# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

#from subprocess import check_output
#print(check_output(["ls", "../input"]).decode("utf8"))

# Any results you write to the current directory are saved as output.

import dicom
import os
import scipy.ndimage
import matplotlib.pyplot as plt

from skimage import measure, morphology
from mpl_toolkits.mplot3d.art3d import Poly3DCollection

# Some constants 
INPUT_FOLDER = '../input/sample_images/'
patients = os.listdir(INPUT_FOLDER)
patients.sort()

def load_scan(path):
    slices = [dicom.read_file(path + '/' + s) for s in os.listdir(path)]
    slices.sort(key = lambda x: float(x.ImagePositionPatient[2]))
    try:
        slice_thickness = np.abs(slices[0].ImagePositionPatient[2] - slices[1].ImagePositionPatient[2])
    except:
        slice_thickness = np.abs(slices[0].SliceLocation - slices[1].SliceLocation)
        
    for s in slices:
        s.SliceThickness = slice_thickness
        
    return slices
    
def get_pixels_hu(slices):
    image = np.stack([s.pixel_array for s in slices])
    # Convert to int16 (from sometimes int16), 
    # should be possible as values should always be low enough (<32k)
    image = image.astype(np.int16)

    # Set outside-of-scan pixels to 0
    # The intercept is usually -1024, so air is approximately 0
    image[image == -2000] = 0
    
    # Convert to Hounsfield units (HU)
    for slice_number in range(len(slices)):
        
        intercept = slices[slice_number].RescaleIntercept
        slope = slices[slice_number].RescaleSlope
        
        if slope != 1:
            image[slice_number] = slope * image[slice_number].astype(np.float64)
            image[slice_number] = image[slice_number].astype(np.int16)
            
        image[slice_number] += np.int16(intercept)
    
    return np.array(image, dtype=np.int16)
    
first_patient = load_scan(INPUT_FOLDER + patients[0])
first_patient_pixels = get_pixels_hu(first_patient)
plt.hist(first_patient_pixels.flatten(), bins=80, color='c')
plt.xlabel("Hounsfield Units (HU)")
plt.ylabel("Frequency")
plt.show()

# Show some slice in the middle
plt.imshow(first_patient_pixels[80], cmap=plt.cm.gray)
plt.show()