{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","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\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport warnings\nwarnings.simplefilter(action=\"ignore\",category=FutureWarning)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d43e1ae653e0450515e801b6c7469b165d01bdc0"},"cell_type":"code","source":"train= pd.read_csv(\"../input/train.csv\",dtype={\"acoustic_data\":np.int16, \"time_ro_failure\": np.float64},nrows=1500000)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f0dc1e4a4e2bbd6107e6937553d9bcddc39ac415"},"cell_type":"code","source":"train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f2dbbbd866c393bbf16e34d089fdec46e87db4b9"},"cell_type":"markdown","source":"lets look at the statistics"},{"metadata":{"trusted":true,"_uuid":"d83fc71a8ebbb92e7a9ce6471998a67848953587"},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6d0671efcc79ae656a2cf9dd7bae8eefa54a2e22"},"cell_type":"markdown","source":"Lets get into the distribution of acoustic data "},{"metadata":{"trusted":true,"_uuid":"b498fb34ca6024d10f8af494ca34a0d615546792"},"cell_type":"code","source":"plt.figure(figsize=(8,6))\nplt.title(\"Distribution of Acoustic data\")\nax= sns.distplot(train.acoustic_data,label=\"acustic_data\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8b2d6c874447cac80d831c087e129fcfab320c69"},"cell_type":"code","source":"This shows most of the signal data centred around mean value of the signals","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"a4c7937c56303ba3d1f9785b2eb6f9836debe028"},"cell_type":"markdown","source":"lets look how  the acuostic data sesmic singal look like."},{"metadata":{"trusted":true,"_uuid":"6cc5ab0e7b73c61d7624856f06996a0689acafc1"},"cell_type":"code","source":"plt.figure(figsize=(12,8))\nplt.title(\"Sesmic signal time_to_failure\")\nplt.plot(train.time_to_failure,train.acoustic_data)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c2d45cfb9a970f98d1b74396179d16c883c0ece1"},"cell_type":"markdown","source":"yet to come >>>"}],"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}