%matplotlib inline
import matplotlib.pyplot as plt

import sys, os, re, time
import urllib

import numpy as np

from IPython import parallel

HAAR_CASCADE_PATH = "haarcascade_frontalface_default.xml"
# if you have opencv installed via homebrew, this would be in
# /usr/local/share/OpenCV/haarcascades/

import cv
storage = cv.CreateMemStorage()
cascade = cv.Load(HAAR_CASCADE_PATH)


def extract_faces(image, faces):
    """Returns any faces in an image in a list of numpy arrays"""
    import numpy as np
    A = np.frombuffer(image.tostring(), dtype=np.uint8).reshape((image.height, image.width, image.nChannels))
    A = A[:,:,::-1]
    face_arrays = []
    for face in faces:
        Aface = A[face[1]:face[1]+face[3],face[0]:face[0]+face[2]]
        face_arrays.append(Aface)
    return face_arrays


def detect_faces(filename):
    """Loads an image into OpenCV, and detects faces

    returns None if no image is found,
    (filename, [list of numpy arrays]) if there are faces
    """
    
    image = cv.LoadImage(filename)
    faces = []
    detected = cv.HaarDetectObjects(image, cascade, storage, 1.2, 2, cv.CV_HAAR_DO_CANNY_PRUNING, (100,100))
    if detected:
        for (x,y,w,h),n in detected:
            faces.append((x,y,w,h))
    if faces:
        return filename, extract_faces(image, faces)


pictures_dir = 'images'

import glob
pictures = []
for directory, subdirs, files in os.walk(pictures_dir):
    for fname in files:
        if fname.endswith('.jpg'):
            pictures.append(os.path.join(directory, fname))


for p in pictures:
    found = detect_faces(p)
    if found:
        break

filename, faces = found
for face in faces:
    plt.figure()
    plt.imshow(face)

rc = parallel.Client()
all_engines = rc[:]
view = rc.load_balanced_view()

%%px
%cd notebooks/parallel

%%px
HAAR_CASCADE_PATH = "haarcascade_frontalface_default.xml"

import cv
storage = cv.CreateMemStorage()
cascade = cv.Load(HAAR_CASCADE_PATH)


all_engines.push(dict(
    extract_faces=extract_faces,
))


tic = time.time()

amr = view.map_async(detect_faces, pictures[:1000], ordered=False)
nfound = 0
for r in amr:
    if not r:
        continue
    filename, faces = r
    nfound += len(faces)
    print "%i faces found in %s" % (len(faces), filename)
    for face in faces:
        plt.imshow(face)
        plt.show()

toc = time.time()

print "found %i faces in %i images in %f s" % (nfound, len(amr), toc-tic)