{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Import Packages"},{"metadata":{"trusted":true},"cell_type":"code","source":"from glob import glob\nfrom mpl_toolkits.mplot3d.art3d import Poly3DCollection\nimport scipy.ndimage\nfrom skimage import morphology\nfrom skimage import measure\nfrom skimage.transform import resize\nfrom sklearn.cluster import KMeans\nfrom plotly import __version__\nfrom plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot\nfrom plotly.tools import FigureFactory as FF\nfrom plotly.graph_objs import *\n","execution_count":null,"outputs":[]},{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport seaborn as sns\nimport os\nimport gc\nimport time\nfrom IPython.display import clear_output\nfrom tensorflow.keras.models import load_model\nfrom tensorflow.keras.callbacks import ModelCheckpoint as MC\nfrom tensorflow.keras import backend as K\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n\nroot = '/kaggle/input/rsna-str-pulmonary-embolism-detection'\nfor item in os.listdir(root):\n    path = os.path.join(root, item)\n    if os.path.isfile(path):\n        print(path)\n\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"print('Reading train data...')\ntrain = pd.read_csv(\"../input/rsna-str-pulmonary-embolism-detection/train.csv\")\nprint(train.shape)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Reading test data...')\ntest = pd.read_csv(\"../input/rsna-str-pulmonary-embolism-detection/test.csv\")\nprint(test.shape)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Reading sample data...')\nss = pd.read_csv(\"../input/rsna-str-pulmonary-embolism-detection/sample_submission.csv\")\nprint(ss.shape)\nss.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import vtk\nfrom vtk.util import numpy_support\nimport cv2\n\nreader = vtk.vtkDICOMImageReader()\ndef get_img(path):\n    reader.SetFileName(path)\n    reader.Update()\n    _extent = reader.GetDataExtent()\n    ConstPixelDims = [_extent[1]-_extent[0]+1, _extent[3]-_extent[2]+1, _extent[5]-_extent[4]+1]\n\n    ConstPixelSpacing = reader.GetPixelSpacing()\n    imageData = reader.GetOutput()\n    pointData = imageData.GetPointData()\n    arrayData = pointData.GetArray(0)\n    ArrayDicom = numpy_support.vtk_to_numpy(arrayData)\n    ArrayDicom = ArrayDicom.reshape(ConstPixelDims, order='F')\n    ArrayDicom = cv2.resize(ArrayDicom,(512,512))\n    return ArrayDicom","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pydicom\ndpath = \"../input/rsna-str-pulmonary-embolism-detection/train/00102474a2db/c1a6d49ce580\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_scan(path):\n    slices = [pydicom.read_file(path + '/' + s) for s in os.listdir(path)]\n    slices.sort(key = lambda x: int(x.InstanceNumber))\n    try:\n        slice_thickness = np.abs(slices[0].ImagePositionPatient[2] - slices[1].ImagePositionPatient[2])\n    except:\n        slice_thickness = np.abs(slices[0].SliceLocation - slices[1].SliceLocation)\n        \n    for s in slices:\n        s.SliceThickness = slice_thickness\n        \n    return slices\n\ndef get_pixels_hu(scans):\n    image = np.stack([s.pixel_array for s in scans])\n    # Convert to int16 (from sometimes int16), \n    # should be possible as values should always be low enough (<32k)\n    image = image.astype(np.int16)\n\n    # Set outside-of-scan pixels to 1\n    # The intercept is usually -1024, so air is approximately 0\n    image[image == -2000] = 0\n    \n    # Convert to Hounsfield units (HU)\n    intercept = scans[0].RescaleIntercept\n    slope = scans[0].RescaleSlope\n    \n    if slope != 1:\n        image = slope * image.astype(np.float64)\n        image = image.astype(np.int16)\n        \n    image += np.int16(intercept)\n    \n    return np.array(image, dtype=np.int16)\n\nid=0\npatient = load_scan(dpath)\nimgs = get_pixels_hu(patient)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output_path = working_path = \"../working/\"\nnp.save(output_path + \"fullimages_%d.npy\" % (id), imgs)\nimport matplotlib.pyplot as plt\nfile_used=output_path+\"fullimages_%d.npy\" % id\nimgs_to_process = np.load(file_used).astype(np.float64) \n\nplt.hist(imgs_to_process.flatten(), bins=50, color='c')\nplt.xlabel(\"Hounsfield Units (HU)\")\nplt.ylabel(\"Frequency\")\nplt.show()\nplt.savefig(\"one.jpg\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"id = 0\nimgs_to_process = np.load(output_path+'fullimages_{}.npy'.format(id))\n\ndef sample_stack(stack, rows=6, cols=6, start_with=10, show_every=3):\n    fig,ax = plt.subplots(rows,cols,figsize=[12,12])\n    for i in range(rows*cols):\n        ind = start_with + i*show_every\n        ax[int(i/rows),int(i % rows)].set_title('slice %d' % ind)\n        ax[int(i/rows),int(i % rows)].imshow(stack[ind],cmap='gray')\n        ax[int(i/rows),int(i % rows)].axis('off')\n    plt.show()\n    plt.savefig(\"two.jpg\")\n\nsample_stack(imgs_to_process)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Slice Thickness: %f\" % patient[0].SliceThickness)\nprint(\"Pixel Spacing (row, col): (%f, %f) \" % (patient[0].PixelSpacing[0], patient[0].PixelSpacing[1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"id = 0\nimgs_to_process = np.load(output_path+'fullimages_{}.npy'.format(id))\ndef resample(image, scan, new_spacing=[1,1,1]):\n    # Determine current pixel spacing\n    #spacing = map(float, ([scan[0].SliceThickness] + scan[0].PixelSpacing))\n    spacing = map(float, ([scan[0].SliceThickness] + list(scan[0].PixelSpacing)))\n    spacing = np.array(list(spacing))\n\n    resize_factor = spacing / new_spacing\n    new_real_shape = image.shape * resize_factor\n    new_shape = np.round(new_real_shape)\n    real_resize_factor = new_shape / image.shape\n    new_spacing = spacing / real_resize_factor\n    \n    image = scipy.ndimage.interpolation.zoom(image, real_resize_factor)\n    \n    return image, new_spacing\n\nprint(\"Shape before resampling\\t\", imgs_to_process.shape)\nimgs_after_resamp, spacing = resample(imgs_to_process, patient, [1,1,1])\nprint(\"Shape after resampling\\t\", imgs_after_resamp.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_mesh(image, threshold=-300, step_size=1):\n\n    print( \"Transposing surface\")\n    p = image.transpose(2,1,0)\n    \n    print(\"Calculating surface\")\n    verts, faces, norm, val = measure.marching_cubes_lewiner(p, threshold, step_size=step_size, allow_degenerate=True) \n    \n    return verts, faces\n\ndef plotly_3d(verts, faces):\n    x,y,z = zip(*verts) \n    \n    print(\"Drawing\") \n    \n    # Make the colormap single color since the axes are positional not intensity. \n#    colormap=['rgb(255,105,180)','rgb(255,255,51)','rgb(0,191,255)']\n    colormap=['rgb(236, 236, 212)','rgb(236, 236, 212)']\n    \n    fig = FF.create_trisurf(x=x,\n                        y=y, \n                        z=z, \n                        plot_edges=False,\n                        colormap=colormap,\n                        simplices=faces,\n                        backgroundcolor='rgb(64, 64, 64)',\n                        title=\"Interactive Visualization\")\n    iplot(fig)\n\ndef plt_3d(verts, faces):\n    print(\"Drawing\")\n    x,y,z = zip(*verts) \n    fig = plt.figure(figsize=(10, 10))\n    ax = fig.add_subplot(111, projection='3d')\n\n    # Fancy indexing: `verts[faces]` to generate a collection of triangles\n    mesh = Poly3DCollection(verts[faces], linewidths=0.05, alpha=1)\n    face_color = [1, 1, 0.9]\n    mesh.set_facecolor(face_color)\n    ax.add_collection3d(mesh)\n\n    ax.set_xlim(0, max(x))\n    ax.set_ylim(0, max(y))\n    ax.set_zlim(0, max(z))\n    ax.set_facecolor((0.9, 0.4, 0.8))\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#v, f = make_mesh(imgs_after_resamp, 350)\n#plt_3d(v, f)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#v, f = make_mesh(imgs_after_resamp, 350, 2)\n#plotly_3d(v, f)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"After defining our image reader, we will test it with a sample DICOM image to load."},{"metadata":{},"cell_type":"markdown","source":"# Segmentation"},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_lungmask(img, display=False):\n    row_size= img.shape[0]\n    col_size = img.shape[1]\n    \n    mean = np.mean(img)\n    std = np.std(img)\n    img = img-mean\n    img = img/std\n    # Find the average pixel value near the lungs\n    # to renormalize washed out images\n    middle = img[int(col_size/5):int(col_size/5*4),int(row_size/5):int(row_size/5*4)] \n    mean = np.mean(middle)  \n    max = np.max(img)\n    min = np.min(img)\n    # To improve threshold finding, I'm moving the \n    # underflow and overflow on the pixel spectrum\n    img[img==max]=mean\n    img[img==min]=mean\n    #\n    # Using Kmeans to separate foreground (soft tissue / bone) and background (lung/air)\n    #\n    kmeans = KMeans(n_clusters=2).fit(np.reshape(middle,[np.prod(middle.shape),1]))\n    centers = sorted(kmeans.cluster_centers_.flatten())\n    threshold = np.mean(centers)\n    thresh_img = np.where(img<threshold,1.5,0.0)  # threshold the image\n\n    # First erode away the finer elements, then dilate to include some of the pixels surrounding the lung.  \n    # We don't want to accidentally clip the lung.\n\n    eroded = morphology.erosion(thresh_img,np.ones([3,3]))\n    dilation = morphology.dilation(eroded,np.ones([8,8]))\n\n    labels = measure.label(dilation) # Different labels are displayed in different colors\n    label_vals = np.unique(labels)\n    regions = measure.regionprops(labels)\n    good_labels = []\n    for prop in regions:\n        B = prop.bbox\n        if B[2]-B[0]<row_size/10*9 and B[3]-B[1]<col_size/10*9 and B[0]>row_size/5 and B[2]<col_size/5*4:\n            good_labels.append(prop.label)\n    mask = np.ndarray([row_size,col_size],dtype=np.int8)\n    mask[:] = 0\n\n    #\n    #  After just the lungs are left, we do another large dilation\n    #  in order to fill in and out the lung mask \n    #\n    for N in good_labels:\n        mask = mask + np.where(labels==N,1,0)\n    mask = morphology.dilation(mask,np.ones([10,10])) # one last dilation\n\n    if (display):\n        fig, ax = plt.subplots(3, 2, figsize=[12, 12])\n        ax[0, 0].set_title(\"Original\")\n        ax[0, 0].imshow(img, cmap='gray')\n        ax[0, 0].axis('off')\n        ax[0, 1].set_title(\"Threshold\")\n        ax[0, 1].imshow(thresh_img, cmap='gray')\n        ax[0, 1].axis('off')\n        ax[1, 0].set_title(\"After Erosion and Dilation\")\n        ax[1, 0].imshow(dilation, cmap='gray')\n        ax[1, 0].axis('off')\n        ax[1, 1].set_title(\"Color Labels\")\n        ax[1, 1].imshow(labels)\n        ax[1, 1].axis('off')\n        ax[2, 0].set_title(\"Final Mask\")\n        ax[2, 0].imshow(mask, cmap='gray')\n        ax[2, 0].axis('off')\n        ax[2, 1].set_title(\"Apply Mask on Original\")\n        ax[2, 1].imshow(mask*img, cmap='gray')\n        ax[2, 1].axis('off')\n        \n        plt.show()\n    return mask*img","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = imgs_after_resamp[260]\nmake_lungmask(img, display=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"masked_lung = []\n\nfor img in imgs_after_resamp:\n    masked_lung.append(make_lungmask(img))\n\nsample_stack(masked_lung, show_every=5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.save(output_path + \"maskedimages_%d.npy\" % (id), imgs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Dense, Dropout, Conv2D\n\n\nbase_model = keras.applications.MobileNetV2(\n    include_top=False,\n    weights=\"imagenet\"\n)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model Creation using MobileVnet Architecutre"},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Dense, Dropout, Conv2D\n\ninputs = Input((512, 512, 3))\n#x = Conv2D(3, (1, 1), activation='relu')(inputs)\nbase_model = keras.applications.MobileNetV2(\n    include_top=False,\n    weights=\"imagenet\"\n)\n\nbase_model.trainable = False\n\noutputs = base_model(inputs, training=False)\noutputs = keras.layers.GlobalAveragePooling2D()(outputs)\noutputs = Dropout(0.25)(outputs)\noutputs = Dense(1024, activation='relu')(outputs)\noutputs = Dense(512, activation='relu')(outputs)\noutputs = Dense(256, activation='relu')(outputs)\noutputs = Dense(128, activation='relu')(outputs)\noutputs = Dense(64, activation='relu')(outputs)\nppoi = Dense(1, activation='sigmoid', name='pe_present_on_image')(outputs)\nrlrg1 = Dense(1, activation='sigmoid', name='rv_lv_ratio_gte_1')(outputs)\nrlrl1 = Dense(1, activation='sigmoid', name='rv_lv_ratio_lt_1')(outputs) \nlspe = Dense(1, activation='sigmoid', name='leftsided_pe')(outputs)\ncpe = Dense(1, activation='sigmoid', name='chronic_pe')(outputs)\nrspe = Dense(1, activation='sigmoid', name='rightsided_pe')(outputs)\naacpe = Dense(1, activation='sigmoid', name='acute_and_chronic_pe')(outputs)\ncnpe = Dense(1, activation='sigmoid', name='central_pe')(outputs)\nindt = Dense(1, activation='sigmoid', name='indeterminate')(outputs)\n\nmodel = Model(inputs=inputs, outputs={'pe_present_on_image':ppoi,\n                                      'rv_lv_ratio_gte_1':rlrg1,\n                                      'rv_lv_ratio_lt_1':rlrl1,\n                                      'leftsided_pe':lspe,\n                                      'chronic_pe':cpe,\n                                      'rightsided_pe':rspe,\n                                      'acute_and_chronic_pe':aacpe,\n                                      'central_pe':cnpe,\n                                      'indeterminate':indt})\n\nopt = keras.optimizers.Adam(lr=0.0001)\n\nmodel.compile(optimizer=opt,\n              loss='binary_crossentropy',\n              metrics=['accuracy'])\n\nmodel.summary()\nmodel.save('pe_detection_model.h5')\ndel model\nK.clear_session()\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training Model"},{"metadata":{},"cell_type":"raw","source":"Refer Venturillo JE - PE Detection with Keras - Model Creation"},{"metadata":{"trusted":true},"cell_type":"code","source":"def convert_to_rgb(array):\n    array = array.reshape((512, 512, 1))\n    return np.stack([array, array, array], axis=2).reshape((512, 512, 3))\n    \ndef custom_dcom_image_generator(batch_size, dataset, test=False, debug=False):\n    \n    fnames = dataset[['StudyInstanceUID', 'SeriesInstanceUID', 'SOPInstanceUID']]\n    \n    if not test:\n        Y = dataset[['pe_present_on_image', 'rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1', 'leftsided_pe',\n                     'chronic_pe', 'rightsided_pe', 'acute_and_chronic_pe', 'central_pe', 'indeterminate'\n                    ]]\n        prefix = 'input/rsna-str-pulmonary-embolism-detection/train'\n        \n    else:\n        prefix = 'input/rsna-str-pulmonary-embolism-detection/test'\n    \n    X = []\n    batch = 0\n    for st, sr, so in fnames.values:\n        if debug:\n            print(f\"Current file: ../{prefix}/{st}/{sr}/{so}.dcm\")\n\n        dicom = get_img(f\"../{prefix}/{st}/{sr}/{so}.dcm\")\n        image = convert_to_rgb(dicom)\n        X.append(image)\n        \n        del st, sr, so\n        \n        if len(X) == batch_size:\n            if test:\n                yield np.array(X)\n                del X\n            else:\n                yield np.array(X), Y[batch*batch_size:(batch+1)*batch_size].values\n                del X\n                \n            gc.collect()\n            X = []\n            batch += 1\n        \n    if test:\n        yield np.array(X)\n    else:\n        yield np.array(X), Y[batch*batch_size:(batch+1)*batch_size].values\n        del Y\n    del X\n    gc.collect()\n    return","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = {}\nstart = time.time()\ndebug = 0\nbatch_size = 1000\ntrain_size = int(batch_size*0.9)\n\nmax_train_time = 3600*4  #hours to seconds of training\n\ncheckpoint = MC(filepath='../working/pe_detection_model.h5', monitor='val_loss', save_best_only=True, verbose=1)\n#Train loop\nfor n, (x, y) in enumerate(custom_dcom_image_generator(batch_size, train.sample(frac=1), False, debug)):\n    \n    if len(x) < 10: #Tries to filter out empty or short data\n        break\n        \n    clear_output(wait=True)\n    print(\"Training batch: %i - %i\" %(batch_size*n, batch_size*(n+1)))\n    \n    model = load_model('../working/pe_detection_model.h5')\n    hist = model.fit(\n        x[:train_size], #Y values are in a dict as there's more than one target for training output\n        {'pe_present_on_image':y[:train_size, 0],\n         'rv_lv_ratio_gte_1':y[:train_size, 1],\n         'rv_lv_ratio_lt_1':y[:train_size, 2],\n         'leftsided_pe':y[:train_size, 3],\n         'chronic_pe':y[:train_size, 4],\n         'rightsided_pe':y[:train_size, 5],\n         'acute_and_chronic_pe':y[:train_size, 6],\n         'central_pe':y[:train_size, 7],\n         'indeterminate':y[:train_size, 8]},\n\n        callbacks = checkpoint,\n\n        validation_split=0.2,\n        epochs=3,\n        batch_size=8,\n        verbose=debug\n    )\n    \n    print(\"Metrics for batch validation:\")\n    model.evaluate(x[train_size:],\n                   {'pe_present_on_image':y[train_size:, 0],\n                    'rv_lv_ratio_gte_1':y[train_size:, 1],\n                    'rv_lv_ratio_lt_1':y[train_size:, 2],\n                    'leftsided_pe':y[train_size:, 3],\n                    'chronic_pe':y[train_size:, 4],\n                    'rightsided_pe':y[train_size:, 5],\n                    'acute_and_chronic_pe':y[train_size:, 6],\n                    'central_pe':y[train_size:, 7],\n                    'indeterminate':y[train_size:, 8]\n                   }\n                  )\n    \n    try:\n        for key in hist.history.keys():\n            history[key] = np.concatenate([history[key], hist.history[key]], axis=0)\n    except:\n        for key in hist.history.keys():\n            history[key] = hist.history[key]\n            \n    #To make sure that our model don't train overtime\n    if time.time() - start >= max_train_time:\n        print(\"Time's up!\")\n        break\n        \n    model.save('pe_detection_mode.h5')\n    del model, x, y, hist\n    K.clear_session()\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training and Validation Plot"},{"metadata":{},"cell_type":"markdown","source":"Refer Venturillo JE - PE Detection with Keras - Model Creation"},{"metadata":{"trusted":true},"cell_type":"code","source":"for key in history.keys():\n    if key.startswith('val'):\n        continue\n    else:\n        epoch = range(len(history[key]))\n        plt.plot(epoch, history[key]) #X=epoch, Y=value\n        plt.plot(epoch, history['val_'+key])\n        plt.title(key)\n        if 'accuracy' in key:\n            plt.axis([0, len(history[key]), -0.1, 1.1]) #Xmin, Xmax, Ymin, Ymax\n        plt.legend(['train', 'validation'], loc='upper right')\n        plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"raw","source":"Prediction"},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = {}\nstopper = 3600*4  #4 hours limit for prediction\npred_start_time = time.time()\n\np, c = time.time(), time.time()\nbatch_size = 500\n    \nl = 0\nn = test.shape[0]\n\nfor x in custom_dcom_image_generator(batch_size, test, True, False):\n    clear_output(wait=True)\n    model = load_model(\"../working/pe_detection_model.h5\")\n    preds = model.predict(x, batch_size=8, verbose=1)\n    \n    try:\n        for key in preds.keys():\n            predictions[key] += preds[key].flatten().tolist()\n            \n    except Exception as e:\n        print(e)\n        for key in preds.keys():\n            predictions[key] = preds[key].flatten().tolist()\n            \n    l = (l+batch_size)%n\n    print('Total predicted:', len(predictions['indeterminate']),'/', n)\n    p, c = c, time.time()\n    print(\"One batch time: %.2f seconds\" %(c-p))\n    print(\"ETA: %.2f\" %((n-l)*(c-p)/batch_size))\n    \n    if c - pred_start_time >= stopper:\n        print(\"Time's up!\")\n        break\n    \n    del model\n    K.clear_session()\n    \n    del x, preds\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Test data "},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ids = []\nfor v in test.StudyInstanceUID:\n    if v not in test_ids:\n        test_ids.append(v)\n        \ntest_preds = test.copy()\ntest_preds = pd.concat([test_preds, pd.DataFrame(predictions)], axis=1)\ntest_preds.to_csv('test_predictions.csv', index=False)\ntest_preds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy.special import softmax\n\nlabel_agg = {key:[] for key in \n             ['id', 'negative_exam_for_pe', 'rv_lv_ratio_gte_1',\n              'rv_lv_ratio_lt_1', 'leftsided_pe', 'chronic_pe',\n              'rightsided_pe', 'acute_and_chronic_pe',\n              'central_pe', 'indeterminate']\n            }\n\nfor uid in test_ids:\n    temp = test_preds.loc[test_preds.StudyInstanceUID ==uid]\n    label_agg['id'].append(uid)\n    \n    n = temp.shape[0]\n    #Check for any image level presence of PE of high confidence\n    positive = any(temp.pe_present_on_image >= 0.5) #50% threshhold\n    \n    #Only one from positive, negative and indeterminate should have value>0.5\n    #per exam\n    if positive: \n        label_agg['indeterminate'].append(temp.indeterminate.min()/2)\n        label_agg['negative_exam_for_pe'].append(0)\n    else:\n        if any(temp.indeterminate >= 0.5):\n            label_agg['indeterminate'].append(temp.indeterminate.max())\n            label_agg['negative_exam_for_pe'].append(1)\n        else:\n            label_agg['indeterminate'].append(temp.indeterminate.min()/2)\n            label_agg['negative_exam_for_pe'].append(1)\n    \n    #I decided that the total ratio should be equal to 1, so I used softmax\n    #We modify the weights by multiplying the bigger by 2 and dividing the smaller by 2\n    a, b = temp[['rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1']].mean().values\n    if a > b:\n        a, b = a*2, b/2\n    elif a < b:\n        a, b = a/2, b*2\n    a, b = softmax([a, b])\n    if positive:\n        label_agg['rv_lv_ratio_gte_1'].append(a)\n        label_agg['rv_lv_ratio_lt_1'].append(b)\n    else:\n        label_agg['rv_lv_ratio_gte_1'].append(a/2)\n        label_agg['rv_lv_ratio_lt_1'].append(b/2)\n    \n    #Next is for Chronic (C), Acute-Chronic (AC) and Acute (A) PE\n    #We need to see if we got a high confidence value from either C or AC\n    #If there is, we add it to a 50% based score for high confidence\n    #and half weight for low confidence score\n    if any(temp['acute_and_chronic_pe'] > 0.5): #50% confidence level\n        label_agg['acute_and_chronic_pe'].append(0.5 + temp['acute_and_chronic_pe'].mean()/2)\n        label_agg['chronic_pe'].append(temp['chronic_pe'].mean()/2)\n        \n    elif any(temp['chronic_pe'] > 0.5):\n        label_agg['acute_and_chronic_pe'].append(temp['acute_and_chronic_pe'].mean()/2)\n        label_agg['chronic_pe'].append(0.5 + temp['chronic_pe'].mean()/2)\n        \n    else: #Else, we set both to half values, as we declare the A as the value\n        label_agg['acute_and_chronic_pe'].append(temp['acute_and_chronic_pe'].mean()/2)\n        label_agg['chronic_pe'].append(temp['chronic_pe'].mean()/2)\n    \n    #for right, left, central, we use the same metric above\n    for key in ['leftsided_pe', 'rightsided_pe', 'central_pe']:\n        if positive:\n            label_agg[key].append(0.5 + temp[key].mean()/2)\n        else:\n            label_agg[key].append(temp[key].mean()/2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"uid = []\nlabels = []\ndf = pd.DataFrame(label_agg)\nfor key in ['negative_exam_for_pe', 'rv_lv_ratio_gte_1', 'rv_lv_ratio_lt_1', 'leftsided_pe', 'chronic_pe',\n            'rightsided_pe', 'acute_and_chronic_pe', 'central_pe', 'indeterminate']:\n    for i in df.id:\n        uid.append('_'.join([i, key]))\n        labels.append(df.loc[df.id==i][key].values[0])\ndel df\ngc.collect()\n\nuid += test_preds.SOPInstanceUID.tolist()\nlabels += test_preds['pe_present_on_image'].tolist()\n\nsub = pd.DataFrame({\"id\":uid, 'label':labels})\nsub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.fillna(0.2, inplace=True)\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}