{"cells":[{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","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)\nfrom tqdm.auto import tqdm\nfrom glob import glob\nimport time, gc\nimport cv2\n\nfrom tensorflow import keras\nimport matplotlib.image as mpimg\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Model\nfrom keras.models import clone_model\nfrom keras.layers import Dense,Conv2D,Flatten,MaxPool2D,Dropout,BatchNormalization, Input\nfrom keras.optimizers import Adam\nfrom keras.callbacks import ReduceLROnPlateau\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\nfrom matplotlib import pyplot as plt\nimport seaborn as sns\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\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","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":"train_df_.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df_.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_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":"example_df=pd.DataFrame({'Animal': [10, 10, 11, 11, 10], 'Max Speed': [380, 370, 24, 26, 385]})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"p=example_df.groupby(['Animal']).size().sort_values(ascending=not True)\nprint(p)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Exploratory Data Analysis\nExploratory data analysis (EDA) is an approach to analyzing data sets to summarize their main characteristics, often with visual methods."},{"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].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":{},"cell_type":"markdown","source":"### Number of unique values"},{"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":{},"cell_type":"markdown","source":"### Most used top 10 Grapheme Roots in training set"},{"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))\nax=ax.flatten()\n\nfor i in range(10):\n    ax[i].imshow(image_from_char(top_10_roots['component'].iloc[i]), cmap='Greys')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Least used 10 Grapheme Roots in training set"},{"metadata":{"trusted":true},"cell_type":"code","source":"bottom_10_roots = get_n(train_df_, 'grapheme_root', 10, False)\nbottom_10_roots","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f, 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":{},"cell_type":"markdown","source":"### Top 5 Vowel Diacritic in taining data"},{"metadata":{"trusted":true},"cell_type":"code","source":"top_5_vowels = get_n(train_df_, 'vowel_diacritic', 5)\ntop_5_vowels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f, 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":{},"cell_type":"markdown","source":"### Top 5 Consonant Diacritic in training data"},{"metadata":{"trusted":true},"cell_type":"code","source":"top_5_consonants = get_n(train_df_, 'consonant_diacritic', 5)\ntop_5_consonants","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f, 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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_df_.head())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']] = train_df_[['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']].astype('uint8')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_df_.head())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_SIZE=64\nN_CHANNELS=1","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's apply some image processing (credits: [this kernel](https://www.kaggle.com/shawon10/bangla-graphemes-image-processing-deep-cnn)) while resizing the images, which will center crop the region of interest from the original images."},{"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":{},"cell_type":"markdown","source":"## Basic Model"},{"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()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's visualize the 3-tailed (3 output) CNN by plotting it."},{"metadata":{"trusted":true},"cell_type":"code","source":"from 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 = 30","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":{},"cell_type":"markdown","source":"### Training loop"},{"metadata":{"trusted":true},"cell_type":"code","source":"histories = []\nfor i in range(4):\n    train_df = pd.merge(pd.read_parquet(f'/kaggle/input/bengaliai-cv19/train_image_data_{i}.parquet'), train_df_, on='image_id').drop(['image_id'], axis=1)\n    \n    # Visualize few samples of current training dataset\n    fig, ax = plt.subplots(nrows=3, ncols=4, figsize=(16, 8))\n    count=0\n    for 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\n    plt.show()\n    \n    X_train = train_df.drop(['grapheme_root', 'vowel_diacritic', 'consonant_diacritic'], axis=1)\n    X_train = resize(X_train)/255\n    \n    # CNN takes images in shape `(batch_size, h, w, channels)`, so reshape the images\n    X_train = X_train.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\n    \n    Y_train_root = pd.get_dummies(train_df['grapheme_root']).values\n    Y_train_vowel = pd.get_dummies(train_df['vowel_diacritic']).values\n    Y_train_consonant = pd.get_dummies(train_df['consonant_diacritic']).values\n\n    print(f'Training images: {X_train.shape}')\n    print(f'Training labels root: {Y_train_root.shape}')\n    print(f'Training labels vowel: {Y_train_vowel.shape}')\n    print(f'Training labels consonants: {Y_train_consonant.shape}')\n\n    # Divide the data into training and validation set\n    x_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    del train_df\n    del X_train\n    del Y_train_root, Y_train_vowel, Y_train_consonant\n\n    # Data augmentation for creating more training data\n    datagen = 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\n    datagen.fit(x_train)\n\n    # Fit the model\n    history = 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\n    histories.append(history)\n    \n    # Delete to reduce memory usage\n    del x_train\n    del x_test\n    del y_train_root\n    del y_test_root\n    del y_train_vowel\n    del y_test_vowel\n    del y_train_consonant\n    del y_test_consonant\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del histories\ngc.collect()","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\nfor i in range(4):\n    df_test_img = pd.read_parquet('/kaggle/input/bengaliai-cv19/test_image_data_{}.parquet'.format(i)) \n    df_test_img.set_index('image_id', inplace=True)\n\n    X_test = resize(df_test_img, need_progress_bar=False)/255\n    X_test = X_test.values.reshape(-1, IMG_SIZE, IMG_SIZE, N_CHANNELS)\n    \n    preds = model.predict(X_test)\n\n    for i, p in enumerate(preds_dict):\n        preds_dict[p] = np.argmax(preds[i], axis=1)\n\n    for 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])\n    del df_test_img\n    del X_test\n    gc.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":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"108585220d384f1d87f3c8444587ae5b":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"IntProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"IntProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"100%","description_tooltip":null,"layout":"IPY_MODEL_e4855ad98fad40deb899d57d401ae8c3","max":50210,"min":0,"orientation":"horizontal","style":"IPY_MODEL_f0b119ea39cc420ea11296b456d078d8","value":50210}},"12ab2aed987f4a2e9bed87f8df6fbace":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_b2e73348f1084afe92c3f03035d8606b","IPY_MODEL_b57249febd6c457baa5d4ba55f379ec1"],"layout":"IPY_MODEL_c9970f6bf5c54ff8808f97fdeb286846"}},"3540aa1072634a95b56adbc63b871c44":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"570a0b20e27c418687a1a1b252721597":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"62710fc6ed3346d5894184aa95d3a0dd":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"75b62e2e75604016b1b25b7dfafd055e":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":"initial"}},"7dc300f0a85241fe8385df414e8a5c97":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"819ad327d8de4df6ab1c59de568544d6":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b1f711e1aaf24dc197f468a9a1d2dac2":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b2e45ab503b34cd68d5ffd0f81cb33f0":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b2e73348f1084afe92c3f03035d8606b":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"IntProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"IntProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"100%","description_tooltip":null,"layout":"IPY_MODEL_3540aa1072634a95b56adbc63b871c44","max":50210,"min":0,"orientation":"horizontal","style":"IPY_MODEL_cfd07d8d18ed471fb9ea717da22823f0","value":50210}},"b57249febd6c457baa5d4ba55f379ec1":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_dc99860fe34c4945b98db54863554527","placeholder":"​","style":"IPY_MODEL_570a0b20e27c418687a1a1b252721597","value":" 50210/50210 [00:34<00:00, 1472.92it/s]"}},"c40188b4079d4a32a3c40d43714ffdeb":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"IntProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"IntProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"100%","description_tooltip":null,"layout":"IPY_MODEL_62710fc6ed3346d5894184aa95d3a0dd","max":50210,"min":0,"orientation":"horizontal","style":"IPY_MODEL_75b62e2e75604016b1b25b7dfafd055e","value":50210}},"c9970f6bf5c54ff8808f97fdeb286846":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"cd962aa4c7514f50a817344fcc4281c0":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_7dc300f0a85241fe8385df414e8a5c97","placeholder":"​","style":"IPY_MODEL_b2e45ab503b34cd68d5ffd0f81cb33f0","value":" 50210/50210 [00:34<00:00, 1453.38it/s]"}},"cfd07d8d18ed471fb9ea717da22823f0":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":"initial"}},"dc99860fe34c4945b98db54863554527":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ddd90cb7822f4ceca0f5bbdb623d9153":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_108585220d384f1d87f3c8444587ae5b","IPY_MODEL_cd962aa4c7514f50a817344fcc4281c0"],"layout":"IPY_MODEL_e175ccd71bbc41ff8aa02b43f00de935"}},"e175ccd71bbc41ff8aa02b43f00de935":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e4855ad98fad40deb899d57d401ae8c3":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f0b119ea39cc420ea11296b456d078d8":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":"initial"}},"f8a313a8731e4aee9ba940aa7bc795b0":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_c40188b4079d4a32a3c40d43714ffdeb","IPY_MODEL_ffa184123d1f45c5a7296f99465f2a08"],"layout":"IPY_MODEL_fcd628bac3174930bdb3727134928c69"}},"fcd628bac3174930bdb3727134928c69":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ffa184123d1f45c5a7296f99465f2a08":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_819ad327d8de4df6ab1c59de568544d6","placeholder":"​","style":"IPY_MODEL_b1f711e1aaf24dc197f468a9a1d2dac2","value":" 50210/50210 [00:34<00:00, 1436.32it/s]"}}},"version_major":2,"version_minor":0}}},"nbformat":4,"nbformat_minor":1}