>>> from anonympy.pandas import dfAnonymizer
>>> from anonympy.pandas.utils_pandas import load_dataset

>>> df = load_dataset() 
>>> print(df)

# Calling the generic function
>>> anonym = dfAnonymizer(df)
>>> anonym.anonymize(inplace = False) # changes will be returned, not applied

# Or applying a specific anonymization technique to a column
>>> from anonympy.pandas.utils_pandas import available_methods

>>> anonym.categorical_columns
... ['name', 'web', 'email', 'ssn']
>>> available_methods('categorical') 
... categorical_fake	categorical_fake_auto	categorical_resampling	categorical_tokenization	categorical_email_masking

>>> anonym.anonymize({'name': 'categorical_fake',  # {'column_name': 'method_name'}
                  'age': 'numeric_noise',
                  'birthdate': 'datetime_noise',
                  'salary': 'numeric_rounding',
                  'web': 'categorical_tokenization', 
                  'email':'categorical_email_masking', 
                  'ssn': 'column_suppression'})
>>> print(anonym.to_df())

# Passing an Image
>>> import cv2
>>> from anonympy.images import imAnonymizer

>>> img = cv2.imread('salty.jpg')
>>> anonym = imAnonymizer(img)

>>> blurred = anonym.face_blur((31, 31), shape='r', box = 'r')  # blurring shape and bounding box ('r' / 'c')
>>> pixel = anonym.face_pixel(blocks=20, box=None)
>>> sap = anonym.face_SaP(shape = 'c', box=None)

# Passing a Folder 
>>> path = 'C:/Users/shakhansho.sabzaliev/Downloads/Data' # images are inside `Data` folder
>>> dst = 'D:/' # destination folder
>>> anonym = imAnonymizer(path, dst)

>>> anonym.blur(method = 'median', kernel = 11) 

# The Data folder had the following structure

|   1.jpg
|   2.jpg
|   3.jpeg
|   
\---test
    |   4.png
    |   5.jpeg
    |   
    \---test2
            6.png

# The Output folder will have the same structure and file names but blurred images

>>> from anonympy.pdf import pdfAnonymizer

# need to specify paths, since I don't have them in system variables
>>> anonym = pdfAnonymizer(path_to_pdf = "Downloads\\test.pdf",
                       pytesseract_path = r"C:\Program Files\Tesseract-OCR\tesseract.exe",
                       poppler_path = r"C:\Users\shakhansho\Downloads\Release-22.01.0-0\poppler-22.01.0\Library\bin")

# Calling the generic function
>>> anonym.anonymize(output_path = 'output.pdf',
                     remove_metadata = True,
                     fill = 'black',
                     outline = 'black')

>>> anonym = pdfAnonymizer(path_to_pdf = r"Downloads\test.pdf")
>>> anonym.pdf2images() #  images are stored in anonym.images variable 
>>> anonym.images2text(anonym.images) # texts are stored in anonym.texts

#  Entities of interest 
>>> locs: dict = anonym.find_LOC(anonym.texts[0])  # index refers to page number
>>> emails: dict = anonym.find_emails(anonym.texts[0])  # {page_number: [coords]}
>>> coords: list = locs['page_1'] + emails['page_1'] 

>>> anonym.cover_box(anonym.images[0], coords)
>>> display(anonym.images[0])