Create app.py

machine_learning.py

@@ -0,0 +1,154 @@
+from statistics import mode
+import spacy
+import re
+import numpy
+import tflearn
+import tensorflow
+
+
+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 = npl(x)       
+        temp = []
+        for z in x1:
+            temp.append(z.lemma_)
+        question.append(temp)
+
+    return question,ans
+
+def addQuestion(file, name):
+    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('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/hello.txt', 'hello')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/how are you.txt', 'how are you')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/interest.txt', 'interest')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/who are you.txt', 'who are you')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/you a robot.txt', 'you a robot')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/tell me about yourself.txt','tell me about yourself')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/what language python.txt','what language python')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/What is AI.txt', 'what is ai')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/Tell me a joke.txt','tell me a joke')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/you are stupid.txt', 'you are stupid')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/Pollak Library.txt','pollak library')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/Where is the building.txt','where is the building')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/hungry.txt','hungry')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/What is your major.txt','what is your major')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/free time.txt', 'free time')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/I need help.txt', 'i need help')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/your food.txt', 'your food')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/what time.txt', 'what time')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/weather.txt', 'weather')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/your job.txt', 'your job')
+addQuestion('/opt/homebrew/anaconda3/envs/tensorflow/Chatbot/question files/old.txt', 'age')
+
+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)
+
+try:
+    model.load('minh103')
+except:
+    model = tflearn.DNN(net)
+    model.fit(training, output, n_epoch=20000, batch_size=10, show_metric=True)
+    model.save('minh103')