{"cells":[{"metadata":{},"cell_type":"markdown","source":""},{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true},"cell_type":"code","source":"import json\nimport math\nimport os\n\nimport cv2\nfrom PIL import Image\nimport numpy as np\nfrom keras import layers\nfrom keras.applications import DenseNet121\nfrom keras.callbacks import Callback, ModelCheckpoint\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.optimizers import Adam\nimport matplotlib.pyplot as plt\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import cohen_kappa_score, accuracy_score\nimport scipy\nimport tensorflow as tf\nfrom tqdm import tqdm\n\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Set random seed for reproducibility."},{"metadata":{"trusted":true},"cell_type":"code","source":"np.random.seed(2019)\ntf.set_random_seed(2019)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loading & Exploration"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/aptos2019-blindness-detection/train.csv')\ntest_df = pd.read_csv('../input/aptos2019-blindness-detection/test.csv')\nprint(train_df.shape)\nprint(test_df.shape)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['diagnosis'].hist()\ntrain_df['diagnosis'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Displaying some Sample Images"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"def display_samples(df, columns=4, rows=3):\n    fig=plt.figure(figsize=(5*columns, 4*rows))\n\n    for i in range(columns*rows):\n        image_path = df.loc[i,'id_code']\n        image_id = df.loc[i,'diagnosis']\n        img = cv2.imread(f'../input/aptos2019-blindness-detection/train_images/{image_path}.png')\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n        \n        fig.add_subplot(rows, columns, i+1)\n        plt.title(image_id)\n        plt.imshow(img)\n    \n    plt.tight_layout()\n\ndisplay_samples(train_df)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Resize Images\n\nWe will resize the images to 224x224, then create a single numpy array to hold the data."},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_pad_width(im, new_shape, is_rgb=True):\n    pad_diff = new_shape - im.shape[0], new_shape - im.shape[1]\n    t, b = math.floor(pad_diff[0]/2), math.ceil(pad_diff[0]/2)\n    l, r = math.floor(pad_diff[1]/2), math.ceil(pad_diff[1]/2)\n    if is_rgb:\n        pad_width = ((t,b), (l,r), (0, 0))\n    else:\n        pad_width = ((t,b), (l,r))\n    return pad_width\n\ndef preprocess_image(image_path, desired_size=224):\n    im = Image.open(image_path)\n    im = im.resize((desired_size, )*2, resample=Image.LANCZOS)\n    \n    return im","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = train_df.shape[0]\nx_train = np.empty((N, 224, 224, 3), dtype=np.uint8)\n\nfor i, image_id in enumerate(tqdm(train_df['id_code'])):\n    x_train[i, :, :, :] = preprocess_image(\n        f'../input/aptos2019-blindness-detection/train_images/{image_id}.png'\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = test_df.shape[0]\nx_test = np.empty((N, 224, 224, 3), dtype=np.uint8)\n\nfor i, image_id in enumerate(tqdm(test_df['id_code'])):\n    x_test[i, :, :, :] = preprocess_image(\n        f'../input/aptos2019-blindness-detection/test_images/{image_id}.png'\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = pd.get_dummies(train_df['diagnosis']).values\n\nprint(x_train.shape)\nprint(y_train.shape)\nprint(x_test.shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Creating multilabels\n\nInstead of predicting a single label, we will change our target to be a multilabel problem; i.e., if the target is a certain class, then it encompasses all the classes before it. E.g. encoding a class 4 retinopathy would usually be `[0, 0, 0, 1]`, but in our case we will predict `[1, 1, 1, 1]`."},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train_multi = np.empty(y_train.shape, dtype=y_train.dtype)\ny_train_multi[:, 4] = y_train[:, 4]\n\nfor i in range(3, -1, -1):\n    y_train_multi[:, i] = np.logical_or(y_train[:, i], y_train_multi[:, i+1])\n\nprint(\"Original y_train:\", y_train.sum(axis=0))\nprint(\"Multilabel version:\", y_train_multi.sum(axis=0))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Now we can split it into a training and validation set."},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_val, y_train, y_val = train_test_split(\n    x_train, y_train_multi, \n    test_size=0.15, \n    random_state=2019\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Mixup & Data Generator\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"class MixupGenerator():\n    def __init__(self, X_train, y_train, batch_size=32, alpha=0.2, shuffle=True, datagen=None):\n        self.X_train = X_train\n        self.y_train = y_train\n        self.batch_size = batch_size\n        self.alpha = alpha\n        self.shuffle = shuffle\n        self.sample_num = len(X_train)\n        self.datagen = datagen\n\n    def __call__(self):\n        while True:\n            indexes = self.__get_exploration_order()\n            itr_num = int(len(indexes) // (self.batch_size * 2))\n\n            for i in range(itr_num):\n                batch_ids = indexes[i * self.batch_size * 2:(i + 1) * self.batch_size * 2]\n                X, y = self.__data_generation(batch_ids)\n\n                yield X, y\n\n    def __get_exploration_order(self):\n        indexes = np.arange(self.sample_num)\n\n        if self.shuffle:\n            np.random.shuffle(indexes)\n\n        return indexes\n\n    def __data_generation(self, batch_ids):\n        _, h, w, c = self.X_train.shape\n        l = np.random.beta(self.alpha, self.alpha, self.batch_size)\n        X_l = l.reshape(self.batch_size, 1, 1, 1)\n        y_l = l.reshape(self.batch_size, 1)\n\n        X1 = self.X_train[batch_ids[:self.batch_size]]\n        X2 = self.X_train[batch_ids[self.batch_size:]]\n        X = X1 * X_l + X2 * (1 - X_l)\n\n        if self.datagen:\n            for i in range(self.batch_size):\n                X[i] = self.datagen.random_transform(X[i])\n                X[i] = self.datagen.standardize(X[i])\n\n        if isinstance(self.y_train, list):\n            y = []\n\n            for y_train_ in self.y_train:\n                y1 = y_train_[batch_ids[:self.batch_size]]\n                y2 = y_train_[batch_ids[self.batch_size:]]\n                y.append(y1 * y_l + y2 * (1 - y_l))\n        else:\n            y1 = self.y_train[batch_ids[:self.batch_size]]\n            y2 = self.y_train[batch_ids[self.batch_size:]]\n            y = y1 * y_l + y2 * (1 - y_l)\n\n        return X, y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 32\n\ndef create_datagen():\n    return ImageDataGenerator(\n        zoom_range=0.15,  # set range for random zoom\n        # set mode for filling points outside the input boundaries\n        fill_mode='constant',\n        cval=0.,  # value used for fill_mode = \"constant\"\n        horizontal_flip=True,  # randomly flip images\n        vertical_flip=True,  # randomly flip images\n    )\n\n# Using original generator\ndata_generator = create_datagen().flow(x_train, y_train, batch_size=BATCH_SIZE, seed=2019)\n# Using Mixup\nmixup_generator = MixupGenerator(x_train, y_train, batch_size=BATCH_SIZE, alpha=0.2, datagen=create_datagen())()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Quadratic Weighted Kappa\n\nQuadratic Weighted Kappa (QWK, the greek letter $\\kappa$), also known as Cohen's Kappa, is the official evaluation metric. For our kernel, we will use a custom callback to monitor the score, and plot it at the end.\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"true_labels = np.array([1, 0, 1, 1, 0, 1])\npred_labels = np.array([1, 0, 0, 0, 0, 1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy_score(true_labels, pred_labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cohen_kappa_score(true_labels, pred_labels)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Creating keras callback for QWK"},{"metadata":{"trusted":true},"cell_type":"code","source":"class Metrics(Callback):\n    def on_train_begin(self, logs={}):\n        self.val_kappas = []\n\n    def on_epoch_end(self, epoch, logs={}):\n        X_val, y_val = self.validation_data[:2]\n        y_val = y_val.sum(axis=1) - 1\n        \n        y_pred = self.model.predict(X_val) > 0.5\n        y_pred = y_pred.astype(int).sum(axis=1) - 1\n\n        _val_kappa = cohen_kappa_score(\n            y_val,\n            y_pred, \n            weights='quadratic'\n        )\n\n        self.val_kappas.append(_val_kappa)\n\n        print(f\"val_kappa: {_val_kappa:.4f}\")\n        \n        if _val_kappa == max(self.val_kappas):\n            print(\"Validation Kappa has improved. Saving model.\")\n            self.model.save('model.h5')\n\n        return","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model: DenseNet-121"},{"metadata":{"trusted":true},"cell_type":"code","source":"densenet = DenseNet121(\n    weights='../input/densenet-keras/DenseNet-BC-121-32-no-top.h5',\n    include_top=False,\n    input_shape=(224,224,3)\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model():\n    model = Sequential()\n    model.add(densenet)\n    model.add(layers.GlobalAveragePooling2D())\n    model.add(layers.Dropout(0.5))\n    model.add(layers.Dense(5, activation='sigmoid'))\n    \n    model.compile(\n        loss='binary_crossentropy',\n        optimizer=Adam(lr=0.00005),\n        metrics=['accuracy']\n    )\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training & Evaluation"},{"metadata":{"trusted":true},"cell_type":"code","source":"kappa_metrics = Metrics()\n\nhistory = model.fit_generator(\n    data_generator,\n    steps_per_epoch=x_train.shape[0] / BATCH_SIZE,\n    epochs=15,\n    validation_data=(x_val, y_val),\n    callbacks=[kappa_metrics]\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open('history.json', 'w') as f:\n    json.dump(history.history, f)\n\nhistory_df = pd.DataFrame(history.history)\nhistory_df[['loss', 'val_loss']].plot()\nhistory_df[['acc', 'val_acc']].plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(kappa_metrics.val_kappas)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Find best threshold\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.load_weights('model.h5')\ny_val_pred = model.predict(x_val)\n\ndef compute_score_inv(threshold):\n    y1 = y_val_pred > threshold\n    y1 = y1.astype(int).sum(axis=1) - 1\n    y2 = y_val.sum(axis=1) - 1\n    score = cohen_kappa_score(y1, y2, weights='quadratic')\n    \n    return 1 - score\n\nsimplex = scipy.optimize.minimize(\n    compute_score_inv, 0.5, method='nelder-mead'\n)\n\nbest_threshold = simplex['x'][0]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submit"},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test = model.predict(x_test) > 0.5\ny_test = y_test.astype(int).sum(axis=1) - 1\n\ntest_df['diagnosis'] = y_test\ntest_df.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"}},"nbformat":4,"nbformat_minor":1}