{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport pickle\nimport os\n\nfrom sklearn.model_selection import train_test_split\n\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow import keras\nfrom tensorflow.keras.layers import * \n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras import backend as k\n\nimport os\nos.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' ","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('../input/histopathologic-cancer-detection/train_labels.csv', dtype=str)\nprint(train.shape)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.id = train.id + '.tif'\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"(train.label.value_counts() / len(train)).to_frame().sort_index().T","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_path = \"../input/histopathologic-cancer-detection/train\"\n\nsample = train.sample(n=16).reset_index()\n\nplt.figure(figsize=(6,6))\n\nfor i, row in sample.iterrows():\n\n    img = mpimg.imread(f'../input/histopathologic-cancer-detection/train/{row.id}')    \n    label = row.label\n\n    plt.subplot(4,4,i+1)\n    plt.imshow(img)\n    plt.text(0, -5, f'Class {label}', color='k')\n        \n    plt.axis('off')\n\nplt.tight_layout()\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df, valid_df = train_test_split(train, test_size=0.2, random_state=1, stratify=train.label)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1/255)\nvalidation_datagen = ImageDataGenerator(rescale=1/255)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BATCH_SIZE = 64\n\ntrain_loader = train_datagen.flow_from_dataframe(\n    dataframe = valid_df,\n    directory = train_path,\n    x_col = 'id',\n    y_col = 'label',\n    batch_size = BATCH_SIZE,\n    seed = 1,\n    shuffle = True,\n    class_mode = 'categorical',\n    target_size = (96,96)\n)\n\nvalid_loader = train_datagen.flow_from_dataframe(\n    dataframe = valid_df,\n    directory = train_path,\n    x_col = 'id',\n    y_col = 'label',\n    batch_size = BATCH_SIZE,\n    seed = 1,\n    shuffle = True,\n    class_mode = 'categorical',\n    target_size = (96,96)\n)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"TR_STEPS = len(train_loader)\nVA_STEPS = len(valid_loader)\n\nprint(TR_STEPS)\nprint(VA_STEPS)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.random.seed(1)\ntf.random.set_seed(1)\n\ncnn = Sequential([\n    Cropping2D(cropping=((32, 32), (32, 32)), input_shape=(96,96,3)),\n    Conv2D(16, (3,3), activation = 'relu', padding = 'same'),\n    Conv2D(16, (3,3), activation = 'relu', padding = 'same'),\n    MaxPooling2D(2,2),\n    Dropout(0.5),\n    BatchNormalization(),\n\n    Conv2D(64, (3,3), activation = 'relu', padding = 'same'),\n    Conv2D(64, (3,3), activation = 'relu', padding = 'same'),\n    MaxPooling2D(2,2),\n    Dropout(0.5),\n    BatchNormalization(),\n    \n    Conv2D(128, (3,3), activation = 'relu', padding = 'same'),\n    Conv2D(128, (3,3), activation = 'relu', padding = 'same'),\n    MaxPooling2D(2,2),\n    Dropout(0.5),\n    BatchNormalization(),\n\n    Flatten(),\n    \n    Dense(16, activation='relu'),\n    Dropout(0.5),\n    Dense(8, activation='relu'),\n    Dropout(0.5),\n    BatchNormalization(),\n    Dense(2, activation='softmax')\n])\n\ncnn.summary()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"opt = tf.keras.optimizers.Adam(0.001)\ncnn.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy', tf.keras.metrics.AUC()])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time \n\nh1 = cnn.fit(\n    x = train_loader, \n    steps_per_epoch = TR_STEPS, \n    epochs = 40,\n    validation_data = valid_loader, \n    validation_steps = VA_STEPS, \n    verbose = 1\n)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = h1.history\nprint(history.keys())","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"epoch_range = range(1, len(history['loss'])+1)\n\nplt.figure(figsize=[14,4])\nplt.subplot(1,3,1)\nplt.plot(epoch_range, history['loss'], label='Training')\nplt.plot(epoch_range, history['val_loss'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Loss'); plt.title('Loss')\nplt.legend()\nplt.subplot(1,3,2)\nplt.plot(epoch_range, history['accuracy'], label='Training')\nplt.plot(epoch_range, history['val_accuracy'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Accuracy'); plt.title('Accuracy')\nplt.legend()\nplt.subplot(1,3,3)\nplt.plot(epoch_range, history['auc'], label='Training')\nplt.plot(epoch_range, history['val_auc'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('AUC'); plt.title('AUC')\nplt.legend()\nplt.tight_layout()\nplt.show()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tf.keras.backend.set_value(cnn.optimizer.learning_rate, 0.0001)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time \n\nh2 = cnn.fit(\n    x = train_loader, \n    steps_per_epoch = TR_STEPS, \n    epochs = 30,\n    validation_data = valid_loader, \n    validation_steps = VA_STEPS, \n    verbose = 1\n)\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for k in history.keys():\n    history[k] += h2.history[k]\n\nepoch_range = range(1, len(history['loss'])+1)\n\nplt.figure(figsize=[14,4])\nplt.subplot(1,3,1)\nplt.plot(epoch_range, history['loss'], label='Training')\nplt.plot(epoch_range, history['val_loss'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Loss'); plt.title('Loss')\nplt.legend()\nplt.subplot(1,3,2)\nplt.plot(epoch_range, history['accuracy'], label='Training')\nplt.plot(epoch_range, history['val_accuracy'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Accuracy'); plt.title('Accuracy')\nplt.legend()\nplt.subplot(1,3,3)\nplt.plot(epoch_range, history['auc'], label='Training')\nplt.plot(epoch_range, history['val_auc'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('AUC'); plt.title('AUC')\nplt.legend()\nplt.tight_layout()\nplt.show()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tf.keras.backend.set_value(cnn.optimizer.learning_rate, 0.0001)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time \n\nh3 = cnn.fit(\n    x = train_loader, \n    steps_per_epoch = TR_STEPS, \n    epochs = 20,\n    validation_data = valid_loader, \n    validation_steps = VA_STEPS, \n    verbose = 1\n)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for k in history.keys():\n    history[k] += h3.history[k]\n\nepoch_range = range(1, len(history['loss'])+1)\n\nplt.figure(figsize=[14,4])\nplt.subplot(1,3,1)\nplt.plot(epoch_range, history['loss'], label='Training')\nplt.plot(epoch_range, history['val_loss'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Loss'); plt.title('Loss')\nplt.legend()\nplt.subplot(1,3,2)\nplt.plot(epoch_range, history['accuracy'], label='Training')\nplt.plot(epoch_range, history['val_accuracy'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('Accuracy'); plt.title('Accuracy')\nplt.legend()\nplt.subplot(1,3,3)\nplt.plot(epoch_range, history['auc'], label='Training')\nplt.plot(epoch_range, history['val_auc'], label='Validation')\nplt.xlabel('Epoch'); plt.ylabel('AUC'); plt.title('AUC')\nplt.legend()\nplt.tight_layout()\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cnn.save('HCDv01.h5')\npickle.dump(history, open(f'HCDv01.pkl', 'wb'))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"test = pd.read_csv('../input/histopathologic-cancer-detection/sample_submission.csv')\n\nprint('Test Set Size:', test.shape)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test['filename'] = test.id + '.tif'","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_path = \"../input/histopathologic-cancer-detection/test\"\nprint('Test Images:', len(os.listdir(test_path)))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BATCH_SIZE = 64\n\ntest_datagen = ImageDataGenerator(rescale=1/255)\n\ntest_loader = test_datagen.flow_from_dataframe(\n    dataframe = test,\n    directory = test_path,\n    x_col = 'filename',\n    batch_size = BATCH_SIZE,\n    shuffle = False,\n    class_mode = None,\n    target_size = (96,96)\n)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_probs = cnn.predict(test_loader)\nprint(test_probs.shape)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(len(test_loader))\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(test_probs[:10,].round(2))\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_pred = np.argmax(test_probs, axis=1)\nprint(test_pred[:10])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('../input/histopathologic-cancer-detection/sample_submission.csv')\nsubmission.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.label = test_probs[:,1]\nsubmission.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', header=True, index=False)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}