for w in ml_data[ques]:
        wrds.extend(w)
    
    for w in words:
        if w in wrds:
            bag.append(1)
            print(f"{w} = 1")
        else:
            bag.append(0)
#             print(f"words: {w} = 0")

    output_row = out_empty[:]
    output_row[labels.index(ques)] = 1
    print('\n', output_row)

    training.append(bag)
    output.append(output_row)
    print(labels)
    print("\n\n****\n\n")

training = numpy.array(training)
output = numpy.array(output)




tensorflow.compat.v1.reset_default_graph()

net = tflearn.input_data(shape=[None, len(training[0])])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, len(output[0]), activation="softmax")
net = tflearn.regression(net)

model = tflearn.DNN(net)

if os.path.exists('minh103.meta'):
    model.load('minh103')
else:
    model = tflearn.DNN(net)
    model.fit(training, output, n_epoch=50000, batch_size=10, show_metric=True)
    model.save('minh103')