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

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

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

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

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

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

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

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

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

#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>