Elsaveram

import multiprocessing as mp

#By default this will use all the cpu cores on your machine by splitting the corpus (or selected list) into n pieces and 
#will run the function specified in the first argument

with mp.Pool() as pool:
    str_business_df['nltk_dict'] = pool.map(nlp.vectorize, str_business_df['corp'])
    

Elsaveram

from collections import defaultdict
import nltk
import string
import re
from nltk.corpus import stopwords
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

stop = stopwords.words('english')

Elsaveram

#AWS credential setup

# pip install awscli
# pip install boto3
# aws configure
# Configure guide: https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-getting-started.html
##Configure-QuickConfigure-IAMconsole-DeleteYourRootAccessKeys-ManageSecurityCredentials-AccessKeys-CreateNewKey

import boto3
s3 = boto3.resource('s3')

Elsaveram

import json
import pandas as pd
from glob import glob
import matplotlib.pyplot as plt

#Convert json string to a flat python dictionary

def convert(x):
    ob = json.loads(x)

Elsaveram

class House():
    def __init__(self, train_data_file, test_data_file):
        train = pd.read_csv(train_data_file)
        test = pd.read_csv(test_data_file)
        self.all = pd.concat([train,test], ignore_index=True)
        self.all['test'] = self.all.SalePrice.isnull()

    def train(self):
        return(self.all[~self.all['test']])