{"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)\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../\"))\nprint(os.listdir(\"../working/\"))\nprint(os.listdir(\"../lib/\"))\nprint(os.listdir(\"../config/\"))\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Creating the necessary directories\n# !mkdir ../images/\n# !mkdir ../images/train\n# !mkdir ../images/val","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# !pip install awscli","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# !aws s3 --no-sign-request cp s3://open-images-dataset/tar/train_f.tar.gz '../images/train' # [target_dir] (46G)\n# !tar -xzf ../images/train/train_f.tar.gz # unzip the files\n# !rm ../images/train/train_f.tar.gz # remove the zipper file from disk","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import bq_helper\nfrom bq_helper import BigQueryHelper\n# https://www.kaggle.com/sohier/introduction-to-the-bq-helper-package\n# https://www.kaggle.com/paultimothymooney/how-to-query-the-open-images-dataset\nopen_images = bq_helper.BigQueryHelper(active_project=\"bigquery-public-data\",\n                                   dataset_name=\"open_images\")\nbq_assistant = BigQueryHelper(\"bigquery-public-data\", \"open_images\")\nprint(bq_assistant.list_tables())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bq_assistant.head(\"annotations_bbox\", num_rows=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bq_assistant.head(\"images\", num_rows=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bq_assistant.head(\"dict\", num_rows=20000)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bq_assistant.head(\"labels\", num_rows=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bq_assistant.table_schema(\"annotations_bbox\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import urllib, urllib.request\nimport matplotlib.pyplot as plt\nfrom PIL import Image\n\n!mkdir ../input/images/\n\ndf = bq_assistant.head(\"images\", num_rows=10)\nfor i in range(2):\n    filename = df.iloc[i]['original_url'].split('/')[-1]\n    urllib.request.urlretrieve(df.iloc[i]['original_url'],filename=os.path.join('../input/images/', filename))\n    plt.figure()\n    image = plt.imread(os.path.join('../input/images/', filename))\n    plt.imshow(image)","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":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}