Briq/camelot-py
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Adds documentation

Browse Source 
[MRG] Adds documentation
This commit is contained in:
Vinayak Mehta
2016-08-09 17:23:50 +05:30
committed by GitHub
parent dda809b286
commit 7e5804f87d
41 changed files with 1133 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/mexican_towns.pdf
BIN
View File
Binary file not shown.
tests/test_lattice.py
+97
View File
@@ -0,0 +1,97 @@
# coding: utf8
import os
from nose.tools import assert_equal
from camelot.pdf import Pdf
from camelot.lattice import Lattice
testdir = os.path.dirname(os.path.abspath(__file__))
def test_lattice_basic():
data = [
["Cycle Name","KI (1/km)","Distance (mi)","Percent Fuel Savings","","",""],
["","","","Improved Speed","Decreased Accel","Eliminate Stops","Decreased Idle"],
["2012_2","3.30","1.3","5.9%","9.5%","29.2%","17.4%"],
["2145_1","0.68","11.2","2.4%","0.1%","9.5%","2.7%"],
["4234_1","0.59","58.7","8.5%","1.3%","8.5%","3.3%"],
["2032_2","0.17","57.8","21.7%","0.3%","2.7%","1.2%"],
["4171_1","0.07","173.9","58.1%","1.6%","2.1%","0.5%"]
]
pdfname = os.path.join(testdir,
"tabula_test_pdfs/icdar2013-dataset/competition-dataset-us/us-030.pdf")
extractor = Lattice(Pdf(pdfname,
pagenos=[{'start': 2, 'end': 2}], clean=True))
tables = extractor.get_tables()
assert_equal(tables['pg-2'][0], data)
def test_lattice_fill():
data = [
["Plan Type","County","Plan Name","Totals"],
["GMC","Sacramento","Anthem Blue Cross","164,380"],
["GMC","Sacramento","Health Net","126,547"],
["GMC","Sacramento","Kaiser Foundation","74,620"],
["GMC","Sacramento","Molina Healthcare","59,989"],
["GMC","San Diego","Care 1st Health Plan","71,831"],
["GMC","San Diego","Community Health Group","264,639"],
["GMC","San Diego","Health Net","72,404"],
["GMC","San Diego","Kaiser","50,415"],
["GMC","San Diego","Molina Healthcare","206,430"],
["GMC","Total GMC Enrollment","","1,091,255"],
["COHS","Marin","Partnership Health Plan of CA","36,006"],
["COHS","Mendocino","Partnership Health Plan of CA","37,243"],
["COHS","Napa","Partnership Health Plan of CA","28,398"],
["COHS","Solano","Partnership Health Plan of CA","113,220"],
["COHS","Sonoma","Partnership Health Plan of CA","112,271"],
["COHS","Yolo","Partnership Health Plan of CA","52,674"],
["COHS","Del Norte","Partnership Health Plan of CA","11,242"],
["COHS","Humboldt","Partnership Health Plan of CA","49,911"],
["COHS","Lake","Partnership Health Plan of CA","29,149"],
["COHS","Lassen","Partnership Health Plan of CA","7,360"],
["COHS","Modoc","Partnership Health Plan of CA","2,940"],
["COHS","Shasta","Partnership Health Plan of CA","61,763"],
["COHS","Siskiyou","Partnership Health Plan of CA","16,715"],
["COHS","Trinity","Partnership Health Plan of CA","4,542"],
["COHS","Merced","Central California Alliance for Health","123,907"],
["COHS","Monterey","Central California Alliance for Health","147,397"],
["COHS","Santa Cruz","Central California Alliance for Health","69,458"],
["COHS","Santa Barbara","CenCal","117,609"],
["COHS","San Luis Obispo","CenCal","55,761"],
["COHS","Orange","CalOptima","783,079"],
["COHS","San Mateo","Health Plan of San Mateo","113,202"],
["COHS","Ventura","Gold Coast Health Plan","202,217"],
["COHS","Total COHS Enrollment","","2,176,064"],
["Subtotal for Two-Plan, Regional Model, GMC and COHS","","","10,132,022"],
["PCCM","Los Angeles","AIDS Healthcare Foundation","828"],
["PCCM","San Francisco","Family Mosaic","25"],
["PCCM","Total PHP Enrollment","","853"],
["All Models Total Enrollments","","","10,132,875"],
["Source: Data Warehouse 12/14/15","","",""]
]
pdfname = os.path.join(testdir, 'row_span_1.pdf')
extractor = Lattice(Pdf(pdfname, clean=True), fill='v', scale=40)
tables = extractor.get_tables()
assert_equal(tables['pg-1'][0], data)
def test_lattice_invert():
data = [
["State","Date","Halt stations","Halt days","Persons directly reached(in lakh)","Persons trained","Persons counseled","Persons testedfor HIV"],
["Delhi","1.12.2009","8","17","1.29","3,665","2,409","1,000"],
["Rajasthan","2.12.2009 to 19.12.2009","","","","","",""],
["Gujarat","20.12.2009 to 3.1.2010","6","13","6.03","3,810","2,317","1,453"],
["Maharashtra","4.01.2010 to 1.2.2010","13","26","1.27","5,680","9,027","4,153"],
["Karnataka","2.2.2010 to 22.2.2010","11","19","1.80","5,741","3,658","3,183"],
["Kerala","23.2.2010 to 11.3.2010","9","17","1.42","3,559","2,173","855"],
["Total","","47","92","11.81","22,455","19,584","10,644"]
]
pdfname = os.path.join(testdir, 'lines_in_background_1.pdf')
extractor = Lattice(Pdf(pdfname, clean=True), invert=True)
tables = extractor.get_tables()
assert_equal(tables['pg-1'][1], data)
tests/test_stream.py
+169
View File
@@ -0,0 +1,169 @@
# coding: utf8
import os
from nose.tools import assert_equal
from camelot.pdf import Pdf
from camelot.stream import Stream
testdir = os.path.dirname(os.path.abspath(__file__))
def test_stream_basic():
data = [
["","","","",""],
["C Appendix C: Summary Statistics","","","",""],
["","Table C1: Summary Statistics","","",""],
["","This table contains summary statistics for 2,012 respondents in SAVE 2009.","","",""],
["Variable","Mean","Std. Dev. Min","","Max"],
["Age","50.8","15.9","21","90"],
["Men","0.47","0.50","0","1"],
["East","0.28","0.45","0","1"],
["Rural","0.15","0.36","0","1"],
["Married","0.57","0.50","0","1"],
["Single","0.21","0.40","0","1"],
["Divorced","0.13","0.33","0","1"],
["Widowed","0.08","0.26","0","1"],
["Separated","0.03","0.16","0","1"],
["Partner","0.65","0.48","0","1"],
["Employed","0.55","0.50","0","1"],
["Fulltime","0.34","0.47","0","1"],
["Parttime","0.20","0.40","0","1"],
["Unemployed","0.08","0.28","0","1"],
["Homemaker","0.19","0.40","0","1"],
["Retired","0.28","0.45","0","1"],
["Household size","2.43","1.22","1","9"],
["Households with children","0.37","0.48","0","1"],
["Number of children","1.67","1.38","0","8"],
["Lower secondary education","0.08","0.27","0","1"],
["Upper secondary education","0.60","0.49","0","1"],
["Post secondary, non tert. education","0.12","0.33","0","1"],
["First stage tertiary education","0.17","0.38","0","1"],
["Other education","0.03","0.17","0","1"],
["Household income (Euro/month)","2,127","1,389","22","22,500"],
["Gross wealth - end of 2007 (Euro)","187,281","384,198","0","7,720,000"],
["Gross financial wealth - end of 2007 (Euro)","38,855","114,128","0","2,870,000"],
["","Source: SAVE 2008 and 2009, data is weighted and imputed.","","",""],
["","","","","ECB"],
["","","","","Working Paper Series No 1299"],
["","","","","Febuary 2011"]
]
pdfname = os.path.join(testdir,
"tabula_test_pdfs/icdar2013-dataset/competition-dataset-eu/eu-027.pdf")
extractor = Stream(Pdf(pdfname, pagenos=[{'start': 3, 'end': 3}],
clean=True))
tables = extractor.get_tables()
assert_equal(tables['pg-3'][0], data)
def test_stream_ncolumns():
data = [
["","","","",""],
["","Bhandara - Key Indicators","","",""],
["","DLHS-4 (2012-13)","","DLHS-3 (2007-08)",""],
["Indicators","TOTAL","RURAL","TOTAL","RURAL"],
["Reported Prevalence of Morbidity","","","",""],
["Any Injury .....................................................................................................................................","1.9","2.1","",""],
["Acute Illness .................................................................................................................................","4.5","5.6","",""],
["Chronic Illness ..............................................................................................................................","5.1","4.1","",""],
["Reported Prevalence of Chronic Illness during last one year (%)","","","",""],
["Disease of respiratory system ......................................................................................................","11.7","15.0","",""],
["Disease of cardiovascular system ................................................................................................","8.9","9.3","",""],
["Persons suffering from tuberculosis .............................................................................................","2.2","1.5","",""],
["Anaemia Status by Haemoglobin Level14 (%)","","","",""],
["Children (6-59 months) having anaemia ......................................................................................","68.5","71.9","",""],
["Children (6-59 months) having severe anaemia ..........................................................................","6.7","9.4","",""],
["Children (6-9 Years) having anaemia - Male ................................................................................","67.1","71.4","",""],
["Children (6-9 Years) having severe anaemia - Male ....................................................................","4.4","2.4","",""],
["Children (6-9 Years) having anaemia - Female ...........................................................................","52.4","48.8","",""],
["Children (6-9 Years) having severe anaemia - Female ................................................................","1.2","0.0","",""],
["Children (6-14 years) having anaemia - Male .............................................................................","50.8","62.5","",""],
["Children (6-14 years) having severe anaemia - Male ..................................................................","3.7","3.6","",""],
["Children (6-14 years) having anaemia - Female .........................................................................","48.3","50.0","",""],
["Children (6-14 years) having severe anaemia - Female ..............................................................","4.3","6.1","",""],
["Children (10-19 Years15) having anaemia - Male .........................................................................","37.9","51.2","",""],
["Children (10-19 Years15) having severe anaemia - Male .............................................................","3.5","4.0","",""],
["Children (10-19 Years15) having anaemia - Female .....................................................................","46.6","52.1","",""],
["Children (10-19 Years15) having severe anaemia - Female .........................................................","6.4","6.5","",""],
["Adolescents (15-19 years) having anaemia ................................................................................","39.4","46.5","",""],
["Adolescents (15-19 years) having severe anaemia .....................................................................","5.4","5.1","",""],
["Pregnant women (15-49 aged) having anaemia ..........................................................................","48.8","51.5","",""],
["Pregnant women (15-49 aged) having severe anaemia ..............................................................","7.1","8.8","",""],
["Women (15-49 aged) having anaemia .........................................................................................","45.2","51.7","",""],
["Women (15-49 aged) having severe anaemia .............................................................................","4.8","5.9","",""],
["Persons (20 years and above) having anaemia ...........................................................................","37.8","42.1","",""],
["Persons (20 years and above) having Severe anaemia ..............................................................","4.6","4.8","",""],
["Blood Sugar Level (age 18 years and above) (%)","","","",""],
["Blood Sugar Level >140 mg/dl (high) ...........................................................................................","12.9","11.1","",""],
["Blood Sugar Level >160 mg/dl (very high) ...................................................................................","7.0","5.1","",""],
["Hypertension (age 18 years and above) (%)","","","",""],
["Above Normal Range (Systolic >140 mm of Hg & Diastolic >90 mm of Hg ) ..............................","23.8","22.8","",""],
["Moderately High (Systolic >160 mm of Hg & Diastolic >100 mm of Hg ) .....................................","8.2","7.1","",""],
["Very High (Systolic >180 mm of Hg & Diastolic >110 mm of Hg ) ...............................................","3.7","3.1","",""],
["14 Any anaemia below 11g/dl, severe anaemia below 7g/dl. 15 Excluding age group 19 years","","","",""],
["","Chronic Illness :Any person with symptoms persisting for longer than one month is defined as suffering from chronic illness","","",""]
]
pdfname = os.path.join(testdir, 'missing_values.pdf')
extractor = Stream(Pdf(pdfname, char_margin=1.0, clean=True),
ncolumns=5)
tables = extractor.get_tables()
assert_equal(tables['pg-1'][0], data)
def test_stream_columns():
data = [
["","","","","",""],
["Clave","","Clave","","Clave",""],
["","Nombre Entidad","","Nombre Municipio","","Nombre Localidad"],
["Entidad","","Municipio","","Localidad",""],
["01","Aguascalientes","001","Aguascalientes","0094","Granja Adelita"],
["01","Aguascalientes","001","Aguascalientes","0096","Agua Azul"],
["01","Aguascalientes","001","Aguascalientes","0100","Rancho Alegre"],
["01","Aguascalientes","001","Aguascalientes","0102","Los Arbolitos [Rancho]"],
["01","Aguascalientes","001","Aguascalientes","0104","Ardillas de Abajo (Las Ardillas)"],
["01","Aguascalientes","001","Aguascalientes","0106","Arellano"],
["01","Aguascalientes","001","Aguascalientes","0112","Bajío los Vázquez"],
["01","Aguascalientes","001","Aguascalientes","0113","Bajío de Montoro"],
["01","Aguascalientes","001","Aguascalientes","0114","Residencial San Nicolás [Baños la Cantera]"],
["01","Aguascalientes","001","Aguascalientes","0120","Buenavista de Peñuelas"],
["01","Aguascalientes","001","Aguascalientes","0121","Cabecita 3 Marías (Rancho Nuevo)"],
["01","Aguascalientes","001","Aguascalientes","0125","Cañada Grande de Cotorina"],
["01","Aguascalientes","001","Aguascalientes","0126","Cañada Honda [Estación]"],
["01","Aguascalientes","001","Aguascalientes","0127","Los Caños"],
["01","Aguascalientes","001","Aguascalientes","0128","El Cariñán"],
["01","Aguascalientes","001","Aguascalientes","0129","El Carmen [Granja]"],
["01","Aguascalientes","001","Aguascalientes","0135","El Cedazo (Cedazo de San Antonio)"],
["01","Aguascalientes","001","Aguascalientes","0138","Centro de Arriba (El Taray)"],
["01","Aguascalientes","001","Aguascalientes","0139","Cieneguilla (La Lumbrera)"],
["01","Aguascalientes","001","Aguascalientes","0141","Cobos"],
["01","Aguascalientes","001","Aguascalientes","0144","El Colorado (El Soyatal)"],
["01","Aguascalientes","001","Aguascalientes","0146","El Conejal"],
["01","Aguascalientes","001","Aguascalientes","0157","Cotorina de Abajo"],
["01","Aguascalientes","001","Aguascalientes","0162","Coyotes"],
["01","Aguascalientes","001","Aguascalientes","0166","La Huerta (La Cruz)"],
["01","Aguascalientes","001","Aguascalientes","0170","Cuauhtémoc (Las Palomas)"],
["01","Aguascalientes","001","Aguascalientes","0171","Los Cuervos (Los Ojos de Agua)"],
["01","Aguascalientes","001","Aguascalientes","0172","San José [Granja]"],
["01","Aguascalientes","001","Aguascalientes","0176","La Chiripa"],
["01","Aguascalientes","001","Aguascalientes","0182","Dolores"],
["01","Aguascalientes","001","Aguascalientes","0183","Los Dolores"],
["01","Aguascalientes","001","Aguascalientes","0190","El Duraznillo"],
["01","Aguascalientes","001","Aguascalientes","0191","Los Durón"],
["01","Aguascalientes","001","Aguascalientes","0197","La Escondida"],
["01","Aguascalientes","001","Aguascalientes","0201","Brande Vin [Bodegas]"],
["01","Aguascalientes","001","Aguascalientes","0207","Valle Redondo"],
["01","Aguascalientes","001","Aguascalientes","0209","La Fortuna"],
["01","Aguascalientes","001","Aguascalientes","0212","Lomas del Gachupín"],
["01","Aguascalientes","001","Aguascalientes","0213","El Carmen (Gallinas Güeras) [Rancho]"],
["01","Aguascalientes","001","Aguascalientes","0216","La Gloria"]
]
pdfname = os.path.join(testdir, 'mexican_towns.pdf')
extractor = Stream(Pdf(pdfname, clean=True),
columns='28,67,180,230,425,475,700')
tables = extractor.get_tables()
assert_equal(tables['pg-1'][0], data)