import cv2
import numpy as np
import os

train_path = 'images/cell_images/train'  # Folder Names are Parasitized and Uninfected
training_names = os.listdir(train_path)

image_paths = []
image_classes = []
class_id = 0

def imglist(path):    
    return [os.path.join(path, f) for f in os.listdir(path)]

for training_name in training_names:
    dir = os.path.join(train_path, training_name)
    class_path = imglist(dir)
    image_paths += class_path
    image_classes += [class_id] * len(class_path)
    class_id += 1

image_paths

image_classes

class_id

des_list = []

brisk = cv2.BRISK_create(30)
for image_path in image_paths:
    im = cv2.imread(image_path)
    kpts, des = brisk.detectAndCompute(im, None)
    des_list.append((image_path, des))   

descriptors = des_list[0][1]
for image_path, descriptor in des_list[1:]:
    descriptors = np.vstack((descriptors, descriptor))  
descriptors

descriptors_float = descriptors.astype(float)

from scipy.cluster.vq import kmeans, vq
 
k = 200  # k means with 100 clusters gives lower accuracy for the aeroplane example
voc, variance = kmeans(descriptors_float, k, 1) 

im_features = np.zeros((len(image_paths), k), "float32")
for i in range(len(image_paths)):
    words, distance = vq(des_list[i][1],voc)
    for w in words:
        im_features[i][w] += 1

words

distance

nbr_occurences = np.sum((im_features > 0) * 1, axis=0)
idf = np.array(np.log((1.0 * len(image_paths) + 1) / (1.0 * nbr_occurences + 1)), 'float32')

from sklearn.preprocessing import StandardScaler
stdSlr = StandardScaler().fit(im_features)
im_features = stdSlr.transform(im_features)

from sklearn.svm import LinearSVC
clf = LinearSVC(max_iter=10000)  # Default of 100 is not converging
clf.fit(im_features, np.array(image_classes))

import joblib
joblib.dump((clf, training_names, stdSlr, k, voc), "bovw.pkl", compress=3)    

import cv2
import numpy as np
import os
import pylab as pl
from sklearn.metrics import confusion_matrix, accuracy_score  # sreeni
import joblib

clf, classes_names, stdSlr, k, voc = joblib.load("bovw.pkl")

test_path = 'images/cell_images/test'
testing_names = os.listdir(test_path)

# Get path to all images and save them in a list
# image_paths and the corresponding label in image_paths
image_paths = []
image_classes = []
class_id = 0
 
# To make it easy to list all file names in a directory let us define a function
 
def imglist(path):
    return [os.path.join(path, f) for f in os.listdir(path)]
 
# Fill the placeholder empty lists with image path, classes, and add class ID number
 
for testing_name in testing_names:
    dir = os.path.join(test_path, testing_name)
    class_path = imglist(dir)
    image_paths+=class_path
    image_classes+=[class_id]*len(class_path)
    class_id+=1
    
# Create feature extraction and keypoint detector objects
# SIFT is not available anymore in openCV    
# Create List where all the descriptors will be stored
des_list = []
 
# BRISK is a good replacement to SIFT. ORB also works but didn;t work well for this example
brisk = cv2.BRISK_create(30)
 
for image_path in image_paths:
    im = cv2.imread(image_path)
    kpts, des = brisk.detectAndCompute(im, None)
    des_list.append((image_path, des))   
    
# Stack all the descriptors vertically in a numpy array
descriptors = des_list[0][1]
for image_path, descriptor in des_list[0:]:
    descriptors = np.vstack((descriptors, descriptor)) 
 
# Calculate the histogram of features
# vq Assigns codes from a code book to observations.
from scipy.cluster.vq import vq    
test_features = np.zeros((len(image_paths), k), "float32")
for i in range(len(image_paths)):
    words, distance = vq(des_list[i][1],voc)
    for w in words:
        test_features[i][w] += 1
 
# Perform Tf-Idf vectorization
nbr_occurences = np.sum( (test_features > 0) * 1, axis = 0)
idf = np.array(np.log((1.0*len(image_paths)+1) / (1.0*nbr_occurences + 1)), 'float32')
 
# Scale the features
# Standardize features by removing the mean and scaling to unit variance
# Scaler (stdSlr comes from the pickled file we imported)
test_features = stdSlr.transform(test_features)

true_class = [classes_names[i] for i in image_classes]

predictions = [classes_names[i] for i in clf.predict(test_features)]

print ("true_class =" + str(true_class))
print ("prediction =" + str(predictions))

def showconfusionmatrix(cm):
    pl.matshow(cm)
    pl.title('Confusion matrix')
    pl.colorbar()
    pl.show()

accuracy = accuracy_score(true_class, predictions)
print ("accuracy = ", accuracy)
cm = confusion_matrix(true_class, predictions)
print (cm)

showconfusionmatrix(cm)