ugik

# use natural language toolkit
import nltk
from nltk.corpus import stopwords
from nltk.stem.lancaster import LancasterStemmer
# word stemmer
stemmer = LancasterStemmer()

# 3 classes of training data
training_data = []
training_data.append({"class":"greeting", "sentence":"how are you?"})

ugik

# use natural language toolkit
import nltk
from nltk.stem.lancaster import LancasterStemmer
# word stemmer
stemmer = LancasterStemmer()

ugik

# 3 classes of training data
training_data = []
training_data.append({"class":"greeting", "sentence":"how are you?"})
training_data.append({"class":"greeting", "sentence":"how is your day?"})
training_data.append({"class":"greeting", "sentence":"good day"})
training_data.append({"class":"greeting", "sentence":"how is it going today?"})

training_data.append({"class":"goodbye", "sentence":"have a nice day"})
training_data.append({"class":"goodbye", "sentence":"see you later"})
training_data.append({"class":"goodbye", "sentence":"have a nice day"})

ugik

# capture unique stemmed words in the training corpus
corpus_words = {}
class_words = {}
# turn a list into a set (of unique items) and then a list again (this removes duplicates)
classes = list(set([a['class'] for a in training_data]))
for c in classes:
    # prepare a list of words within each class
    class_words[c] = []

# loop through each sentence in our training data

ugik

# calculate a score for a given class
def calculate_class_score(sentence, class_name, show_details=True):
    score = 0
    # tokenize each word in our new sentence
    for word in nltk.word_tokenize(sentence):
        # check to see if the stem of the word is in any of our classes
        if stemmer.stem(word.lower()) in class_words[class_name]:
            # treat each word with same weight
            score += 1
            

ugik

# we can now calculate a score for a new sentence
sentence = "good day for us to have lunch?"

# now we can find the class with the highest score
for c in class_words.keys():
    print ("Class: %s  Score: %s \n" % (c, calculate_class_score(sentence, c)))

ugik

# calculate a score for a given class taking into account word commonality
def calculate_class_score(sentence, class_name, show_details=True):
    score = 0
    # tokenize each word in our new sentence
    for word in nltk.word_tokenize(sentence):
        # check to see if the stem of the word is in any of our classes
        if stemmer.stem(word.lower()) in class_words[class_name]:
            # treat each word with relative weight
            score += (1 / corpus_words[stemmer.stem(word.lower())])

ugik

# return the class with highest score for sentence
def classify(sentence):
    high_class = None
    high_score = 0
    # loop through our classes
    for c in class_words.keys():
        # calculate score of sentence for each class
        score = calculate_class_score_commonality(sentence, c, show_details=False)
        # keep track of highest score
        if score > high_score:

ugik

class NeuralNetwork():
    def __init__(self):
        # Seed the random number generator, so it generates the same numbers
        # every time the program runs.
        random.seed(1)

        # We model a single neuron, with 3 input connections and 1 output connection.
        # We assign random weights to a 3 x 1 matrix, with values in the range -1 to 1
        # and mean 0.
        self.synaptic_weights = 2 * random.random((3, 1)) - 1

ugik

import numpy
# The training set. We have 4 examples, each consisting of 3 input values
# and 1 output value.
training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 0]])
training_set_outputs = array([[0, 1, 1, 0]]).T