HeenaR17

## libraries.py
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from flask import Flask, render_template, request
import os.path
from rivescript import RiveScript

## rive.py
rive = os.getcwd()
bot = RiveScript()
bot.load_directory(brain)
bot.sort_replies()

## cv.txt
+-----+-----+------+-----------+--------+-----+----------+
| The | Bot | will | recommend | pizzas | for | customer |
+-----+-----+------+-----------+--------+-----+----------+
|   2 |   1 |    1 |         1 |      1 |   1 |        1 |
+-----+-----+------+-----------+--------+-----+----------+

## getMyPizza.py
def getMyPizza(ingredients):
    # load the dataset and clean the text
    pizza_df = pd.read_csv("PizzaIngredients.csv",na_values=['?'," ",""])
    pizza_df.Ingredients.replace(to_replace="[|]",value=" ",inplace=True,regex=True)
    myRow = ['MyPizza']  #converting ingredients column to list
    myRow.append(ingredients)
    pizza_df.loc[len(pizza_df)] = myRow

    cv=CountVectorizer()
    cv_matrix=cv.fit_transform(pizza_df['Ingredients']) #gives the matrix of n*n with count of words matched

## getReply.py
def getReply(ingredients):
    ans = getMyPizza(ingredients)
    if ans != 0:
        return "You may like: "+ans
    else:
        return str(bot.reply('localuser',ingredients))


## flask.py
app = Flask(__name__)

# render the home.html file
@app.route("/")
def home():
    return render_template("home.html")
@app.route("/get")
def get_bot_response():
    userText = request.args.get('msg')
    return getReply(userText)

## brain.rive
+hi
-Hi!, welcome to our Pizzeria! Please enter your preferred ingredients to help us recommend you the best pizza for your palate.

+hello
-Hello!, welcome to our Pizzeria! Please enter your preferred ingredients to help us recommend you the best pizza for your palate.

+ i want pizza
-Which pizza would you like to have?

+ [*] (farmhouse|tandoori chicken|tanddori paneer|margherita) [*]

## home.html
<!DOCTYPE html>
<html>

  <head>
        <title>Pizza Predicter</title>
    <link
      rel="shortcut icon"
      type="image/x-icon"
      href="../static/pizza.png"
    />

## TDB.txt
+-----+------------+
| Tid |   Items    |
+-----+------------+
|  10 | A, C, D    |
|  20 | B, C, E    |
|  30 | A, B, C, E |
|  40 | B, E       |
+-----+------------+

## C1.txt
+-----+------------+
| Tid |   Items    |
+-----+------------+
|  10 | A, C, D    |
|  20 | B, C, E    |
|  30 | A, B, C, E |
|  40 | B, E       |
+-----+------------+
	import pandas as pd
	from sklearn.feature_extraction.text import CountVectorizer
	from sklearn.metrics.pairwise import cosine_similarity
	from flask import Flask, render_template, request
	import os.path
	from rivescript import RiveScript
	rive = os.getcwd()
	bot = RiveScript()
	bot.load_directory(brain)
	bot.sort_replies()
	+-----+-----+------+-----------+--------+-----+----------+
	\| The \| Bot \| will \| recommend \| pizzas \| for \| customer \|
	+-----+-----+------+-----------+--------+-----+----------+
	\| 2 \| 1 \| 1 \| 1 \| 1 \| 1 \| 1 \|
	+-----+-----+------+-----------+--------+-----+----------+
	def getMyPizza(ingredients):
	# load the dataset and clean the text
	pizza_df = pd.read_csv("PizzaIngredients.csv",na_values=['?'," ",""])
	pizza_df.Ingredients.replace(to_replace="[\|]",value=" ",inplace=True,regex=True)
	myRow = ['MyPizza'] #converting ingredients column to list
	myRow.append(ingredients)
	pizza_df.loc[len(pizza_df)] = myRow

	cv=CountVectorizer()
	cv_matrix=cv.fit_transform(pizza_df['Ingredients']) #gives the matrix of n*n with count of words matched
	def getReply(ingredients):
	ans = getMyPizza(ingredients)
	if ans != 0:
	return "You may like: "+ans
	else:
	return str(bot.reply('localuser',ingredients))
	app = Flask(__name__)

	# render the home.html file
	@app.route("/")
	def home():
	return render_template("home.html")
	@app.route("/get")
	def get_bot_response():
	userText = request.args.get('msg')
	return getReply(userText)
	+hi
	-Hi!, welcome to our Pizzeria! Please enter your preferred ingredients to help us recommend you the best pizza for your palate.

	+hello
	-Hello!, welcome to our Pizzeria! Please enter your preferred ingredients to help us recommend you the best pizza for your palate.

	+ i want pizza
	-Which pizza would you like to have?

	+ [] (farmhouse\|tandoori chicken\|tanddori paneer\|margherita) []
	<!DOCTYPE html>
	<html>

	<head>
	<title>Pizza Predicter</title>
	<link
	rel="shortcut icon"
	type="image/x-icon"
	href="../static/pizza.png"
	/>
	+-----+------------+
	\| Tid \| Items \|
	+-----+------------+
	\| 10 \| A, C, D \|
	\| 20 \| B, C, E \|
	\| 30 \| A, B, C, E \|
	\| 40 \| B, E \|
	+-----+------------+