BCC-Datapreprocess

preprocess1.py

# Dataset Extraction from github
!git clone 'https://github.com/Shenggan/BCCD_Dataset.git'

import os, sys, random, shutil
import xml.etree.ElementTree as ET
from glob import glob
import pandas as pd
from shutil import copyfile
import pandas as pd
from sklearn import preprocessing, model_selection
import matplotlib.pyplot as plt
%matplotlib inline
from matplotlib import patches
import numpy as np

annotations = sorted(glob('/content/BCCD_Dataset/BCCD/Annotations/*.xml'))

df = []
cnt = 0
for file in annotations:
  prev_filename = file.split('/')[-1].split('.')[0] + '.jpg'
  filename = str(cnt) + '.jpg'
  row = []
  parsedXML = ET.parse(file)
  for node in parsedXML.getroot().iter('object'):
    blood_cells = node.find('name').text
    xmin = int(node.find('bndbox/xmin').text)
    xmax = int(node.find('bndbox/xmax').text)
    ymin = int(node.find('bndbox/ymin').text)
    ymax = int(node.find('bndbox/ymax').text)

    row = [prev_filename, filename, blood_cells, xmin, xmax, ymin, ymax]
    df.append(row)
  cnt += 1

data = pd.DataFrame(df, columns=['prev_filename', 'filename', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax'])

data[['prev_filename','filename', 'cell_type', 'xmin', 'xmax', 'ymin', 'ymax']].to_csv('/content/blood_cell_detection.csv', index=False)
data.head(10)