{"cells":[{"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nfrom tqdm.auto import tqdm    # TQDM is a progress bar library with good support for nested loops and Jupyter/IPython notebooks.\nfrom glob import glob    # https://pymotw.com/2/glob/\nimport time, gc   # gc : The process by which Python periodically frees and reclaims blocks of memory that no longer are in use is called Garbage Collection.\nimport cv2   # openCV\n\nfrom tensorflow import keras\nimport matplotlib.image as mpimg   # matplotlib.image : The image module supports basic image loading, rescaling and display operations. class matplotlib.image\nfrom keras.preprocessing.image import ImageDataGenerator   # Keras’ImageDataGenerator class to perform data augmentation. https://www.pyimagesearch.com/2019/07/08/keras-imagedatagenerator-and-data-augmentation/\nfrom keras.models import Model\nfrom keras.models import clone_model   # Model cloning is similar to calling a model on new inputs, except that it creates new layers (and thus new weights) instead of sharing the weights of the existing layers.\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization,Input\nfrom keras.optimizers import Adam\nfrom keras.callbacks import ReduceLROnPlateau  # Reduce learning rate when a metric has stopped improving\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport PIL.Image as Image, PIL.ImageDraw as ImageDraw, PIL.ImageFont as ImageFont   # PIL : the Python Imaging Library which provides the python interpreter with image editing capabilities.  https://www.geeksforgeeks.org/python-pil-image-new-method/\nfrom matplotlib import pyplot as plt\nimport seaborn as sns\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df_ = pd.read_csv('/kaggle/input/bengaliai-cv19/train.csv')\ntest_df_ = pd.read_csv('/kaggle/input/bengaliai-cv19/test.csv')\nclass_map_df = pd.read_csv('/kaggle/input/bengaliai-cv19/class_map.csv')\nsample_sub_df = pd.read_csv('/kaggle/input/bengaliai-cv19/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_df_.shape, test_df_.shape)\nprint(class_map_df.shape, sample_sub_df.shape)\ntrain_df_.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df_.head()\nsample_sub_df.head()\nclass_map_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f'Size of training data: {train_df_.shape}')\nprint(f'Size of test data: {test_df_.shape}')\nprint(f'Size of class map: {class_map_df.shape}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 236\nWIDTH = 236\n\ndef get_n(df, field, n, top=True):  \n    top_graphemes = df.groupby([field]).size().reset_index(name='counts')['counts'].sort_values(ascending=not top)[:n]\n    top_grapheme_roots = top_graphemes.index\n    top_grapheme_counts = top_graphemes.values\n    top_graphemes = class_map_df[class_map_df['component_type'] == field].reset_index().iloc[top_grapheme_roots]\n    top_graphemes.drop(['component_type', 'label'], axis=1, inplace=True)\n    top_graphemes.loc[:, 'count'] = top_grapheme_counts\n    return top_graphemes\n\ndef image_from_char(char):   \n    image = Image.new('RGB', (WIDTH, HEIGHT))\n    draw = ImageDraw.Draw(image)\n    myfont = ImageFont.truetype('/kaggle/input/kalpurush-fonts/kalpurush-2.ttf', 120)\n    w, h = draw.textsize(char, font=myfont)\n    draw.text(((WIDTH - w) / 2,(HEIGHT - h) / 3), char, font=myfont)\n\n    return image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f'Number of unique grapheme roots: {train_df_[\"grapheme_root\"].nunique()}')\nprint(f'Number of unique vowel diacritic: {train_df_[\"vowel_diacritic\"].nunique()}')\nprint(f'Number of unique consonant diacritic: {train_df_[\"consonant_diacritic\"].nunique()}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"top_10_roots = get_n(train_df_, 'grapheme_root', 10)\ntop_10_roots","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f, ax = plt.subplots(2, 5, figsize=(16, 8))   # fig, ax = plt.subplots()\nax = ax.flatten()  \n\nfor i in range(10):\n    ax[i].imshow(image_from_char(top_10_roots['component'].iloc[i]), cmap='Greys')  # cmap : colormap","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bottom_10_roots = get_n(train_df_, 'grapheme_root', 10, False)\nbottom_10_roots\nf, ax = plt.subplots(2, 5, figsize=(16, 8))\nax = ax.flatten()\n\nfor i in range(10):\n    ax[i].imshow(image_from_char(bottom_10_roots['component'].iloc[i]), cmap='Greys')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"top_5_vowels = get_n(train_df_, 'vowel_diacritic', 5)\ntop_5_vowels\nf, ax = plt.subplots(1, 5, figsize=(16, 8))\nax = ax.flatten()\n\nfor i in range(5):\n    ax[i].imshow(image_from_char(top_5_vowels['component'].iloc[i]), cmap='Greys')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"top_5_consonants = get_n(train_df_, 'consonant_diacritic', 5)\ntop_5_consonants\nf, ax = plt.subplots(1, 5, figsize=(16, 8))\nax = ax.flatten()\n\nfor i in range(5):\n    ax[i].imshow(image_from_char(top_5_consonants['component'].iloc[i]), cmap='Greys')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_ = train_df_.drop(['grapheme'], axis=1, inplace=False)\ntrain_df_.head()\ntrain_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']] = train_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']].astype('uint8')\n\nIMG_SIZE=64\nN_CHANNELS=1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def resize(df, size=64, need_progress_bar=True):\n    resized = {}\n    resize_size=64\n    if need_progress_bar:\n        for i in tqdm(range(df.shape[0])):\n            image=df.loc[df.index[i]].values.reshape(137,236)\n            _, thresh = cv2.threshold(image, 30, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)\n            contours, _ = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)[-2:]\n\n            idx = 0 \n            ls_xmin = []\n            ls_ymin = []\n            ls_xmax = []\n            ls_ymax = []\n            for cnt in contours:\n                idx += 1\n                x,y,w,h = cv2.boundingRect(cnt)\n                ls_xmin.append(x)\n                ls_ymin.append(y)\n                ls_xmax.append(x + w)\n                ls_ymax.append(y + h)\n            xmin = min(ls_xmin)\n            ymin = min(ls_ymin)\n            xmax = max(ls_xmax)\n            ymax = max(ls_ymax)\n\n            roi = image[ymin:ymax,xmin:xmax]\n            resized_roi = cv2.resize(roi, (resize_size, resize_size),interpolation=cv2.INTER_AREA)\n            resized[df.index[i]] = resized_roi.reshape(-1)\n    else:\n        for i in range(df.shape[0]):\n            #image = cv2.resize(df.loc[df.index[i]].values.reshape(137,236),(size,size),None,fx=0.5,fy=0.5,interpolation=cv2.INTER_AREA)\n            image=df.loc[df.index[i]].values.reshape(137,236)\n            _, thresh = cv2.threshold(image, 30, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)\n            contours, _ = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)[-2:]\n\n            idx = 0 \n            ls_xmin = []\n            ls_ymin = []\n            ls_xmax = []\n            ls_ymax = []\n            for cnt in contours:\n                idx += 1\n                x,y,w,h = cv2.boundingRect(cnt)\n                ls_xmin.append(x)\n                ls_ymin.append(y)\n                ls_xmax.append(x + w)\n                ls_ymax.append(y + h)\n            xmin = min(ls_xmin)\n            ymin = min(ls_ymin)\n            xmax = max(ls_xmax)\n            ymax = max(ls_ymax)\n\n            roi = image[ymin:ymax,xmin:xmax]\n            resized_roi = cv2.resize(roi, (resize_size, resize_size),interpolation=cv2.INTER_AREA)\n            resized[df.index[i]] = resized_roi.reshape(-1)\n    resized = pd.DataFrame(resized).T\n    return resized","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_dummies(df):\n    cols = []\n    for col in df:\n        cols.append(pd.get_dummies(df[col].astype(str)))\n    return pd.concat(cols, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inputs = Input(shape = (IMG_SIZE, IMG_SIZE, 1))\n\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu', input_shape=(IMG_SIZE, IMG_SIZE, 1))(inputs)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=32, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=32, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=64, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=64, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=128, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=128, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = Conv2D(filters=256, kernel_size=(3, 3), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = MaxPool2D(pool_size=(2, 2))(model)\nmodel = Conv2D(filters=256, kernel_size=(5, 5), padding='SAME', activation='relu')(model)\nmodel = BatchNormalization(momentum=0.15)(model)\nmodel = Dropout(rate=0.3)(model)\n\nmodel = Flatten()(model)\nmodel = Dense(1024, activation = \"relu\")(model)\nmodel = Dropout(rate=0.3)(model)\ndense = Dense(512, activation = \"relu\")(model)\n\nhead_root = Dense(168, activation = 'softmax')(dense)\nhead_vowel = Dense(11, activation = 'softmax')(dense)\nhead_consonant = Dense(7, activation = 'softmax')(dense)\n\nmodel = Model(inputs=inputs, outputs=[head_root, head_vowel, head_consonant])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()\nfrom keras.utils import plot_model\nplot_model(model, to_file='model.png')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Set a learning rate annealer. Learning rate will be half after 3 epochs if accuracy is not increased\nlearning_rate_reduction_root = ReduceLROnPlateau(monitor='dense_3_accuracy', \n                                            patience=3, \n                                            verbose=1,\n                                            factor=0.5, \n                                            min_lr=0.00001)\nlearning_rate_reduction_vowel = ReduceLROnPlateau(monitor='dense_4_accuracy', \n                                            patience=3, \n                                            verbose=1,\n                                            factor=0.5, \n                                            min_lr=0.00001)\nlearning_rate_reduction_consonant = ReduceLROnPlateau(monitor='dense_5_accuracy', \n                                            patience=3, \n                                            verbose=1,\n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 256\nepochs = 10  ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class MultiOutputDataGenerator(keras.preprocessing.image.ImageDataGenerator):\n\n    def flow(self,\n             x,\n             y=None,\n             batch_size=32,\n             shuffle=True,\n             sample_weight=None,\n             seed=None,\n             save_to_dir=None,\n             save_prefix='',\n             save_format='png',\n             subset=None):\n\n        targets = None\n        target_lengths = {}\n        ordered_outputs = []\n        for output, target in y.items():\n            if targets is None:\n                targets = target\n            else:\n                targets = np.concatenate((targets, target), axis=1)\n            target_lengths[output] = target.shape[1]\n            ordered_outputs.append(output)\n\n\n        for flowx, flowy in super().flow(x, targets, batch_size=batch_size,\n                                         shuffle=shuffle):\n            target_dict = {}\n            i = 0\n            for output in ordered_outputs:\n                target_length = target_lengths[output]\n                target_dict[output] = flowy[:, i: i + target_length]\n                i += target_length\n\n            yield flowx, target_dict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 137\nWIDTH = 236","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"histories = []\n#for i in range(4):    \ntrain_df = pd.merge(pd.read_parquet(f'/kaggle/input/bengaliai-cv19/train_image_data_0.parquet'), train_df_, on='image_id').drop(['image_id'], axis=1)\n\n# Visualize few samples of current training dataset\nfig, ax = plt.subplots(nrows=3, ncols=4, figsize=(16, 8))\ncount=0\nfor row in ax:\n    for col in row:\n        col.imshow(resize(train_df.drop(['grapheme_root', 'vowel_diacritic', 'consonant_diacritic'], axis=1).iloc[[count]], need_progress_bar=False).values.reshape(-1).reshape(IMG_SIZE, IMG_SIZE).astype(np.float64))\n        count += 1\nplt.show()\n    \nX_train = train_df.drop(['grapheme_root', 'vowel_diacritic', 'consonant_diacritic'], axis=1)\nX_train = resize(X_train)/255\n    \n# CNN takes images in shape `(batch_size, h, w, channels)`, so reshape the images\nX_train = X_train.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\n\nY_train_root = pd.get_dummies(train_df['grapheme_root']).values\nY_train_vowel = pd.get_dummies(train_df['vowel_diacritic']).values\nY_train_consonant = pd.get_dummies(train_df['consonant_diacritic']).values\n\nprint(f'Training images: {X_train.shape}')\nprint(f'Training labels root: {Y_train_root.shape}')\nprint(f'Training labels vowel: {Y_train_vowel.shape}')\nprint(f'Training labels consonants: {Y_train_consonant.shape}')\n\nx_train, x_test, y_train_root, y_test_root, y_train_vowel, y_test_vowel, y_train_consonant, y_test_consonant = train_test_split(X_train, Y_train_root, Y_train_vowel, Y_train_consonant, test_size=0.08, random_state=666)\n\ndel train_df\ndel X_train\ndel Y_train_root, Y_train_vowel, Y_train_consonant\n\n# Data augmentation for creating more training data\ndatagen = MultiOutputDataGenerator(\n    featurewise_center=False,  # set input mean to 0 over the dataset\n    samplewise_center=False,  # set each sample mean to 0\n    featurewise_std_normalization=False,  # divide inputs by std of the dataset\n    samplewise_std_normalization=False,  # divide each input by its std\n    zca_whitening=False,  # apply ZCA whitening\n    rotation_range=8,  # randomly rotate images in the range (degrees, 0 to 180)\n    zoom_range = 0.15, # Randomly zoom image \n    width_shift_range=0.15,  # randomly shift images horizontally (fraction of total width)\n    height_shift_range=0.15,  # randomly shift images vertically (fraction of total height)\n    horizontal_flip=False,  # randomly flip images\n    vertical_flip=False)  # randomly flip images\n\n\n# This will just calculate parameters required to augment the given data. This won't perform any augmentations\ndatagen.fit(x_train)\n\nhistory = model.fit_generator(datagen.flow(x_train, {'dense_3': y_train_root, 'dense_4': y_train_vowel, 'dense_5': y_train_consonant}, batch_size=batch_size),\n                          epochs = epochs, validation_data = (x_test, [y_test_root, y_test_vowel, y_test_consonant]), \n                          steps_per_epoch=x_train.shape[0] // batch_size, \n                          callbacks=[learning_rate_reduction_root, learning_rate_reduction_vowel, learning_rate_reduction_consonant])\n\nhistories.append(history)   \n\ndel x_train\ndel x_test\ndel y_train_root\ndel y_test_root\ndel y_train_vowel\ndel y_test_vowel\ndel y_train_consonant\ndel y_test_consonant\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%matplotlib inline\ndef plot_loss(his, epoch, title):\n    plt.style.use('ggplot')\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history['loss'], label='train_loss')\n    plt.plot(np.arange(0, epoch), his.history['dense_3_loss'], label='train_root_loss')\n    plt.plot(np.arange(0, epoch), his.history['dense_4_loss'], label='train_vowel_loss')\n    plt.plot(np.arange(0, epoch), his.history['dense_5_loss'], label='train_consonant_loss')\n    \n    plt.plot(np.arange(0, epoch), his.history['val_dense_3_loss'], label='val_train_root_loss')\n    plt.plot(np.arange(0, epoch), his.history['val_dense_4_loss'], label='val_train_vowel_loss')\n    plt.plot(np.arange(0, epoch), his.history['val_dense_5_loss'], label='val_train_consonant_loss')\n    \n    plt.title(title)\n    plt.xlabel('Epoch #')\n    plt.ylabel('Loss')\n    plt.legend(loc='upper right')\n    plt.show()\n\ndef plot_acc(his, epoch, title):\n    plt.style.use('ggplot')\n    plt.figure()\n    plt.plot(np.arange(0, epoch), his.history['dense_3_accuracy'], label='train_root_acc')\n    plt.plot(np.arange(0, epoch), his.history['dense_4_accuracy'], label='train_vowel_acc')\n    plt.plot(np.arange(0, epoch), his.history['dense_5_accuracy'], label='train_consonant_acc')\n    \n    plt.plot(np.arange(0, epoch), his.history['val_dense_3_accuracy'], label='val_root_acc')\n    plt.plot(np.arange(0, epoch), his.history['val_dense_4_accuracy'], label='val_vowel_acc')\n    plt.plot(np.arange(0, epoch), his.history['val_dense_5_accuracy'], label='val_consonant_acc')\n    plt.title(title)\n    plt.xlabel('Epoch #')\n    plt.ylabel('Accuracy')\n    plt.legend(loc='upper right')\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nfor dataset in range(1):\n    plot_loss(histories[dataset], epochs, f'Training Dataset: {dataset}')\n    plot_acc(histories[dataset], epochs, f'Training Dataset: {dataset}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del histories\ngc.collect()  # Garbage Collector  메모리 관리","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_dict = {\n    'grapheme_root': [],\n    'vowel_diacritic': [],\n    'consonant_diacritic': []\n}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"components = ['consonant_diacritic', 'grapheme_root', 'vowel_diacritic']\ntarget=[] # model predictions placeholder\nrow_id=[] # row_id place holder\n#for i in range(4):\ndf_test_img = pd.read_parquet('/kaggle/input/bengaliai-cv19/test_image_data_0.parquet'.format(0)) # test data 가져옴\ndf_test_img.set_index('image_id', inplace=True)\n\nX_test = resize(df_test_img, need_progress_bar=False)/255\nX_test = X_test.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\n\npreds = model.predict(X_test) \n\nfor i, p in enumerate(preds_dict):\n    preds_dict[p] = np.argmax(preds[i], axis=1)\n\nfor k,id in enumerate(df_test_img.index.values):  \n    for i,comp in enumerate(components):\n        id_sample=id+'_'+comp\n        row_id.append(id_sample)\n        target.append(preds_dict[comp][k])\ndel df_test_img\ndel X_test\ngc.collect()\n\ndf_sample = pd.DataFrame(\n    {\n        'row_id': row_id,\n        'target':target\n    },\n    columns = ['row_id','target'] \n)\ndf_sample.to_csv('submission.csv',index=False)\ndf_sample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}