Sachin Kumar S skwolvie

## workex_noise.csv
yoe
15
10
20
12
8
16
14
5
11

## ti_sample.csv

          
            Date
            weekend_or_holiday
            Mumbai
            New Delhi
            DELHI
            MUMBAI

            
              3/7/2019
              0
              11.05
              6.88

            
              3/8/2019
              0
              53.76
              34.12

            
              3/9/2019
              1
              23.82
              38.49

            
              3/10/2019
              1
              11.56
              27.41

            
              3/11/2019
              0
              34.58
              36.21

            
              3/12/2019
              0
              46.38
              42.8

            
              3/13/2019
              0
              45.34
              41.87

            
              3/14/2019
              0
              36.9
              45.45

            
              3/15/2019
              0
              43.16
              45.56

## .py
import yake
import swifter
from nltk.tokenize import RegexpTokenizer
def keywords_yake(text):
    # take keywords for each post & turn them into a text string "sentence"
    simple_kwextractor = yake.KeywordExtractor(lan='ja',
                                     n=1,
                                     dedupLim=.99,
                                     dedupFunc='seqm',
                                     windowsSize=100,

## .py
import spacy
from spacy import displacy
from IPython.display import HTML, display
# change the model to en_core_web_sm/lg for english
nlp = spacy.load('ja_core_news_lg')

text= "アプリインフラWebサイト等幅広く手掛けます RPAAIシステム開発にも携わって頂きます HTML Javascript PHP Python JAVAの知識が身につきます "

def extract_noun_phrase_experience(doc):
    a=[]

## .py
import re
import string
import nltk
from nltk.corpus import stopwords

nltk.download('stopwords')

st = set(stopwords.words('japanese'))
punc= string.punctuation
SYMBOLS = r"[★・︾◯●：（）【】、⇒_。①②./」「\-◆?～※！:><＜＞→〇×△→―]"
Date	weekend_or_holiday	Mumbai	New Delhi	DELHI	MUMBAI
3/7/2019	0	11.05	6.88
3/8/2019	0	53.76	34.12
3/9/2019	1	23.82	38.49
3/10/2019	1	11.56	27.41
3/11/2019	0	34.58	36.21
3/12/2019	0	46.38	42.8
3/13/2019	0	45.34	41.87
3/14/2019	0	36.9	45.45
3/15/2019	0	43.16	45.56
	import yake
	import swifter
	from nltk.tokenize import RegexpTokenizer
	def keywords_yake(text):
	# take keywords for each post & turn them into a text string "sentence"
	simple_kwextractor = yake.KeywordExtractor(lan='ja',
	n=1,
	dedupLim=.99,
	dedupFunc='seqm',
	windowsSize=100,
	import spacy
	from spacy import displacy
	from IPython.display import HTML, display
	# change the model to en_core_web_sm/lg for english
	nlp = spacy.load('ja_core_news_lg')

	text= "アプリインフラWebサイト等幅広く手掛けます RPAAIシステム開発にも携わって頂きます HTML Javascript PHP Python JAVAの知識が身につきます "

	def extract_noun_phrase_experience(doc):
	a=[]
	import re
	import string
	import nltk
	from nltk.corpus import stopwords

	nltk.download('stopwords')

	st = set(stopwords.words('japanese'))
	punc= string.punctuation
	SYMBOLS = r"[★・︾◯●：（）【】、⇒_。①②./」「\-◆?～※！:><＜＞→〇×△→―]"