{"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":"# 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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-07-28T09:19:33.899348Z","iopub.execute_input":"2023-07-28T09:19:33.899649Z","iopub.status.idle":"2023-07-28T09:19:33.917477Z","shell.execute_reply.started":"2023-07-28T09:19:33.899621Z","shell.execute_reply":"2023-07-28T09:19:33.916336Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split\nfrom PIL import Image\nimport glob\nimport matplotlib.pyplot as plt\nimport random\nimport matplotlib.image as mpimg\nimport shutil","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:19:33.919652Z","iopub.execute_input":"2023-07-28T09:19:33.919989Z","iopub.status.idle":"2023-07-28T09:19:45.105378Z","shell.execute_reply.started":"2023-07-28T09:19:33.919956Z","shell.execute_reply":"2023-07-28T09:19:45.104127Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# zipファイルを展開","metadata":{}},{"cell_type":"code","source":"base_dir = \"../input/dogs-vs-cats\"\ntrain_dir = os.path.join(base_dir, \"train.zip\")\ntest_dir = os.path.join(base_dir, \"test1.zip\")\n\nimport zipfile\nwith zipfile.ZipFile(train_dir,\"r\") as z:\n    z.extractall()\n\nwith zipfile.ZipFile(test_dir,\"r\") as z:\n    z.extractall()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:19:45.106925Z","iopub.execute_input":"2023-07-28T09:19:45.107768Z","iopub.status.idle":"2023-07-28T09:20:00.371022Z","shell.execute_reply.started":"2023-07-28T09:19:45.107712Z","shell.execute_reply":"2023-07-28T09:20:00.369914Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.listdir(\"/kaggle/working/\") #dir確認","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.373572Z","iopub.execute_input":"2023-07-28T09:20:00.373915Z","iopub.status.idle":"2023-07-28T09:20:00.382779Z","shell.execute_reply.started":"2023-07-28T09:20:00.373881Z","shell.execute_reply":"2023-07-28T09:20:00.381728Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.getcwd()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.384512Z","iopub.execute_input":"2023-07-28T09:20:00.384903Z","iopub.status.idle":"2023-07-28T09:20:00.395796Z","shell.execute_reply.started":"2023-07-28T09:20:00.384870Z","shell.execute_reply":"2023-07-28T09:20:00.394943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"passを作る","metadata":{}},{"cell_type":"code","source":"train_path = '/kaggle/working/train/' #trainデータ\ntest1_path = '/kaggle/working/test1/' #testデータ","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.397158Z","iopub.execute_input":"2023-07-28T09:20:00.398115Z","iopub.status.idle":"2023-07-28T09:20:00.405888Z","shell.execute_reply.started":"2023-07-28T09:20:00.398082Z","shell.execute_reply":"2023-07-28T09:20:00.404959Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 猫と犬のディレクトリを作り分ける","metadata":{}},{"cell_type":"code","source":"\"\"\"\nos.mkdir(train_path + 'cats')\ncat_dir = ('/kaggle/working/train/cats/')\nos.mkdir(train_path + 'dogs')\ndog_dir = ('/kaggle/working/train/dogs/')\n\ndirs = [each for each in os.listdir(train_path)]\n\nfor file in dirs:\n    folder = file.split(\".\")[0]\n    if folder == 'cat':\n        shutil.move(train_path+file, cat_dir)\n    elif folder == 'dog':\n        shutil.move(train_path+file, dog_dir)\n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.407531Z","iopub.execute_input":"2023-07-28T09:20:00.407939Z","iopub.status.idle":"2023-07-28T09:20:00.421764Z","shell.execute_reply.started":"2023-07-28T09:20:00.407907Z","shell.execute_reply":"2023-07-28T09:20:00.420017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 画像の前処理","metadata":{}},{"cell_type":"code","source":"\"\"\"\nfolder = ['cats','dogs']\nimage_size = 224 #インプット画像のサイズ\nX = []\nY = []\nfor index, name in enumerate(folder): #ディレクトリの種類、画像ファイル名を繰返し取得する\n    dir = train_path + name\n    files = glob.glob(dir + \"/*.jpg\") #ファイル名の取得\n    for i, file in enumerate(files): #各画像へ↓の処理を繰返し実施する\n        image = Image.open(file) #画像の読み込み\n        image = image.convert(\"RGB\") #RGBに変換\n        image = image.resize((image_size, image_size)) #サイズ変更\n        data = np.asarray(image) #画像データを配列へ変更\n        X.append(data) #画像データを繰返し追加\n        Y.append(index) #cat:0, dog:1の値を繰返し追加\nX = np.array(X)\nY = np.array(Y)\n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.424186Z","iopub.execute_input":"2023-07-28T09:20:00.424590Z","iopub.status.idle":"2023-07-28T09:20:00.434068Z","shell.execute_reply.started":"2023-07-28T09:20:00.424558Z","shell.execute_reply":"2023-07-28T09:20:00.432873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\"\"\"\n#正解ラベルの形式を変換\nY = to_categorical(Y, 2)\nprint(Y)\n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.438882Z","iopub.execute_input":"2023-07-28T09:20:00.439141Z","iopub.status.idle":"2023-07-28T09:20:00.447831Z","shell.execute_reply.started":"2023-07-28T09:20:00.439117Z","shell.execute_reply":"2023-07-28T09:20:00.446876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filenames = os.listdir(train_path) #dog123~~~,cat1234~~など\ncategories = [] #リスト初期化\nfor filename in filenames: #filenames(dog123~~~,cat1234~~)を一つずつfilenameに入れてforループ\n    category = filename.split('.')[0]#filenameは(dog.4784.jpg)この形なのでsplitを用いることにより[dog,4784,jpg]に分けられるこれの[0]をとることで[dog,cat]を受け取れる\n    if category == 'dog':\n        categories.append(1)#dog = 1,cat = 0をcnnでの判定で用いる。\n    else:\n        categories.append(0)\ndata = pd.DataFrame({'filename' : filenames , 'category' : categories})#dataframe型でdataに代入する(filename = dog.4784.jpg,category = 1(dog))\ndata.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.449310Z","iopub.execute_input":"2023-07-28T09:20:00.449806Z","iopub.status.idle":"2023-07-28T09:20:00.532176Z","shell.execute_reply.started":"2023-07-28T09:20:00.449772Z","shell.execute_reply":"2023-07-28T09:20:00.530848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['category'].value_counts()#確認(dogとcatの数)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.533744Z","iopub.execute_input":"2023-07-28T09:20:00.534581Z","iopub.status.idle":"2023-07-28T09:20:00.551273Z","shell.execute_reply.started":"2023-07-28T09:20:00.534537Z","shell.execute_reply":"2023-07-28T09:20:00.550280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data['category1'] = data['category'].apply(lambda x: 'cat' if x== 0 else 'dog')#datafram型にcategory1(dog,cat)を追加する\ndata.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.552607Z","iopub.execute_input":"2023-07-28T09:20:00.553062Z","iopub.status.idle":"2023-07-28T09:20:00.720406Z","shell.execute_reply.started":"2023-07-28T09:20:00.553024Z","shell.execute_reply":"2023-07-28T09:20:00.719255Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.drop(['category'] , inplace = True , axis = 1)#category(1,0)を削除する\ndata.rename(columns  = {'category1' : 'category'} , inplace =True)#category1(dog,cat)をcategoryに名前を変える\ndata.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.722331Z","iopub.execute_input":"2023-07-28T09:20:00.722957Z","iopub.status.idle":"2023-07-28T09:20:00.741832Z","shell.execute_reply.started":"2023-07-28T09:20:00.722744Z","shell.execute_reply":"2023-07-28T09:20:00.740631Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df , val_df = train_test_split(data , test_size = 0.2 , random_state = 42)#traindataをtrainとval(確認用)に分けるsizeはtrainが80%valが20%,seed値(random_state)を設定することで毎回同じデータに分けることが可能\ntrain_df = train_df.reset_index(drop = True)#splitをすることでindexがランダムになるので初期化する\nval_df = val_df.reset_index(drop = True)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.743651Z","iopub.execute_input":"2023-07-28T09:20:00.744033Z","iopub.status.idle":"2023-07-28T09:20:00.757442Z","shell.execute_reply.started":"2023-07-28T09:20:00.743997Z","shell.execute_reply":"2023-07-28T09:20:00.756490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\"\"\"\n#学習用データとテストデータへ分割\nX_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20)\n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.759079Z","iopub.execute_input":"2023-07-28T09:20:00.759469Z","iopub.status.idle":"2023-07-28T09:20:00.768854Z","shell.execute_reply.started":"2023-07-28T09:20:00.759430Z","shell.execute_reply":"2023-07-28T09:20:00.767865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\"\"\"\ndel X #メモリ削減\n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.770245Z","iopub.execute_input":"2023-07-28T09:20:00.770893Z","iopub.status.idle":"2023-07-28T09:20:00.779409Z","shell.execute_reply.started":"2023-07-28T09:20:00.770831Z","shell.execute_reply":"2023-07-28T09:20:00.778463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ジェネレータの作成","metadata":{}},{"cell_type":"code","source":"image_size = 224#画像サイズ一辺\nImage_size = (image_size,image_size)#縦,横(224,224)\nbatch_size = 128#まとまり\nepochs = 10#iteration","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.780813Z","iopub.execute_input":"2023-07-28T09:20:00.781296Z","iopub.status.idle":"2023-07-28T09:20:00.790705Z","shell.execute_reply.started":"2023-07-28T09:20:00.781259Z","shell.execute_reply":"2023-07-28T09:20:00.789668Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 画像データの拡張と前処理の設定\ntrain_datagen = ImageDataGenerator(\n    rescale=1.0/255,#0~1に正規化\n    rotation_range=45,#回転,-45~45\n    shear_range = 0.1,#シアー強度\n    zoom_range = 0.2 , #ズーム\n    horizontal_flip = True , #左右反転\n    width_shift_range = 0.1 , #水平シフト\n    height_shift_range = 0.1 #垂直シフト\n)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.792574Z","iopub.execute_input":"2023-07-28T09:20:00.793149Z","iopub.status.idle":"2023-07-28T09:20:00.803138Z","shell.execute_reply.started":"2023-07-28T09:20:00.793114Z","shell.execute_reply":"2023-07-28T09:20:00.802167Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ジェネレータの作成\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df, #dataframe\n    train_path, #trainデータへのパス('/kaggle/working/train/')\n    x_col='filename',#特徴量\n    y_col='category',#category(0,1)\n    target_size=Image_size,#size\n    class_mode='categorical',#返すラベルの配列の形を決定する\n    batch_size=batch_size\n)  ","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:00.804849Z","iopub.execute_input":"2023-07-28T09:20:00.805153Z","iopub.status.idle":"2023-07-28T09:20:01.052480Z","shell.execute_reply.started":"2023-07-28T09:20:00.805123Z","shell.execute_reply":"2023-07-28T09:20:01.051451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale = 1./255)\nval_generator = validation_datagen.flow_from_dataframe(\n    val_df, \n    train_path, \n    x_col='filename',\n    y_col='category',\n    target_size=Image_size,\n    class_mode='categorical',\n    batch_size=batch_size\n)  ","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:01.053914Z","iopub.execute_input":"2023-07-28T09:20:01.054351Z","iopub.status.idle":"2023-07-28T09:20:01.126896Z","shell.execute_reply.started":"2023-07-28T09:20:01.054317Z","shell.execute_reply":"2023-07-28T09:20:01.125995Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# モデルの作成","metadata":{}},{"cell_type":"code","source":"\n#CNNモデル（ResNet50）のライブラリをインポート\nfrom tensorflow.keras.applications.resnet50 import ResNet50\nfrom tensorflow.keras.models import Sequential, Model\nfrom tensorflow.keras.layers import Input, Flatten, Dense, Conv2D , MaxPooling2D , Dropout, Activation , BatchNormalization\n\n#input画像の定義\ninput_tensor = tf.keras.Input(shape=(image_size, image_size, 3))\n#ResNet50モデルの呼出し。ここでweights=\"imagenet\"とすることで学習済の重みを使うことができる\n#include_top=Falseとすることで出力層だけを今回の学習に合わせた形で書き換えます\nResNet50 = tf.keras.applications.ResNet50(include_top=False, weights=\"imagenet\", \n                                          input_tensor=input_tensor,classes=2,)\n#出力層の書換え。今回は2種類の画像分類のモデルを作成。\ntop_model = Sequential()\ntop_model.add(Flatten(input_shape = ResNet50.output_shape[1:]))\ntop_model.add(Dense(2, activation = 'sigmoid'))\nmodel = Model(inputs=ResNet50.inputs, outputs=top_model(ResNet50.outputs))","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:01.128254Z","iopub.execute_input":"2023-07-28T09:20:01.128582Z","iopub.status.idle":"2023-07-28T09:20:08.693018Z","shell.execute_reply.started":"2023-07-28T09:20:01.128555Z","shell.execute_reply":"2023-07-28T09:20:08.691975Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.optimizers import Adam \nadam = Adam(learning_rate=0.0001)\nmodel.compile(optimizer= adam, loss='categorical_crossentropy', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:08.696660Z","iopub.execute_input":"2023-07-28T09:20:08.696941Z","iopub.status.idle":"2023-07-28T09:20:08.721121Z","shell.execute_reply.started":"2023-07-28T09:20:08.696915Z","shell.execute_reply":"2023-07-28T09:20:08.720033Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:08.722763Z","iopub.execute_input":"2023-07-28T09:20:08.723143Z","iopub.status.idle":"2023-07-28T09:20:09.304135Z","shell.execute_reply.started":"2023-07-28T09:20:08.723106Z","shell.execute_reply":"2023-07-28T09:20:09.303333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 学習","metadata":{}},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau\nearlystop = EarlyStopping(patience = 10)\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=2, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\ncallbacks = [earlystop , learning_rate_reduction]","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:09.315824Z","iopub.execute_input":"2023-07-28T09:20:09.316161Z","iopub.status.idle":"2023-07-28T09:20:09.327061Z","shell.execute_reply.started":"2023-07-28T09:20:09.316127Z","shell.execute_reply":"2023-07-28T09:20:09.326218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# モデルの学習\nhistory = model.fit_generator(\n    train_generator , \n    epochs = epochs , \n    validation_data=val_generator,\n    validation_steps=val_df.shape[0]//batch_size,\n    steps_per_epoch=train_df.shape[0]//batch_size,\n    callbacks=callbacks\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T09:20:09.328122Z","iopub.execute_input":"2023-07-28T09:20:09.328483Z","iopub.status.idle":"2023-07-28T10:21:37.834947Z","shell.execute_reply.started":"2023-07-28T09:20:09.328447Z","shell.execute_reply":"2023-07-28T10:21:37.833894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 保存","metadata":{}},{"cell_type":"code","source":"model.save_weights('model.1')","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:21:37.838579Z","iopub.execute_input":"2023-07-28T10:21:37.838891Z","iopub.status.idle":"2023-07-28T10:21:39.496737Z","shell.execute_reply.started":"2023-07-28T10:21:37.838857Z","shell.execute_reply":"2023-07-28T10:21:39.495618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# モデル→予測","metadata":{}},{"cell_type":"code","source":"test_filenames = os.listdir(test1_path)\ntest = pd.DataFrame({'filename' : test_filenames})\nnb_samples = test.shape[0]","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:21:39.497988Z","iopub.execute_input":"2023-07-28T10:21:39.498364Z","iopub.status.idle":"2023-07-28T10:21:39.514055Z","shell.execute_reply.started":"2023-07-28T10:21:39.498328Z","shell.execute_reply":"2023-07-28T10:21:39.512974Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test , \n    test1_path ,\n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=(image_size,image_size),\n    batch_size=batch_size,\n    shuffle=False\n    )","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:21:39.515416Z","iopub.execute_input":"2023-07-28T10:21:39.515847Z","iopub.status.idle":"2023-07-28T10:21:39.650834Z","shell.execute_reply.started":"2023-07-28T10:21:39.515810Z","shell.execute_reply":"2023-07-28T10:21:39.649940Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predict = model.predict_generator(test_generator , steps = np.ceil(nb_samples/batch_size))\ntest['category'] = np.argmax(predict  , axis= -1)\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:21:39.652419Z","iopub.execute_input":"2023-07-28T10:21:39.652776Z","iopub.status.idle":"2023-07-28T10:22:26.223294Z","shell.execute_reply.started":"2023-07-28T10:21:39.652743Z","shell.execute_reply":"2023-07-28T10:22:26.222278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission_df = test.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:22:26.224906Z","iopub.execute_input":"2023-07-28T10:22:26.225286Z","iopub.status.idle":"2023-07-28T10:22:26.264329Z","shell.execute_reply.started":"2023-07-28T10:22:26.225247Z","shell.execute_reply":"2023-07-28T10:22:26.263036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission_df.drop(['filename' , 'category'] , axis = 1 , inplace = True)\nsubmission_df.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T10:22:26.266007Z","iopub.execute_input":"2023-07-28T10:22:26.266527Z","iopub.status.idle":"2023-07-28T10:22:26.307413Z","shell.execute_reply.started":"2023-07-28T10:22:26.266487Z","shell.execute_reply":"2023-07-28T10:22:26.306512Z"},"trusted":true},"execution_count":null,"outputs":[]}]}