AI2020_Project/garbageDumpSorting.py

#Creating training and test set
import os
import numpy as np
import shutil
#Feature descriptors
import cv2
import mahotas
#saving data
import h5py
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import MinMaxScaler
#classifier
from sklearn.ensemble import RandomForestClassifier
#other
import random
from models.Garbagetruck import GarbageTruck
from models.garbageDump import Dump

#https://www.kaggle.com/asdasdasasdas/garbage-classification - dataset


def createSets():
    if not path.exists('ClassificationGarbage/trainSet'):
        rootDir = 'ClassificationGarbage'
        typesDir = ['/cardboard', '/glass', '/metal', '/paper', '/plastic']
        testRatio = 0.2

        for cls in typesDir:
            os.makedirs(rootDir + '/trainSet' + cls)
            os.makedirs(rootDir + '/testSet' + cls)
            sourceDir = rootDir + cls
            allFileNames = os.listdir(sourceDir)
            np.random.shuffle(allFileNames)
            trainingFileNames, testFileNames = np.split(np.array(allFileNames), [int(len(allFileNames) * (1 - testRatio))])
            trainingFileNames = [sourceDir +'/' + name for name in trainingFileNames.tolist()]
            testFileNames = [sourceDir +'/' + name for name in testFileNames.tolist()]
            print(cls + ':')
            print('Total images: ', len(allFileNames))
            print('Training: ', len(trainingFileNames))
            print('Testing: ', len(testFileNames))

            for name in trainingFileNames:
                shutil.copy(name, rootDir +'/trainSet' + cls)
            for name in testFileNames:
                shutil.copy(name, rootDir +'/testSet' + cls)
            print("Images copied.")


def processTrainData():
    trainTypes = os.listdir('ClassificationGarbage/trainSet')
    trainTypes.sort()
    features = []
    types = []
    trainDir = 'ClassificationGarbage/trainSet/'
    size = tuple((500, 500))

    #process data

    for type in trainTypes:
        dir = os.path.join(trainDir, type)
        currentType = type
        print("Processing " + type + "...")
        for imagename in os.listdir(dir):
            file = dir + "/" + imagename
            image = cv2.imread(file)
            image = cv2.resize(image, size)
            #Global features
            huMoments = hu_moments(image)
            hara = haralick(image)
            histo = histogram(image)
            allFeatures = np.hstack([histo, hara, huMoments])
            types.append(currentType)
            features.append(allFeatures)
        print("Done.")
    print("All processed.")
    print("Training...")

    #save data

    h5Data = 'output/data.h5'
    h5Types = 'output/types.h5'

    targetNames = np.unique(types)
    le = LabelEncoder()
    target = le.fit_transform(types)
    scaler = MinMaxScaler(feature_range=(0, 1))
    rescaledFeatures = scaler.fit_transform(features)

    fileData = h5py.File(h5Data, 'w')
    fileData.create_dataset('dataset_1', data=np.array(rescaledFeatures))
    fileTypes = h5py.File(h5Types, 'w')
    fileTypes.create_dataset('dataset_1', data=np.array(target))
    fileData.close()
    fileTypes.close()


def processTestData():
    trainTypes = os.listdir('ClassificationGarbage/trainSet')
    trainTypes.sort()
    testDir = 'ClassificationGarbage/testSet/'
    size = tuple((500, 500))
    testTypes = []
    testFeatures = []
    print("Testing...")

    #process data

    for type in trainTypes:
        dir = os.path.join(testDir, type)
        currentType = type
        for imagename in os.listdir(dir):
            file = dir + "/" + imagename
            image = cv2.imread(file)
            image = cv2.resize(image, size)
            #Global features
            huMoments = hu_moments(image)
            hara = haralick(image)
            histo = histogram(image)
            allFeatures = np.hstack([histo, hara, huMoments])
            testTypes.append(currentType)
            testFeatures.append(allFeatures)

    #save data

    h5TestData = 'output/testdata.h5'
    h5TestTypes = 'output/testtypes.h5'

    targetNames = np.unique(testTypes)
    le = LabelEncoder()
    target = le.fit_transform(testTypes)
    scaler = MinMaxScaler(feature_range=(0, 1))
    rescaledFeatures = scaler.fit_transform(testFeatures)

    fileTestData = h5py.File(h5TestData, 'w')
    fileTestData.create_dataset('dataset_1', data=np.array(rescaledFeatures))
    fileTestTypes = h5py.File(h5TestTypes, 'w')
    fileTestTypes.create_dataset('dataset_1', data=np.array(target))
    fileTestData.close()
    fileTestTypes.close()




def trainAndTest():
    h5Data = 'output/data.h5'
    h5Types = 'output/types.h5'
    h5TestData = 'output/testdata.h5'
    h5TestTypes = 'output/testtypes.h5'

    #import train data
    fileData = h5py.File(h5Data, 'r')
    fileTypes = h5py.File(h5Types, 'r')
    features = fileData['dataset_1']
    types = fileTypes['dataset_1']
    allFeatures = np.array(features)
    allTypes = np.array(types)
    fileData.close()
    fileTypes.close()

    # create model
    clf  = RandomForestClassifier(n_estimators=100, random_state=9)
    clf.fit(allFeatures, allTypes)

    #import test data
    fileTestData = h5py.File(h5TestData, 'r')
    fileTestTypes = h5py.File(h5TestTypes, 'r')
    features = fileTestData['dataset_1']
    types = fileTestTypes['dataset_1']
    allFeatures = np.array(features)
    allTypes = np.array(types)
    fileTestData.close()
    fileTestTypes.close()

    #Rfc score
    print("Random Forest Classifier score:")
    print(clf.score(allFeatures, allTypes))
    return clf


#global features

def hu_moments(image):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    moments = cv2.moments(gray)
    huMoments = cv2.HuMoments(moments).flatten()
    return huMoments

def haralick(image):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    haralick = mahotas.features.haralick(gray).mean(axis=0)
    return haralick

def histogram(image, mask=None):
    image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
    hist  = cv2.calcHist([image], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256])
    cv2.normalize(hist, hist)
    histogram = hist.flatten()
    return histogram


#Test one image
def classifyImage(file, clf):
    size = tuple((500, 500))
    types = os.listdir('ClassificationGarbage/testSet')
    types.sort()
    image = cv2.imread(file)
    image = cv2.resize(image, size)
    #Global features
    huMoments = hu_moments(image)
    hara   = haralick(image)
    histo  = histogram(image)
    allFeatures = np.hstack([histo, hara, huMoments])
    features = allFeatures.reshape(1,-1)
    prediction = clf.predict(features)[0]
    return types[prediction]


#At the garbage dump
def sortDump(cardboard, glass, metal, paper, plastic, clf, GT, dump):
    testDir = 'ClassificationGarbage/testSet'
    testTypes = os.listdir(testDir)
    testTypes.sort()
    noGarbage = [cardboard, glass, metal, paper, plastic]
    for i in range(len(testTypes)):
        print("Among " + testTypes[i] + ", we found: ")
        for j in range(0, noGarbage[i]):
            image = random.choice(os.listdir(testDir + '/' + testTypes[i]))
            file = testDir + '/' + testTypes[i] + "/"+ image
            prediction = classifyImage(file, clf)
            print(prediction)
            GT.empty(testTypes[i])
            dump.addGarbage(prediction)