{"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)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\nimport warnings\nwarnings.filterwarnings(\"ignore\")\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":17,"outputs":[{"output_type":"stream","text":"['train.csv', 'sample_submission.csv', 'test']\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"#**Understanding Dataset**"},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.options.display.precision=15\ntrain=pd.read_csv(\"../input/train.csv\",nrows=10000000,dtype={'acoustic_data': np.int16, 'time_to_failure': np.float64})\ntrain.head()","execution_count":18,"outputs":[{"output_type":"execute_result","execution_count":18,"data":{"text/plain":"   acoustic_data  time_to_failure\n0             12     1.4690999832\n1              6     1.4690999821\n2              8     1.4690999810\n3              5     1.4690999799\n4              8     1.4690999788","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>acoustic_data</th>\n      <th>time_to_failure</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>12</td>\n      <td>1.4690999832</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>6</td>\n      <td>1.4690999821</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>8</td>\n      <td>1.4690999810</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>5</td>\n      <td>1.4690999799</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>8</td>\n      <td>1.4690999788</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.rename({\"acoustic_data\":\"sinyal\",\"time_to_failure\":\"time\"},axis=\"columns\",inplace=True)\ntrain.head()","execution_count":19,"outputs":[{"output_type":"execute_result","execution_count":19,"data":{"text/plain":"   sinyal          time\n0      12  1.4690999832\n1       6  1.4690999821\n2       8  1.4690999810\n3       5  1.4690999799\n4       8  1.4690999788","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>sinyal</th>\n      <th>time</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>12</td>\n      <td>1.4690999832</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>6</td>\n      <td>1.4690999821</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>8</td>\n      <td>1.4690999810</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>5</td>\n      <td>1.4690999799</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>8</td>\n      <td>1.4690999788</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"tests=os.listdir(\"../input/test\")\nprint(tests[0:3])\nlen(tests)","execution_count":20,"outputs":[{"output_type":"stream","text":"['seg_d35274.csv', 'seg_7bec10.csv', 'seg_fbf17a.csv']\n","name":"stdout"},{"output_type":"execute_result","execution_count":20,"data":{"text/plain":"2624"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission=pd.read_csv(\"../input/sample_submission.csv\")\nsample_submission.head(2)","execution_count":21,"outputs":[{"output_type":"execute_result","execution_count":21,"data":{"text/plain":"       seg_id  time_to_failure\n0  seg_00030f                0\n1  seg_0012b5                0","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>seg_id</th>\n      <th>time_to_failure</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>seg_00030f</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>seg_0012b5</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(sample_submission))","execution_count":22,"outputs":[{"output_type":"stream","text":"2624\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe().T","execution_count":23,"outputs":[{"output_type":"execute_result","execution_count":23,"data":{"text/plain":"             count       ...                   max\nsinyal  10000000.0       ...        3252.000000000\ntime    10000000.0       ...          11.540799987\n\n[2 rows x 8 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>count</th>\n      <th>mean</th>\n      <th>std</th>\n      <th>min</th>\n      <th>25%</th>\n      <th>50%</th>\n      <th>75%</th>\n      <th>max</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>sinyal</th>\n      <td>10000000.0</td>\n      <td>4.502072300000000</td>\n      <td>17.807072466151062</td>\n      <td>-4621.00000000000000</td>\n      <td>2.000000000000</td>\n      <td>4.00000000000</td>\n      <td>7.00000000000</td>\n      <td>3252.000000000</td>\n    </tr>\n    <tr>\n      <th>time</th>\n      <td>10000000.0</td>\n      <td>5.183597857290694</td>\n      <td>5.091285869422851</td>\n      <td>0.00079547982295</td>\n      <td>0.649897064645</td>\n      <td>1.29889864835</td>\n      <td>10.89169840325</td>\n      <td>11.540799987</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax=plt.subplots(1,2,figsize=(20,5))\nax[0].set_title(\"Signal distribution\")\nax[1].set_title(\"Signal distribution without peaks\");\n\nsns.kdeplot(train.sinyal,ax=ax[0],shade=True);\nlow = train.sinyal.mean() - 3 * train.sinyal.std()\nhigh = train.sinyal.mean() + 3 * train.sinyal.std() \nsns.distplot(train.loc[(train.sinyal >= low) & (train.sinyal <= high), \"sinyal\"].values,ax=ax[1]);","execution_count":24,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1440x360 with 2 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=\"sinyal\",data=train)","execution_count":25,"outputs":[{"output_type":"execute_result","execution_count":25,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7f63d62369e8>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}