{"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":"markdown","source":"# Please, upvote if you find the code useful :D","metadata":{}},{"cell_type":"code","source":"!conda install ../input/packages/*.tar.bz2\n# Note that \"*.tar.bz2\" should be the directory of your binary notebook outputs\n# e.g. (../input/{notebook_name}/*.tar.bz2)","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:38:06.031621Z","iopub.execute_input":"2022-09-28T21:38:06.032441Z","iopub.status.idle":"2022-09-28T21:40:21.061399Z","shell.execute_reply.started":"2022-09-28T21:38:06.032396Z","shell.execute_reply":"2022-09-28T21:40:21.060115Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nimport dill\ndill.load_session('../input/joselito/your_bk_dill.pkl')","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:21.063728Z","iopub.execute_input":"2022-09-28T21:40:21.064118Z","iopub.status.idle":"2022-09-28T21:40:32.965292Z","shell.execute_reply.started":"2022-09-28T21:40:21.064074Z","shell.execute_reply":"2022-09-28T21:40:32.964245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#!pip install pyvips","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:32.966547Z","iopub.execute_input":"2022-09-28T21:40:32.966865Z","iopub.status.idle":"2022-09-28T21:40:32.971674Z","shell.execute_reply.started":"2022-09-28T21:40:32.966836Z","shell.execute_reply":"2022-09-28T21:40:32.970616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#!pip install meson\n\n\n","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:32.975226Z","iopub.execute_input":"2022-09-28T21:40:32.97594Z","iopub.status.idle":"2022-09-28T21:40:32.98417Z","shell.execute_reply.started":"2022-09-28T21:40:32.975891Z","shell.execute_reply":"2022-09-28T21:40:32.983261Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#!pip install --user pyvips","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:32.985364Z","iopub.execute_input":"2022-09-28T21:40:32.985656Z","iopub.status.idle":"2022-09-28T21:40:32.995496Z","shell.execute_reply.started":"2022-09-28T21:40:32.985628Z","shell.execute_reply":"2022-09-28T21:40:32.994339Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#!conda install --channel conda-forge pyvips -y","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:32.996831Z","iopub.execute_input":"2022-09-28T21:40:32.997204Z","iopub.status.idle":"2022-09-28T21:40:33.008745Z","shell.execute_reply.started":"2022-09-28T21:40:32.997161Z","shell.execute_reply":"2022-09-28T21:40:33.007307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pyvips\n# import _libvips\n# image = pyvips.Image.new_from_file('../input/mayo-clinic-strip-ai/test/006388_0.tif', access='sequential')\n# image.write_to_file('x.jpg')","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:33.010625Z","iopub.execute_input":"2022-09-28T21:40:33.011143Z","iopub.status.idle":"2022-09-28T21:40:33.023564Z","shell.execute_reply.started":"2022-09-28T21:40:33.011087Z","shell.execute_reply":"2022-09-28T21:40:33.022221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# print(image)","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:33.02533Z","iopub.execute_input":"2022-09-28T21:40:33.025958Z","iopub.status.idle":"2022-09-28T21:40:33.034826Z","shell.execute_reply.started":"2022-09-28T21:40:33.025902Z","shell.execute_reply":"2022-09-28T21:40:33.033996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"director = '../input/mayo-clinic-strip-ai/test'\ncase = os.listdir(director)\ncase\nfile_name = []\nimage_matrix = []\n\n#from pathlib import Path\n#for f in Path('./').glob('*.jpg'):\n#    try:\n#        f.unlink()\n #   except OSError as e:\n #       print('Error')\n        \n#dirs = [\"../input/mayo-clinic-strip-ai/train/\", \"../input/mayo-clinic-strip-ai/test/\"]\n#df_test = df_train.copy()\n#df_test = pd.read_csv('../input/mayo-clinic-strip-ai/test.csv')\n#try:\n  #  os.mkdir(\"'../test/'\")\n#except:\n#    pass\n#for i in tqdm(range(df_test.shape[0])):\n#    img_id = df_test.iloc[i].image_id\n#    try:\n #       sz = os.path.getsize(dirs[1] + img_id + \".tif\")\n #   except:\n#        sz = 1000000000\n#    if(sz > 8e8):\n  #      img = np.zeros((512,512,3), np.uint8)\n  #  else:\n  #      try:\n #           img = cv2.resize(tifffile.imread(dirs[1] + img_id + \".tif\"), (512, 512))\n   #     except:\n #           img = np.zeros((512,512,3), np.uint8)\n  #  cv2.imwrite(f\"../test/{img_id}.jpg\", img)\n  #  del img\n   # gc.collect()","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:33.03698Z","iopub.execute_input":"2022-09-28T21:40:33.037873Z","iopub.status.idle":"2022-09-28T21:40:33.048845Z","shell.execute_reply.started":"2022-09-28T21:40:33.037839Z","shell.execute_reply":"2022-09-28T21:40:33.047474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# try:\n#     size = os.path.getsize(image_path)\n# except:\n#     size = 2*1e9\n    \n# if(size > 1.2*1e9):\n#     df['CE'] = 0.5\n#     df['LAA'] = 0.5\n# else:\n#     try:\n#         #code\n        \n#     except:\n#         df['CE'] = 0.5\n#         df['LAA'] = 0.5","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:33.054265Z","iopub.execute_input":"2022-09-28T21:40:33.054625Z","iopub.status.idle":"2022-09-28T21:40:33.059986Z","shell.execute_reply.started":"2022-09-28T21:40:33.054593Z","shell.execute_reply":"2022-09-28T21:40:33.058859Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"half = len(case)//2\nfor i in case[0:half]:\n    im1 = []\n    directory_ = '../input/mayo-clinic-strip-ai/test/'\n    imagenes = os.listdir(directory_)\n    k = k+1\n    im1 = pyvips.Image.new_from_file('../input/mayo-clinic-strip-ai/test/'+ i, access='sequential')\n    im1.write_to_file(str(k)+'.jpg')\n    del im1\n    gc.collect()\n    \nfor i in case[half:len(case)]:\n    im1 = []\n    directory_ = '../input/mayo-clinic-strip-ai/test/'\n    imagenes = os.listdir(directory_)\n    k = k+1\n    im1 = pyvips.Image.new_from_file('../input/mayo-clinic-strip-ai/test/'+ i, access='sequential')\n    im1.write_to_file(str(k)+'.jpg')\n    del im1\n    gc.collect()","metadata":{"execution":{"iopub.status.busy":"2022-09-28T21:40:33.061703Z","iopub.execute_input":"2022-09-28T21:40:33.062446Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# half = len(case)//2\n# for i in case[0:half]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/test/'\n#     imagenes = os.listdir(directory_)\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/test/'+ i)\n#     res = cv2.resize(im1, dsize=(170, 304), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n#     del im1\n#     del res\n#     gc.collect()\n    \n# for i in case[half:len(case)]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/test/'\n#     imagenes = os.listdir(directory_)\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/test/'+ i)\n#     res = cv2.resize(im1, dsize=(170, 304), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n#     del im1\n#     del res\n#     gc.collect()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# for i in case:\n#     try:\n#         size = os.path.getsize(i)\n#     except:\n#         size = 2*1e9\n    \n#     if(size > 1.2*1e9):\n#         df['CE'] = 0.5\n#         df['LAA'] = 0.5\n#     else:\n#         try:\n#             im1 = []\n#             directory_ = '../input/mayo-clinic-strip-ai/test/'\n#             imagenes = os.listdir(directory_)\n#             k = k+1\n#             im1 = pyvips.Image.new_from_file('../input/mayo-clinic-strip-ai/test/'+ i, access='sequential')\n#             im1.write_to_file(str(k)+'.jpg')\n#             del im1\n#             gc.collect()\n#         except:\n#             df['CE'] = 0.5\n#             df['LAA'] = 0.5","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = df_train.copy()\ndf_test = pd.read_csv('../input/mayo-clinic-strip-ai/test.csv')\n\nlabels = []\nnames = []\nfor i in range(len(df_test['patient_id'])):\n    labels.append(df_train['label'][i])\n    names.append(df_test['patient_id'][i])\nlabels_code = []\nfor i in labels:\n    labels_code.append(labels.index(i))\n\ndatadir='./' \nflat_data_arr=[] \ntarget_arr=[] \npath=datadir\nfor img in os.listdir(path):\n    if os.path.isfile(path + img)==True:\n        if imghdr.what(img)=='jpeg':\n            print(img)\n            im1 = pyvips.Image.new_from_file(path + img, access='sequential')\n            im1_ = pyvips.Image.thumbnail(img, 200, height=300, size=\"both\") \n            im1___ = np.asarray(im1_)\n#             img_array=skio.imread(path + img)\n#             img_array=iio.imread(img)\n            img_resized=resize(im1___,(150,150,3))\n            flat_data_arr.append(img_resized.flatten())\nflat_data=np.array(flat_data_arr)\ntarget=np.array(labels_code)\ndf = df_train.copy()\ndf=pd.DataFrame(flat_data) \ndf.head()\n#df['Target']=target\n#df.drop_duplicates(subset=['patient_id'], keep='last')\nxtest=df.iloc[:,:] \nytest=df.iloc[:,-1]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import gc\nfrom PIL import Image\nfrom tqdm.auto import tqdm\nimport os, glob","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"xtest","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\ny_pred=model.predict_proba(xtest)\nprint(\"The predicted Data is :\")\nprint(y_pred)\nprint(\"The actual data is:\")\nprint(np.array(ytest))\n\nDATASET_FOLDER='../input/mayo-clinic-strip-ai'\nImage.MAX_IMAGE_PIXELS = 25_000_000_000\nls_imgs = glob.glob(os.path.join(DATASET_FOLDER, \"test\", \"*.tif\"))\n\npreds = []\n\nfor p_img in ls_imgs:\n    name, _ = os.path.splitext(os.path.basename(p_img))\n    preds.append({\n        \"patient_id\": name.split(\"_\")[0],\n    })\n    \n\n\n\n\ndf=pd.DataFrame(list(zip(names,y_pred[:,0],y_pred[:,1])),columns=['patient_id','CE','LAA'])\n#df.drop_duplicates(subset=['patient_id'], keep='last')\nt = 0\nfor i in case:\n    try:\n        size = os.path.getsize(i)\n    except:\n        size = 2*1e9\n    \n    if(size > 1.2*1e9):\n        df['CE'][t] = 0.5\n        df['LAA'][t] = 0.5\n    else:\n        try:\n            im1 = []\n            directory_ = '../input/mayo-clinic-strip-ai/test/'\n            imagenes = os.listdir(directory_)\n            k = k+1\n            im1 = pyvips.Image.new_from_file('../input/mayo-clinic-strip-ai/test/'+ i, access='sequential')\n            im1.write_to_file(str(k)+'.jpg')\n            del im1\n            gc.collect()\n        except:\n            df['CE'][t] = 0.5\n            df['LAA'][t] = 0.5\n        t = t + 1\n\n\nimport csv\nimport math\nfor i in range(len(df)):\n    if math.isnan(df['CE'][i]) == True:\n        df['CE'][i] = 0.5\n    if math.isnan(df['LAA'][i]) == True:\n        df['LAA'][i] =0.5\ndf = df.groupby(\"patient_id\").mean()\ndf[[\"CE\", \"LAA\"]].round(6).to_csv(\"submission.csv\")\n# open the file in the write moded\n#df.to_csv('./submission.csv',index = None)\nprint(df)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# from sklearn.metrics import log_loss\n# ytest[0] = 0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# logloss = log_loss(ytest, model.predict_proba(xtest))\n# logloss","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!head submission.csv","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['LAA']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import numpy as np \n# import pandas as pd \n# import os\n# import matplotlib.pyplot as plt\n# import seaborn as sns\n# import cv2\n# import skimage.io as skio\n# from sklearn.metrics import accuracy_score\n# import os\n# import gc\n# import cv2\n# import copy\n# import time\n# import random\n# import string\n# import joblib\n# import tifffile\n# import numpy as np \n# import pandas as pd \n# import torch\n# from torch import nn\n# import seaborn as sns\n# from torchvision import models\n# import matplotlib.pyplot as plt\n# from torch.utils.data import Dataset, DataLoader\n# from sklearn.model_selection import train_test_split\n# from tqdm.notebook import tqdm\n# from torch.optim import lr_scheduler\n# import warnings\n# warnings.filterwarnings(\"ignore\")\n# gc.enable()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train = pd.read_csv('../input/mayo-clinic-strip-ai/train.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# im1 = skio.imread('../input/mayo-clinic-strip-ai/train/006388_0.tif')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_other = df_train.copy()\n# df_other = pd.read_csv('../input/mayo-clinic-strip-ai/other.csv')\n# df_other.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sample_submission = df_train.copy()\n# sample_submission = pd.read_csv('../input/mayo-clinic-strip-ai/sample_submission.csv')\n# sample_submission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# director = '../input/mayo-clinic-strip-ai/train'\n# case = os.listdir(director)\n# case\n# file_name = []\n# image_matrix = []","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# k=0\n# label = []\n# for i in case[0:20]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/train/'\n#     imagenes = os.listdir(directory_)\n#     label.append(df_train['label'][k])\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/train/'+ i)\n#     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# labels = []\n# for i in range(len(df_train['label'])):\n#     labels.append(df_train['label'][i])\n# labels_code = []\n# for i in labels:\n#     labels_code.append(labels.index(i))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# SVC: Select the whole text and press Ctrl + / to delete the # symbols","metadata":{}},{"cell_type":"code","source":"# import pandas as pd\n# import os\n# from skimage.transform import resize\n# from skimage.io import imread\n# import numpy as np\n# import matplotlib.pyplot as plt\n# import imageio.v3 as iio\n# import imghdr\n# Categories=['CE','LAA']\n# flat_data_arr=[] \n# target_arr=[] \n# datadir='./' \n\n# path=datadir\n# for img in os.listdir(path):\n#     if imghdr.what(img)=='jpeg':\n#         print(img)\n\n# k=0\n# label = []\n# for i in case[0:200]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/train/'\n#     imagenes = os.listdir(directory_)\n#     label.append(df_train['label'][k])\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/train/'+ i)\n#     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n\n# label = []\n# for i in case[200:400]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/train/'\n#     imagenes = os.listdir(directory_)\n#     label.append(df_train['label'][k])\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/train/'+ i)\n#     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n\n\n# label = []\n# for i in case[400:600]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/train/'\n#     imagenes = os.listdir(directory_)\n#     label.append(df_train['label'][k])\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/train/'+ i)\n#     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n\n# label = []\n# for i in case[600:754]:\n#     im1 = []\n#     directory_ = '../input/mayo-clinic-strip-ai/train/'\n#     imagenes = os.listdir(directory_)\n#     label.append(df_train['label'][k])\n#     k = k+1\n#     im1 = skio.imread('../input/mayo-clinic-strip-ai/train/'+ i)\n#     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n#     cv2.imwrite(str(k)+'.jpg', res)\n\n# import pandas as pd\n# import os\n# from skimage.transform import resize\n# from skimage.io import imread\n# import numpy as np\n# import matplotlib.pyplot as plt\n# import imageio.v3 as iio\n# Categories=['CE','LAA']\n# flat_data_arr=[] \n# target_arr=[] \n# datadir='./' \n\n# path=datadir\n# for img in os.listdir(path):\n#     print(img)\n#     if imghdr.what(img)=='jpeg':\n#         print(img)\n#         img_array=skio.imread(path + img)\n#         img_array=iio.imread(img)\n#         img_resized=resize(img_array,(150,150,3))\n#         flat_data_arr.append(img_resized.flatten())\n# flat_data=np.array(flat_data_arr)\n# target=np.array(labels_code)\n# df = df_train.copy()\n# df=pd.DataFrame(flat_data) \n# df.head()\n# df['Target']=target\n        \n# x=df.iloc[:,:-1] \n# y=df.iloc[:,-1] \n\n# from sklearn import svm\n# from sklearn.model_selection import GridSearchCV\n# param_grid={'C':[0.1,1,10,100],'gamma':[0.0001,0.001,0.1,1],'kernel':['rbf','poly']}\n# svc=svm.SVC(probability=True)\n# model=GridSearchCV(svc,param_grid)\n\n# # from sklearn.model_selection import train_test_split\n# # x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.20,random_state=77,stratify=y)\n# # print('Splitted Successfully')\n# # model.fit(x_train,y_train)\n# # print('The Model is trained well with the given images')\n\n# # y_pred=model.predict_proba(x_test)\n# # print(\"The predicted Data is :\")\n# # print(y_pred)\n# # print(\"The actual data is:\")\n# # print(np.array(y_test))\n\n# # print(f\"The model is {accuracy_score(y_pred,y_test)*100}% accurate\")\n\n\n# director = '../input/mayo-clinic-strip-ai/test'\n# case = os.listdir(director)\n# case\n# file_name = []\n# image_matrix = []\n\n# from pathlib import Path\n# for f in Path('./').glob('*.jpg'):\n#     try:\n#         f.unlink()\n#     except OSError as e:\n#         print('Error')\n        \n# dirs = [\"../input/mayo-clinic-strip-ai/train/\", \"../input/mayo-clinic-strip-ai/test/\"]\n# df_test = df_train.copy()\n# df_test = pd.read_csv('../input/mayo-clinic-strip-ai/test.csv')\n# try:\n#     os.mkdir(\"'../test/'\")\n# except:\n#     pass\n# for i in tqdm(range(df_test.shape[0])):\n#     img_id = df_test.iloc[i].image_id\n#     try:\n#         sz = os.path.getsize(dirs[1] + img_id + \".tif\")\n#     except:\n#         sz = 1000000000\n#     if(sz > 8e8):\n#         img = np.zeros((512,512,3), np.uint8)\n#     else:\n#         try:\n#             img = cv2.resize(tifffile.imread(dirs[1] + img_id + \".tif\"), (512, 512))\n#         except:\n#             img = np.zeros((512,512,3), np.uint8)\n#     cv2.imwrite(f\"../test/{img_id}.jpg\", img)\n#     del img\n#     gc.collect()\n        \n        \n\n# label = []\n# # half = len(case)//2\n# # for i in case[0:half]:\n# #     im1 = []\n# #     directory_ = '../input/mayo-clinic-strip-ai/test/'\n# #     imagenes = os.listdir(directory_)\n# #     k = k+1\n# #     im1 = skio.imread('../input/mayo-clinic-strip-ai/test/'+ i)\n# #     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n# #     cv2.imwrite(str(k)+'.jpg', res)\n    \n# # for i in case[half:len(case)]:\n# #     im1 = []\n# #     directory_ = '../input/mayo-clinic-strip-ai/test/'\n# #     imagenes = os.listdir(directory_)\n# #     k = k+1\n# #     im1 = skio.imread('../input/mayo-clinic-strip-ai/test/'+ i)\n# #     res = cv2.resize(im1, dsize=(1700, 3040), interpolation=cv2.INTER_CUBIC)\n# #     cv2.imwrite(str(k)+'.jpg', res)\n\n\n# df_test = df_train.copy()\n# df_test = pd.read_csv('../input/mayo-clinic-strip-ai/test.csv')\n\n# labels = []\n# names = []\n# for i in range(len(df_test['patient_id'])):\n#     labels.append(df_train['label'][i])\n#     names.append(df_test['patient_id'][i])\n# labels_code = []\n# for i in labels:\n#     labels_code.append(labels.index(i))\n\n# datadir='./' \n# flat_data_arr=[] \n# target_arr=[] \n# path=datadir\n# for img in os.listdir(path):\n#     print(img)\n#     if imghdr.what(img)=='jpeg':\n#         print(img)\n#         img_array=skio.imread(path + img)\n#         img_array=iio.imread(img)\n#         img_resized=resize(img_array,(150,150,3))\n#         flat_data_arr.append(img_resized.flatten())\n# flat_data=np.array(flat_data_arr)\n# target=np.array(labels_code)\n# df = df_train.copy()\n# df=pd.DataFrame(flat_data) \n# df.head()\n# df['Target']=target\n        \n# xtest=df.iloc[:,:-1] \n# ytest=df.iloc[:,-1] \n\n# model.fit(x,y)\n# print('The Model is trained well with the given images')\n\n# from sklearn.metrics import accuracy_score\n# y_pred=model.predict(xtest)\n# from sklearn.metrics import log_loss\n\n# logloss = log_loss(ytest, y_pred,eps=1e-15, normalize=True, sample_weight=None, labels=None)\n# print(log_loss)\n# # print(y_pred)\n# # print(\"The actual data is:\")\n# # print(np.array(ytest))\n\n# df=pd.DataFrame(list(zip(names,logloss[:,0],logloss[:,1])),columns=['patient_id','CE','LAA']) \n# import csv\n\n# # open the file in the write moded\n# df.to_csv('./submission.csv',index = None)\n\n# import dill;\n# # Save the entire session by creating a new pickle file \n# dill.dump_session('./your_bk_dill.pkl');\n\n# # Restore the entire session\n# # dill.load_session('./your_bk_dill.pkl');","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}