def test(self):
text = 'The smelt of fliwers bring back memories.'
parser = GingerIt()
output = parser.parse(text)
self.assertEqual(
output.get("result"), "The smell of flowers brings back memories"
)
def useInSentence(secretWord):
'''
secretWor: list, word + data
Starts up an interactive module of using word in sentence.
* At the start of the game, let the user know the secret word.
* Ask the user to supply one grammatically sentence containing the secret word.
* The user should receive feedback immediately whether their sentence is correct.
'''
# 'exiguous', 'scanty; meager; small; slender', 'adjective', '19', '51-Few English speakers likely know this word', 'Late Latin'
word = secretWord[0]
meaning = secretWord[1]
usage = secretWord[2]
points = secretWord[3]
difficulty = secretWord[4]
origin = secretWord[5]
print "Welcome to the use in a sentence module!"
print "Use the following word in a sentence: " + word
print "The meaning of " + word + " is: " + meaning
print "It is generally used as (a/an): " + usage
print "Points assigned: " + points
print "Difficulty: " + difficulty
print "Origin: " + origin
sentence = raw_input("Sentence containing the above mentioned word: ")
if word not in sentence.split(' '):
print "You have not used %s in the sentence. Please check if the spelling and form used is correct!" % (word)
else:
parser = GingerIt()
op = parser.parse(sentence)
if not op['corrections']:
print "Your sentence is correct!"
else:
print "The correct sentence should be: " + op['result'] + sentence[-1]
import streamlit as st
from gingerit.gingerit import GingerIt
st.title("Devashish's Grammarly!")
incorrect_sent = st.text_area("Enter the sentence to be corrected")
if st.button("Correct!"):
if incorrect_sent == "":
st.warning("Please Enter the text!")
else:
parser = GingerIt()
output = parser.parse(incorrect_sent)
print(output['result'])
st.text_area("Corrected Sentence:", value=output['result'])
#Issue in selectbox
user_rating = st.sidebar.selectbox(
"Rate the corrected sentence output with 1 being worst and 5 being best",
[None, 1, 2, 3, 4, 5])
if user_rating == None:
pass
else:
print("User Rating: ", user_rating)
else:
pass
def ginger(text):
parser = GingerIt()
grammar_error_counter = parser.parse(text)
return grammar_error_counter
def classify():
comment = request.form['comment']
parser = GingerIt()
x = parser.parse(comment)
s = x['result']
return render_template('result.html', pred=s)
def check(text):
p = GingerIt()
q = p.parse(text)
return q['result']
def correction(text):
parser = GingerIt()
pred = parser.parse(text)
return pred['result']
df["mean_word_len"] = df["comment_text"].apply(lambda x: np.mean([len(w) for w in str(x).split()]))
#Average length of the words - takes special characters into account - Length of the sentence divided by
Df["Name Length"]/(df['count_word']+1)
### Spelling Correction
# Option1: https://www.analyticsvidhya.com/blog/2018/02/natural-language-processing-for-beginners-using-textblob/
import textblob
from textblob import TextBlob
Df["Text_Var_Corrected"] = Df["Text_Var"].apply(lambda x: str(TextBlob(x).correct()))
# Option2: Takes a lot of time for many rows
from gingerit.gingerit import GingerIt
parser = GingerIt()
corrected = parser.parse("Analytics Vidhya is a gret platfrm to learn data scence")['result']
NewVar = []
# For each row
for row in Df['Var']:
NewVar.append(parser.parse(row)['result'])
Df['NewVar'] = NewVar
# Option3: Takes more time even for a single sentence and doesn't do the correction properly
!pip install pyspellchecker
from spellchecker import SpellChecker
SpellChecker().correction("The smelt of fliwers bring back memories")
# Option4: hunspell (Didn't try)
https://github.com/hunspell/hunspell
### Regex - Pattern Extraction/Matching Findall search
def checkGrammer(self,text):
# print (text)
parser = GingerIt()
item = parser.parse(text)
return item['result']
def autoCorrect(text):
from gingerit.gingerit import GingerIt
parser = GingerIt()
return parser.parse(text)['result']
from DocSim import DocSim
from gingerit.gingerit import GingerIt
googlenews_model_path = './data/GoogleNews-vectors-negative300.bin'
stopwords_path = "./data/stopwords_en.txt"
model = KeyedVectors.load_word2vec_format(googlenews_model_path, binary=True)
with open(stopwords_path, 'r') as fh:
stopwords = fh.read().split(",")
ds = DocSim(model, stopwords=stopwords)
while (1):
source_doc = raw_input("Enter first sentence : ")
parser = GingerIt()
corrected_text = parser.parse(source_doc)['result']
while source_doc != corrected_text:
if len(corrected_text.strip()) != len(source_doc.strip()) - 1:
#print "Did you mean : \"",corrected_text,"\""
print "Did you mean : \"", corrected_text, "\""
print("Press 0 to continue with suggested version ")
print("Press 1 to re-enter the sentence ")
print("Press 2 to continue with your version ")
cond = input(" --> ")
if cond == 1:
source_doc = raw_input("Enter first sentence : ")
corrected_text = parser.parse(source_doc)['result']
elif cond == 0:
source_doc = corrected_text.strip()
break
else:
from gingerit.gingerit import GingerIt
text = "I would like to buy one apples"
ginger_parser = GingerIt()
ginger_grammar_results = ginger_parser.parse(text)
ginger_corrections = ginger_grammar_results['corrections']
print("\nNumber of grammar issues found with Ginger: " +
str(len(ginger_corrections)) + "\n")
def gen_Question(keywords, qno):
print(keywords)
print("keywors")
typo = "nonested"
typo2 = "nontechnical"
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(keywords)
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
# print(tagged)
# namedEnt = nltk.ne_chunk(tagged, binary=True)
# gen_Question(namedEnt)
# namedEnt.draw()
key, words = zip(*tagged)
compare = list(words)
#print(key)
print(words)
a = dict(zip(key, words))
b = dict(zip(words, key))
print(a)
# print("hey")
print(
[b for b, v in a.items() if v in NonTechnicalQuestionDirectory.l1])
except Exception as e:
print(str(e))
if compare == NonTechnicalQuestionDirectory.l1:
question = "What " + b['NNP']
# print(question)
elif compare == NonTechnicalQuestionDirectory.l2:
question = "Why should we " + b['NN'] + " " + b['PRP'] + "?"
# print(question)
elif compare == NonTechnicalQuestionDirectory.l3:
question = "What are " + b['PRP$'] + " " + b['NNS'] + "?"
# print(question)
elif compare == NonTechnicalQuestionDirectory.l4:
question = "Tell about " + b['PRP'] + "?"
# print(question)
elif compare == NonTechnicalQuestionDirectory.l5:
question = "What are your " + b['JJ'] + " " + b['NNS'] + "?"
# print(question)
elif compare == NonTechnicalQuestionDirectory.l6:
question = "What is " + b['PRP$'] + " " + b['JJ'] + " " + b['NN'] + "?"
# print(question)
else:
question = "Explain about your " + keywords + " and its technologies?"
# print(question)
parser = GingerIt()
grammer_corrected_question_list = parser.parse(question)
question = grammer_corrected_question_list.get("result")
print(question, "hiiiiiiiiiiiiiiiiiii")
print(vik_test_codes.question(question, qno))
#jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj
voice_record = AudioRecorder.audio_recorder(qno)
print(
"error testing question numberrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr"
+ str(qno))
answer_validity = SpeachToText.validation("", typo2, typo,
"question" + str(qno))[0]
if str(qno) == "20" or qno == 20:
print(
"jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhjjjjjjjjjjj"
)
open('Controller/questionSaver_testing.py', 'w').close()
# fruits = ["gcpq = 'end'\n"]
fruits = ["global gcpq\n", "gcpq = 'end'\n"]
new_file = open("Controller/questionSaver_testing.py",
mode="a+",
encoding="utf-8")
new_file.writelines(fruits)
for line in new_file:
print(line)
new_file.close()
filelist = glob.glob("Audio/*.wav")
for file in filelist:
os.remove(file)
# if qno == "20" or qno == 20:
#
# filelist = glob.glob("Audio/*.wav")
# for file in filelist:
# os.remove(file)
return question
def generate_cv_questions():
db = "CV"
db2 = "project"
db3 = "project_d"
# node_Count = ConnectionToNeo4j.getNodeCount(db)
lang = 'en'
q_list = []
pro_list = []
count = 1
session = 0
answer_validity = 0
global question_number
question_number = 0
while count <= 3:
session = session + 1
print("session")
print(session)
session_no_string = str(session)
session_node_count = ConnectionToNeo4j.session_Node_Count(
db, session_no_string)
print("this is ")
print(session_node_count)
node_id = ConnectionToNeo4j.get_node_id(db, session_no_string)
for id in range(node_id, session_node_count + node_id):
q_list.append(str(id))
print(q_list)
print("node_count")
print(session_node_count)
for question_no in range(session_node_count):
print("question number")
print(question_no)
random_que = random.choice(q_list)
print("random que")
print(random_que)
non_technical_question = ConnectionToNeo4j.cvQuestionGen(
db, random_que)
q_list.remove(random_que)
print(q_list)
print(non_technical_question)
actual_question = QuestionCreator.gen_Question(
non_technical_question)
parser = GingerIt()
grammer_corrected_question_list = parser.parse(actual_question)
grammer_corrected_question = grammer_corrected_question_list.get(
"result")
TextToSpeechConverter.text_to_speech(grammer_corrected_question,
lang)
question_number = question_number + 1
print(question_number)
print("hiiiiiiiiiiiiiiiiii printing count")
if random_que == "5":
pro = ConnectionToNeo4j.getProjects(db, "5")
print(pro)
for id in range(1, pro + 1):
pro_list.append(str(id))
print(pro_list)
random_proj_que = random.choice(pro_list)
modify_random_proj_que = "p" + random_proj_que
print(modify_random_proj_que)
project_question = ConnectionToNeo4j.cvQuestionProjectGen(
db2, db3, modify_random_proj_que, userid)
actual_project_question = QuestionCreator.gen_Question(
project_question)
parser = GingerIt()
grammer_corrected_project_question_list = parser.parse(
actual_project_question)
grammer_corrected_pr0ject_question = grammer_corrected_project_question_list.get(
"result")
TextToSpeechConverter.text_to_speech(
grammer_corrected_pr0ject_question, lang)
question_number = question_number + 1
print(question_number)
print("hiiiiiiiiiiiiiiiiii printing count")
global technology_list
tech = test.kes()
tech = NestedQuestionCreator.keywordSelector("", tech, "1", "")
print(tech)
print("tech printed")
technology_list = NestedQuestionCreator.nonTechnicalKeywordSeelector(
tech, modify_random_proj_que)
print("hello tech")
print(technology_list)
print("check validity")
print("after a while")
answer_validity = test.test()
while (answer_validity == "None"):
answer_validity = test.test()
q_list = []
count = count + 1
async def text_correction(text : str):
if text:
parser = GingerIt()
response = parser.parse(text)
return {"Text":text,"Result":response['result']}
return {"text": "is None."}
def gen_Question(keywords, questionno, nesornot):
global question
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(keywords)
print("keywords for question")
print(keywords)
print("keywords for question")
keyword_count = len(keywords.split())
print(keyword_count)
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
# print(tagged)
# namedEnt = nltk.ne_chunk(tagged, binary=True)
# gen_Question(namedEnt)
# namedEnt.draw()
key, words = zip(*tagged)
#print(key)
compare = list(words)
print(words)
print(compare)
a = dict(zip(key, words))
b = dict(zip(words, key))
print(a)
print("hey")
# print([b for b, v in a.items() if v in l1])
except Exception as e:
print(str(e))
if compare == TechnicalQuestionDictionary.tl1:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl2:
question = "Can you explain " + keywords
elif compare == TechnicalQuestionDictionary.tl3:
question = "Describe about " + keywords
elif compare == TechnicalQuestionDictionary.tl4:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl5:
question = "What are " + keywords
elif compare == TechnicalQuestionDictionary.tl6:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl7:
question = "What are " + keywords
elif compare == TechnicalQuestionDictionary.tl9:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl10:
question = "What are " + keywords
elif compare == TechnicalQuestionDictionary.tl11:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl12:
question = "How to use" + keywords
elif compare == TechnicalQuestionDictionary.tl13:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl14:
question = "Describe about " + keywords
elif compare == TechnicalQuestionDictionary.tl15:
question = "Describe about " + keywords
elif compare == TechnicalQuestionDictionary.tl16:
question = "Describe about " + keywords
elif compare == TechnicalQuestionDictionary.tl17:
question = "Tell about " + keywords
elif compare == TechnicalQuestionDictionary.tl18:
question = "Explain about " + keywords
elif compare == TechnicalQuestionDictionary.tl19:
question = "Describe " + keywords
elif compare == TechnicalQuestionDictionary.tl20:
question = "What is a " + keywords
elif compare == TechnicalQuestionDictionary.tl21:
question = "Describe about " + keywords
elif compare == TechnicalQuestionDictionary.tl22:
question = "Tell about " + keywords
else:
question = "Define about " + keywords
parser = GingerIt()
grammer_corrected_question_list = parser.parse(question)
question = grammer_corrected_question_list.get("result")
question_list = question.split()
question_suffix_list = question_list[:-keyword_count]
question_suffix = ' '.join(question_suffix_list)
question = question_suffix + " " + keywords
print(question)
print(vik_test_codes.question(question, questionno))
voice_record = AudioRecorder.audio_recorder(questionno)
answer_validity = SpeachToText.validation(keywords, "technical", nesornot,
"question" + str(questionno))[0]
if str(questionno) == "20" or questionno == 20:
print(
"jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhjjjjjjjjjjj"
)
open('Controller/questionSaver_testing.py', 'w').close()
# fruits = ["gcpq = 'end'\n"]
fruits = ["global gcpq\n", "gcpq = 'end'\n"]
new_file = open("Controller/questionSaver_testing.py",
mode="a+",
encoding="utf-8")
new_file.writelines(fruits)
for line in new_file:
print(line)
new_file.close()
filelist = glob.glob("Audio/*.wav")
for file in filelist:
os.remove(file)
# if questionno == "20" or questionno == 20:
#
# filelist = glob.glob("Audio/*.wav")
# for file in filelist:
# os.remove(file)
return question
#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Sat Jan 16 15:00:43 2021 @author: akshay """ from gingerit.gingerit import GingerIt text = 'Narendra Modi is our prme mnister. He is from Gujaratt' parser = GingerIt() print(len(parser.parse(text)['corrections']))
def auto_correct(text):
# text = 'The smelt of fliwers bring back memories.'
parser = GingerIt()
result = parser.parse(text)
return result['result']
def checkGrammar(*args):
from gingerit.gingerit import GingerIt
blog_id = args[0]
if Blog.objects.filter(id=blog_id).exists():
blog = Blog.objects.filter(id=blog_id).first()
blogBody = blog.body
blogBody = blogBody.replace('"',
'"').replace('<', '<').replace(
'>', '>').replace(' ', ' ')
jsonData = json.loads(blogBody)
futures = []
if blog.title:
futures.append({
"blog_id": blog_id,
"section_id": 0,
"text": blog.title,
"speed": False
})
for idx, data in enumerate(jsonData["blocks"]):
if "quote" == data["type"] and "text" in data["data"]:
quoteText = "Quote: " + handleHTML(data["data"]["text"])
if data["data"]["caption"]:
quoteText = quoteText + " By " + data["data"]["caption"]
futures.append({
"blog_id": blog_id,
"section_id": idx + 1,
"text": quoteText,
"speed": False
})
elif "text" in data["data"]:
futures.append({
"blog_id": blog_id,
"section_id": idx + 1,
"text": handleHTML(data["data"]["text"]),
"speed": False
})
elif "items" in data["data"]: #list,checklist
if data["type"] == "checklist":
final_section = ""
for item in data["data"]["items"]:
final_section = final_section + item["text"]
futures.append({
"blog_id": blog_id,
"section_id": idx + 1,
"text": handleHTML(final_section),
"speed": False
})
elif data["type"] == "list":
final_section = ""
for item in data["data"]["items"]:
final_section = final_section + item
futures.append({
"blog_id": blog_id,
"section_id": idx + 1,
"text": handleHTML(final_section),
"speed": False
})
for text in futures:
try:
print("text: ", text)
parser = GingerIt()
result = parser.parse(text["text"][:199])
print("result: ", result)
except Exception as e:
return response_500("internal error", e)
def analyze(request):
puncts = string.punctuation
word_to_find = request.POST.get("word_input")
djText = request.POST.get('text', 'default')
remPunc = request.POST.get('option', 'removepunc')
cap = request.POST.get('option', 'capitalize')
small = request.POST.get('option', 'toSmall')
upper = request.POST.get('option', 'toUpper')
word_find_flag = request.POST.get('option', 'word_find')
New_Line = request.POST.get('option', 'New_line')
Emails = request.POST.get('option', 'Email_Address')
Links = request.POST.get('option', 'Links')
Passgen = request.POST.get('option', 'Password_Generator')
search_word = request.POST.get('option', 'Search_word')
gallery = request.POST.get('option', 'q')
Suggest_word = request.POST.get('option', 'suggest_word')
Sen_Analysis = request.POST.get('option', 'Sentiment')
Grammar = request.POST.get('option', 'grammar')
Channel = request.POST.get('option', 'suggest_youtube')
books = request.POST.get('option', 'suggest_books')
articles = request.POST.get('option', 'suggest_articles')
lemmitizer = request.POST.get('option', 'grammar')
start_pdf = request.POST.get('option', 'generate_pdf')
replace_text = request.POST.get('option', 'replace')
Word_cloud = request.POST.get('option', 'wordcloud')
Date = request.POST.get('option', 'date')
Word_frequency = request.POST.get('option', 'word_frequency')
analyzed_text = ""
word_status = ""
countword = len(djText.split())
if word_find_flag == "word_find":
if word_to_find != "":
if djText.find(word_to_find) != -1:
word_status = "found"
word = djText.replace(
word_to_find,
f"""<b style="color:{"red"};">""" + word_to_find + "</b>")
djText = word
try:
synonym_01 = get_synonyms(word_to_find)
synonyms2 = random.sample(synonym_01, 4)
final = ""
for f in synonyms2:
final += f + " , "
example = get_example(word_to_find)
synonyms = final + example
except:
synonyms = "Not Available"
else:
word_status = "not found"
synonyms = "Text Not Found"
analyzed_text = djText
word_find = "Find Word = " + word_to_find
synonym = format_html('<b style="color:{};">{}</b>', 'green',
synonyms)
result = {
"analyzed_text": analyzed_text,
"highlight":
"Chosen word is highlighted in red colour and synonyms/examples in green colour",
"purpose": word_find,
"status": word_status,
"synonym": synonym,
"wordcount": countword,
"analyze_text": True,
"findWord": True
}
elif New_Line == "New_line":
for char in djText:
if char == '.':
char = '\n'
analyzed_text = analyzed_text + char
result = {
"analyzed_text": analyzed_text,
"purpose": "Changes '.' to New Line",
"analyze_text": True,
"wordcount": countword
}
elif Emails == "Email_Address":
regex = '^[a-z0-9]+[\._]?[a-z0-9]+[@]\w+[.]\w{2,3}$'
lst = re.findall('\S+@+\S+', djText)
tmp = ""
for x in lst:
if (re.search(regex, x)):
tmp += x
tmp += '\n'
result = {
"analyzed_text": tmp,
"purpose": "Find All Emails",
"analyze_text": True,
"wordcount": countword
}
elif Passgen == "Password_Generator":
stop_words = set(stopwords.words('english'))
chars = "!£$%&*#@"
ucase_letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
text = re.sub(r'[^\w\s]', '', djText)
token = word_tokenize(text)
filtered_sentence = []
for w in token:
if w not in stop_words:
filtered_sentence.append(w)
if len(filtered_sentence) > 0:
random_word = random.choice(filtered_sentence)
else:
random_word = token[0]
random_word = random_word.title()
merge = ""
for word in random_word.split():
merge+=random.choice(chars)+word[:-1]+ word[-1].upper()\
+random.choice(string.ascii_letters)+"@"+random.choice(ucase_letters)\
+random.choice(string.digits)+" "
final_text = merge[:-1]
result = {
"analyzed_text": final_text,
"purpose": "Generate password from text",
"generate_text": True,
"wordcount": countword
}
elif search_word == "Search_word":
url = 'https://www.dictionary.com/browse/'
headers = requests.utils.default_headers()
headers.update({
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'
})
req = requests.get(url + djText, headers)
soup = BeautifulSoup(req.content, 'html.parser')
mydivs = soup.findAll("div", {"value": "1"})[0]
for tags in mydivs:
meaning = tags.text
wrap = textwrap.TextWrapper(width=100)
word_meaning = wrap.fill(text=meaning)
result = {
"analyzed_text": word_meaning,
"purpose": "Searched Word",
"generate_text": True,
"wordcount": countword
}
elif Suggest_word == "suggest_word":
find = requests.get(
f"https://www.dictionaryapi.com/api/v3/references/thesaurus/json/{djText}?key={api_key}"
)
response = find.json()
if len(response) == 0:
print("Word Not Recognized!")
else:
k = []
if str(response[0]).count(" ") == 0:
for j in range(len(response)):
k.append(response[j])
predict = " , ".join(k)
djText = predict
else:
dictionary = PyDictionary()
testdict = dictionary.synonym(djText)
suggest = " , ".join(testdict)
djText = suggest
wrap = textwrap.TextWrapper(width=100)
suggest = wrap.fill(text=djText)
result = {
"analyzed_text": suggest,
"purpose": "Suggested Word",
"generate_text": True,
"wordcount": countword
}
elif Sen_Analysis == "Sentiment":
djText = ' '.join(
re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)", " ",
djText).split())
analysis = TextBlob(djText)
# set sentiment
if analysis.sentiment.polarity > 0:
final = str(djText) + " (Positive Text)"
elif analysis.sentiment.polarity == 0:
final = str(djText) + " (Neutral Text)"
else:
final = str(djText) + " (Negative Text)"
result = {
"analyzed_text": final,
"purpose": "Sentiment Analysis",
"analyze_text": True,
"wordcount": countword
}
elif Grammar == "grammar":
parser = GingerIt()
result = parser.parse(djText)
final = result["result"]
if final == '':
final = "Please write some text to check grammar"
result = {
"analyzed_text": final,
"grammar": djText,
"purpose": "Spelling & Grammar Check",
"analyze_text": True,
"wordcount": countword
}
elif lemmitizer == "lemmitize":
wordnet_lemmatizer = WordNetLemmatizer()
tokenization = nltk.word_tokenize(djText)
count = True
for w in tokenization:
k = wordnet_lemmatizer.lemmatize(w, pos="v")
if w != k:
result = "{} -> {}".format(
w, wordnet_lemmatizer.lemmatize(w, pos="v"))
count = False
if count == True:
final = "No need for lemmatization"
if count == False:
final = "(Original word) - > (Lemmatized word)"
result = {
"analyzed_text": result,
"highlight": final,
"purpose": "Lemmatization of text",
"analyze_text": True,
"wordcount": countword
}
elif Channel == "suggest_youtube":
request.session['user-input'] = djText
result = {
"analyzed_text": djText,
"purpose": "Suggest youtube channels",
"status": "Press Button To View Channel links",
"find_channel": True,
"generate_text": True,
"wordcount": countword
}
elif books == "suggest_books":
request.session['user-input'] = djText
result = {
"analyzed_text": djText,
"purpose": "Search Books",
"status": "Press Button To View Books",
"find_books": True,
"generate_text": True,
"wordcount": countword
}
elif articles == "suggest_articles":
request.session['user-input'] = djText
result = {
"analyzed_text": djText,
"purpose": "Search Articles",
"status": "Press Button To View Articles",
"find_articles": True,
"generate_text": True,
"wordcount": countword
}
elif start_pdf == "generate_pdf":
request.session['user-input'] = djText
result = {
"analyzed_text": "Check Your Pdf",
"purpose": "Generate Pdf",
"status": "Press Button To View Pdf",
"make_pdf": True,
"generate_text": True,
"wordcount": countword
}
elif replace_text == "replace":
final_text = re.sub(word_to_find, replace_input, djText)
result = {
"analyzed_text": final_text,
"purpose": "Replacemet of text in sentence",
"analyze_text": True,
"wordcount": countword
}
elif Word_cloud == "wordcloud":
cloud = WordCloud(background_color="white",
max_words=200,
stopwords=set(STOPWORDS))
wc = cloud.generate(djText)
buf = io.BytesIO()
wc.to_image().save(buf, format="png")
data = base64.b64encode(buf.getbuffer()).decode("utf8")
final = "data:image/png;base64,{}".format(data)
result = {
"analyzed_text": " ",
"purpose": "Wordcloud",
"my_wordcloud": final,
"generate_text": True,
"wordcount": countword
}
elif Date == "date":
final = extract_dates(djText)
final_text = final[0].date()
result = {
"analyzed_text": final_text,
"purpose": "Extract Dates from text",
"analyze_text": True,
"wordcount": countword
}
elif Word_frequency == "word_frequency":
input_text = djText.replace("\n", " ")
djText = input_text.lower()
words_dict = get_words_dict(djText)
# create graph
if len(words_dict) > 10:
k = 10
else:
k = len(words_dict)
y_pos = range(0, k)
bars = []
height = []
count = 0
# print and save values to graph
format_spaces("word", "occurrences")
for word_str, word_amount in words_dict.items():
format_spaces(word_str, word_amount)
count += 1
if count <= 10:
bars.append(word_str)
height.append(int(word_amount))
else:
pass
# # Create bars
plt.bar(y_pos, height)
# Create names on the x-axis
plt.xticks(y_pos, bars, size=9)
plt.xticks(rotation='horizontal')
plt.ylabel('Word Frequency', fontsize=12, labelpad=10)
plt.xlabel('Words', fontsize=12, labelpad=10)
fig = plt.gcf()
buf = BytesIO()
fig.savefig(buf, format='png')
buf.seek(0)
data = base64.b64encode(buf.read())
uri = urllib.parse.quote(data)
final = "data:image/png;base64,{}".format(uri)
result = {
"analyzed_text": " ",
"purpose": "Word Frequency for every word in text",
"bar_graph": final,
"analyze_text": True,
"wordcount": countword
}
elif gallery == "q":
request.session['user-input'] = djText
result = {
"analyzed_text": djText,
"purpose": "Images",
"status": "Press Button To View Images",
"find_image": True,
"generate_text": True,
"wordcount": countword
}
elif remPunc == 'removepunc':
for char in djText:
if char not in puncts:
analyzed_text = analyzed_text + char
result = {
"analyzed_text": analyzed_text,
"purpose": "Remove Punctuations",
"analyze_text": True,
"wordcount": countword
}
elif cap == "capitalize":
analyzed_text = djText.capitalize()
result = {
"analyzed_text": analyzed_text,
"purpose": "Capitalize",
"analyze_text": True,
"wordcount": countword
}
elif small == "toSmall":
analyzed_text = djText.lower()
result = {
"analyzed_text": analyzed_text,
"purpose": "To Smallercase",
"analyze_text": True,
"wordcount": countword
}
elif upper == "toUpper":
analyzed_text = djText.upper()
result = {
"analyzed_text": analyzed_text,
"purpose": "To Uppercase",
"analyze_text": True,
"wordcount": countword
}
elif Links == "Links":
pattern = '(?:(?:https?|ftp|file):\/\/|www\.|ftp\.)(?:\([-A-Z0-9+&@#\/%=~_|$?!:,.]*\)|[-A-Z0-9+&@#\/%=~_|$?!:,.])*(?:\([-A-Z0-9+&@#\/%=~_|$?!:,.]*\)|[A-Z0-9+&@#\/%=~_|$])'
links = re.findall(pattern, djText, re.IGNORECASE)
analyzed_text = ""
i = 0
for x in links:
i = i + 1
analyzed_text += f'<a href="{x}" target="_blank">Link {i}</a>'
analyzed_text += '\n '
result = {
"analyzed_text": analyzed_text,
"purpose": "Find All Links",
"analyze_text": True,
"wordcount": countword
}
else:
return HttpResponse(
'''<script type="text/javascript">alert("Please select atleast one option.");</script>'''
)
return render(request, 'analyze.html', result)
def test_gingerit(text, expected):
parser = GingerIt()
assert parser.parse(text)["result"] == expected
def check(mail):
try:
f = word(mail, 'sentence')
corrections = 0
for s in f:
g = GingerIt()
h = g.parse(s)
corrections += len(h['corrections'])
return corrections
except:
print("Error while checking grammer errors in text")
def search(search_term, next=False, page=0, board=0):
"""function to search and return comments"""
if next == False:
page = requests.get("https://www.nairaland.com/search?q=" + urllib.parse.quote_plus(str(search_term)) + "&board="+str(board))
else:
page = requests.get("https://www.nairaland.com/search/"
+ str(search_term) + "/0/"+str(board)+"/0/1" + str(page))
soup = BeautifulSoup(page.content, 'html.parser')
comments = soup.findAll("div", {"class": "narrow"})
return comments
WordList = []
def analysis(text):
"""function to evaluate sentiment"""
try:
j = 0
board = 29
while j < 10:
if j == 0:
nextItem = False
else:
nextItem = True
commentsCurrent = search(text, nextItem, j, board)
add_to_word_list(commentsCurrent)
j += 1
except:
print("Search failed")
positive = 0
negative = 0
neutral = 0
previous = []
for tweet in WordList:
if tweet in previous:
continue
previous.append(tweet)
analysis = TextBlob(tweet)
"""evaluating polarity of comments"""
polarity = analysis.sentiment.polarity
if (analysis.sentiment.polarity == 0):
neutral += 1
elif (analysis.sentiment.polarity < 0.00):
negative += 1
elif (analysis.sentiment.polarity > 0.0):
positive += 1
noOfSearchTerms = positive + negative + neutral
positive = percentage(positive, noOfSearchTerms)
negative = percentage(negative, noOfSearchTerms)
neutral = percentage(neutral, noOfSearchTerms)
return positive, negative, neutral
)
if __name__ == "__main__":
app = TextToSpeech(subscription_key)
# app.get_token()
mtime_last = 0
pdata = []
while True:
mtime_cur = os.path.getmtime("texts.txt")
if mtime_cur != mtime_last:
time.sleep(2)
print(
f'LOG {time.strftime("%Y%m%d-%H%M")}: file watch event triggerred'
)
with open('texts.txt', 'r') as file:
data = file.read().split('\n')
if data != pdata:
pdata = data
try:
parser = GingerIt()
correctedText = parser.parse(data[-1])['result']
app.tts = correctedText
if len(correctedText) > 0:
app.save_audio()
except:
print(
f"LOG {time.strftime('%Y%m%d-%H%M')}: No data in file"
)
mtime_last = mtime_cur
# print(targeted_sentences[100])
wrong_sentences = []
for j in range(0, len(targeted_sentences)):
wrong_sentences.append(targeted_sentences[j].replace(" is ", " are "))
print("There are {} wrong sentences.".format(len(wrong_sentences)))
# print(wrong_sentences[100])
counter = 0
parser = GingerIt()
for j in range(1, 100):
try:
text = wrong_sentences[j] + " "
if parser.parse(text).get("result") == targeted_sentences[j]:
counter += 1
except IndexError:
pass
print(counter)
# class TestGingerIt(unittest.TestCase):
# def test_is(self):
# parser = GingerIt()
# for j in range (302,303):
# text = wrong_sentences[j] + " "
# # print(parser.parse(text).get("result") == targeted_sentences[j])
# self.assertEqual(parser.parse(text).get("result"), targeted_sentences[j])
for i in range(0, le_list):
for j in range(0, le_greet1):
if list[i].lower() == greet1[j].lower():
list[i] = greet1_re[j]
for i in range(0, le_list):
for j in range(0, le_greet2):
if list[i].lower() == greet2[j].lower():
list[i] = list[i] + ','
for i in range(0, le_list):
if list[i].lower() in bold:
print(style.BOLD + list[i] + style.END)
sys.stdout.flush()
else:
print(list[i])
sys.stdout.flush()
from gingerit.gingerit import GingerIt
text = 'good morning'
parser = GingerIt()
str = parser.parse(text)['result']
str1 = parser.parse(str)['result']
if len(str) > len(str1):
text_proess(str)
else:
text_proess(str1)
