{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd \n\nimport random\n\n%matplotlib inline\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport seaborn as sns; sns.set_style(\"white\")\n\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"print(os.listdir(\"../input/train_images\")[:5])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(\"../input/train.csv\")\nprint(df_train.head())\nprint(df_train.diagnosis.unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"PATH = \"../input/train_images\"\n\n\nfor i in range(10):\n    plt.figure(figsize=(10,10))\n    _id = random.choice(os.listdir(PATH))\n    id_code = _id.split(\".\")[0]\n    pil_im = Image.open(os.path.join(PATH, _id))\n    print(id_code, df_train.loc[df_train.id_code == id_code, 'diagnosis'])\n    plt.imshow(np.asarray(pil_im))    \n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10, 6))\ndf_train.diagnosis.hist()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.diagnosis.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(\"../input/sample_submission.csv\")\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(sub.diagnosis)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"n = 1928\na = [0]*1805\nb = [1]*370\nc = [2]*999\nd = [3]*193\ne = [4]*295\n_list = a + b + c + d + e\nrandom_guess = [random.choice(_list) for i in range(n)]\nrandom_guess[:10]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['diagnosis'] = random_guess\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# random guess --nothing interesting here... :'(\nsub.to_csv(\"submission.csv\", index=False)","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}