Ahanmr

We couldn’t find that file to show.

Ahanmr

import re, os
from collections import Counter
from symspellpy.symspellpy import SymSpell as SymSpellPy, Verbosity

class SpellCheck:
    def __init__(self, dictionary=None, verbose=0):
        self.verbose = verbose
        self.dictionary = dictionary
        
    def correction(self, text):

Ahanmr

"""
Problem:
  How to Convert PDF to Image with Python Script ?

  $ sudo apt-get install libmagickwand-dev
  $ pip install Wand

"""

from PIL import Image as Img

Ahanmr

import PIL.Image
import PIL.ImageDraw
import wand.image
import sys, os
from io import BytesIO

    def draw_rect(self, bbox_or_obj,
        fill=DEFAULT_FILL,
        stroke=DEFAULT_STROKE,
        stroke_width=DEFAULT_STROKE_WIDTH):

Ahanmr

import io
from PIL import Image
import pytesseract
from wand.image import Image as wi

pdf = wi(filename = "sample2.pdf", resolution = 300)
pdfImage = pdf.convert('jpeg')

imageBlobs = []

Ahanmr

class TableFinder(object):
    """
    Given a PDF page, finds table structures.
    """
    def __init__(self, page, settings={}):
        for k in settings.keys():
            if k not in DEFAULT_TABLE_SETTINGS:
                raise ValueError("Unrecognized table setting: '{0}'".format(
                    k
                ))

Ahanmr

    def find_tables(self, table_settings={}):
        return TableFinder(self, table_settings).tables

    def extract_tables(self, table_settings={}):
        tables = self.find_tables(table_settings)
        return [ table.extract() for table in tables ]

    def extract_table(self, table_settings={}):
        tables = self.find_tables(table_settings)
        # Return the largest table, as measured by number of cells.

Ahanmr

def modelfit(alg, dtrain, predictors,useTrainCV=True, cv_folds=5, early_stopping_rounds=50):
    
    if useTrainCV:
        xgb_param = alg.get_xgb_params()
        xgtrain = xgb.DMatrix(dtrain[predictors].values, label=dtrain[target].values)
        cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
            metrics='auc', early_stopping_rounds=early_stopping_rounds, show_progress=False)
        alg.set_params(n_estimators=cvresult.shape[0])
    
    #Fit the algorithm on the data

Ahanmr

#Import libraries:
import pandas as pd
import numpy as np
import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn import cross_validation, metrics   #Additional scklearn functions
from sklearn.grid_search import GridSearchCV   #Perforing grid search

import matplotlib.pylab as plt
%matplotlib inline

Ahanmr

car : 52.74809002876282
car : 54.43572402000427
car : 61.86940670013428
car : 64.99541997909546
car : 54.53670620918274
car : 54.111236333847046
car : 55.92341423034668
person : 54.37796711921692
person : 61.132240295410156
car : 70.4900324344635