chatbot (ai by mathieu rodic, gui by me)

chatbot.py

#updated 5/7/17
import tkinter as tk
import re
import sqlite3
from collections import Counter
from string import punctuation
from math import sqrt
from time import sleep ##for delay realism
global B

# initialize the connection to the database
connection = sqlite3.connect('chatbot.sqlite')
cursor = connection.cursor()

# create the tables needed by the program
create_table_request_list = [
    'CREATE TABLE words(word TEXT UNIQUE)',
    'CREATE TABLE sentences(sentence TEXT UNIQUE, used INT NOT NULL DEFAULT 0)',
    'CREATE TABLE associations (word_id INT NOT NULL, sentence_id INT NOT NULL, weight REAL NOT NULL)',
]
for create_table_request in create_table_request_list:
    try:
        cursor.execute(create_table_request)
    except:
        pass
    
def get_id(entityName, text):
    """Retrieve an entity's unique ID from the database, given its associated text.
    If the row is not already present, it is inserted.
    The entity can either be a sentence or a word."""
    tableName = entityName + 's'
    columnName = entityName
    cursor.execute('SELECT rowid FROM ' + tableName + ' WHERE ' + columnName + ' = ?', (text,))
    row = cursor.fetchone()
    if row:
        return row[0]
    else:
        cursor.execute('INSERT INTO ' + tableName + ' (' + columnName + ') VALUES (?)', (text,))
        return cursor.lastrowid

def get_words(text):
    """Retrieve the words present in a given string of text.
    The return value is a list of tuples where the first member is a lowercase word,
    and the second member the number of time it is present in the text."""
    wordsRegexpString = '(?:\w+|[' + re.escape(punctuation) + ']+)'
    wordsRegexp = re.compile(wordsRegexpString)
    wordsList = wordsRegexp.findall(text.lower())
    return Counter(wordsList).items()
 

root = tk.Tk()
root.resizable(width=False, height=False)
root.wm_title("stuff")
root.geometry('{}x{}'.format(800, 600))

x = tk.Label(root) #text = ""
e = tk.Entry(root, bd =5)

#the variable 'ok' is the user message, the variable 'B' is the bots message
#remove "event" in case of error
def send(event):
    global B
    try:
        B
    except:
        B = "Hello"
        y.insert(tk.END, "Bot: " + B + "\n") ##print('B: ' + B)
    ok = e.get() # convert entry to string
    if ok is not "":

        y.insert(tk.END, "You: " + ok + "\n") #insert to textbox
        e.delete(0, 'end')
        # output bot's message
        # ask for user input; if blank line, exit the loop
        H = ok.strip()
        # store the association between the bot's message words and the user's response
        words = get_words(B)
        words_length = sum([n * len(word) for word, n in words])
        sentence_id = get_id('sentence', H)
        for word, n in words:
            word_id = get_id('word', word)
            weight = sqrt(n / float(words_length)) ##another indecipherable formula, for choosing the most suitable wordset to match the other, presumably
            cursor.execute('INSERT INTO associations VALUES (?, ?, ?)', (word_id, sentence_id, weight))
        connection.commit() ##commit is a native function to python without use of any modules
        # retrieve the most likely answer from the database
        cursor.execute('CREATE TEMPORARY TABLE results(sentence_id INT, sentence TEXT, weight REAL)')
        words = get_words(H)
        words_length = sum([n * len(word) for word, n in words]) ##some indecipherable formula?
        for word, n in words:
            weight = sqrt(n / float(words_length))
            cursor.execute('INSERT INTO results SELECT associations.sentence_id, sentences.sentence, ?*associations.weight/(4+sentences.used) FROM words INNER JOIN associations ON associations.word_id=words.rowid INNER JOIN sentences ON sentences.rowid=associations.sentence_id WHERE words.word=?', (weight, word,))
        # if matches were found, give the best one
        cursor.execute('SELECT sentence_id, sentence, SUM(weight) AS sum_weight FROM results GROUP BY sentence_id ORDER BY sum_weight DESC LIMIT 1')
        row = cursor.fetchone()
        cursor.execute('DROP TABLE results')
        # otherwise, just randomly pick one of the least used sentences
        if row is None:
            cursor.execute('SELECT rowid, sentence FROM sentences WHERE used = (SELECT MIN(used) FROM sentences) ORDER BY RANDOM() LIMIT 1')
            row = cursor.fetchone()
        # tell the database the sentence has been used once more, and prepare the sentence
        B = row[1]
        cursor.execute('UPDATE sentences SET used=used+1 WHERE rowid=?', (row[0],))
        y.insert(tk.END, "Bot: " + B + "\n")



root.bind('<Return>', send)
s = tk.Button(root, text = "Send", width = 10, command=send)
y = tk.Text(root, width = 90, height = 25)


s.grid(row = 0, column = 0); s.place(x = 700, y = 500)
x.pack(); e.place(x = 100, y = 500, width = 600); y.pack()
root.mainloop()