/twle-data-preparation

Primary LanguageJupyter Notebook

tests

tests/text/

coordinates

0

10aims, references
20requirements
30first page, all boxes
40first page, keyword

10

extract corridnates using pdfplumber

https://github.com/jsvine/pdfplumber#extracting-text

20

requirements
mkdir tests/text
tests/text/context.py

file:readme.org::single page text 20

readme.org tests/text/ single page text 20

readme.org

readme.org tests/text/ single page text 50 tests/text/context.py

tests/text

30

first page
import pdfplumber

import os

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    boxes = p0.extract_words()

    print( boxes )

40

first page keyword
import pdfplumber

import re

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    boxes = p0.extract_words()

    keyword = "1.0"
    
    for box in boxes:
	  if keyword in box["text"]:
	      print( box )
first page all boxes
import pdfplumber

import os

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    boxes = p0.extract_words()

    print( boxes )

50

first page keyword
import pdfplumber

import re

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    boxes = p0.extract_words()

    keyword = "1.0"
    
    for box in boxes:
	  if keyword in box["text"]:
	      print( box )
first page all boxes
import pdfplumber

import os

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    boxes = p0.extract_words()

    print( boxes )

single page text

0

10aims, references
20mkdir
30
40single-page-text.ipynb
50tests/text/context.py import pathofpdf
60

10

https://pypi.org/project/pdfplumber/

20

pwd 

ls -l tests

mkdir tests/text

40

extract_text()
import pdfplumber

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )
extract_text(), absolute and relative path
import pdfplumber

pathofpdf = "/home/appuser/files/111m1/111020_33_醫學(五)（包括外科.pdf"
# pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )

111年第一次專門職業及技術人員高等考試醫師牙醫師藥師考試分階 段考試、醫事檢驗師、醫事放射師、物理治療師考試 代 號：3302 類科名稱：醫師(二) 科目名稱：醫學(五)（包括外科、骨科、泌尿科等科目及其相關臨床實例與醫學倫理） 考試時間：2小時 座號：___________ ※本科目測驗試題為單一選擇題，請就各選項中選出一個正確或最適當的答案，複選作答者，該題不予計分! ※注意：本試題禁止使用電子計算器 1.下列敘述，何者正確？ A.病人從上消化道或腹瀉大量流失碳酸氫鹽（bicarbonate）時，會造成鹼血症（alkalemia） B.醫源性呼吸性酸中毒（iatrogenic respiratory acidosis）常見的原因之一是氣管插管後的呼吸器過度機械性通氣 （mechanical ventilation） C.敗血性休克（septic shock）病人會有代謝性鹼中毒（metabolic alkalosis） D.快速靜脈輸注大量等張氯化鈉溶液（isotonic sodium chloride solutions）時，會發生代謝性酸血症（metabolic acidemia） 2.絞刑骨折（hangman’s fracture）是指下列何者？ A.disruption of C1 ring in multiple locations ; blow-out ring B.odontoid fracture, type II : through base C.odontoid fracture, type I : tip of odontoid D.bilateral C2 pedicles with spondylolisthesis 3.在臺灣，目前下列何者不適合作為腦死器官的捐贈者？ A.血清中B型肝炎病毒（hepatitis B virus）表面抗原陽性之腦死病人 B.血清中巨細胞病毒（cytomegalovirus）抗體陽性之腦死病人 C.血清中人類嗜T淋巴球病毒（human T-lymphotropic virus）抗體陽性之腦死病人 D.血清中弓漿蟲（toxoplasma）抗體陽性之腦死病人 4.一位53歲女性駕駛小轎車與對側高速來車相撞，立刻被緊急送至第一級（Level I）創傷中心急救。到院時意識 狀態清楚，主訴兩側胸部及腹部疼痛、兩側手腕及左下肢劇痛。理學檢查發現血壓80/50 mmHg、心跳115次/ 分、呼吸20次/分，給與氧氣5公升/分鐘使用後，動脈血氧飽和度可達98%；另左胸呼吸音減低，腹部微脹有明 顯瀰漫性壓痛，雙側手腕變形及左股骨開放性骨折。經快速大量輸液治療後血壓上升至100/55 mmHg，故安排 緊急全身顯影電腦斷層，結果如附圖。病人送回急救區後發現意識模糊，但對深痛刺激有反應，生命徵象為血 壓60/40 mmHg、心跳125次/分、呼吸20次/分，動脈血氧飽和度無法偵測。下列何種醫療處置較為適當？ A.再次給予快速大量輸液後立即再安排一次腦部電腦斷層

chars[]
import pdfplumber

pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print(first_page.chars[0])

{‘matrix’: (0.739011017207873, 0.0, 0.0, 0.739011017207873, 39.34615559257678, 791.4886591493051), ‘fontname’: ‘DFKaiShu-SB-Estd-BF’, ‘adv’: 12.0, ‘upright’: True, ‘x0’: 39.34615559257678, ‘y0’: 787.95526272328, ‘x1’: 48.21428779907126, ‘y1’: 805.691527136269, ‘width’: 8.86813220649448, ‘height’: 17.73626441298893, ‘size’: 17.73626441298893, ‘object_type’: ‘char’, ‘page_number’: 1, ‘ncs’: ‘DeviceRGB’, ‘text’: ‘1’, ‘stroking_color’: (0, 0, 0), ‘stroking_pattern’: None, ‘non_stroking_color’: (0, 0, 0), ‘non_stroking_pattern’: None, ‘top’: 36.228452863731036, ‘bottom’: 53.964717276719966, ‘doctop’: 36.228452863731036}

50

tests/text/context.py
import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

# tangle c-u c-c C-v t

tests

readme.org tests/path/ 50

extract_text() import pathofpdf
import pdfplumber

import os

from context import pathofpdf

# home_path = os.path.expanduser("~")

# folder = "files/111m1"

# file = "111020_33_醫學(五)（包括外科.pdf"

# pathofpdf = os.path.join(home_path, folder, file)

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )
extract_text()
import pdfplumber

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )
extract_text(), absolute and relative path
import pdfplumber

pathofpdf = "/home/appuser/files/111m1/111020_33_醫學(五)（包括外科.pdf"
# pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )

111年第一次專門職業及技術人員高等考試醫師牙醫師藥師考試分階 段考試、醫事檢驗師、醫事放射師、物理治療師考試 代 號：3302 類科名稱：醫師(二) 科目名稱：醫學(五)（包括外科、骨科、泌尿科等科目及其相關臨床實例與醫學倫理） 考試時間：2小時 座號：___________ ※本科目測驗試題為單一選擇題，請就各選項中選出一個正確或最適當的答案，複選作答者，該題不予計分! ※注意：本試題禁止使用電子計算器 1.下列敘述，何者正確？ A.病人從上消化道或腹瀉大量流失碳酸氫鹽（bicarbonate）時，會造成鹼血症（alkalemia） B.醫源性呼吸性酸中毒（iatrogenic respiratory acidosis）常見的原因之一是氣管插管後的呼吸器過度機械性通氣 （mechanical ventilation） C.敗血性休克（septic shock）病人會有代謝性鹼中毒（metabolic alkalosis） D.快速靜脈輸注大量等張氯化鈉溶液（isotonic sodium chloride solutions）時，會發生代謝性酸血症（metabolic acidemia） 2.絞刑骨折（hangman’s fracture）是指下列何者？ A.disruption of C1 ring in multiple locations ; blow-out ring B.odontoid fracture, type II : through base C.odontoid fracture, type I : tip of odontoid D.bilateral C2 pedicles with spondylolisthesis 3.在臺灣，目前下列何者不適合作為腦死器官的捐贈者？ A.血清中B型肝炎病毒（hepatitis B virus）表面抗原陽性之腦死病人 B.血清中巨細胞病毒（cytomegalovirus）抗體陽性之腦死病人 C.血清中人類嗜T淋巴球病毒（human T-lymphotropic virus）抗體陽性之腦死病人 D.血清中弓漿蟲（toxoplasma）抗體陽性之腦死病人 4.一位53歲女性駕駛小轎車與對側高速來車相撞，立刻被緊急送至第一級（Level I）創傷中心急救。到院時意識 狀態清楚，主訴兩側胸部及腹部疼痛、兩側手腕及左下肢劇痛。理學檢查發現血壓80/50 mmHg、心跳115次/ 分、呼吸20次/分，給與氧氣5公升/分鐘使用後，動脈血氧飽和度可達98%；另左胸呼吸音減低，腹部微脹有明 顯瀰漫性壓痛，雙側手腕變形及左股骨開放性骨折。經快速大量輸液治療後血壓上升至100/55 mmHg，故安排 緊急全身顯影電腦斷層，結果如附圖。病人送回急救區後發現意識模糊，但對深痛刺激有反應，生命徵象為血 壓60/40 mmHg、心跳125次/分、呼吸20次/分，動脈血氧飽和度無法偵測。下列何種醫療處置較為適當？ A.再次給予快速大量輸液後立即再安排一次腦部電腦斷層

chars[]
import pdfplumber

pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print(first_page.chars[0])

{‘matrix’: (0.739011017207873, 0.0, 0.0, 0.739011017207873, 39.34615559257678, 791.4886591493051), ‘fontname’: ‘DFKaiShu-SB-Estd-BF’, ‘adv’: 12.0, ‘upright’: True, ‘x0’: 39.34615559257678, ‘y0’: 787.95526272328, ‘x1’: 48.21428779907126, ‘y1’: 805.691527136269, ‘width’: 8.86813220649448, ‘height’: 17.73626441298893, ‘size’: 17.73626441298893, ‘object_type’: ‘char’, ‘page_number’: 1, ‘ncs’: ‘DeviceRGB’, ‘text’: ‘1’, ‘stroking_color’: (0, 0, 0), ‘stroking_pattern’: None, ‘non_stroking_color’: (0, 0, 0), ‘non_stroking_pattern’: None, ‘top’: 36.228452863731036, ‘bottom’: 53.964717276719966, ‘doctop’: 36.228452863731036}

60

text.find
import pdfplumber

import os

from context import pathofpdf

with pdfplumber.open( pathofpdf ) as pdf:

    p0 = pdf.pages[0]

    text = p0.extract_text()

    word_intex = text.find("3.")

    bonding_box = p0.get_word_bounding_box( word_intex )
    
    print( bonding_box )
tests/text/context.py
import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

# tangle c-u c-c C-v t

tests

readme.org tests/path/ 50

extract_text() import pathofpdf
import pdfplumber

import os

from context import pathofpdf

# home_path = os.path.expanduser("~")

# folder = "files/111m1"

# file = "111020_33_醫學(五)（包括外科.pdf"

# pathofpdf = os.path.join(home_path, folder, file)

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )
extract_text()
import pdfplumber

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )
extract_text(), absolute and relative path
import pdfplumber

pathofpdf = "/home/appuser/files/111m1/111020_33_醫學(五)（包括外科.pdf"
# pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print( first_page.extract_text() )
    # print( first_page.chars[0] )

111年第一次專門職業及技術人員高等考試醫師牙醫師藥師考試分階 段考試、醫事檢驗師、醫事放射師、物理治療師考試 代 號：3302 類科名稱：醫師(二) 科目名稱：醫學(五)（包括外科、骨科、泌尿科等科目及其相關臨床實例與醫學倫理） 考試時間：2小時 座號：___________ ※本科目測驗試題為單一選擇題，請就各選項中選出一個正確或最適當的答案，複選作答者，該題不予計分! ※注意：本試題禁止使用電子計算器 1.下列敘述，何者正確？ A.病人從上消化道或腹瀉大量流失碳酸氫鹽（bicarbonate）時，會造成鹼血症（alkalemia） B.醫源性呼吸性酸中毒（iatrogenic respiratory acidosis）常見的原因之一是氣管插管後的呼吸器過度機械性通氣 （mechanical ventilation） C.敗血性休克（septic shock）病人會有代謝性鹼中毒（metabolic alkalosis） D.快速靜脈輸注大量等張氯化鈉溶液（isotonic sodium chloride solutions）時，會發生代謝性酸血症（metabolic acidemia） 2.絞刑骨折（hangman’s fracture）是指下列何者？ A.disruption of C1 ring in multiple locations ; blow-out ring B.odontoid fracture, type II : through base C.odontoid fracture, type I : tip of odontoid D.bilateral C2 pedicles with spondylolisthesis 3.在臺灣，目前下列何者不適合作為腦死器官的捐贈者？ A.血清中B型肝炎病毒（hepatitis B virus）表面抗原陽性之腦死病人 B.血清中巨細胞病毒（cytomegalovirus）抗體陽性之腦死病人 C.血清中人類嗜T淋巴球病毒（human T-lymphotropic virus）抗體陽性之腦死病人 D.血清中弓漿蟲（toxoplasma）抗體陽性之腦死病人 4.一位53歲女性駕駛小轎車與對側高速來車相撞，立刻被緊急送至第一級（Level I）創傷中心急救。到院時意識 狀態清楚，主訴兩側胸部及腹部疼痛、兩側手腕及左下肢劇痛。理學檢查發現血壓80/50 mmHg、心跳115次/ 分、呼吸20次/分，給與氧氣5公升/分鐘使用後，動脈血氧飽和度可達98%；另左胸呼吸音減低，腹部微脹有明 顯瀰漫性壓痛，雙側手腕變形及左股骨開放性骨折。經快速大量輸液治療後血壓上升至100/55 mmHg，故安排 緊急全身顯影電腦斷層，結果如附圖。病人送回急救區後發現意識模糊，但對深痛刺激有反應，生命徵象為血 壓60/40 mmHg、心跳125次/分、呼吸20次/分，動脈血氧飽和度無法偵測。下列何種醫療處置較為適當？ A.再次給予快速大量輸液後立即再安排一次腦部電腦斷層

chars[]
import pdfplumber

pathofpdf = "../../../files/111m1/111020_33_醫學(五)（包括外科.pdf"

with pdfplumber.open( pathofpdf ) as pdf:
    first_page = pdf.pages[0]
    print(first_page.chars[0])

{‘matrix’: (0.739011017207873, 0.0, 0.0, 0.739011017207873, 39.34615559257678, 791.4886591493051), ‘fontname’: ‘DFKaiShu-SB-Estd-BF’, ‘adv’: 12.0, ‘upright’: True, ‘x0’: 39.34615559257678, ‘y0’: 787.95526272328, ‘x1’: 48.21428779907126, ‘y1’: 805.691527136269, ‘width’: 8.86813220649448, ‘height’: 17.73626441298893, ‘size’: 17.73626441298893, ‘object_type’: ‘char’, ‘page_number’: 1, ‘ncs’: ‘DeviceRGB’, ‘text’: ‘1’, ‘stroking_color’: (0, 0, 0), ‘stroking_pattern’: None, ‘non_stroking_color’: (0, 0, 0), ‘non_stroking_pattern’: None, ‘top’: 36.228452863731036, ‘bottom’: 53.964717276719966, ‘doctop’: 36.228452863731036}

tests/path/pathofpdf

0

10aims, references
20mkdir
30
40os.path.expanduser(“~”) os.getcwd()
50pathofpdf
60from context import pathofpdf

10

https://pypi.org/project/pdfplumber/

20

pwd 

ls -l tests

mkdir tests/path

40

os.path.expanduser(“~”)

import os

home_directory = os.path.expanduser("~")

print("Home Directory:", home_directory)

os.getcwd()

import os

cwd = os.getcwd()  # Get current working directory

print( cwd )

50

pathofpdf

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

if os.path.exists(pathofpdf):
  # Do something with the file
    print( pathofpdf )
else:
  print("File does not exist.")

os.path.expanduser(“~”)

import os

home_directory = os.path.expanduser("~")

print("Home Directory:", home_directory)

os.getcwd()

import os

cwd = os.getcwd()  # Get current working directory

print( cwd )

60

tests/path/context.py

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

tests

readme.org tests/path/ 50

import context

import os

from context import pathofpdf
# from .context import pathofpdf  # ImportError: attempted relative import with no known parent package

if os.path.exists(pathofpdf):
    print( pathofpdf )
else:
    print("File does not exist.")

https://docs.python-guide.org/writing/structure/

pathofpdf

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

if os.path.exists(pathofpdf):
  # Do something with the file
    print( pathofpdf )
else:
  print("File does not exist.")

os.path.expanduser(“~”)

import os

home_directory = os.path.expanduser("~")

print("Home Directory:", home_directory)

os.getcwd()

import os

cwd = os.getcwd()  # Get current working directory

print( cwd )

tests/context.py

0

10aims, references
20tests/path/context.py
30
40

10

https://docs.python-guide.org/writing/structure/ tests/context.py

2 parts
tests/pathofpdf.py
import

20

tests

readme.org tests/path/ 50

import os

home_path = os.path.expanduser("~")

folder = "files/111m1"

file = "111020_33_醫學(五)（包括外科.pdf"

pathofpdf = os.path.join(home_path, folder, file)

30

tests/version.ipynb

0

10aims, references
20version
30

10

20

version

import pdfplumber
import pandas as pd

print(pdfplumber.__version__)

requirements

0

10
20
30folders anatomy
40

10

20

30

container mount pointreporepo folder
/home/appuser/files1files
/home/appuser/app2/

https://github.com/changmingchen/twle

https://github.com/changmingchen/twle-data-preparation