{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport plotly.express as px","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-01-30T20:41:31.997211Z","iopub.execute_input":"2022-01-30T20:41:31.997676Z","iopub.status.idle":"2022-01-30T20:41:32.004621Z","shell.execute_reply.started":"2022-01-30T20:41:31.997635Z","shell.execute_reply":"2022-01-30T20:41:32.003515Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"targetName = 'label'\nidName = 'id'\ncompetitionDir = '/kaggle/input/tpu-getting-started'\nsubmission = pd.read_csv('../input/tpu-getting-started/sample_submission.csv')\nsubmission.sort_values(by=[idName], inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.006615Z","iopub.execute_input":"2022-01-30T20:41:32.007667Z","iopub.status.idle":"2022-01-30T20:41:32.048098Z","shell.execute_reply.started":"2022-01-30T20:41:32.007593Z","shell.execute_reply":"2022-01-30T20:41:32.046641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os, re, math\n\nimport numpy as np \nimport pandas as pd\n\nfrom sklearn.metrics import f1_score, accuracy_score, roc_auc_score\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nimport tensorflow as tf\nfrom tensorflow import keras\n\nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.049884Z","iopub.execute_input":"2022-01-30T20:41:32.050155Z","iopub.status.idle":"2022-01-30T20:41:32.062016Z","shell.execute_reply.started":"2022-01-30T20:41:32.050117Z","shell.execute_reply":"2022-01-30T20:41:32.061059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.065372Z","iopub.execute_input":"2022-01-30T20:41:32.066485Z","iopub.status.idle":"2022-01-30T20:41:32.077872Z","shell.execute_reply.started":"2022-01-30T20:41:32.066442Z","shell.execute_reply":"2022-01-30T20:41:32.076865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Loading dataset from Google cloud","metadata":{}},{"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.079544Z","iopub.execute_input":"2022-01-30T20:41:32.080273Z","iopub.status.idle":"2022-01-30T20:41:32.554864Z","shell.execute_reply.started":"2022-01-30T20:41:32.080169Z","shell.execute_reply":"2022-01-30T20:41:32.553978Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [512, 512] # default image sizes\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-512x512'\nAUTO = tf.data.experimental.AUTOTUNE # parallening data manipulation techniqu like (Reading data from differnet file at the same time).\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') \n\nCLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102\n\n\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n#     label = tf.keras.utils.to_categorical(label, num_classes=104)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['id']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.559007Z","iopub.execute_input":"2022-01-30T20:41:32.559273Z","iopub.status.idle":"2022-01-30T20:41:32.991865Z","shell.execute_reply.started":"2022-01-30T20:41:32.559226Z","shell.execute_reply":"2022-01-30T20:41:32.991104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO)\n    # statement in the next function (below), this happens essentially\n    # for free on TPU. Data pipeline code is executed on the \"CPU\"\n    # part of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048) # Randomly shuffles the elements of this dataset\n    dataset = dataset.batch(BATCH_SIZE) # Combines consecutive elements of this dataset into batches\n    # This allows later elements to be prepared while the current element is being processed. This often improves latency and throughput\n    # prefetch next batch while training (autotune prefetch buffer size)\n    dataset = dataset.prefetch(AUTO) \n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache() # The first time the dataset is iterated over, its elements will be cached either in the specified file or in memory\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec\n    # files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:32.995630Z","iopub.execute_input":"2022-01-30T20:41:32.995828Z","iopub.status.idle":"2022-01-30T20:41:33.006404Z","shell.execute_reply.started":"2022-01-30T20:41:32.995805Z","shell.execute_reply":"2022-01-30T20:41:33.005469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 (=16*8) with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:57:53.694518Z","iopub.execute_input":"2022-01-30T20:57:53.695151Z","iopub.status.idle":"2022-01-30T20:57:53.859276Z","shell.execute_reply.started":"2022-01-30T20:57:53.695112Z","shell.execute_reply":"2022-01-30T20:57:53.858573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot as plt\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case,\n                                     # these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is\n    # the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square\n    # or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()\n\n\ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:59:42.520363Z","iopub.execute_input":"2022-01-30T20:59:42.520622Z","iopub.status.idle":"2022-01-30T20:59:42.539719Z","shell.execute_reply.started":"2022-01-30T20:59:42.520594Z","shell.execute_reply":"2022-01-30T20:59:42.538831Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Splitting the data into betch sizes of 20 just for displaying them\nds_iter = iter(ds_train.unbatch().batch(20))\none_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T21:00:02.364645Z","iopub.execute_input":"2022-01-30T21:00:02.364999Z","iopub.status.idle":"2022-01-30T21:00:14.751711Z","shell.execute_reply.started":"2022-01-30T21:00:02.364966Z","shell.execute_reply":"2022-01-30T21:00:14.749313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Import any number of public notebooks to update the ensemble prediction¶","metadata":{}},{"cell_type":"code","source":"preds = []\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(filename)\n        if (dirname != competitionDir) & ('.csv' in filename):\n            df = pd.read_csv(os.path.join(dirname, filename))\n            if len(df) == len(submission):\n                try:\n                    df.sort_values(by=[idName], inplace=True)\n                    preds.append(df[targetName])\n                except Exception:\n                    pass\n","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:41:33.007867Z","iopub.execute_input":"2022-01-30T20:41:33.008185Z","iopub.status.idle":"2022-01-30T20:41:33.083034Z","shell.execute_reply.started":"2022-01-30T20:41:33.008150Z","shell.execute_reply":"2022-01-30T20:41:33.082289Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Save ensemble prediction to csv¶","metadata":{}},{"cell_type":"code","source":"submission[targetName] = stats.mode(np.array(preds), axis=0)[0].transpose()\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:56:18.740965Z","iopub.execute_input":"2022-01-30T20:56:18.741263Z","iopub.status.idle":"2022-01-30T20:56:18.984367Z","shell.execute_reply.started":"2022-01-30T20:56:18.741217Z","shell.execute_reply":"2022-01-30T20:56:18.983622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.head()   ## check submission","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:45:25.835061Z","iopub.execute_input":"2022-01-30T20:45:25.835590Z","iopub.status.idle":"2022-01-30T20:45:25.843725Z","shell.execute_reply.started":"2022-01-30T20:45:25.835551Z","shell.execute_reply":"2022-01-30T20:45:25.842918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Distribution of the predicted classes¶","metadata":{}},{"cell_type":"code","source":"target_df = pd.DataFrame(np.log(submission[targetName].value_counts())).reset_index()\ntarget_df.columns = [targetName, 'Count']\nfig = px.bar(data_frame = target_df, \n             x = targetName,\n             y = 'Count' , \n             color = \"Count\",\n             color_continuous_scale=\"Emrld\") \nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-01-30T20:52:00.156420Z","iopub.execute_input":"2022-01-30T20:52:00.157013Z","iopub.status.idle":"2022-01-30T20:52:00.221395Z","shell.execute_reply.started":"2022-01-30T20:52:00.156967Z","shell.execute_reply":"2022-01-30T20:52:00.220651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Credits to those who provided the codes","metadata":{}}]}