{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"f1a9d117-1f61-2b60-9a19-8d16b0f3a274"},"source":"## Data exploration ##\n 1. Visualisation of all data\n 2. red: adult males \n 3. magenta: sub-adult males\n 4. brown: adult females\n 5.  blue: juveniles\n 6. green: pups"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d6dcf1b1-f596-5f02-2838-4eab564f005b"},"outputs":[],"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\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\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"09384a31-f335-8a43-e528-2924ae51acde"},"outputs":[],"source":"from glob import glob\ninputDir = \"../input/\"\ntraincsv = pd.read_csv(inputDir + 'Train/train.csv')\ntrain = glob(inputDir + 'Train/*.jpg')\ntraindot = glob(inputDir + 'TrainDotted/*.jpg')\nsubm = pd.read_csv(inputDir + 'sample_submission.csv')\nprint(len(traincsv),len(train), len(traindot), len(subm))"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e833fc92-1937-be90-0b6e-7334fb0656f1"},"outputs":[],"source":"print(traincsv.head())"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"432e82df-55f3-33d6-c1be-1ee08f6f8a88"},"outputs":[],"source":"import cv2\nimport matplotlib.pylab as plt\n\n\ndef read_imgs(img):\n    print('{}'.format(img))\n    im = cv2.imread(img, cv2.IMREAD_COLOR)\n    img = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)\n    return img\ntrain = glob(inputDir + 'Train/*.jpg')\nprint('Reading Train images... ')\nfor trn in (train):\n    img = read_imgs(trn)\n    plt.figure()\n    plt.imshow(img)\n    plt.axis('off')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d2201679-78dc-b5ce-cbdf-ce68a9c6b02d"},"outputs":[],"source":"trainDot = glob(inputDir + 'TrainDotted/*.jpg')\nprint('Reading TrainDotted images... ')\nfor trn in (trainDot):\n    img = read_imgs(trn)\n    plt.figure()\n    plt.imshow(img)\n    plt.axis('off')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"94619659-f50e-4f62-3674-c74f2d672b74"},"outputs":[],"source":"import plotly.plotly as py\nimport plotly.graph_objs as go\ntraincsv = pd.read_csv(inputDir + 'Train/train.csv')\n\nhist = traincsv.sum(axis=0)\nprint(his)\n\nplt.hist(his)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"7e19cfac-62b2-e65c-f102-91697aba3f5c"},"outputs":[],"source":"subm = pd.read_csv(inputDir + 'sample_submission.csv')\nprint(subm.head())"}],"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}