alaakh42

#Python libraries that we need to import for our bot
import random
from flask import Flask, request
from pymessenger.bot import Bot
from core import get_bot_response

app = Flask(__name__)

ACCESS_TOKEN = #<ACCESS_TOKEN>
VERIFY_TOKEN = #<ACCESS_TOKEN>

alaakh42

import spacy
import random 

urw_replies = [u'Happy to help you :)', u'You are more than Welcome! :)', u'No problem, Anytime! :)']
nonsense_replies = [u"Sorry, I don't understand what you are saying", u"Sorry, I cannot help you on that!",
                    u"That's not my area of expertise"]
break_the_ice_replies = [u"Hello, Anything I can do for you?", u"Hi there! How can I help you today?"]
friendly_replies = [u"Sure! ", u"Sure! Let's see what we have here "]

nlp = spacy.load('xx_ent_wiki_sm')

alaakh42

{
  "entities": [], 
  "intent": {
    "confidence": 0.9892104618120521, 
    "name": "laliga_questions"
  }, 
  "text": "tell me about the foundation of the Barcelona team", 
  "intent_ranking": [
    {
      "confidence": 0.9892104618120521, 

alaakh42

from rasa_nlu.model import Interpreter
import json 

interpreter = Interpreter.load("./models/current/nlu")
message = ' '.join([x.strip() for x in "tell me about the foundation of the Barcelona team".split()])
result = interpreter.parse(message)
print(json.dumps(result, indent=2))

alaakh42

language: "en"

pipeline:
- name: "nlp_spacy"
- name: "tokenizer_spacy"
- name: "intent_entity_featurizer_regex"
- name: "intent_featurizer_spacy"
- name: "ner_crf"
- name: "ner_synonyms"
- name: "intent_classifier_sklearn"

alaakh42

df = pd.DataFrame({'Team': first_col,
     'Summary': summary,
     'History': history,
     'Team_Page': teams_links,
     'Location': locations,
     'Stadium': stadiums,
     'Stadiums_Capcity': stadiums_capcity
    })

# crawling the history of those three clubs were somehow tricky so I had to hard code the section names myself

alaakh42

first_col = []
teams_links = []
summary = []
history = []
stadiums = []
locations = []
stadiums_capcity = []
table = soup.find("table", style="text-align: left;")
table_body = table.find("tbody")

alaakh42

import re
import urllib
import requests
import wikipedia
import numpy as np
import pandas as pd
from bs4 import BeautifulSoup

hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

alaakh42

from __future__ import print_function

import json
import os
import numpy as np

from gensim.models import Word2Vec
from gensim.utils import simple_preprocess
from keras.engine import Input
from keras.layers import Embedding, merge

alaakh42

Multicollinearity → is the fact that one independent variable is dependent on another independent variable. like the 2 dummy variables New York and California
For example, In case of ‘Dummy Variable’ - which is the encoding of the categorical variable into numerical variables - if there is 2 levels in a categorical column called ‘State’: [New York, California] 
State
New York
California
California
New York
California

then the Dummy variables will be: D2 = 1 - D1