{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"1d1b33b2-62ff-c052-9d1f-61b00849e1b4"},"outputs":[],"source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\nimport glob\nimport cv2\nimport os\nimport matplotlib.pyplot as plt\n%matplotlib inline"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"11415f95-4e4b-4e85-80bd-f58fb165b4de"},"outputs":[],"source":"train_csv = pd.read_csv('../input/Train/train.csv')\ntrain_jpg = glob.glob('../input/Train/{}.jpg')\ntrain_dotjpg = glob.glob('../input/TrainDotted/{}.jpg')\n\nsubmission = pd.read_csv('../input/sample_submission.csv')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"6e8ee4a4-ba75-5472-1dde-6e8c0ef9629e"},"outputs":[],"source":"print(train_csv.shape)\nprint('Number of Train Images: {:d}'.format(len(train_jpg)))\nprint('Number of Dotted-Train Images: {:d}'.format(len(train_dotjpg)))"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"fba33d0b-585e-d402-e2f0-bb9c329bcebd"},"outputs":[],"source":"train_csv[['adult_males', 'subadult_males', 'adult_females', 'juveniles', 'pups']].sum(axis=0).plot.barh()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c8e512b9-edf1-481f-cda5-660adb1f5246"},"outputs":[],"source":"train_csv[\"Total\"] = train_csv['adult_males']+ train_csv['subadult_males']+train_csv['adult_females']+ train_csv['juveniles']+ train_csv['pups']"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"6f0ce34b-64d0-fb4c-6d13-67ce3a6fab81"},"outputs":[],"source":"corr = train_csv[['Total','adult_males', 'subadult_males', 'adult_females', 'juveniles', 'pups']].corr()\ncorr\n# High correlation between adult_females, adult_males and pups"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"ef6a1da7-0e99-edc2-4ec4-f0c681ab2096"},"outputs":[],"source":"file_names = os.listdir(\"../input/Train/\")\nfile_names = sorted(file_names, key=lambda \n                    item: (int(item.partition('.')[0]) if item[0].isdigit() else float('inf'), item)) "},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"942cb439-5ae9-76e1-62b5-4f1dc8457e5b"},"outputs":[],"source":"file_names"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e9cdee2a-2699-a529-61ac-fa7ff69e621d"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}