sagorbrur

import re
import glob
import json
from tqdm import tqdm

def cleanhtml(raw_html):
  cleanr = re.compile('<.*?>')
  cleantext = re.sub(cleanr, '', raw_html)
  return cleantext

sagorbrur

import itertools
from gensim.models import Word2Vec
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm



def tsne_plot(model, vocab):
    "Creates and TSNE model and plots it"

sagorbrur

import pandas as pd

def get_meta_from_json(json_file):
    df = pd.read_json(json_file)
    df = df.T
    return df


if __name__=="__main__":
    json_file = "myjson.json"

sagorbrur

"""
Dependencies:
$sudo apt-get install libfreetype6-dev libharfbuzz-dev libfribidi-dev gtk-doc-tools
$git clone https://github.com/python-pillow/Pillow.git
$cd Pillow/depends
$chmod +x install_raqm.sh
$./install_raqm.sh
$pip install pillow

"""

sagorbrur

import re
text = "I live in Bangladesh.\n\n\nBangladesh is a beautiful country.\n\nI love my country."
res = re.sub(r'\n+', '\n',text)
print(res)

sagorbrur

import os
from tqdm import tqdm
count = 0

for root, dirs, files in tqdm(os.walk("/path")):
    for file in files:
        if file.endswith(".txt"):
            # print(file)
            filename = "files/text_{}".format(count)
            output = open(filename, "w")

sagorbrur

# Removing HTML Tag from text using regex

# code ref: https://stackoverflow.com/questions/9662346/python-code-to-remove-html-tags-from-a-string

import re

def cleanhtml(raw_html):
  cleanr = re.compile('<.*?>')
  cleantext = re.sub(cleanr, '', raw_html)
  return cleantext

sagorbrur

import re

text = "Hello123 with 563"
result = re.findall(r"\d+", text)
print(result)

# output:  ['123', '563']

sagorbrur

import re

TEXTO = sys.argv[1]
my_regex = r"\b(?=\w)" + re.escape(TEXTO) + r"\b(?!\w)"

result = re.search(my_regex, subject, re.IGNORECASE)
print(result)

# ref
# https://stackoverflow.com/questions/6930982/how-to-use-a-variable-inside-a-regular-expression

sagorbrur

# Dependecies
# python 3
# pip install fpdf
# to run:  python fpdf.py

from fpdf import FPDF
from PIL import Image
import os

listPages = os.listdir("images")