{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport cv2\nimport shutil\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 all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    print(dirname)\n    break\n    \n    for filename in filenames:\n        os.path.join(dirname, filename)\n\n# Any results you write to the current directory are saved as output.\n\n# returns file path from the train.zip\ndef imgPath(num):\n    path = \"../input/painter-by-numbers/train/\" + num\n    return path\n\n# prints out image from filename column\ndef printImg(num):\n    path = imgPath(num)\n    print(path)\n    plt.figure(figsize=(12,12))\n    plt.subplot(1,2,1)\n    img = cv2.imread(path)\n    imgplot = plt.imshow(img)\n    \n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# import train info along with removing art without any style\npbn = pd.read_csv(\"../input/painter-by-numbers/train_info.csv\")\npbn = pbn.fillna(np.nan)\npbn.drop(labels = [\"title\",\"genre\",\"date\",\"artist\"], axis=1, inplace=True)\npbn = pbn.dropna(how='any',axis=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pbn.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stylesDict = {}\n\nfor index, row in pbn.iterrows():\n    if row[\"style\"] in stylesDict:\n        stylesDict[row[\"style\"]] = stylesDict[row[\"style\"]] + 1\n    else:\n        stylesDict[row[\"style\"]] = 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for x in stylesDict:\n    if(stylesDict[x] > 1000):\n        print(x,\": \",stylesDict[x])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# removing unneeded images from the data in a better way\nstylesToKeep = []\nfor x in stylesDict:\n    if stylesDict[x] > 1000:\n        stylesToKeep.append(x)\nfor index, row in pbn.iterrows():\n    if not row[\"style\"] in stylesToKeep:\n        pbn.drop(index, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pbn","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pbn.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# pbn.to_csv('cleaned.csv', index = False)\n# shutil.os.mkdir('/kaggle/output/images')\n# path = '/kaggle/output/images/'\n# for x in stylesToKeep:\n#     shutil.os.mkdir(path+x)\n    \n# shutil.move('/kaggle/output/cleaned.csv',/kaggle/output/images/cleaned.csv)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# prints out an image\n\n# %pylab inline\n# import matplotlib.pyplot as plt\n# import matplotlib.image as mpimg\n\n# img=imread('../input/painter-by-numbers/train_2/2000.jpg')\n# imgplot = plt.imshow(img)\n# plt.show()","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":1}