{"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\nimport cv2\nimport matplotlib.pyplot as plt\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(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Print some images, and simple describe\nPrint some images for training data. \nThese image data (documents) are various types of documents.  \nFor example, novel(#12), Cooking recipes(#1), Seasonal food list(#6), picture book(#10), and so on. And, some document has kana pronouncing(#1, #2, #4, ...).  \nIn this competition, the kana pronouncing letters shall be ignored. Normally, the kana pronouncing letters are write smaller size than main letters (Some people write in large letters ...). #10 document have kuzusiji letter, so this image should no label in submission data. \nAnd, I think, there are beautiful letters and dirty letters. For example, #12 document is easy to read because the letters are written carefully (or Woodblock printing document), but #1 is a litter difficult beacuse the letters are durty ( perhaps, this document is handwritten document).  \n  \nWe shall try to recognise these variety of documents."},{"metadata":{"trusted":true},"cell_type":"code","source":"# Show some image data\nimageList = os.listdir(\"../input/train_images/\")[:12]\nprint(imageList)\nplt.figure(figsize=(27,27))\nfor index, imageFile in enumerate(imageList):\n    filePath = \"../input/train_images/\" + imageFile\n    image = cv2.imread(filePath)\n    plt.subplot(4,3,index+1)\n    plt.title(\"#{}\".format(index+1))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(\"../input/train.csv\")\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"unicode_df = pd.read_csv(\"../input/unicode_translation.csv\")\nunicode_df","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}