corpus Knowledge and Information local .png with examples#

Examples related to the corpus submodule.

# Authors: The scikit-plots developers
# SPDX-License-Identifier: BSD-3-Clause

import os
import json
import sys
import textwrap
from pathlib import Path

import scikitplot as sp
from scikitplot import corpus
from scikitplot.corpus import (
    DocumentReader,
    CorpusPipeline,
    SentenceChunker,
    SentenceChunkerConfig,
    ExportFormat,
    CorpusDocument,
    SourceType,
    SentenceBackend,
    EnricherConfig,
    NLPEnricher,
)

via `CorpusPipeline`#

pipeline_zip = CorpusPipeline(
    chunker=SentenceChunker(SentenceChunkerConfig(backend=SentenceBackend.NLTK)),
    output_dir=Path("output/"),
    export_format=ExportFormat.CSV,
)
result_zip = pipeline_zip.run(Path("data/echo_of_the_wise/AI_Generated_Image_1ix.png"))
result_zip

PipelineResult(source='data/echo_of_the_wise/AI_Generated_Image_1ix.png', n_documents=8, n_omitted=0, n_embedded=0, elapsed=4.2s, output=output/AI_Generated_Image_1ix.csv)

import pandas as pd
from pprint import pprint

pprint(pd.read_csv(result_zip.output_path).head().to_dict())

{'act': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'bbox': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'char_end': {0: 229, 1: 299, 2: 607, 3: 1011, 4: 1179},
 'char_start': {0: 6, 1: 230, 2: 301, 3: 608, 4: 1013},
 'chunk_index': {0: 0, 1: 1, 2: 2, 3: 3, 4: 4},
 'chunking_strategy': {0: 'sentence',
                       1: 'sentence',
                       2: 'sentence',
                       3: 'sentence',
                       4: 'sentence'},
 'collection_id': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'confidence': {0: 0.6372, 1: 0.6372, 2: 0.6372, 3: 0.6372, 4: 0.6372},
 'content_hash': {0: '72d9a66ad2010fe6f95c336e9b967aef',
                  1: '2ae9055ee90f61d3ed9a6ee7a8425acc',
                  2: '929db36bee285ec5d8f380cacba9e157',
                  3: '8fd437ea14514826c2c1dcae91e2c3c3',
                  4: '1890c9fdc4ee3b5ba62205dd8c1c7cf0'},
 'doc_id': {0: '033fe979c6bb209c',
            1: '2829df524657858f',
            2: '4f3824727d6cf878',
            3: '2c4188cef46cee22',
            4: 'b203e048a59ee500'},
 'doi': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'frame_index': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'image_height': {0: 1024, 1: 1024, 2: 1024, 3: 1024, 4: 1024},
 'image_width': {0: 1024, 1: 1024, 2: 1024, 3: 1024, 4: 1024},
 'isbn': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'keywords': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'language': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'lemmas': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'line_number': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'modality': {0: 'text', 1: 'text', 2: 'text', 3: 'text', 4: 'text'},
 'normalized_text': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'ocr_engine': {0: 'tesseract',
                1: 'tesseract',
                2: 'tesseract',
                3: 'tesseract',
                4: 'tesseract'},
 'page_number': {0: 0, 1: 0, 2: 0, 3: 0, 4: 0},
 'paragraph_index': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'parent_doc_id': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'raw_dtype': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'raw_shape': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'scene_number': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'section_type': {0: 'text', 1: 'text', 2: 'text', 3: 'text', 4: 'text'},
 'source_author': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'source_date': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'source_file': {0: 'AI_Generated_Image_1ix.png',
                 1: 'AI_Generated_Image_1ix.png',
                 2: 'AI_Generated_Image_1ix.png',
                 3: 'AI_Generated_Image_1ix.png',
                 4: 'AI_Generated_Image_1ix.png'},
 'source_title': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'source_type': {0: 'image', 1: 'image', 2: 'image', 3: 'image', 4: 'image'},
 'stems': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'text': {0: 'ire uursacesced Caraga io\n'
             '10 Bi6doKew 8 Erna monet) 1b / aoe Maa ETT\n'
             'RCO RSP eo ere\n'
             '\n'
             'Memmnminsane(s)\n'
             'erklaren kannst, hast du\n'
             'Creerona eats\n'
             '\n'
             ' \n'
             ' \n'
             '      \n'
             '     \n'
             '   \n'
             ' \n'
             ' \n'
             ' \n'
             ' \n'
             ' \n'
             '  \n'
             ' \n'
             '\n'
             ' \n'
             '\n'
             'Brome ccrlhy | |\n'
             ' Petesercne | verstanden.',
          1: '>\n'
             'If you cannot explain\n'
             '» Sas ONAN Co oiag\n'
             'understand it well enough.',
          2: 'ge VIDA ND TRON\n'
             '\n'
             'Sa eas\n'
             'aE Nia)\n'
             '\n'
             '   \n'
             '\n'
             '‘ApiotoréAnc + AASEavSp0¢ , Richard P. Feynman j Albert '
             'Einstein\n'
             '\n'
             '384-322 BC - 356-323 BC | Mieza, Macedonia 1918-1988 | New York, '
             'USA — Princeton — Pasadena 99-1955 | Ulm — Princeton\n'
             '\n'
             ' \n'
             ' \n'
             ' \n'
             ' \n'
             '  \n'
             '  \n'
             ' \n'
             ' \n'
             '   \n'
             '\n'
             'ONSEN\n'
             'venient Cc ae\n'
             '| Crore mokoeoeri ae} A\n'
             '\n'
             'to a bartender.',
          3: 'aa ve, r\n'
             'es Clenrecemnnc\n'
             'ahupiingao ka taea\n'
             'POMBELCUICIC IN\n'
             'SSRI LIC\n'
             '\n'
             ' \n'
             '\n'
             'Pye matterhow much you kaov\n'
             'your words reach only as far as the\n'
             'other person can understand,\n'
             '\n'
             ': ugh $9) glen a lat 9 CS lb cle Lage I y\n'
             '\n'
             ' \n'
             '\n'
             '       \n'
             ' \n'
             '\n'
             'Ernest Rutherford F Mevlana\n'
             '1871-1937 | Nelson, NZ > Cambridge _—_ warm, Ed 3 | Balkh > '
             'Konya\n'
             '\n'
             '           \n'
             ' \n'
             '\n'
             'Sato r le Scholar aCe Is\n'
             '\n'
             'Simplicity is the mark\n'
             '7 Os true knowledge.',
          4: '“ (Focused)  (Pocused) | (Distracted)\n'
             '\n'
             'cenit)\n'
             '(Innocent)\n'
             '\n'
             '   \n'
             '\n'
             'You may know all the worlds, but the conversation sto,\n'
             'j at the other person’s intelligence and vision.'},
 'timecode_end': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'timecode_start': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'tokens': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan},
 'total_frames': {0: 1, 1: 1, 2: 1, 3: 1, 4: 1},
 'url': {0: nan, 1: nan, 2: nan, 3: nan, 4: nan}}

import matplotlib.pyplot as plt
import matplotlib.image as mpimg

img = mpimg.imread(result_zip.source)
plt.imshow(img)
plt.axis('off')  # hides axes
plt.show()