{"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)\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\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":{"_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":"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 trainig 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":{},"cell_type":"markdown","source":"# EDA"},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 236\nWIDTH = 236\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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    return image","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Number of unique values"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df_.head()\nlen(train_df_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f'Number of unique graheme roots : {train_df_[\"grapheme_root\"].nunique()}')\nprint(f'Number of unique vowel diacritic : {train_df_[\"vowel_diacritic\"].nunique()}')\n\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":"top_graphemes = train_df_.groupby(['grapheme_root']).size().reset_index(name='counts')['counts'].sort_values(ascending=not True)[:10]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"type(top_graphemes)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"top_graphemes.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(train_df_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(top_graphemes)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"top_graphemes.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"a = pd.DataFrame([('bird', 'Falconiformes', 389.0),\n\t                    ('bird', 'Psittaciformes', 24.0),\n\t                    ('mammal', 'Carnivora', 80.2),\n\t                    ('mammal', 'Primates', np.nan),\n\t                    ('mammal', 'Carnivora', 58)],\n\t                  index=['falcon', 'parrot', 'lion', 'monkey', 'leopard'],\n\t                  columns=('class', 'order', 'max_speed'))\n ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"a","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"b=a.groupby(['class'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"b.groups","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"b.indices","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 training 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":"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":"IMG_SIZE=64\nN_CHANNELS=1","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's apply some image processing 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            is_xmin=[]\n            is_ymin=[]\n            is_xmax=[]\n            is_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=min(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=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            is_xmin=[]\n            is_ymin=[]\n            is_xmax=[]\n            is_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=min(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_dummieds(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":{"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 annealer. Learning rate will be half after 3 epochs if accuracy is not increased\n\nlearning_rate_reduction_root = ReduceLROnPlateau(monitor='dense_3_accuracy',\n                                                patience=3,\n                                                verbose=1,\n                                                factor=0.5,\n                                                min_lr=0.0001)\nlearning_rate_reduction_vowel = ReduceLROnPlateau(monitor='dense_4_accuracy',\n                                                 patience=3,\n                                                 verbose=1, #it may show progress bar \n                                                  factor=0.5,\n                                                  min_lr=0.00001\n                                                 )\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    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        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        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    #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    #CNN takes images in shape '(batch_size,h,w,channels)', so reshape the images\n\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'Trainign labels vowel : {Y_train_vowel.shape}')\n    print(f'Training labels consonants : {Y_train_consonant.shpae}')\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, \n        y_train_consonant, y_test_consonant = \n            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 imput mean to 0 over the data set\n        samplewise_cneter=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    # This will just calculate parameters required to augment the given data. This won't perform any augmentations\n    datagee.fix(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    histories.append(history)\n    \n    #Delete to reduce memory usage\n    \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    \n    gc.collect()\n    \n    ","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":1}