Read data from JSON and normalize then write into excel

pip install pandas

pip install jupyterlabjupyter labjupyter server list

import pandas as pddf = pd.read_json('data.json')

len(df.index)

df.info()

first_element = df.iloc[0]first_element['helpdesk_ticket']

class Person:  def __init__(self, name, age):    self.name = name    self.age = agep1 =
Person("John", 36)print(p1.name)print(p1.age)

import pandas as pda = [1, 7, 2]myvar = pd.Series(a)print(myvar)

0    11    72    2dtype: int64

fruits = ["apple", "banana", "cherry"]
for x in fruits:  print(x)

pip install nltk
pip install unidecode
pip install pycontractions
pip install word2number

$ sudo apt install openjdk-8-jdk$ sudo update-alternatives --set java
/usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java$ pip install language-check$ pip install
pycontractions

pip install language-tool-python

python3
import nltknltk.download()punkt

sentences =
sent_tokenize(text)
print(sentences)['“Everything we’re doing is about going forward,” Phoebe Philo told Vogue in 2009, shortly before showing her debut Resort collection for Céline.', 'Although the label had garnered headlines when it was revived by Michael Kors in the late ’90s, it was Philo who truly brought the till then somewhat somnambulant luxury house to the forefront.', 'Critics credited her with pushing fashion in a new direction, toward a more spare, stripped-down kind of sophistication.', 'What Céline now offered women was, as the magazine put it, “a grown-up and hip way to put themselves together.”']

stop_words = set(stopwords.words('english'))
filtered = [word for word in
word_tokenize(test_sentence) if word not in stop_words]
print(filtered)['“', 'Everything', 'going',
'forward', '”', 'Phoebe', 'Philo', 'told', 'Vogue', '2009', 'shortly', 'showing', 'debut', 'Resort',
'collection', 'Céline', '.']

>>> import nltk>>> nltk.download('stopwords')

test_sentence = re.sub(' +',' ', test_sentence)
print(test_sentence)

test_sentence = test_sentence.lower()
print(test_sentence)

pattern = r'we[\’\']re'
replacement = 'we are'
test_sentence =
re.sub(pattern,replacement,test_sentence)
print(test_sentence)

import gensim.downloader as apiapi.info()  # return dict with info about available
models/datasetsapi.info("text8")  # return dict with info about "text8" dataset

import gensim.downloader as apimodel = api.load("glove-twitter-25")  # load glove vectors

Check Java installation :    for language-check, Java 8 is expected    For MacOS: Follow these steps
: https://stackoverflow.com/a/24657630    Install language-checkpip install language-check,
won't directly work, you would have to:    Install from a forked & fixed repo for language-check    pip install git+https://github.com/MCFreddie777/language-check.git    Install pyemdpip install pyemd again runs into installation issues in Python 3.7, therefore, follow the following steps:    Ensure you have XCode installed - xcode-select --install    Set export MACOSX_DEPLOYMENT_TARGET=10.9    pip install pyemd, should now work    Now, pip install pycontractions should work!

@staticmethod    def simple_normalize(text) :        text = re.sub(' +',' ', text)        text =
text.replace('\n', ' ')        text = text.replace('\t', ' ')        text = text.replace('\r', ' ')
text = text.replace('\"', ' ')        text = text.replace('\'', ' ')        text = text.lower()
pattern = r'we[\'\']re'        replacement = 'we are'        text = re.sub(pattern,replacement,text)
pattern = r'we[\'\']ll'        replacement = 'we will'        text =
re.sub(pattern,replacement,text)         return text