{"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":"markdown","source":"# Histopathic Cancer Detection (HCD)\n### Taylor Kern","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2022-04-05T19:43:13.752757Z","iopub.execute_input":"2022-04-05T19:43:13.753173Z","iopub.status.idle":"2022-04-05T19:43:19.774107Z","shell.execute_reply.started":"2022-04-05T19:43:13.753089Z","shell.execute_reply":"2022-04-05T19:43:19.773307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Helper Functions","metadata":{}},{"cell_type":"code","source":"def merge_history(hlist):\n    history = {}\n    for k in hlist[0].history.keys():\n        history[k] = sum([h.history[k] for h in hlist], [])\n    return history\n\ndef vis_training(h, start=1):\n    epoch_range = range(start, len(h['loss'])+1)\n    s = slice(start-1, None)\n\n    plt.figure(figsize=[14,4])\n\n    n = int(len(h.keys()) / 2)\n\n    for i in range(n):\n        k = list(h.keys())[i]\n        plt.subplot(1,n,i+1)\n        plt.plot(epoch_range, h[k][s], label='Training')\n        plt.plot(epoch_range, h['val_' + k][s], label='Validation')\n        plt.xlabel('Epoch'); plt.ylabel(k); plt.title(k)\n        plt.grid()\n        plt.legend()\n\n    plt.tight_layout()\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:19.777775Z","iopub.execute_input":"2022-04-05T19:43:19.779015Z","iopub.status.idle":"2022-04-05T19:43:19.786842Z","shell.execute_reply.started":"2022-04-05T19:43:19.778125Z","shell.execute_reply":"2022-04-05T19:43:19.786261Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load Training DataFrame","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('../input/histopathologic-cancer-detection/train_labels.csv', dtype=str)\nprint(train.shape)","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:19.788111Z","iopub.execute_input":"2022-04-05T19:43:19.78858Z","iopub.status.idle":"2022-04-05T19:43:20.219363Z","shell.execute_reply.started":"2022-04-05T19:43:19.788546Z","shell.execute_reply":"2022-04-05T19:43:20.218564Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:20.221442Z","iopub.execute_input":"2022-04-05T19:43:20.221689Z","iopub.status.idle":"2022-04-05T19:43:20.242628Z","shell.execute_reply.started":"2022-04-05T19:43:20.221655Z","shell.execute_reply":"2022-04-05T19:43:20.241775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.id = train.id + '.tif'","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:20.244118Z","iopub.execute_input":"2022-04-05T19:43:20.24439Z","iopub.status.idle":"2022-04-05T19:43:20.295395Z","shell.execute_reply.started":"2022-04-05T19:43:20.244354Z","shell.execute_reply":"2022-04-05T19:43:20.294606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:20.296786Z","iopub.execute_input":"2022-04-05T19:43:20.297045Z","iopub.status.idle":"2022-04-05T19:43:20.307002Z","shell.execute_reply.started":"2022-04-05T19:43:20.297011Z","shell.execute_reply":"2022-04-05T19:43:20.306001Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Label Distribution","metadata":{}},{"cell_type":"code","source":"(train.label.value_counts() / len(train)).to_frame().sort_index().T","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:20.308603Z","iopub.execute_input":"2022-04-05T19:43:20.308896Z","iopub.status.idle":"2022-04-05T19:43:20.347458Z","shell.execute_reply.started":"2022-04-05T19:43:20.30886Z","shell.execute_reply":"2022-04-05T19:43:20.346148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Extract Images","metadata":{}},{"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":{"iopub.status.busy":"2022-04-05T19:43:20.348956Z","iopub.execute_input":"2022-04-05T19:43:20.349494Z","iopub.status.idle":"2022-04-05T19:43:21.166355Z","shell.execute_reply.started":"2022-04-05T19:43:20.349456Z","shell.execute_reply":"2022-04-05T19:43:21.164615Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training and Validation Sets","metadata":{}},{"cell_type":"code","source":"train_df, valid_df = train_test_split(train, test_size=0.2, random_state=1, stratify=train.label)","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:21.167382Z","iopub.execute_input":"2022-04-05T19:43:21.167596Z","iopub.status.idle":"2022-04-05T19:43:21.465865Z","shell.execute_reply.started":"2022-04-05T19:43:21.167566Z","shell.execute_reply":"2022-04-05T19:43:21.465135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Data Generators","metadata":{}},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1/255)\nvalidation_datagen = ImageDataGenerator(rescale=1/255)","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:43:21.468398Z","iopub.execute_input":"2022-04-05T19:43:21.468658Z","iopub.status.idle":"2022-04-05T19:43:21.473378Z","shell.execute_reply.started":"2022-04-05T19:43:21.468623Z","shell.execute_reply":"2022-04-05T19:43:21.472362Z"},"trusted":true},"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":{"iopub.status.busy":"2022-04-05T19:43:21.474872Z","iopub.execute_input":"2022-04-05T19:43:21.475194Z","iopub.status.idle":"2022-04-05T19:45:09.768035Z","shell.execute_reply.started":"2022-04-05T19:43:21.475159Z","shell.execute_reply":"2022-04-05T19:45:09.767267Z"},"trusted":true},"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":{"iopub.status.busy":"2022-04-05T19:45:09.769366Z","iopub.execute_input":"2022-04-05T19:45:09.769806Z","iopub.status.idle":"2022-04-05T19:45:09.775214Z","shell.execute_reply.started":"2022-04-05T19:45:09.769758Z","shell.execute_reply":"2022-04-05T19:45:09.774491Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load Base Model","metadata":{}},{"cell_type":"code","source":"base_model = tf.keras.applications.ResNet50(\n    input_shape=(96,96,3), \n    include_top=False, \n    weights='imagenet'\n)\n\nbase_model.trainable = False\n\nbase_model.summary()","metadata":{"execution":{"iopub.status.busy":"2022-04-05T19:45:09.776583Z","iopub.execute_input":"2022-04-05T19:45:09.777049Z","iopub.status.idle":"2022-04-05T19:45:14.212338Z","shell.execute_reply.started":"2022-04-05T19:45:09.777008Z","shell.execute_reply":"2022-04-05T19:45:14.211629Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Build and Train","metadata":{}},{"cell_type":"code","source":"np.random.seed(1)\ntf.random.set_seed(1)\n\ncnn = Sequential([\n    base_model,\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":{"iopub.status.busy":"2022-04-05T19:45:14.213343Z","iopub.execute_input":"2022-04-05T19:45:14.213971Z","iopub.status.idle":"2022-04-05T19:45:14.647066Z","shell.execute_reply.started":"2022-04-05T19:45:14.213916Z","shell.execute_reply":"2022-04-05T19:45:14.64627Z"},"trusted":true},"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":{"iopub.status.busy":"2022-04-05T19:45:14.648237Z","iopub.execute_input":"2022-04-05T19:45:14.648491Z","iopub.status.idle":"2022-04-05T19:45:14.67108Z","shell.execute_reply.started":"2022-04-05T19:45:14.648456Z","shell.execute_reply":"2022-04-05T19:45:14.670389Z"},"trusted":true},"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":{"iopub.status.busy":"2022-04-05T19:45:14.672327Z","iopub.execute_input":"2022-04-05T19:45:14.672555Z","iopub.status.idle":"2022-04-05T19:47:32.981918Z","shell.execute_reply.started":"2022-04-05T19:45:14.67252Z","shell.execute_reply":"2022-04-05T19:47:32.98122Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = merge_history([h1])\nvis_training(history)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Fine Tuning","metadata":{}},{"cell_type":"code","source":"base_model.trainable = True\nk.set_value(cnn.optimizer.learning_rate, 0.00001)\ncnn.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy', tf.keras.metrics.AUC()])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cnn.summary()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train 2","metadata":{}},{"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)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"h2.history['auc'] = h2.history['auc_1']\nh2.history['val_auc'] = h2.history['val_auc_1']","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = merge_history([h1, h2])\nvis_training(history, start=10)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training 3","metadata":{}},{"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":"h3.history['auc'] = h3.history['auc_1'] \nh3.history['val_auc'] = h3.history['val_auc_1'] ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = merge_history([h1, h2, h3])\nvis_training(history, start=10)","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))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(test_probs[:10,].round(2))","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":"markdown","source":"# Prepare Submission","metadata":{}},{"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":[]}]}