{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-output":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\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\n# import os\n# for 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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm.autonotebook import tqdm\ntqdm.pandas()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"base_dir = '/kaggle/input/landmark-recognition-2020'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Analyze training dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(os.path.join(base_dir,'train.csv'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.duplicated().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['landmark_id'].value_counts().hist()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# missing data in training data \ntotal = train.isnull().sum().sort_values(ascending = False)\npercent = (train.isnull().sum()/train.isnull().count()).sort_values(ascending = False)\nmissing_train_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])\nmissing_train_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"temp_data= pd.DataFrame(train['landmark_id'].value_counts().head(10)).reset_index()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"temp_data.columns=['landmark_id','count']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport warnings\nfrom scipy import stats\nimport glob\nwarnings.filterwarnings('ignore')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(8,9))\nplt.title('Most frequent Landmarks')\nsns.set_color_codes(\"pastel\")\nsns.barplot(x=\"landmark_id\", y=\"count\", data=temp_data,\n            label=\"Count\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Occurance of landmark_id in increasing order\ntemp = pd.DataFrame(train.landmark_id.value_counts().tail(8))\ntemp.reset_index(inplace=True)\ntemp.columns = ['landmark_id','count']\ntemp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Plot the least frequent landmark_ids\nplt.figure(figsize = (9, 8))\nplt.title('Least frequent landmarks')\nsns.set_color_codes(\"pastel\")\nsns.barplot(x=\"landmark_id\", y=\"count\", data=temp,\n            label=\"Count\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Landmark ID distribution\nplt.figure(figsize = (10, 8))\nplt.title('Landmark ID Distribuition')\nsns.distplot(train['landmark_id'])\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Number of classes under 20 occurences\",(train['landmark_id'].value_counts() <= 20).sum(),'out of total number of categories',len(train['landmark_id'].unique()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_list = glob.glob(os.path.join(base_dir,'train/*/*/*/*'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.rcParams[\"axes.grid\"] = False\nf, axarr = plt.subplots(8, 7, figsize=(24, 22))\n\ncurr_row = 0\nfor i in range(56):\n    example = cv2.imread(train_list[i])\n    example = example[:,:,::-1]\n    \n    col = i%8\n    axarr[col, curr_row].imshow(example)\n    if col == 7 :\n        curr_row += 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_train = train[train['landmark_id'].isin(temp_data['landmark_id'])].reset_index(drop = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.landmark_id.nunique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_train.landmark_id.nunique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import shutil","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"landmark_id = list(sample_train.landmark_id.unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_folder_structure(base_dir,landmark_id, mode=\"train\"):\n    \"\"\"\n    :param output_dir:\n    :param mode:\n    :return:\n    \"\"\"\n    base_dir = base_dir + \"/\" + mode\n    if os.path.exists(base_dir):\n        shutil.rmtree(base_dir)\n    os.makedirs(base_dir)\n    for id_ in landmard_id:\n        os.makedirs(base_dir + \"/\" + str(id_)) \n    return base_dir","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"****Create folder structure for sample dataset****"},{"metadata":{"trusted":true},"cell_type":"code","source":"output_dir = '/kaggle/working'\ntrain_dir = create_folder_structure(output_dir,landmark_id,mode='train')\nvalidation_dir = create_folder_structure(output_dir,landmark_id,mode='validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_file_path(input_dir,path_id,mode='train'):\n    prefix = path_id[:3]\n    path = input_dir + \"/\" + mode + \"/\" +\"{0}/{1}/{2}/\".format(prefix[0],prefix[1],prefix[2])\n    filename = path_id\n    return path + filename + \".jpg\"\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def copy(dataframe,output_dir,id_,mode='train'):\n    destination = output_dir + \"/\" + mode + \"/\" + str(id_)\n    for index,row in dataframe.iterrows():\n        shutil.copy(row['file_path'],destination)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def copy_files(input_dir,output_dir,dataframe,landmark_id):\n    for id_ in tqdm(landmark_id):\n        print('Landmark with id: {}'.format(id_))\n        temp = dataframe[sample_train['landmark_id']==id_]\n        train = temp.sample(frac = 0.8,random_state = 1)\n        validation = temp[~temp['id'].isin(train.id)]\n        train['file_path'] = train.apply(lambda x: get_file_path(input_dir,x['id'],mode = 'train'),axis =1)\n        validation['file_path'] = validation.apply(lambda x: get_file_path(input_dir,x['id'],mode = 'train'),axis =1)\n        # Copy training files\n        copy(train,output_dir,id_,mode = 'train')\n        # Copy validation files\n        copy(validation,output_dir,id_,mode = 'validation')\n    \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"copy_files(base_dir,output_dir,sample_train,landmark_id)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_train_list = glob.glob(os.path.join(output_dir,'train/*/*'))\nsample_validation_list = glob.glob(os.path.join(output_dir,'validation/*/*'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Number of training images: {}'.format(len(sample_train_list))+\"\\n\" + \"Number of validation images: {}\".format(len(sample_validation_list)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from zipfile import ZipFile\nimport os\nfrom os.path import basename\n# create a ZipFile object\nwith ZipFile('/kaggle/working/sample_google_landmark_retrieval.zip', 'w') as zipObj:\n   # Iterate over all the files in directory\n   for folderName, subfolders, filenames in os.walk(output_dir):\n        for filename in filenames:\n           #create complete filepath of file in directory\n           filePath = os.path.join(folderName, filename)\n           # Add file to zip\n           zipObj.write(filePath, basename(filePath))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import datetime\ndef print_info(archive_name):\n    zf = ZipFile(archive_name)\n    size = sum([zinfo.file_size for zinfo in  zf.filelist])\n    zip_mb = float(size)/1000000 #MB\n    print('Archive size: {}'.format(zip_mb))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print_info(archive_name=os.path.join(output_dir,'sample_google_landmark_retrieval.zip'))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"****Generate Download Link****"},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'sample_google_landmark_retrieval.zip')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}