{"cells":[{"metadata":{"_uuid":"98189f36fd3e16592fc072ff705a5d3073fd06cb","_cell_guid":"33d00425-f595-41fa-b822-f50882d56476"},"cell_type":"markdown","source":"# Overview\nSince the discussion from the [top](https://www.kaggle.com/agoodman) (yet illegible) of leaderboard mention [RCNN](https://www.kaggle.com/c/data-science-bowl-2018/discussion/48130), and the Kaggle staff were quick to add it to the [kernel](https://github.com/Kaggle/docker-python/pull/173). This kernel is a simple example of how to apply this\n1. the preprocessing steps to load the data\n1. a quick visualization of the color-space\n1. training a simple RCNN\n1. applying the model to the test data\n1. creating the RLE test data"},{"metadata":{"_uuid":"bd906a2f847afc7d10764bfc7a91a3e4b2be6996","collapsed":true,"_cell_guid":"01ef30eb-1363-4e51-9d5d-42f7011348e1","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom glob import glob\nimport os\nfrom skimage.io import imread\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\ndsb_data_dir = os.path.join('..', 'input')\nstage_label = 'stage1'","execution_count":1,"outputs":[]},{"metadata":{"_uuid":"eb73ed385cad7f50245eb3e35190d402ed5cdece","_cell_guid":"4700c733-6359-4727-91dd-fada2f4e397e"},"cell_type":"markdown","source":"# Read in the labels\nLoad the RLE-encoded output for the training set"},{"metadata":{"_uuid":"9b9b10ba7c40e3092dfccb86cf41298a64de62c4","_cell_guid":"766bc1d7-c066-4429-9fe7-5eb61d3c38e4","trusted":true},"cell_type":"code","source":"train_labels = pd.read_csv(os.path.join(dsb_data_dir,'{}_train_labels.csv'.format(stage_label)))\ntrain_labels['EncodedPixels'] = train_labels['EncodedPixels'].map(lambda ep: [int(x) for x in ep.split(' ')])\ntrain_labels.sample(3)","execution_count":2,"outputs":[{"output_type":"execute_result","execution_count":2,"data":{"text/plain":"                                                 ImageId  \\\n3735   1c8b905c9519061d6d091e702b45274f4485c80dcf7fb1...   \n4893   23830d0e51245fc0c9e410efa4c17d2a7d83a0104a3777...   \n17196  947c0d94c8213ac7aaa41c4efc95d854246550298259cf...   \n\n                                           EncodedPixels  \n3735   [110259, 5, 110777, 8, 111295, 12, 111813, 15,...  \n4893   [51007, 6, 51262, 10, 51518, 11, 51773, 13, 52...  \n17196  [13155, 3, 13409, 5, 13417, 1, 13664, 5, 13673...  ","text/html":"<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ImageId</th>\n      <th>EncodedPixels</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>3735</th>\n      <td>1c8b905c9519061d6d091e702b45274f4485c80dcf7fb1...</td>\n      <td>[110259, 5, 110777, 8, 111295, 12, 111813, 15,...</td>\n    </tr>\n    <tr>\n      <th>4893</th>\n      <td>23830d0e51245fc0c9e410efa4c17d2a7d83a0104a3777...</td>\n      <td>[51007, 6, 51262, 10, 51518, 11, 51773, 13, 52...</td>\n    </tr>\n    <tr>\n      <th>17196</th>\n      <td>947c0d94c8213ac7aaa41c4efc95d854246550298259cf...</td>\n      <td>[13155, 3, 13409, 5, 13417, 1, 13664, 5, 13673...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"_uuid":"835cbe19871b155ea14d3aa6a238567c50dccd21","_cell_guid":"493040fb-d048-4e65-9d91-cc9c022df15f"},"cell_type":"markdown","source":"# Load in all Images\nHere we load in the images and process the paths so we have the appropriate information for each image"},{"metadata":{"_uuid":"d5bf5405f63a39c9e3a6da0a7d71eb0ff03cfb90","_cell_guid":"4ba1187a-33e4-40b7-aa17-b49d0df11dd5","trusted":true},"cell_type":"code","source":"all_images = glob(os.path.join(dsb_data_dir, 'stage1_*', '*', '*', '*'))\nimg_df = pd.DataFrame({'path': all_images})\nimg_id = lambda in_path: in_path.split('/')[-3]\nimg_type = lambda in_path: in_path.split('/')[-2]\nimg_group = lambda in_path: in_path.split('/')[-4].split('_')[1]\nimg_stage = lambda in_path: in_path.split('/')[-4].split('_')[0]\nimg_df['ImageId'] = img_df['path'].map(img_id)\nimg_df['ImageType'] = img_df['path'].map(img_type)\nimg_df['TrainingSplit'] = img_df['path'].map(img_group)\nimg_df['Stage'] = img_df['path'].map(img_stage)\nimg_df.sample(2)","execution_count":3,"outputs":[{"output_type":"execute_result","execution_count":3,"data":{"text/plain":"                                                    path  \\\n2214   ../input/stage1_train/bf7691b0a79811fa068b7408...   \n29215  ../input/stage1_train/e23e11414ee645b51081fb20...   \n\n                                                 ImageId ImageType  \\\n2214   bf7691b0a79811fa068b7408cbce636a73f01ef9e971a9...     masks   \n29215  e23e11414ee645b51081fb202d38b793f0c8ef2940f822...     masks   \n\n      TrainingSplit   Stage  \n2214          train  stage1  \n29215         train  stage1  ","text/html":"<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>path</th>\n      <th>ImageId</th>\n      <th>ImageType</th>\n      <th>TrainingSplit</th>\n      <th>Stage</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2214</th>\n      <td>../input/stage1_train/bf7691b0a79811fa068b7408...</td>\n      <td>bf7691b0a79811fa068b7408cbce636a73f01ef9e971a9...</td>\n      <td>masks</td>\n      <td>train</td>\n      <td>stage1</td>\n    </tr>\n    <tr>\n      <th>29215</th>\n      <td>../input/stage1_train/e23e11414ee645b51081fb20...</td>\n      <td>e23e11414ee645b51081fb202d38b793f0c8ef2940f822...</td>\n      <td>masks</td>\n      <td>train</td>\n      <td>stage1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"_uuid":"243582157d1c6f41c7822da75e1ddc2c2bf65159","_cell_guid":"363ff396-e102-4cc4-b31b-156d994fadfb"},"cell_type":"markdown","source":"# Create Training Data\nHere we make training data and load all the images into the dataframe. We take a simplification here of grouping all the regions together (rather than keeping them distinct)."},{"metadata":{"_uuid":"47c96aec86be1cd5292554483310a06ee9d45da2","_cell_guid":"4c3ec4b5-bc8d-4ab9-a54c-9971da341845","trusted":true},"cell_type":"code","source":"%%time\ntrain_df = img_df.query('TrainingSplit==\"train\"')\ntrain_rows = []\ngroup_cols = ['Stage', 'ImageId']\nfor n_group, n_rows in train_df.groupby(group_cols):\n    c_row = {col_name: col_value for col_name, col_value in zip(group_cols, n_group)}\n    c_row['mask_paths'] = n_rows.query('ImageType == \"masks\"')['path'].values.tolist()\n    c_row['image_paths'] = n_rows.query('ImageType == \"images\"')['path'].values.tolist()\n    \n    train_rows += [c_row]\ntrain_img_df = pd.DataFrame(train_rows)    \nIMG_CHANNELS = 3\ndef read_and_stack(in_img_list):\n    return np.sum(np.stack([imread(c_img) for c_img in in_img_list], 0), 0)/255.0\ntrain_img_df['images'] = train_img_df['image_paths'].map(read_and_stack).map(lambda x: x[:,:,:IMG_CHANNELS])\ndef read_and_stack_masks(in_img_list):\n    return np.sum(np.stack([i*(imread(c_img)>0) for i, c_img in \n                            enumerate(in_img_list,1)], 0), 0)\ntrain_img_df['masks'] = train_img_df['mask_paths'].map(read_and_stack_masks).map(lambda x: x.astype(int))\ntrain_img_df.sample(1)","execution_count":4,"outputs":[{"output_type":"stream","text":"CPU times: user 1min 24s, sys: 57 s, total: 2min 21s\nWall time: 2min 21s\n","name":"stdout"}]},{"metadata":{"_uuid":"895ed6676984a257cd1e5ba0cd51a5dd31e64584","_cell_guid":"2b85d62b-92f6-465d-8277-516e3b6b46bf"},"cell_type":"markdown","source":"# Show a few images\nHere we show a few images of the cells where we see there is a mixture of brightfield and fluorescence which will probably make using a single segmentation algorithm difficult"},{"metadata":{"_uuid":"48836bbf0dd9f45245b9a7edeca6a817d53e0426","_cell_guid":"877319ab-2cb1-4da8-b67b-12d3d8c8d6dc","trusted":true},"cell_type":"code","source":"n_img = 6\nfig, m_axs = plt.subplots(2, n_img, figsize = (12, 4))\nfor (_, c_row), (c_im, c_lab) in zip(train_img_df.sample(n_img).iterrows(), \n                                     m_axs.T):\n    c_im.imshow(c_row['images'])\n    c_im.axis('off')\n    c_im.set_title('Microscope')\n    \n    c_lab.imshow(c_row['masks'])\n    c_lab.axis('off')\n    c_lab.set_title('Labeled')","execution_count":5,"outputs":[{"output_type":"display_data","data":{"text/plain":"<matplotlib.figure.Figure at 0x7fcbfb186518>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAskAAAEFCAYAAAAR93q/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTgAAAABJRU5ErkJggg==\n"},"metadata":{}}]},{"metadata":{"_uuid":"30deb6f5f1a0596dd5803b312eef5b94bb4c83cc","_cell_guid":"8c0aea8a-67ba-4b29-8218-132651a16ef4"},"cell_type":"markdown","source":"# Check Dimensions \nHere we show the dimensions of the data to see the variety in the input images"},{"metadata":{"_uuid":"fb77a503aed7cf9725f3d7b6f79217ad2704facc","_cell_guid":"63d036a9-7cf5-4c53-b11d-d25abb436c29","trusted":true},"cell_type":"code","source":"train_img_df['images'].map(lambda x: x.shape).value_counts()","execution_count":6,"outputs":[{"output_type":"execute_result","execution_count":6,"data":{"text/plain":"(256, 256, 3)      334\n(256, 320, 3)      112\n(520, 696, 3)       92\n(360, 360, 3)       91\n(1024, 1024, 3)     16\n(512, 640, 3)       13\n(603, 1272, 3)       6\n(260, 347, 3)        5\n(1040, 1388, 3)      1\nName: images, dtype: int64"},"metadata":{}}]},{"metadata":{"_uuid":"4eb7e96b55f939fda9631eef96c045543e992706","_cell_guid":"450d3523-0382-4919-a90f-a3575f9930c4","trusted":true},"cell_type":"code","source":"train_img_df.sample(1)","execution_count":7,"outputs":[{"output_type":"execute_result","execution_count":7,"data":{"text/plain":"                                               ImageId   Stage  \\\n542  cdab367b30db47061df837c1ae9fa875d6057614f79733...  stage1   \n\n                                           image_paths  \\\n542  [../input/stage1_train/cdab367b30db47061df837c...   \n\n                                            mask_paths  \\\n542  [../input/stage1_train/cdab367b30db47061df837c...   \n\n                                                images  \\\n542  [[[0.113725490196, 0.113725490196, 0.113725490...   \n\n                                                 masks  \n542  [[17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, ...  ","text/html":"<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ImageId</th>\n      <th>Stage</th>\n      <th>image_paths</th>\n      <th>mask_paths</th>\n      <th>images</th>\n      <th>masks</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>542</th>\n      <td>cdab367b30db47061df837c1ae9fa875d6057614f79733...</td>\n      <td>stage1</td>\n      <td>[../input/stage1_train/cdab367b30db47061df837c...</td>\n      <td>[../input/stage1_train/cdab367b30db47061df837c...</td>\n      <td>[[[0.113725490196, 0.113725490196, 0.113725490...</td>\n      <td>[[17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, ...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"_uuid":"d4f14ac4e3c0c11ad646c2568fb1f33a91906fb9","_cell_guid":"10370313-e802-4a2d-a59f-1147c078ebbf"},"cell_type":"markdown","source":"# Create a fancy dictionary with bounding boxes\nReformat the data for bounding box style annotation"},{"metadata":{"_uuid":"d89dfa16bf73044cd9c6644258efdddb3c20af49","_cell_guid":"b2298831-08ba-4476-9194-ae12c7c1ec06","trusted":true},"cell_type":"code","source":"from skimage.morphology import label\nfrom skimage.measure import regionprops\ntrain_dict = [dict(image = dict(\n    pathname = c_row['image_paths'][0],\n                  shape =  dict(zip(['r', 'c', 'channels'], c_row['images'].shape))),\n                   objects = [{'bounding_box' : dict(\n                    minimum = dict(r = c_reg.bbox[0], c = c_reg.bbox[1]),\n                   maximum = dict(r = c_reg.bbox[2], c = c_reg.bbox[3])),\n                                  'class' : \"nucleus\",\n                               'mask': dict(pathname = c_path)\n                              }\n                                   for c_reg, c_path in zip(\n                                       regionprops(label(c_row['masks'])),\n                                       c_row['mask_paths']\n                                   )]\n                  ) \n              for _, c_row in train_img_df.iterrows()]\nprint(str(train_dict[0])[:500])","execution_count":8,"outputs":[{"output_type":"stream","text":"{'image': {'pathname': '../input/stage1_train/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552/images/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552.png', 'shape': {'r': 256, 'c': 256, 'channels': 3}}, 'objects': [{'bounding_box': {'minimum': {'r': 0, 'c': 188}, 'maximum': {'r': 8, 'c': 206}}, 'class': 'nucleus', 'mask': {'pathname': '../input/stage1_train/00071198d059ba7f5914a526d124d28e6d010c92466da21d4a04cd5413362552/masks/ffae764df84788e8047c0942f55676c96632\n","name":"stdout"}]},{"metadata":{"_uuid":"a8f7221aa69a07ec7f5ce8b55220c7b0884d8935","_cell_guid":"bdd7f061-b4a8-401f-ad0e-060dfe985abc"},"cell_type":"markdown","source":"## An Improved Data Generator\nI stole this nice generator from the latest [pull request](https://github.com/broadinstitute/keras-rcnn/blob/f37ffa61a1b8bbed19b667ffb01a1c35e5a84db6/keras_rcnn/preprocessing/_image_segmentation.py) on the rcnn repo, thanks [Allen](https://github.com/0x00b1)"},{"metadata":{"_uuid":"6a7b1f30eb393590a89089a39838b3f215d809f2","_cell_guid":"a1bdab26-c438-408b-8136-9fd947e73b06","trusted":true},"cell_type":"code","source":"import keras.backend\nimport keras.preprocessing.image\nimport numpy\nimport skimage.io\nimport skimage.transform\n\ndef scale_size(size, min_size, max_size):\n    \"\"\"\n    Rescales a given image size such that the larger axis is\n    no larger than max_size and the smallest axis is as close\n    as possible to min_size.\n    \"\"\"\n    assert (len(size) == 2)\n\n    scale = min_size / numpy.min(size)\n\n    # Prevent the biggest axis from being larger than max_size.\n    if numpy.round(scale * numpy.max(size)) > max_size:\n        scale = max_size / numpy.max(size)\n\n    rows, cols = size\n    rows *= scale\n    cols *= scale\n\n    return (int(rows), int(cols)), scale\n\n\nclass DictionaryIterator(keras.preprocessing.image.Iterator):\n    def __init__(\n            self,\n            dictionary,\n            classes,\n            generator,\n            target_shape=None,\n            scale=1,\n            ox=None,\n            oy=None,\n            batch_size=1,\n            shuffle=False,\n            seed=None\n    ):\n        self.dictionary = dictionary\n        self.classes = classes\n        self.generator = generator\n\n        r = dictionary[0][\"image\"][\"shape\"][\"r\"]\n        c = dictionary[0][\"image\"][\"shape\"][\"c\"]\n\n        channels = dictionary[0][\"image\"][\"shape\"][\"channels\"]\n\n        self.image_shape = (r, c, channels)\n        self.scale = scale\n        self.ox = ox\n        self.oy = oy\n\n        self.batch_size = batch_size\n\n        if target_shape is None:\n            self.target_shape, self.scale = scale_size(self.image_shape[0:2], numpy.min(self.image_shape[:2]), numpy.max(self.image_shape[:2]))\n\n            self.target_shape = self.target_shape + (self.image_shape[2],)\n\n        else:\n            self.target_shape = target_shape + (self.image_shape[2],)\n\n        # Metadata needs to be computed only once.\n        r, c, channels = self.target_shape\n\n        self.target_metadata = numpy.array([[r, c, self.scale]])\n\n        super(DictionaryIterator, self).__init__(len(self.dictionary), batch_size, shuffle, seed)\n\n    def next(self):\n        with self.lock:\n            selection = next(self.index_generator)\n\n        return self._get_batches_of_transformed_samples(selection)\n\n    def _get_batches_of_transformed_samples(self, selection):\n        # Labels has num_classes + 1 elements, since 0 is reserved for\n        # background.\n        num_classes = len(self.classes)\n\n        target_bounding_boxes = numpy.zeros((self.batch_size, 0, 4), dtype=keras.backend.floatx())\n\n        target_images = numpy.zeros((self.batch_size,) + self.target_shape, dtype=keras.backend.floatx())\n\n        target_masks = numpy.zeros((self.batch_size,) + self.target_shape, dtype=keras.backend.floatx())\n\n        target_scores = numpy.zeros((self.batch_size, 0, num_classes + 1), dtype=numpy.uint8)\n\n        for batch_index, image_index in enumerate(selection):\n            count = 0\n\n            while count == 0:\n                # Image\n                target_image_pathname = self.dictionary[image_index][\"image\"][\"pathname\"]\n\n                target_image = skimage.io.imread(target_image_pathname)[:, :, :3]\n\n                if target_image.ndim == 2:\n                    target_image = numpy.expand_dims(target_image, -1)\n\n                # crop\n                if self.ox is None:\n                    offset_x = numpy.random.randint(0, self.image_shape[1] - self.target_shape[1] + 1)\n                else:\n                    offset_x = self.ox\n\n                if self.oy is None:\n                    offset_y = numpy.random.randint(0, self.image_shape[0] - self.target_shape[0] + 1)\n                else:\n                    offset_y = self.oy\n\n                target_image = target_image[offset_y:self.target_shape[0] + offset_y, offset_x:self.target_shape[1] + offset_x, :]\n\n                # Copy image to batch blob.\n                target_images[batch_index] = skimage.transform.rescale(target_image, scale=self.scale, mode=\"reflect\")\n\n                # Set ground truth boxes.\n                for object_index, b in enumerate(self.dictionary[image_index][\"objects\"]):\n                    if b[\"class\"] not in self.classes:\n                        continue\n\n                    bounding_box = b[\"bounding_box\"]\n\n                    minimum_c = bounding_box[\"minimum\"][\"c\"] - offset_x\n                    minimum_r = bounding_box[\"minimum\"][\"r\"] - offset_y\n\n                    maximum_c = bounding_box[\"maximum\"][\"c\"] - offset_x\n                    maximum_r = bounding_box[\"maximum\"][\"r\"] - offset_y\n\n                    if maximum_c == target_image.shape[1]:\n                        maximum_c -= 1\n\n                    if maximum_r == target_image.shape[0]:\n                        maximum_r -= 1\n\n                    if minimum_c >= 0 and maximum_c < target_image.shape[1] and minimum_r >= 0 and maximum_r < target_image.shape[0]:\n                        count += 1\n\n                        target_bounding_box = [\n                            minimum_c,\n                            minimum_r,\n                            maximum_c,\n                            maximum_r\n                        ]\n\n                        target_bounding_boxes = numpy.append(target_bounding_boxes, [[target_bounding_box]], axis=1)\n\n                        target_score = [0] * (num_classes + 1)\n\n                        target_score[self.classes[b[\"class\"]]] = 1\n\n                        target_scores = numpy.append(target_scores, [[target_score]], axis=1)\n\n            # Scale the ground truth boxes to the selected image scale.\n            target_bounding_boxes[batch_index, :, :4] *= self.scale\n\n        return [target_bounding_boxes, target_images, target_masks, self.target_metadata, target_scores], None\n\n\nclass ImageSegmentationGenerator:\n    def flow(self, dictionary, classes, target_shape=None, scale=None, ox=None, oy=None, batch_size=1, shuffle=True, seed=None):\n        return DictionaryIterator(dictionary, classes, self, target_shape, scale, ox, oy, batch_size, shuffle, seed)","execution_count":9,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"}]},{"metadata":{"_uuid":"548c15f8f4653eb0ec954ae397e63a78f0419df7","_cell_guid":"76a3ceb7-bc7e-4887-90e7-5ec8726f142f"},"cell_type":"markdown","source":"# Check to see it's loaded correctly"},{"metadata":{"_uuid":"1e2119dbcf09004a8f7418bf30b5b4a3ab6ed541","_cell_guid":"605cf1df-d150-43bd-ba47-8c6a416558fa","trusted":true},"cell_type":"code","source":"import matplotlib\nseg_gen = ImageSegmentationGenerator().flow(train_dict, {'nucleus': 1})\nx_out, _ = seg_gen.next()\nprint('x', len(x_out))\nfor x in x_out:\n    print('\\t', x.shape)\n\n(target_bounding_boxes, target_image, _, _, target_scores) = x_out\ntarget_bounding_boxes = np.squeeze(target_bounding_boxes)\ntarget_image = np.squeeze(target_image)\ntarget_scores = np.argmax(target_scores, -1)\ntarget_scores = np.squeeze(target_scores)\n\n_, axis = plt.subplots(1, figsize=(12, 8))\naxis.imshow(target_image)\n\nfor target_index, target_score in enumerate(target_scores):\n    if target_score > 0:\n        xy = [\n            target_bounding_boxes[target_index][0],\n            target_bounding_boxes[target_index][1]\n        ]\n\n        w = target_bounding_boxes[target_index][2] - target_bounding_boxes[target_index][0]\n        h = target_bounding_boxes[target_index][3] - target_bounding_boxes[target_index][1]\n\n        rectangle = matplotlib.patches.Rectangle(xy, w, h, \n                                                 edgecolor=plt.cm.RdBu(target_score), \n                                                 facecolor=\"none\")\n        axis.add_patch(rectangle)\n\nmatplotlib.pyplot.show()","execution_count":10,"outputs":[{"output_type":"stream","text":"x 5\n\t (1, 21, 4)\n\t (1, 256, 256, 3)\n\t (1, 256, 256, 3)\n\t (1, 3)\n\t (1, 21, 2)\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"<matplotlib.figure.Figure at 0x7fcb98171470>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAd4AAAHVCAYAAABfWZoAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEDnwJhKJRCJxQOTAm0gkEonEAfH/AShadmDGlPDlAAAAAElFTkSuQmCC\n"},"metadata":{}}]},{"metadata":{"_uuid":"1e213d2a85498af6d9fe0b344f4115a6d3d2bf08","_cell_guid":"0b378f50-bc3c-4393-b720-3878ab5aa0d7","trusted":true},"cell_type":"code","source":"import keras\nfrom keras.layers import Input\nfrom keras_rcnn.models import RCNN\nimg_in = Input((None, None, 3))\nrcnn_model = RCNN(img_in, 2)\noptimizer = keras.optimizers.Adam(0.0001)\nrcnn_model.compile(optimizer)\nprint('Input:', rcnn_model.get_input_shape_at(0))\nprint('Output:', rcnn_model.get_output_shape_at(0))\n#rcnn_model.summary()","execution_count":11,"outputs":[{"output_type":"stream","text":"Input: [(None, None, 4), (None, None, None, 3), (None, None, 2), (None, 3)]\nOutput: [(1, 1, 8), (1, 1, 2)]\n","name":"stdout"},{"output_type":"stream","text":"/opt/conda/lib/python3.6/site-packages/keras_rcnn/models/_rcnn.py:91: UserWarning: Output \"object_detection_1\" missing from loss dictionary. We assume this was done on purpose, and we will not be expecting any data to be passed to \"object_detection_1\" during training.\n  super(RCNN, self).compile(optimizer, None)\n","name":"stderr"}]},{"metadata":{"_uuid":"657dbed20238a890365d1c90a1c69f9e24bac9c3","_cell_guid":"785fb1fe-b1b5-4865-81f7-40c92b91dadd","trusted":true},"cell_type":"code","source":"def fit_gen():\n    for (boxes, target_img, img_b, meta_out, target_scores), _ in seg_gen:\n        # for debugging\n        #print([(i, x.shape) for i, x in enumerate((boxes, target_img, img_b, meta_out, target_scores))])\n        yield [boxes, target_img, target_scores, meta_out], None\nrcnn_model.fit_generator(fit_gen(),\n                        steps_per_epoch = 20,\n                        epochs = 2)","execution_count":12,"outputs":[{"output_type":"stream","text":"/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:98: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.\n  \"Converting sparse IndexedSlices to a dense Tensor of unknown shape. \"\n","name":"stderr"},{"output_type":"stream","text":"Epoch 1/2\n20/20 [==============================] - 118s 6s/step - loss: 23.6705\nEpoch 2/2\n20/20 [==============================] - 110s 5s/step - loss: 9.5184\n","name":"stdout"},{"output_type":"execute_result","execution_count":12,"data":{"text/plain":"<keras.callbacks.History at 0x7fcb981a65c0>"},"metadata":{}}]},{"metadata":{"_uuid":"1cc1bc84b76c1b41a3fa5b057b72feed880b3068","_cell_guid":"5c7c329a-3185-4a6b-a963-99248deedb15"},"cell_type":"markdown","source":"# Show Predictions on Single Image\nHere we apply the model to the test data"},{"metadata":{"_uuid":"fa3f74b818eaa583c79083bd14e0c6041a547ef2","_cell_guid":"9a95e716-98e1-4a49-9691-ff5d83c52a01","trusted":true},"cell_type":"code","source":"test_ds = next(fit_gen())\ny_anchors, y_scores = rcnn_model.predict(test_ds[0])\nprint(y_anchors.shape, y_scores.shape)","execution_count":13,"outputs":[{"output_type":"stream","text":"(1, 300, 4) (1, 300, 2)\n","name":"stdout"}]},{"metadata":{"_uuid":"444a8dc797d4d70e2ce6e3c240baac394b85a73e","_cell_guid":"ca94980c-6432-48b8-8a8f-ee959d5a76da"},"cell_type":"markdown","source":"Some issues to sort out, but seems to be vaguely in the right direction"},{"metadata":{"_uuid":"d081e8f489d46b43436ba4eeeb7d97301efe0441","_cell_guid":"fb69a368-32f1-43a7-8b9f-ded50233c7f0","trusted":true},"cell_type":"code","source":"target_bounding_boxes = np.squeeze(y_anchors)\ntarget_image = np.squeeze(test_ds[0][1][0])\ntarget_scores = np.argmax(np.squeeze(y_scores), -1)\n\n_, axis = plt.subplots(1, figsize=(12, 8))\n\naxis.imshow(target_image)\n\nfor target_index, target_score in enumerate(target_scores):\n    if target_score > 0:\n        xy = [\n            target_bounding_boxes[target_index][0],\n            target_bounding_boxes[target_index][1]\n        ]\n\n        w = target_bounding_boxes[target_index][2] - target_bounding_boxes[target_index][0]\n        h = target_bounding_boxes[target_index][3] - target_bounding_boxes[target_index][1]\n\n        rectangle = matplotlib.patches.Rectangle(xy, w, h, \n                                                 edgecolor=plt.cm.RdBu(target_score), \n                                                 facecolor=\"none\")\n        axis.add_patch(rectangle)\n\nmatplotlib.pyplot.show()","execution_count":14,"outputs":[{"output_type":"display_data","data":{"text/plain":"<matplotlib.figure.Figure at 0x7fcb9025bf98>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAd4AAAHVCAYAAABfWZoAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n"},"metadata":{}}]},{"metadata":{"_uuid":"e59fd13dd68c213754bf2c1b0366a693714de6dd","_cell_guid":"c840d28b-f57b-4cd1-b1b4-6cd0d21079ab"},"cell_type":"markdown","source":"# Prepare the test data (WIP)"},{"metadata":{"_uuid":"058a5059e44f710a31cd19e1e9b8a72180befc49","_cell_guid":"5afdbc12-09b7-456c-9a72-dbeb10a289a7","trusted":true},"cell_type":"code","source":"%%time\ntest_df = img_df.query('TrainingSplit==\"test\"')\ntest_rows = []\ngroup_cols = ['Stage', 'ImageId']\nfor n_group, n_rows in test_df.groupby(group_cols):\n    c_row = {col_name: col_value for col_name, col_value in zip(group_cols, n_group)}\n    c_row['images'] = n_rows.query('ImageType == \"images\"')['path'].values.tolist()\n    test_rows += [c_row]\ntest_img_df = pd.DataFrame(test_rows)    \n\ntest_img_df['images'] = test_img_df['images'].map(read_and_stack).map(lambda x: x[:,:,:IMG_CHANNELS])\nprint(test_img_df.shape[0], 'images to process')\ntest_img_df.sample(1)","execution_count":15,"outputs":[{"output_type":"stream","text":"65 images to process\nCPU times: user 832 ms, sys: 12 ms, total: 844 ms\nWall time: 836 ms\n","name":"stdout"}]},{"metadata":{"_uuid":"e0db0bd3e6af0e2d79f7aa2fa81e3371ab11621a","_cell_guid":"9d784556-bcf6-4dfe-90b2-aa44dc54fe0c","trusted":true},"cell_type":"code","source":"%%time\ntest_img_df['masks'] = test_img_df['images'].map(lambda x: simple_cnn.predict(np.expand_dims(x, 0))[0, :, :, 0])","execution_count":16,"outputs":[{"output_type":"error","ename":"NameError","evalue":"name 'simple_cnn' is not defined","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m<timed exec>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36mmap\u001b[0;34m(self, arg, na_action)\u001b[0m\n\u001b[1;32m   2156\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2157\u001b[0m             \u001b[0;31m# arg is a function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2158\u001b[0;31m             \u001b[0mnew_values\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmap_f\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2159\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2160\u001b[0m         return self._constructor(new_values,\n","\u001b[0;32mpandas/_libs/src/inference.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.map_infer (pandas/_libs/lib.c:66645)\u001b[0;34m()\u001b[0m\n","\u001b[0;32m<timed exec>\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(x)\u001b[0m\n","\u001b[0;31mNameError\u001b[0m: name 'simple_cnn' is not defined"]}]},{"metadata":{"_uuid":"c5c545456e4a10e33d4df4dcbbab254155bea42f","_cell_guid":"6fb7b659-e779-4cce-a729-5fe2e72021aa"},"cell_type":"markdown","source":"## Show a few predictions"},{"metadata":{"_uuid":"d7e88a1c070da81a0255a3792eea2a3c0b0ec3e3","_cell_guid":"31f9f734-b193-48db-9342-9ceb49faab39","trusted":true},"cell_type":"code","source":"n_img = 3\nfrom skimage.morphology import closing, opening, disk\ndef clean_img(x):\n    return opening(closing(x, disk(1)), disk(3))\nfig, m_axs = plt.subplots(3, n_img, figsize = (12, 6))\nfor (_, d_row), (c_im, c_lab, c_clean) in zip(test_img_df.sample(n_img).iterrows(), \n                                     m_axs):\n    c_im.imshow(d_row['images'])\n    c_im.axis('off')\n    c_im.set_title('Microscope')\n    \n    c_lab.imshow(d_row['masks'])\n    c_lab.axis('off')\n    c_lab.set_title('Predicted')\n    \n    c_clean.imshow(clean_img(d_row['masks']))\n    c_clean.axis('off')\n    c_clean.set_title('Clean')","execution_count":17,"outputs":[{"output_type":"error","ename":"KeyError","evalue":"'masks'","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2482\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2483\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mlibts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value_box\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2484\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mIndexError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/tslib.pyx\u001b[0m in \u001b[0;36mpandas._libs.tslib.get_value_box (pandas/_libs/tslib.c:18843)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/tslib.pyx\u001b[0m in \u001b[0;36mpandas._libs.tslib.get_value_box (pandas/_libs/tslib.c:18477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mTypeError\u001b[0m: 'str' object cannot be interpreted as an integer","\nDuring handling of the above exception, another exception occurred:\n","\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)","\u001b[0;32m<ipython-input-17-77f34ee349ff>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     10\u001b[0m     \u001b[0mc_im\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_title\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Microscope'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 12\u001b[0;31m     \u001b[0mc_lab\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0md_row\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'masks'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     13\u001b[0m     \u001b[0mc_lab\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'off'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     14\u001b[0m     \u001b[0mc_lab\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_title\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Predicted'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m    599\u001b[0m         \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_apply_if_callable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    600\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 601\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    602\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    603\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2489\u001b[0m                     \u001b[0;32mraise\u001b[0m \u001b[0mInvalidIndexError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2490\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2491\u001b[0;31m                     \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2492\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pragma: no cover\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2493\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2475\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2476\u001b[0m             return self._engine.get_value(s, k,\n\u001b[0;32m-> 2477\u001b[0;31m                                           tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[1;32m   2478\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2479\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minferred_type\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'integer'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'boolean'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4404)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4087)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5126)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20523)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mKeyError\u001b[0m: 'masks'"]},{"output_type":"display_data","data":{"text/plain":"<matplotlib.figure.Figure at 0x7fcb887bb828>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAtEAAAF1CAYAAAAurLZiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n"},"metadata":{}}]},{"metadata":{"_uuid":"fdabcaf0484232ba704aeaa1b9bfeba1a539271f","collapsed":true,"_cell_guid":"52734b1b-617a-4075-b6c1-4eaf019594cb"},"cell_type":"markdown","source":"# Check RLE\nCheck that our approach for RLE encoding (stolen from [here](https://www.kaggle.com/rakhlin/fast-run-length-encoding-python)) works"},{"metadata":{"_uuid":"8fa0c109c0f035833d60a94e93867f0228c2e6dd","collapsed":true,"_cell_guid":"1d207c46-f3a8-42ec-8381-d4e6362cac9c","trusted":true},"cell_type":"code","source":"from skimage.morphology import label # label regions\ndef rle_encoding(x):\n    '''\n    x: numpy array of shape (height, width), 1 - mask, 0 - background\n    Returns run length as list\n    '''\n    dots = np.where(x.T.flatten()==1)[0] # .T sets Fortran order down-then-right\n    run_lengths = []\n    prev = -2\n    for b in dots:\n        if (b>prev+1): run_lengths.extend((b+1, 0))\n        run_lengths[-1] += 1\n        prev = b\n    return run_lengths\n\ndef prob_to_rles(x, cut_off = 0.5):\n    lab_img = label(x>cut_off)\n    if lab_img.max()<1:\n        lab_img[0,0] = 1 # ensure at least one prediction per image\n    for i in range(1, lab_img.max()+1):\n        yield rle_encoding(lab_img==i)","execution_count":18,"outputs":[]},{"metadata":{"_uuid":"ccf9ce4c65200467574c93a8a4adb8d4b4cb4815","_cell_guid":"3731ae6b-b38c-4bf7-afa7-4338126fc0a7"},"cell_type":"markdown","source":"## Calculate the RLEs for a Train Image"},{"metadata":{"_uuid":"5f2bb3e72ec8ed8186b55212f141d67beee101c7","collapsed":true,"_cell_guid":"6a247714-aa63-482e-a8a1-b0f11a3ac31f","trusted":true},"cell_type":"code","source":"_, train_rle_row = next(train_img_df.tail(5).iterrows()) \ntrain_row_rles = list(prob_to_rles(train_rle_row['masks']))","execution_count":19,"outputs":[]},{"metadata":{"_uuid":"d311881b690401d4032da7bbe2aa5f7f97b207e5","_cell_guid":"817ae2a7-e0b3-469f-b41e-691512e582cc"},"cell_type":"markdown","source":"## Take the RLEs from the CSV"},{"metadata":{"_uuid":"984845ff5072fc3ebb1b106831e4992170d5902f","collapsed":true,"_cell_guid":"c74939d8-f78d-4856-b2ae-a69c2ca0b83c","trusted":true},"cell_type":"code","source":"tl_rles = train_labels.query('ImageId==\"{ImageId}\"'.format(**train_rle_row))['EncodedPixels']","execution_count":20,"outputs":[]},{"metadata":{"_uuid":"80f40ffd0afe3710f3646d843abfb0ed0491630e","_cell_guid":"7af84b83-644c-44f7-a902-4797a0da9487"},"cell_type":"markdown","source":"## Check\nSince we made some simplifications, we don't expect everything to be perfect, but pretty close"},{"metadata":{"_uuid":"4841b68b07de08b6d3bb7e054e2d5830962148d8","_cell_guid":"72dd2317-89c7-4408-b42e-56c843fd54f6","trusted":true},"cell_type":"code","source":"match, mismatch = 0, 0\nfor img_rle, train_rle in zip(sorted(train_row_rles, key = lambda x: x[0]), \n                             sorted(tl_rles, key = lambda x: x[0])):\n    for i_x, i_y in zip(img_rle, train_rle):\n        if i_x == i_y:\n            match += 1\n        else:\n            mismatch += 1\nprint('Matches: %d, Mismatches: %d, Accuracy: %2.1f%%' % (match, mismatch, 100.0*match/(match+mismatch)))","execution_count":21,"outputs":[{"output_type":"stream","text":"Matches: 360, Mismatches: 0, Accuracy: 100.0%\n","name":"stdout"}]},{"metadata":{"_uuid":"19c34be3cc8c907e4d36bfcb98b6781948ec21df","collapsed":true,"_cell_guid":"d4801c91-c922-452f-a835-a4e93ae1f356"},"cell_type":"markdown","source":"# Calculate RLE for all the masks\nHere we generate the RLE for all the masks and output the the results to a table. We use a few morphological operations to clean up the images before submission since they can be very messy (remove single pixels, connect nearby regions, etc)"},{"metadata":{"_uuid":"26d2c83004921a8b985084d8d168a54f4b728b61","_cell_guid":"2e9375d2-e6b8-462d-95b7-0fda696fbfc4","trusted":true},"cell_type":"code","source":"test_img_df['rles'] = test_img_df['masks'].map(clean_img).map(lambda x: list(prob_to_rles(x)))","execution_count":22,"outputs":[{"output_type":"error","ename":"KeyError","evalue":"'masks'","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2441\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2442\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2443\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5280)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5126)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20523)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mKeyError\u001b[0m: 'masks'","\nDuring handling of the above exception, another exception occurred:\n","\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)","\u001b[0;32m<ipython-input-22-b3dbe8d59f43>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtest_img_df\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'rles'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtest_img_df\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'masks'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mclean_img\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprob_to_rles\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1962\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1963\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1964\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1965\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1966\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_getitem_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m_getitem_column\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1969\u001b[0m         \u001b[0;31m# get column\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1970\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_unique\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1971\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_item_cache\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1972\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1973\u001b[0m         \u001b[0;31m# duplicate columns & possible reduce dimensionality\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m_get_item_cache\u001b[0;34m(self, item)\u001b[0m\n\u001b[1;32m   1643\u001b[0m         \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1644\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mres\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1645\u001b[0;31m             \u001b[0mvalues\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1646\u001b[0m             \u001b[0mres\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_box_item_values\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalues\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1647\u001b[0m             \u001b[0mcache\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mres\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/internals.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(self, item, fastpath)\u001b[0m\n\u001b[1;32m   3588\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3589\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misnull\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3590\u001b[0;31m                 \u001b[0mloc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3591\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3592\u001b[0m                 \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0misnull\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2442\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2443\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2444\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2445\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2446\u001b[0m         \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5280)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5126)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20523)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mKeyError\u001b[0m: 'masks'"]}]},{"metadata":{"_uuid":"93f011b814251537f4c574908876e6157566c0b3","_cell_guid":"65be8e2b-b46a-452f-a1d6-fe97b1932e68","trusted":true},"cell_type":"code","source":"out_pred_list = []\nfor _, c_row in test_img_df.iterrows():\n    for c_rle in c_row['rles']:\n        out_pred_list+=[dict(ImageId=c_row['ImageId'], \n                             EncodedPixels = ' '.join(np.array(c_rle).astype(str)))]\nout_pred_df = pd.DataFrame(out_pred_list)\nprint(out_pred_df.shape[0], 'regions found for', test_img_df.shape[0], 'images')\nout_pred_df.sample(3)","execution_count":23,"outputs":[{"output_type":"error","ename":"KeyError","evalue":"'rles'","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2482\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2483\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mlibts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value_box\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2484\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mIndexError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/tslib.pyx\u001b[0m in \u001b[0;36mpandas._libs.tslib.get_value_box (pandas/_libs/tslib.c:18843)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/tslib.pyx\u001b[0m in \u001b[0;36mpandas._libs.tslib.get_value_box (pandas/_libs/tslib.c:18477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mTypeError\u001b[0m: 'str' object cannot be interpreted as an integer","\nDuring handling of the above exception, another exception occurred:\n","\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)","\u001b[0;32m<ipython-input-23-e38d069412bc>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mout_pred_list\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mc_row\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtest_img_df\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miterrows\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m     \u001b[0;32mfor\u001b[0m \u001b[0mc_rle\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mc_row\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'rles'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m         out_pred_list+=[dict(ImageId=c_row['ImageId'], \n\u001b[1;32m      5\u001b[0m                              EncodedPixels = ' '.join(np.array(c_rle).astype(str)))]\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m    599\u001b[0m         \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_apply_if_callable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    600\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 601\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    602\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    603\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2489\u001b[0m                     \u001b[0;32mraise\u001b[0m \u001b[0mInvalidIndexError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2490\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2491\u001b[0;31m                     \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2492\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pragma: no cover\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2493\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   2475\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2476\u001b[0m             return self._engine.get_value(s, k,\n\u001b[0;32m-> 2477\u001b[0;31m                                           tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[1;32m   2478\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2479\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minferred_type\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'integer'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'boolean'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4404)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value (pandas/_libs/index.c:4087)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5126)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20523)\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20477)\u001b[0;34m()\u001b[0m\n","\u001b[0;31mKeyError\u001b[0m: 'rles'"]}]},{"metadata":{"_uuid":"4524606e4ae416dcf364a5170f82cf4ceea6d2af","_cell_guid":"7f5f0c3a-222f-4470-88a7-d2f77bd54542","trusted":true},"cell_type":"code","source":"out_pred_df[['ImageId', 'EncodedPixels']].to_csv('predictions.csv', index = False)","execution_count":24,"outputs":[{"output_type":"error","ename":"NameError","evalue":"name 'out_pred_df' is not defined","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m<ipython-input-24-40be2396a3ad>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mout_pred_df\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'ImageId'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'EncodedPixels'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'predictions.csv'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;31mNameError\u001b[0m: name 'out_pred_df' is not defined"]}]},{"metadata":{"_uuid":"e118dc861c34fcf23e1954166b7a4e9607987955","collapsed":true,"_cell_guid":"576a277d-3815-4d59-a5b8-1924c1bafcee","trusted":true},"cell_type":"code","source":"","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}