{"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":1,"outputs":[{"output_type":"stream","text":"['test', 'train.csv', 'sample_submission.csv']\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom tqdm import tqdm\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import NuSVR\nfrom sklearn.metrics import mean_absolute_error","execution_count":2,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv', dtype={'acoustic_data': np.int16, 'time_to_failure': np.float64})","execution_count":3,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":"   acoustic_data  time_to_failure\n0             12           1.4691\n1              6           1.4691\n2              8           1.4691\n3              5           1.4691\n4              8           1.4691","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>1.4691</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>6</td>\n      <td>1.4691</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>8</td>\n      <td>1.4691</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>5</td>\n      <td>1.4691</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>8</td>\n      <td>1.4691</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# pandas doesn't show us all the decimals\npd.options.display.precision = 15","execution_count":5,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":7,"outputs":[{"output_type":"execute_result","execution_count":7,"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.info(memory_usage='deep')","execution_count":8,"outputs":[{"output_type":"stream","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 629145480 entries, 0 to 629145479\nData columns (total 2 columns):\nacoustic_data      int16\ntime_to_failure    float64\ndtypes: float64(1), int16(1)\nmemory usage: 5.9 GB\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# much better!\ntrain.head()","execution_count":9,"outputs":[{"output_type":"execute_result","execution_count":9,"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":"# Create a training file with simple derived features\n\nrows = 50_000\nsegments = int(np.floor(train.shape[0] / rows))\n\nX_train = pd.DataFrame(index=range(segments), dtype=np.float64,\n                       columns=['ave', 'std', 'max', 'min','kurt','skew','time_to_failure'])\ny_train = pd.DataFrame(index=range(segments), dtype=np.float64,\n                       columns=['time_to_failure'])\n\nfor segment in tqdm(range(segments)):\n    seg = train.iloc[segment*rows:segment*rows+rows]\n    x = seg['acoustic_data'].values\n    y = seg['time_to_failure'].values[-1]\n    \n    y_train.loc[segment, 'time_to_failure'] = y\n    \n    X_train.loc[segment, 'ave'] = x.mean()\n    X_train.loc[segment, 'std'] = x.std()\n    X_train.loc[segment, 'max'] = x.max()\n    X_train.loc[segment, 'min'] = x.min()\n    X_train.loc[segment, 'time_to_failure'] = y\n    X_train.loc[segment, 'skew'] = ((x-x.mean())/x.std() ** 3).mean()\n    X_train.loc[segment,'kurt'] = ((x-x.mean())/x.std() ** 4).mean()\n    ","execution_count":248,"outputs":[{"output_type":"stream","text":"100%|██████████| 12582/12582 [00:45<00:00, 274.27it/s]\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":249,"outputs":[{"output_type":"execute_result","execution_count":249,"data":{"text/plain":"       ave       ...         time_to_failure\n0  4.96210       ...            1.4563990515\n1  5.06978       ...            1.4435981187\n2  4.62046       ...            1.4307971859\n3  4.69840       ...            1.4180962531\n4  4.69056       ...            1.4041998259\n\n[5 rows x 7 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>ave</th>\n      <th>std</th>\n      <th>max</th>\n      <th>min</th>\n      <th>kurt</th>\n      <th>skew</th>\n      <th>time_to_failure</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>4.96210</td>\n      <td>6.488487003146419</td>\n      <td>104.0</td>\n      <td>-98.0</td>\n      <td>-1.709743457922741e-19</td>\n      <td>-9.592326932761353e-19</td>\n      <td>1.4563990515</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>5.06978</td>\n      <td>4.735325833730980</td>\n      <td>52.0</td>\n      <td>-56.0</td>\n      <td>4.665712260987220e-19</td>\n      <td>2.275957200481571e-18</td>\n      <td>1.4435981187</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>4.62046</td>\n      <td>3.664626773410902</td>\n      <td>30.0</td>\n      <td>-21.0</td>\n      <td>2.247091401841317e-18</td>\n      <td>8.668621376273222e-18</td>\n      <td>1.4307971859</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4.69840</td>\n      <td>7.305159645072789</td>\n      <td>181.0</td>\n      <td>-154.0</td>\n      <td>-1.051936315832336e-19</td>\n      <td>-6.594724766273430e-19</td>\n      <td>1.4180962531</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4.69056</td>\n      <td>6.833187168986373</td>\n      <td>152.0</td>\n      <td>-150.0</td>\n      <td>1.709743457922741e-19</td>\n      <td>1.336708521648689e-18</td>\n      <td>1.4041998259</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nsns.boxplot(x=X_train['ave'])","execution_count":250,"outputs":[{"output_type":"execute_result","execution_count":250,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa92c198>"},"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":"X_train['ave'].describe()","execution_count":251,"outputs":[{"output_type":"execute_result","execution_count":251,"data":{"text/plain":"count    12582.000000000000000\nmean         4.519464272770620\nstd          0.274993078997747\nmin          3.421900000000000\n25%          4.339515000000000\n50%          4.522460000000001\n75%          4.701910000000000\nmax          5.515800000000000\nName: ave, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier First Time\n#Q1 (25%) = 4.3495\n#Q3 (75%) = 4.6934\n#IQR = Q3 - Q1 = 0.3439\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 4.6934 + 0.51585\n#Outlier > 5.20925\n# Lower Outlier\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < 4.3495 - 0.51585\n#Outlier < 3.8337\n\n# Removing Upper Outliers\n#X_train=X_train[X_train['ave']<=5.20925]\n# Removing Lower Outliers\n#X_train=X_train[X_train['ave']>=3.8337]\n\n# Second Time \n# Upper Outlier\n#Q1 (25%) = 4.3518\n#Q3 (75%) = 4.6933\n#IQR = Q3 - Q1 = 0.3415\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 4.6933 + 0.51225\n#Outlier > 5.20555\n# Lower Outlier\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < 4.3518 - 0.51225\n#Outlier < 3.83955\n\n#X_train=X_train.drop([552,584,585,589,607,610,611,626,784,939])\n#y_train=y_train.drop([552,584,585,589,607,610,611,626,784,939])\n\n","execution_count":252,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Removing Upper Outliers\nX_train=X_train[X_train['ave']<=5.20555]\n# Removing Lower Outliers\nX_train=X_train[X_train['ave']>=3.83955]","execution_count":253,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['ave'])","execution_count":254,"outputs":[{"output_type":"execute_result","execution_count":254,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa91d320>"},"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":"sns.boxplot(x=X_train['std'])","execution_count":255,"outputs":[{"output_type":"execute_result","execution_count":255,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa876710>"},"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":"X_train['std'].describe()","execution_count":256,"outputs":[{"output_type":"execute_result","execution_count":256,"data":{"text/plain":"count    12401.000000000000000\nmean         6.161254957678552\nstd          8.853386702091816\nmin          2.681901109287962\n25%          4.107232588690346\n50%          5.240864747577445\n75%          6.693291061951512\nmax        257.275448473620145\nName: std, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier\n#Q1 (25%) = 4.4741\n#Q3 (75%) =6.8839\n#IQR = Q3 - Q1 = 2.4098\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 6.8839 + 3.6147\n#Outlier > 10.4986\n#X_train=X_train[X_train['std']<=10.4986]\n\n# Second Time\n# Upper Outlier\n#Q1 (25%) =  4.4370\n#Q3 (75%) =6.7284\n#IQR = Q3 - Q1 = 2.2914\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 6.73 + 3.4371\n#Outlier > 10.1655\n#X_train=X_train[X_train['std']<=10.1655]\n\n# Third Time\n# Upper Outlier\n#Q1 (25%) =  4.4339\n#Q3 (75%) =6.6950\n#IQR = Q3 - Q1 = 2.2611\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 6.70 + 3.39165\n#Outlier > 10.0867\n#X_train=X_train[X_train['std']<=10.0867]\n\n# Fourth Time\n# Upper Outlier\n#Q1 (25%) =  4.4331\n#Q3 (75%) =6.6903\n#IQR = Q3 - Q1 = 2.2572\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 6.6903 + 3.3858\n#Outlier > 10.0761\n#X_train=X_train[X_train['std']<=10.0761] # 10.0761\n\n# Fifth Time\n# Upper Outlier\n#Q1 (25%) =  4.4330\n#Q3 (75%) =6.6881\n#IQR = Q3 - Q1 = 2.2551\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 6.6881 + 3.3827\n#Outlier > 10.0708\n","execution_count":257,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train[X_train['std']<=10.0708]","execution_count":258,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['std'])","execution_count":259,"outputs":[{"output_type":"execute_result","execution_count":259,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa851550>"},"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":"X_train=X_train[X_train['std']<=9.4]","execution_count":260,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['std'])","execution_count":261,"outputs":[{"output_type":"execute_result","execution_count":261,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa823e48>"},"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":"sns.boxplot(x=X_train['max'])","execution_count":262,"outputs":[{"output_type":"execute_result","execution_count":262,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa77e358>"},"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":"X_train['max'].describe()","execution_count":263,"outputs":[{"output_type":"execute_result","execution_count":263,"data":{"text/plain":"count    11563.000000000000000\nmean        86.115886880567331\nstd         42.218567366883001\nmin         16.000000000000000\n25%         55.000000000000000\n50%         78.000000000000000\n75%        109.000000000000000\nmax        356.000000000000000\nName: max, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier\n#Q1 (25%) =  90\n#Q3 (75%) =162\n#IQR = Q3 - Q1 = 72\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 162 + 108\n#Outlier > 270\n#X_train=X_train[X_train['max']<=270]\n\n# Second Time\n# Upper Outlier\n#Q1 (25%) =  90\n#Q3 (75%) =156\n#IQR = Q3 - Q1 = 66\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 156 + 99\n#Outlier > 255\n#X_train=X_train[X_train['max']<=255]\n\n# Third Time\n# Upper Outlier\n#Q1 (25%) =  89\n#Q3 (75%) =155\n#IQR = Q3 - Q1 = 66\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 155 + 99\n#Outlier > 254","execution_count":264,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train[X_train['max']<=254]","execution_count":265,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['max'])","execution_count":266,"outputs":[{"output_type":"execute_result","execution_count":266,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa75c7f0>"},"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":"X_train=X_train[X_train['max']<=231]","execution_count":267,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train[X_train['max']<=185]","execution_count":310,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['max'])","execution_count":311,"outputs":[{"output_type":"execute_result","execution_count":311,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa2a60f0>"},"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":"sns.boxplot(x=X_train['min'])","execution_count":269,"outputs":[{"output_type":"execute_result","execution_count":269,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa67f780>"},"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":"X_train['min'].describe()","execution_count":270,"outputs":[{"output_type":"execute_result","execution_count":270,"data":{"text/plain":"count    11502.000000000000000\nmean       -73.940879846983137\nstd         39.454375577636647\nmin       -283.000000000000000\n25%        -97.000000000000000\n50%        -67.000000000000000\n75%        -44.000000000000000\nmax         -7.000000000000000\nName: min, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Lower Outlier\n#Q1 (25%) = -141\n#Q3 (75%) = -77\n#IQR = Q3 - Q1 = 64\n\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < -141 - 96\n#Outlier < -237\n#X_train=X_train[X_train['min']>=-237]\n\n# Second Time\n# Lower Outlier\n#Q1 (25%) = -138\n#Q3 (75%) = -77\n#IQR = Q3 - Q1 = 61\n\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < -138 - 91.5\n#Outlier < -229.5\n#X_train=X_train[X_train['min']>=-229.5]\n\n# Third Time\n# Lower Outlier\n#Q1 (25%) = -137\n#Q3 (75%) = -76\n#IQR = Q3 - Q1 = 61\n\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < -137 - 91.5\n#Outlier < -228.5","execution_count":271,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train[X_train['min']>=-228.5]","execution_count":272,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['min'])","execution_count":273,"outputs":[{"output_type":"execute_result","execution_count":273,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa63e898>"},"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":"X_train=X_train[X_train['min']>=-211.5]","execution_count":274,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train[X_train['min']>=-175.5]","execution_count":306,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['min'])","execution_count":307,"outputs":[{"output_type":"execute_result","execution_count":307,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa31a438>"},"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":"sns.boxplot(x=X_train['skew'])","execution_count":276,"outputs":[{"output_type":"execute_result","execution_count":276,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa67f198>"},"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":"X_train['skew'].describe()","execution_count":277,"outputs":[{"output_type":"execute_result","execution_count":277,"data":{"text/plain":"count    1.145900000000000e+04\nmean    -2.288674771802777e-20\nstd      3.820940388327863e-18\nmin     -2.092548356813495e-17\n25%     -1.476041511239146e-18\n50%     -2.220446049250313e-21\n75%      1.385558334732195e-18\nmax      2.351896455365932e-17\nName: skew, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier First Time\n#Q1 (25%) = -1.3\n#Q3 (75%) = 1.16\n#IQR = Q3 - Q1 = 2.46\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 1.16 + 3.69\n#Outlier > 4.85\n# Lower Outlier\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < -1.3 - 3.69\n#Outlier < -4.99\n\n# Removing Upper Outliers\n#X_train=X_train[X_train['ave']<=5.20925]\n# Removing Lower Outliers\n#X_train=X_train[X_train['ave']>=3.8337]\n\n# Second Time \n# Upper Outlier\n#Q1 (25%) = 4.3518\n#Q3 (75%) = 4.6933\n#IQR = Q3 - Q1 = 0.3415\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 4.6933 + 0.51225\n#Outlier > 5.20555\n# Lower Outlier\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < 4.3518 - 0.51225\n#Outlier < 3.83955\n\n#X_train=X_train.drop([552,584,585,589,607,610,611,626,784,939])\n#y_train=y_train.drop([552,584,585,589,607,610,611,626,784,939])\n\n","execution_count":278,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Removing Upper Outliers\nX_train=X_train[X_train['skew']<=3.9e-18]\n# Removing Lower Outliers\nX_train=X_train[X_train['skew']>=-4e-18]","execution_count":279,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['skew'])","execution_count":280,"outputs":[{"output_type":"execute_result","execution_count":280,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa55fcf8>"},"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":"# Removing Upper Outliers\nX_train=X_train[X_train['skew']<=3.5e-18]\n# Removing Lower Outliers\nX_train=X_train[X_train['skew']>=-3.5e-18]","execution_count":281,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['skew'])","execution_count":282,"outputs":[{"output_type":"execute_result","execution_count":282,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa4b9d30>"},"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":"sns.boxplot(x=X_train['kurt'])","execution_count":283,"outputs":[{"output_type":"execute_result","execution_count":283,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa554fd0>"},"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":"X_train['kurt'].describe()","execution_count":284,"outputs":[{"output_type":"execute_result","execution_count":284,"data":{"text/plain":"count    8.881000000000000e+03\nmean    -7.203502716161208e-21\nstd      3.686890200147156e-19\nmin     -3.259614800299460e-18\n25%     -1.811051308919787e-19\n50%     -2.498001805406602e-21\n75%      1.704192342799615e-19\nmax      2.700062395888381e-18\nName: kurt, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier First Time\n#Q1 (25%) = -1.77\n#Q3 (75%) = 1.69\n#IQR = Q3 - Q1 = 3.46\n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 1.69 + 4.31\n#Outlier > 6\n# Lower Outlier\n#Outlier < Q1 - (1.5* IQR)\n#Outlier < -1.77 - 3.46\n#Outlier < -5.23","execution_count":285,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Removing Upper Outliers\nX_train=X_train[X_train['kurt']<=5.7e-19]\n# Removing Lower Outliers\nX_train=X_train[X_train['kurt']>=-5.23e-19]","execution_count":286,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['kurt'])","execution_count":287,"outputs":[{"output_type":"execute_result","execution_count":287,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa3f5630>"},"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":"sns.boxplot(x=X_train['time_to_failure'])","execution_count":288,"outputs":[{"output_type":"execute_result","execution_count":288,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa3c9198>"},"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":"X_train['time_to_failure'].describe()","execution_count":289,"outputs":[{"output_type":"execute_result","execution_count":289,"data":{"text/plain":"count    7732.000000000000000\nmean        5.017124758348265\nstd         3.386771021335830\nmin         0.000095753262030\n25%         2.226773493050000\n50%         4.525698487050001\n75%         7.268372375399999\nmax        16.076598207000000\nName: time_to_failure, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Upper Outlier First Time\n#Q1 (25%) = 2.33\n#Q3 (75%) = 7.38\n#IQR = Q3 - Q1 = 5.05 \n#Outlier > Q3 + (1.5 * IQR) \n#Outlier > 7.38 + 7.56\n#Outlier > 14.94","execution_count":290,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Removing Upper Outliers\nX_train=X_train[X_train['time_to_failure']<=14.92]","execution_count":291,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Removing Upper Outliers\nX_train=X_train[X_train['time_to_failure']<=14]","execution_count":304,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x=X_train['time_to_failure'])","execution_count":305,"outputs":[{"output_type":"execute_result","execution_count":305,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fa4aa31d7b8>"},"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":"X_train.shape","execution_count":312,"outputs":[{"output_type":"execute_result","execution_count":312,"data":{"text/plain":"(7352, 7)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy import stats\n\n#1\npearson_coef, p_value = stats.pearsonr(X_train['ave'], X_train['time_to_failure'])\nprint(\"ave: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#2\npearson_coef, p_value = stats.pearsonr(X_train['std'], X_train['time_to_failure'])\nprint(\"std: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#3\n\npearson_coef, p_value = stats.pearsonr(X_train['kurt'], X_train['time_to_failure'])\nprint(\"kurt: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#4\npearson_coef, p_value = stats.pearsonr(X_train['max'], X_train['time_to_failure'])\nprint(\"max: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#5\npearson_coef, p_value = stats.pearsonr(X_train['min'], X_train['time_to_failure'])\nprint(\"min: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#6\npearson_coef, p_value = stats.pearsonr(X_train['skew'], X_train['time_to_failure'])\nprint(\"skew: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)","execution_count":313,"outputs":[{"output_type":"stream","text":"ave: The Pearson Correlation Coefficient is -0.01203825234185786  with a P-value of P = 0.30204052695222333\nstd: The Pearson Correlation Coefficient is -0.3343338610498918  with a P-value of P = 1.814299191093816e-191\nkurt: The Pearson Correlation Coefficient is -0.0054486905682333  with a P-value of P = 0.6404172547469379\nmax: The Pearson Correlation Coefficient is -0.10403373311474019  with a P-value of P = 3.787251850359757e-19\nmin: The Pearson Correlation Coefficient is 0.1115394482513439  with a P-value of P = 8.62818120714846e-22\nskew: The Pearson Correlation Coefficient is -0.004392407749410708  with a P-value of P = 0.7065009689890849\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train=X_train [['ave','max','min','std','kurt','skew']]\nx_train.head()","execution_count":314,"outputs":[{"output_type":"execute_result","execution_count":314,"data":{"text/plain":"       ave          ...                             skew\n0  4.96210          ...           -9.592326932761353e-19\n1  5.06978          ...            2.275957200481571e-18\n3  4.69840          ...           -6.594724766273430e-19\n4  4.69056          ...            1.336708521648689e-18\n5  4.78834          ...            1.509903313490213e-18\n\n[5 rows x 6 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>ave</th>\n      <th>max</th>\n      <th>min</th>\n      <th>std</th>\n      <th>kurt</th>\n      <th>skew</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>4.96210</td>\n      <td>104.0</td>\n      <td>-98.0</td>\n      <td>6.488487003146419</td>\n      <td>-1.709743457922741e-19</td>\n      <td>-9.592326932761353e-19</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>5.06978</td>\n      <td>52.0</td>\n      <td>-56.0</td>\n      <td>4.735325833730980</td>\n      <td>4.665712260987220e-19</td>\n      <td>2.275957200481571e-18</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4.69840</td>\n      <td>181.0</td>\n      <td>-154.0</td>\n      <td>7.305159645072789</td>\n      <td>-1.051936315832336e-19</td>\n      <td>-6.594724766273430e-19</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4.69056</td>\n      <td>152.0</td>\n      <td>-150.0</td>\n      <td>6.833187168986373</td>\n      <td>1.709743457922741e-19</td>\n      <td>1.336708521648689e-18</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>4.78834</td>\n      <td>111.0</td>\n      <td>-115.0</td>\n      <td>5.493015569284325</td>\n      <td>2.137179322403426e-19</td>\n      <td>1.509903313490213e-18</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape","execution_count":315,"outputs":[{"output_type":"execute_result","execution_count":315,"data":{"text/plain":"(7352, 6)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train=X_train[['time_to_failure']]","execution_count":316,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.head()","execution_count":317,"outputs":[{"output_type":"execute_result","execution_count":317,"data":{"text/plain":"   time_to_failure\n0     1.4563990515\n1     1.4435981187\n3     1.4180962531\n4     1.4041998259\n5     1.3914988931","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>time_to_failure</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1.4563990515</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1.4435981187</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1.4180962531</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1.4041998259</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>1.3914988931</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":318,"outputs":[{"output_type":"execute_result","execution_count":318,"data":{"text/plain":"(7352, 1)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"scaler = StandardScaler()\nscaler.fit(x_train)\nX_train_scaled = scaler.transform(x_train)","execution_count":319,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"svm = NuSVR()\nsvm.fit(X_train_scaled, y_train.values.flatten())\ny_pred = svm.predict(X_train_scaled)","execution_count":320,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(6, 6))\nplt.scatter(y_train.values.flatten(), y_pred)\nplt.xlim(0, 20)\nplt.ylim(0, 20)\nplt.xlabel('actual', fontsize=12)\nplt.ylabel('predicted', fontsize=12)\nplt.plot([(0, 0), (20, 20)], [(0, 0), (20, 20)])\nplt.show()","execution_count":321,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x432 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"score = mean_absolute_error(y_train.values.flatten(), y_pred)\nprint(f'Score: {score:0.3f}')","execution_count":322,"outputs":[{"output_type":"stream","text":"Score: 2.302\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/sample_submission.csv', index_col='seg_id')","execution_count":323,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":324,"outputs":[{"output_type":"execute_result","execution_count":324,"data":{"text/plain":"            time_to_failure\nseg_id                     \nseg_00030f                0\nseg_0012b5                0\nseg_00184e                0\nseg_003339                0\nseg_0042cc                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>time_to_failure</th>\n    </tr>\n    <tr>\n      <th>seg_id</th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>seg_00030f</th>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>seg_0012b5</th>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>seg_00184e</th>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>seg_003339</th>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>seg_0042cc</th>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=X_train.drop(['time_to_failure'], axis=1)","execution_count":325,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = pd.DataFrame(columns=X_train.columns, dtype=np.float64, index=submission.index)","execution_count":326,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for seg_id in X_test.index:\n    seg = pd.read_csv('../input/test/' + seg_id + '.csv')\n    \n    x = seg['acoustic_data'].values\n    \n    X_test.loc[seg_id, 'ave'] = x.mean()\n    X_test.loc[seg_id, 'std'] = x.std()\n    X_test.loc[seg_id, 'max'] = x.max()\n    X_test.loc[seg_id, 'min'] = x.min()\n    X_test.loc[seg_id, 'kurt'] = ((x-x.mean())/x.std() ** 4).mean()\n    X_test.loc[seg_id, 'skew'] = ((x-x.mean())/x.std() ** 3).mean()","execution_count":327,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":328,"outputs":[{"output_type":"execute_result","execution_count":328,"data":{"text/plain":"(2624, 6)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test_scaled = scaler.transform(X_test)\nsubmission['time_to_failure'] = svm.predict(X_test_scaled)\nsubmission.to_csv('submission.csv')","execution_count":329,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"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}