Aditya kumar aditya00kumar

## monitor.html
<html>
   <head>
      <!-- Plotly.js -->
      <script src="https://cdn.plot.ly/plotly-latest.min.js"></script>
      <style>
         #myDIV {
         border: 1px solid black;
         background-color: lightblue;
         width: auto;
         overflow: auto;

## monitoring.py
import plotly
import plotly.express as px

def generate_div(prediction_distribution):
    """
    function to generate div html tags from model prediction distribution dictionary.

    :param prediction_distribution: dictionary with keys as model name and its values as a dictionary having
    its classes and values. It should look like:
    {'1.0': {'Class 1': 23,

## bayesian_rating.py
import math
import scipy.stats as st

def bayesian_rating_products(n, confidence=0.95):
    """
    Function to calculate wilson score for N star rating system.
    :param n: Array having count of star ratings where ith index represent the votes for that category i.e. [3, 5, 6, 7, 10]
    here, there are 3 votes for 1-star rating, similarly 5 votes for 2-star rating.
    :param confidence: Confidence interval
    :return: Score

## wilson_score.py
import math
import scipy.stats as st

def wilson_lower_bound(pos, n, confidence=0.95):
    """
    Function to provide lower bound of wilson score
    :param pos: No of positive ratings
    :param n: Total number of ratings
    :param confidence: Confidence interval, by default is 95 %
    :return: Wilson Lower bound score

## mmr.py
from sklearn.metrics.pairwise import cosine_similarity

def maximal_marginal_relevance(sentence_vector, phrases, embedding_matrix, lambda_constant=0.5, threshold_terms=10):
    """
    Return ranked phrases using MMR. Cosine similarity is used as similarity measure.
    :param sentence_vector: Query vector
    :param phrases: list of candidate phrases
    :param embedding_matrix: matrix having index as phrases and values as vector
    :param lambda_constant: 0.5 to balance diversity and accuracy. if lambda_constant is high, then higher accuracy. If lambda_constant is low then high diversity.
    :param threshold_terms: number of terms to include in result set

## similar_keyphrases_removal.py
def club_similar_keywords(emb_mat, sim_score=0.9):
    """
    :param emb_mat: matrix having vectors with words as index
    :param sim_score: 0.9 by default
    :return: returns list of unique words from index after combining words which has similarity score of more than
    0.9
    """
    if len(emb_mat) == 0:
        return 'NA'
    xx = cosine_similarity(emb_mat)
	<html>
	<head>
	<!-- Plotly.js -->
	<script src="https://cdn.plot.ly/plotly-latest.min.js"></script>
	<style>
	#myDIV {
	border: 1px solid black;
	background-color: lightblue;
	width: auto;
	overflow: auto;
	import plotly
	import plotly.express as px

	def generate_div(prediction_distribution):
	"""
	function to generate div html tags from model prediction distribution dictionary.

	:param prediction_distribution: dictionary with keys as model name and its values as a dictionary having
	its classes and values. It should look like:
	{'1.0': {'Class 1': 23,
	import math
	import scipy.stats as st

	def bayesian_rating_products(n, confidence=0.95):
	"""
	Function to calculate wilson score for N star rating system.
	:param n: Array having count of star ratings where ith index represent the votes for that category i.e. [3, 5, 6, 7, 10]
	here, there are 3 votes for 1-star rating, similarly 5 votes for 2-star rating.
	:param confidence: Confidence interval
	:return: Score
	import math
	import scipy.stats as st

	def wilson_lower_bound(pos, n, confidence=0.95):
	"""
	Function to provide lower bound of wilson score
	:param pos: No of positive ratings
	:param n: Total number of ratings
	:param confidence: Confidence interval, by default is 95 %
	:return: Wilson Lower bound score
	from sklearn.metrics.pairwise import cosine_similarity

	def maximal_marginal_relevance(sentence_vector, phrases, embedding_matrix, lambda_constant=0.5, threshold_terms=10):
	"""
	Return ranked phrases using MMR. Cosine similarity is used as similarity measure.
	:param sentence_vector: Query vector
	:param phrases: list of candidate phrases
	:param embedding_matrix: matrix having index as phrases and values as vector
	:param lambda_constant: 0.5 to balance diversity and accuracy. if lambda_constant is high, then higher accuracy. If lambda_constant is low then high diversity.
	:param threshold_terms: number of terms to include in result set
	def club_similar_keywords(emb_mat, sim_score=0.9):
	"""
	:param emb_mat: matrix having vectors with words as index
	:param sim_score: 0.9 by default
	:return: returns list of unique words from index after combining words which has similarity score of more than
	0.9
	"""
	if len(emb_mat) == 0:
	return 'NA'
	xx = cosine_similarity(emb_mat)