# data analysis and wranglingimport numpy as npimport pandas as pdimport osimport random
# visualizationimport matplotlib.pyplot as pltfrom PIL import Image# machine learningfrom keras.models import Sequentialfrom keras.layers import Densefrom tensorflow.keras.optimizers import Adamfrom keras.utils.np_utils import to_categoricalfrom keras.layers import Dropout, Flattenfrom keras.layers.convolutional import Conv2D, MaxPooling2Dimport cv2from sklearn.model_selection import train_test_splitfrom keras.preprocessing.image import ImageDataGenerator

# Importing of the Imagescount = 0images = []classNo = []myList = os.listdir(path)print("Total Classes Detected:",len(myList))noOfClasses=len(myList)print("Importing Classes.....")for x in range (0,len(myList)):    myPicList = os.listdir(path+"/"+str(count))    for y in myPicList:        curImg = cv2.imread(path+"/"+str(count)+"/"+y)        curImg = cv2.resize(curImg, (30, 30))        images.append(curImg)        classNo.append(count)    print(count, end =" ")    count +=1print(" ")images = np.array(images)classNo = np.array(classNo)

# Split DataX_train, X_test, y_train, y_test = train_test_split(images, classNo, test_size=testRatio)X_train, X_validation, y_train, y_validation = train_test_split(X_train, y_train, test_size=validationRatio)

# DISPLAY SOME SAMPLES IMAGES OF ALL THE CLASSESnum_of_samples = []cols = 5num_classes = noOfClassesfig, axs = plt.subplots(nrows=num_classes, ncols=cols, figsize=(5, 300))fig.tight_layout()for i in range(cols):    for j,row in data.iterrows():        x_selected = X_train[y_train == j]        axs[j][i].imshow(x_selected[random.randint(0, len(x_selected)- 1), :, :], cmap=plt.get_cmap("gray"))        axs[j][i].axis("off")        if i == 2:            axs[j][i].set_title(str(j)+ "-"+row["Name"])            num_of_samples.append(len(x_selected))

# DISPLAY A BAR CHART SHOWING NO OF SAMPLES FOR EACH CATEGORYprint(num_of_samples)plt.figure(figsize=(12, 4))plt.bar(range(0, num_classes), num_of_samples)plt.title("Distribution of the training dataset")plt.xlabel("Class number")plt.ylabel("Number of images")plt.show()

# PREPROCESSING THE IMAGESdef grayscale(img):    img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)    return img
def equalize(img):    img =cv2.equalizeHist(img)    return img
def preprocessing(img):    img = grayscale(img)     # CONVERT TO GRAYSCALE    img = equalize(img)      # STANDARDIZE THE LIGHTING IN AN IMAGE    img = img/255            # TO NORMALIZE VALUES BETWEEN 0 AND 1 INSTEAD OF 0 TO 255    return img
X_train=np.array(list(map(preprocessing,X_train)))  # TO IRETATE AND PREPROCESS ALL IMAGESX_validation=np.array(list(map(preprocessing,X_validation)))X_test=np.array(list(map(preprocessing,X_test)))

#AUGMENTATAION OF IMAGES: TO MAKEIT MORE GENERICdataGen= ImageDataGenerator(width_shift_range=0.1,   # 0.1 = 10%     IF MORE THAN 1 E.G 10 THEN IT REFFERS TO NO. OF  PIXELS EG 10 PIXELS                            height_shift_range=0.1,                            zoom_range=0.2,  # 0.2 MEANS CAN GO FROM 0.8 TO 1.2                            shear_range=0.1,  # MAGNITUDE OF SHEAR ANGLE                            rotation_range=10)  # DEGREESdataGen.fit(X_train)batches= dataGen.flow(X_train,y_train,batch_size=20)  # REQUESTING DATA GENRATOR TO GENERATE IMAGES  BATCH SIZE = NO. OF IMAGES CREAED EACH TIME ITS CALLEDX_batch,y_batch = next(batches)

y_train = to_categorical(y_train,noOfClasses)y_validation = to_categorical(y_validation,noOfClasses)y_test = to_categorical(y_test,noOfClasses)

def myModel():    model = Sequential()    model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu', input_shape=X_train.shape[1:]))    model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))    model.add(MaxPooling2D(pool_size=(2, 2)))    model.add(Dropout(rate=0.25))    model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))    model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))    model.add(MaxPooling2D(pool_size=(2, 2)))    model.add(Dropout(rate=0.25))    model.add(Flatten())    model.add(Dense(256, activation='relu'))    model.add(Dropout(rate=0.5))    model.add(Dense(43, activation='softmax'))    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])    return model

# TRAINmodel = myModel()print(model.summary())history = model.fit(X_train, y_train, batch_size=batch_size_val, epochs=epochs_val, validation_data=(X_validation,y_validation))

#PLOTplt.figure(1)plt.plot(history.history['loss'])plt.plot(history.history['val_loss'])plt.legend(['training','validation'])plt.title('loss')plt.xlabel('epoch')plt.figure(2)plt.plot(history.history['accuracy'])plt.plot(history.history['val_accuracy'])plt.legend(['training','validation'])plt.title('Acurracy')plt.xlabel('epoch')plt.show()score =model.evaluate(X_test,y_test,verbose=0)print('Test Score:',score[0])print('Test Accuracy:',score[1])

#testing accuracy on test datasetfrom sklearn.metrics import accuracy_score
y_test = pd.read_csv('Test.csv')labels = y_test["ClassId"].valuesimgs = y_test["Path"].valuesdata=[]for img in imgs:    image = Image.open(img)    image = image.resize((30,30))    data.append(np.array(image))X_test=np.array(data)X_test=np.array(list(map(preprocessing,X_test)))predict_x=model.predict(X_test) pred=np.argmax(predict_x,axis=1)print(accuracy_score(labels, pred))

model.save("CNN_model_3.h5")