{"cells":[{"metadata":{"_uuid":"b787e4a0ce54ea38ae1c10fee2a75b135d368a11"},"cell_type":"markdown","source":"# Motivation\n![Owl](https://i.kym-cdn.com/photos/images/newsfeed/000/572/078/d6d.jpg)"},{"metadata":{"_uuid":"5b12f60d3992203bdc6f54735f6b15d307cd1116"},"cell_type":"markdown","source":""},{"metadata":{"trusted":true,"_uuid":"85fa10a42b5ae09d4259f41720e8d9ad2fd0ae41","_kg_hide-input":true},"cell_type":"code","source":"%matplotlib inline\nimport pandas as pd\nimport numpy as np\nfrom IPython.core.interactiveshell import InteractiveShell\nInteractiveShell.ast_node_interactivity = \"all\"\nimport datetime as dt\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport ast\nsns.set_palette(sns.color_palette('copper', 20))\nfrom datetime import date, timedelta\n\nstart = dt.datetime.now()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dfc74b0c36c8c8a472009fcb247e7f8fafb5bdf6"},"cell_type":"markdown","source":"# Step 0 - Data Understanding"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"owls = pd.read_csv('../input/train_simplified/owl.csv')\nowls = owls[owls.recognized]\nowls['timestamp'] = pd.to_datetime(owls.timestamp)\nowls = owls.sort_values(by='timestamp', ascending=False)[-100:]\nowls['drawing'] = owls['drawing'].apply(ast.literal_eval)\n\nowls.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"cc337c00d0509b1b97fc27eb93da003c4e5db2d5"},"cell_type":"code","source":"n = 10\nfig, axs = plt.subplots(nrows=n, ncols=n, sharex=True, sharey=True, figsize=(16, 10))\nfor i, drawing in enumerate(owls.drawing):\n    ax = axs[i // n, i % n]\n    for x, y in drawing:\n        ax.plot(x, -np.array(y), lw=3)\n    ax.axis('off')\nfig.savefig('owls.png', dpi=200)\nplt.show();","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"a1ca9c950d3860e88f2529806fbfe228e171acf3"},"cell_type":"markdown","source":"# Step 1 - Create baseline model"},{"metadata":{"trusted":true,"_uuid":"ac08165760c73d6253993c3f2b906455d6712304"},"cell_type":"code","source":"submission = pd.read_csv('../input/sample_submission.csv')\nsubmission.shape\n\nsubmission['word'] = 'owl owl owl'\nsubmission.to_csv('submission_owl.csv', index=False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3a0555462a64f8eda0e878dde96cc1f731798516"},"cell_type":"markdown","source":"# Step 2 - Train a Neural Network\n\n..."},{"metadata":{"trusted":true,"_uuid":"eb4746eb3cbc23868d7c22bbdbab298456ea9a4a","_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"target = [\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n    'owl owl owl',\n]","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"a65d78aeb665294223b7b9cd7c1d7d81c0f959dd"},"cell_type":"markdown","source":"# Step 3 - Profit"},{"metadata":{"trusted":true,"_uuid":"798aae80897ced48ee8c0c99b2c237aca0efa11f"},"cell_type":"code","source":"end = dt.datetime.now()\nprint('Latest run {}.\\nTotal time {}s'.format(end, (end - start).seconds))","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}