JohnDeJesus22

# kmeans grouper dashboard
@bp.route('/kmeansdashboard/<email>', methods=['GET', 'POST'])
@login_required
def kmeansdashboard(email):
    # get user data from database
    user = User.query.filter_by(email=email).first_or_404()
    data = user.upload

    # get columns
    columns = [*data.columns]

JohnDeJesus22

import numpy as np
import matplotlib.pyplot as plt
from scipy.special import comb

def hypergeom_pmf(N, A, n, x):
    
    '''
    Probability Mass Function for Hypergeometric Distribution
    :param N: population size
    :param A: total number of desired items in N

JohnDeJesus22

def hypergeom_cdf(N, A, n, t, min_value=None):
    
    '''
    Cumulative Density Funtion for Hypergeometric Distribution
    :param N: population size
    :param A: total number of desired items in N
    :param n: number of draws made from N
    :param t: number of desired items in our draw of n items up to t
    :returns: CDF computed up to t
    '''

JohnDeJesus22

def hypergeom_plot(N, A, n):
    
    '''
    Visualization of Hypergeometric Distribution for given parameters
    :param N: population size
    :param A: total number of desired items in N
    :param n: number of draws made from N
    :returns: Plot of Hypergeometric Distribution for given parameters
    '''
    

JohnDeJesus22

import pandas as pd
from scipy.stats import pointbiserialr

# get data
data = pd.read_csv('D:\quiz-Alg2U0Quiz-standard20180510.csv')

# get continuous and dichotomous data
grades = data['Percent Correct']
question_1 = data['Q1']

JohnDeJesus22

def pbc_scratch(binary_data, continuous_data, data):
    """
    Function that computes the point biserial correlation of two pandas data frame columns
    :param binary_data: name of dichotomous data column
    :param continuous_data: name of dichotomous data column
    :param data: dataframe where above columns come from
    :returns: Point Biserial Correlation
    """

    bd_unique = data[binary_data].unique()

JohnDeJesus22

# import libraries

import pandas as pd
from googlesearch import search  
from newspaper import Article, Config
from newspaper.article import ArticleException, ArticleDownloadState
import matplotlib.pyplot as plt
import seaborn as sns
from nltk import ne_chunk, pos_tag, word_tokenize
import torch 

JohnDeJesus22

# Run google search and convert to list
search_text = 'covid learning loss'
search_results = [url for url in search(search_text, tld='com', lang='en', num=78, start=0, stop=78, pause=2.0)]

JohnDeJesus22

# set configuration to not capture images
config = Config()
config.fetch_images = False

# applying article function from newspaper to each link and creating list
articles = [Article(url) for url in search_results]

# download the articles
articles_downloaded = [article.download() for article in articles]

JohnDeJesus22

# initiate dataframe for text data
text_data = pd.DataFrame()

# Create columns for text data
text_data['title'] = [article.title for article in articles]
text_data['authors'] = [article.authors for article in articles]
text_data['text'] = article_text
text_data['links'] = search_results