{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import cv2\n\nX_img = []\ny_p = []\ndef create_training_set(label, path):\n    img = cv2.imread(path, cv2.IMREAD_COLOR)\n    img = cv2.resize(img, (150,150))\n    X_img.append(np.array(img))\n    y_p.append(str(label))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('../input/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = df_train['id_code']\ny = df_train['diagnosis']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\n\nTRAIN_DIR = '../input/train_images'\nfor id_code, diagnosis in tqdm(zip(X,y)):\n    path = os.path.join(TRAIN_DIR, '{}.png'.format(id_code))\n    create_training_set(diagnosis, path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils import to_categorical\n\nY = to_categorical(y_p)\nX= np.array(X_img)\nX=X/255","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Feature Extraction"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\nfeat_extraction = ImageDataGenerator(\n    featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True)\n\n# compute quantities required for featurewise normalization\n# (std, mean, and principal components if ZCA whitening is applied)\nfeat_extraction.fit(X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX_train, X_valid, Y_train, Y_valid = train_test_split(X, Y, test_size=0.2, random_state=22)\n\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y.hist()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#Modelling"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, BatchNormalization, GlobalAveragePooling2D\nfrom keras.layers import Dropout, Flatten, Dense, GaussianDropout\nfrom keras.constraints import maxnorm\nfrom keras import regularizers, optimizers\n\nmodel = Sequential()\n\nmodel.add(Conv2D(filters=16, kernel_size=2, padding='same', activation='relu', input_shape=(150,150,3)))\nmodel.add(MaxPooling2D(pool_size=2))\nmodel.add(Conv2D(filters=32, kernel_size=2, padding='same', activation='relu'))\nmodel.add(MaxPooling2D(pool_size=2))\nmodel.add(Conv2D(filters=64, kernel_size=2, padding='same', activation='relu'))\nmodel.add(MaxPooling2D(pool_size=2))\nmodel.add(GlobalAveragePooling2D())\n\nmodel.add(Dense(5, activation='softmax'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import Adam, SGD, Adagrad, Adadelta, RMSprop\n\nmodel.compile(optimizer= Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size =50\nepochs= 50","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import ModelCheckpoint\n\ncheckpointer =  ModelCheckpoint(filepath= 'CNN_keras.hdf5', verbose=1, save_best_only=True)\n\n#model_history = model.fit_generator(feat_extraction.flow(X_train, Y_train, batch_size=batch_size),\n #        epochs= epochs, validation_data=feat_extraction.flow(X_valid, Y_valid, batch_size= batch_size),\n  #       callbacks= [checkpointer], verbose=1, steps_per_epoch=X_train.shape[0]//batch_size, validation_steps=X_train.shape[0]//batch_size )\n\n\nmodel_history=model.fit(X_train, Y_train, \n          validation_data=(X_valid, Y_valid),\n          epochs=epochs, batch_size=batch_size, callbacks=[checkpointer], verbose=1)\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n# list all data in history\nprint(model_history.history.keys())\n# summarize history for accuracy\nplt.plot(model_history.history['acc'])\nplt.plot(model_history.history['val_acc'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'validation'], loc='upper left')\nplt.show()\n# summarize history for loss\nplt.plot(model_history.history['loss'])\nplt.plot(model_history.history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'validation'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir('../input/test_images/')[0:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_image = cv2.imread('../input/test_images/3d4d693f7983.png', cv2.IMREAD_COLOR)\ntest_image = cv2.resize(test_image, (150,150))\nimport matplotlib.pyplot as plt\n\nplt.imshow(test_image)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_X = np.array(test_image)\ntest_X = test_X/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_test= model.predict(np.expand_dims(test_X,axis=0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/test.csv')\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ids = test_df['id_code']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = []\ndef create_test_set(path):\n    img = cv2.imread(path,cv2.IMREAD_COLOR)\n    img = cv2.resize(img, (150,150))\n\n    test_images.append(np.array(img))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\nfor id_code in tqdm(test_ids):\n    path = os.path.join('../input/test_images','{}.png'.format(id_code))\n    create_test_set(path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import load_model\nmodel=load_model('CNN_keras.hdf5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_X=np.array(test_images)\ntest_X=test_X/255\nfeat_extraction.fit(test_X)\npredictions=model.predict(test_X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = np.argmax(predictions, axis=1)\npred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.unique(pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_cnn = pd.DataFrame({'id_code' : test_ids , 'diagnosis' : pred})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_cnn.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_cnn.to_csv(\"submission.csv\",index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}