{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"188da95a-903a-491d-ddcb-1053c3e123ae"},"source":"#Exploring the Intel & MobileODT Cervical Cancer Screening\n\nThis is my first stab at an original Kaggle script meaning not forked from others. I have chosen to work with the Intel & MobileODT Cervical Cancer Screening after spending some time on the site participating on practice problems like titanic and the digit recognizer. I will also focus on doing some illustrative data visualizations as well as feature engineering."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"5366fe3d-f8db-7410-97d1-eeea23cbb1ce"},"outputs":[],"source":"import matplotlib.pylab as plt\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom glob import glob\nimport os\nCAT_COLUMN = 'type_cat'"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e6dc6642-57c9-0209-6ee0-ee546b81f3ac"},"outputs":[],"source":"# Read in the file paths\ntrain_df = pd.DataFrame([{'path': c_path, \n                           'image_name': os.path.basename(c_path),\n                          CAT_COLUMN: os.path.basename(os.path.dirname(c_path))}\n              for c_path in glob('../input/train/*/*')])\nprint('Total Training Data',train_df.shape[0])\nprint('Sample Summary\\n', pd.value_counts(train_df['type_cat']))\ntrain_df.sample(3)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"55c1aca9-8d93-6a6d-cad4-5271412f487b"},"outputs":[],"source":"test_df = pd.DataFrame([dict(path = c_path, \n                           image_name = os.path.basename(c_path)) \n              for c_path in glob('../input/test/*')])\nprint('Total Testing',test_df.shape[0])\ntest_df.sample(3)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"13897282-e6bd-046d-3094-1455a1df9cce"},"outputs":[],"source":"train_df['type_cat']"}],"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}