Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

HindiDataCleaning.py#108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Merged
Sirajmolla merged 1 commit intocoder2hacker:mainfromgauravtrivedi967:patch-4
Oct 2, 2022
Merged
Changes fromall commits
Commits
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 78 additions & 0 deletionsHindiDataCleaning.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,78 @@
#%%
'''
pip install googletrans==3.1.0a0

from googletrans import Translator
from google.colab import files

uploaded = files.upload()
'''
import pandas as pd
df=pd.read_csv("C:/Users/GAURAV/Downloads/data.csv")
df=df[['first_party','property_description','second_party']]
print(df.head(10))

#pip install indic-nlp-library

#pip install xlrd==1.2.0

'''
from indicnlp.tokenize import indic_tokenize
def tokenization(indic_string):
tokens = []
for t in indic_tokenize.trivial_tokenize(indic_string):
tokens.append(t)
return tokens
prop=['first_party','property_description','second_party']
for i in prop:
try:
df[i] = df[i].apply(lambda x: tokenization(x))
except:
df[i] = df[i].astype(str)
df[i] = df[i].apply(lambda x: tokenization(x))

df['first_party'] = df['first_party'].apply(lambda x: tokenization(x))
df["second_party"] = df["second_party"].astype(str)
df['second_party'] = df['second_party'].apply(lambda x: tokenization(x))
'''
#%%
from indicnlp.tokenize import indic_tokenize
def tokenization(indic_string):
tokens = []
for t in indic_tokenize.trivial_tokenize(indic_string):
tokens.append(t)
return tokens
prop=['first_party','property_description','second_party']
for i in prop:
try:
df[i] = df[i].apply(lambda x: tokenization(x))
stopwords_hi = ['तुम','मेरी','मुझे','क्योंकि','हम','प्रति','अबकी','आगे','माननीय','शहर','बताएं','कौनसी','क्लिक','किसकी','बड़े','मैं','and','रही','आज','लें','आपके','मिलकर','सब','मेरे','जी','श्री','वैसा','आपका','अंदर', 'अत', 'अपना', 'अपनी', 'अपने', 'अभी', 'आदि', 'आप', 'इत्यादि', 'इन', 'इनका', 'इन्हीं', 'इन्हें', 'इन्हों', 'इस', 'इसका', 'इसकी', 'इसके', 'इसमें', 'इसी', 'इसे', 'उन', 'उनका', 'उनकी', 'उनके', 'उनको', 'उन्हीं', 'उन्हें', 'उन्हों', 'उस', 'उसके', 'उसी', 'उसे', 'एक', 'एवं', 'एस', 'ऐसे', 'और', 'कई', 'कर','करता', 'करते', 'करना', 'करने', 'करें', 'कहते', 'कहा', 'का', 'काफ़ी', 'कि', 'कितना', 'किन्हें', 'किन्हों', 'किया', 'किर', 'किस', 'किसी', 'किसे', 'की', 'कुछ', 'कुल', 'के', 'को', 'कोई', 'कौन', 'कौनसा', 'गया', 'घर', 'जब', 'जहाँ', 'जा', 'जितना', 'जिन', 'जिन्हें', 'जिन्हों', 'जिस', 'जिसे', 'जीधर', 'जैसा', 'जैसे', 'जो', 'तक', 'तब', 'तरह', 'तिन', 'तिन्हें', 'तिन्हों', 'तिस', 'तिसे', 'तो', 'था', 'थी', 'थे', 'दबारा', 'दिया', 'दुसरा', 'दूसरे', 'दो', 'द्वारा', 'न', 'नहीं', 'ना', 'निहायत', 'नीचे', 'ने', 'पर', 'पर', 'पहले', 'पूरा', 'पे', 'फिर', 'बनी', 'बही', 'बहुत', 'बाद', 'बाला', 'बिलकुल', 'भी', 'भीतर', 'मगर', 'मानो', 'मे', 'में', 'यदि', 'यह', 'यहाँ', 'यही', 'या', 'यिह', 'ये', 'रखें', 'रहा', 'रहे', 'ऱ्वासा', 'लिए', 'लिये', 'लेकिन', 'व', 'वर्ग', 'वह', 'वह', 'वहाँ', 'वहीं', 'वाले', 'वुह', 'वे', 'वग़ैरह', 'संग', 'सकता', 'सकते', 'सबसे', 'सभी', 'साथ', 'साबुत', 'साभ', 'सारा', 'से', 'सो', 'ही', 'हुआ', 'हुई', 'हुए', 'है', 'हैं', 'हो', 'होता', 'होती', 'होते', 'होना', 'होने', 'अपनि', 'जेसे', 'होति', 'सभि', 'तिंहों', 'इंहों', 'दवारा', 'इसि', 'किंहें', 'थि', 'उंहों', 'ओर', 'जिंहें', 'वहिं', 'अभि', 'बनि', 'हि', 'उंहिं', 'उंहें', 'हें', 'वगेरह', 'एसे', 'रवासा', 'कोन', 'निचे', 'काफि', 'उसि', 'पुरा', 'भितर', 'हे', 'बहि', 'वहां', 'कोइ', 'यहां', 'जिंहों', 'तिंहें', 'किसि', 'कइ', 'यहि', 'इंहिं', 'जिधर', 'इंहें', 'अदि', 'इतयादि', 'हुइ', 'कोनसा', 'इसकि', 'दुसरे', 'जहां', 'अप', 'किंहों', 'उनकि', 'भि', 'वरग', 'हुअ', 'जेसा', 'नहिं',"-मे "," मे ","मे.","-मे,"," मे,","-मै "," मै ","मै.","मै,","-मेस "," मेस ","-मेस."," मेस.","मेसर्स","एम/एस"]
stopwords_en = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn', "hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn', "mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", 'won', "won't", 'wouldn', "wouldn't","-ms "," ms ","m/s ","m/s."]
punctuations = ['nn','n', '।','/', '`', '+', '\', ', '?', '▁(', '$', '@', '[', '_', "'", '!', ',', ':', '^', '|', ']', '=', '%', '&', '.', ')', '(', '*', '', ';', '-','{', '}','|','"']
trial=['एकूण', "क्षेत्रफि", "क्षेत्रफळ", "क्षेत्र","क्षेञ"]
to_be_removed = stopwords_hi + punctuations + stopwords_en+trial

for j in range(len(df)):
df[i][j]=[ele for ele in df[i][j] if ele not in (to_be_removed)]

except:
df[i] = df[i].astype(str)
df[i] = df[i].apply(lambda x: tokenization(x))
stopwords_hi = ['तुम','मेरी','मुझे','क्योंकि','हम','प्रति','अबकी','आगे','माननीय','शहर','बताएं','कौनसी','क्लिक','किसकी','बड़े','मैं','and','रही','आज','लें','आपके','मिलकर','सब','मेरे','जी','श्री','वैसा','आपका','अंदर', 'अत', 'अपना', 'अपनी', 'अपने', 'अभी', 'आदि', 'आप', 'इत्यादि', 'इन', 'इनका', 'इन्हीं', 'इन्हें', 'इन्हों', 'इस', 'इसका', 'इसकी', 'इसके', 'इसमें', 'इसी', 'इसे', 'उन', 'उनका', 'उनकी', 'उनके', 'उनको', 'उन्हीं', 'उन्हें', 'उन्हों', 'उस', 'उसके', 'उसी', 'उसे', 'एक', 'एवं', 'एस', 'ऐसे', 'और', 'कई', 'कर','करता', 'करते', 'करना', 'करने', 'करें', 'कहते', 'कहा', 'का', 'काफ़ी', 'कि', 'कितना', 'किन्हें', 'किन्हों', 'किया', 'किर', 'किस', 'किसी', 'किसे', 'की', 'कुछ', 'कुल', 'के', 'को', 'कोई', 'कौन', 'कौनसा', 'गया', 'घर', 'जब', 'जहाँ', 'जा', 'जितना', 'जिन', 'जिन्हें', 'जिन्हों', 'जिस', 'जिसे', 'जीधर', 'जैसा', 'जैसे', 'जो', 'तक', 'तब', 'तरह', 'तिन', 'तिन्हें', 'तिन्हों', 'तिस', 'तिसे', 'तो', 'था', 'थी', 'थे', 'दबारा', 'दिया', 'दुसरा', 'दूसरे', 'दो', 'द्वारा', 'न', 'नहीं', 'ना', 'निहायत', 'नीचे', 'ने', 'पर', 'पर', 'पहले', 'पूरा', 'पे', 'फिर', 'बनी', 'बही', 'बहुत', 'बाद', 'बाला', 'बिलकुल', 'भी', 'भीतर', 'मगर', 'मानो', 'मे', 'में', 'यदि', 'यह', 'यहाँ', 'यही', 'या', 'यिह', 'ये', 'रखें', 'रहा', 'रहे', 'ऱ्वासा', 'लिए', 'लिये', 'लेकिन', 'व', 'वर्ग', 'वह', 'वह', 'वहाँ', 'वहीं', 'वाले', 'वुह', 'वे', 'वग़ैरह', 'संग', 'सकता', 'सकते', 'सबसे', 'सभी', 'साथ', 'साबुत', 'साभ', 'सारा', 'से', 'सो', 'ही', 'हुआ', 'हुई', 'हुए', 'है', 'हैं', 'हो', 'होता', 'होती', 'होते', 'होना', 'होने', 'अपनि', 'जेसे', 'होति', 'सभि', 'तिंहों', 'इंहों', 'दवारा', 'इसि', 'किंहें', 'थि', 'उंहों', 'ओर', 'जिंहें', 'वहिं', 'अभि', 'बनि', 'हि', 'उंहिं', 'उंहें', 'हें', 'वगेरह', 'एसे', 'रवासा', 'कोन', 'निचे', 'काफि', 'उसि', 'पुरा', 'भितर', 'हे', 'बहि', 'वहां', 'कोइ', 'यहां', 'जिंहों', 'तिंहें', 'किसि', 'कइ', 'यहि', 'इंहिं', 'जिधर', 'इंहें', 'अदि', 'इतयादि', 'हुइ', 'कोनसा', 'इसकि', 'दुसरे', 'जहां', 'अप', 'किंहों', 'उनकि', 'भि', 'वरग', 'हुअ', 'जेसा', 'नहिं',"-मे "," मे ","मे.","-मे,"," मे,","-मै "," मै ","मै.","मै,","-मेस "," मेस ","-मेस."," मेस.","मेसर्स","एम/एस"]
stopwords_en = ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn', "hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn', "mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", 'won', "won't", 'wouldn', "wouldn't","-ms "," ms ","m/s ","m/s."]
punctuations = ['nn','n', '।','/', '`', '+', '\', ', '?', '▁(', '$', '@', '[', '_', "'", '!', ',', ':', '^', '|', ']', '=', '%', '&', '.', ')', '(', '*', '', ';', '-','{', '}','|','"']
trial=['एकूण', "क्षेत्रफि", "क्षेत्रफळ", "क्षेत्र","क्षेञ"]
to_be_removed = stopwords_hi + punctuations + stopwords_en+trial

for j in range(len(df)):
df[i][j]=[ele for ele in df[i][j] if ele not in (to_be_removed)]
df.head(20)

#pip install English-to-Hindi
#%%
from googletrans import Translator
str="सलील जनार्दन बोरवंडकर"
translator = Translator()
translated = translator.translate(str, src='hi', dest='en')
print(translated.text)
# %%
[8]ページ先頭
©2009-2025 Movatter.jp