File size: 3,161 Bytes
b20f5ed ad93163 97aa13e 943a06b 4af6be2 943a06b 97aa13e 943a06b de6415b 943a06b f66ad4d 943a06b 0c9ae8f f66ad4d 0c9ae8f 943a06b 4af6be2 943a06b 4af6be2 943a06b ee2bc44 943a06b |
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 |
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')
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, 8)
net = tflearn.fully_connected(net, 8)
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=20000, batch_size=10, show_metric=True)
model.save('minh103')
|