{"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":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv', dtype={'acoustic_data': np.int16, 'time_to_failure': np.float64})\n \n #nrows=6000000)","execution_count":3,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# pandas doesn't show us all the decimals\npd.options.display.precision = 15","execution_count":4,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":5,"outputs":[{"output_type":"execute_result","execution_count":5,"data":{"text/plain":"(629145480, 2)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info(memory_usage='deep')","execution_count":6,"outputs":[{"output_type":"stream","text":"\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":"train.rename({\"acoustic_data\": \"signal\", \"time_to_failure\": \"time\"}, axis=\"columns\", inplace=True)","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":" signal time\n0 12 1.4690999832\n1 6 1.4690999821\n2 8 1.4690999810\n3 5 1.4690999799\n4 8 1.4690999788","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
signaltime
0121.4690999832
161.4690999821
281.4690999810
351.4690999799
481.4690999788
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create a training file with simple derived features\n\nrows = 150_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','median','var','sum','q1','q19','iqr','diff'\\\n 'q2','Q1','q3','q4','Q2','q6','q7','Q3','q8','q81','q82','q9','q10','abs_mean',\\\n 'hmean','gmean','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['signal'].values\n y = seg['time'].values[-1]\n \n y_train.loc[segment, 'time_to_failure'] = y\n \n X_train.loc[segment, 'ave'] = np.mean(x)\n X_train.loc[segment, 'std'] = np.std(x)\n X_train.loc[segment, 'max'] = np.max(x)\n X_train.loc[segment, 'min'] = np.min(x)\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 X_train.loc[segment, 'sum'] = np.sum(x)\n X_train.loc[segment, 'median'] = np.median(x)\n X_train.loc[segment, 'var'] = np.var(x)\n #X_train.loc[segment, 'exp'] = np(x)\n #X_train.loc[segment, 'log'] = ln(x)\n X_train.loc[segment, 'q1'] = np.quantile(x,.1)\n X_train.loc[segment, 'q19'] = np.quantile(x,.19)\n X_train.loc[segment, 'q2'] = np.quantile(x,.2)\n X_train.loc[segment, 'Q1'] = np.quantile(x,.25)\n X_train.loc[segment, 'q3'] = np.quantile(x,.3)\n X_train.loc[segment, 'q4'] = np.quantile(x,.4)\n X_train.loc[segment, 'Q2'] = np.quantile(x,.5)\n X_train.loc[segment, 'q6'] = np.quantile(x,.6)\n X_train.loc[segment, 'q7'] = np.quantile(x,.7)\n X_train.loc[segment, 'Q3'] = np.quantile(x,.75)\n X_train.loc[segment, 'q8'] = np.quantile(x,.8)\n X_train.loc[segment, 'q81'] = np.quantile(x,.81)\n X_train.loc[segment, 'q82'] = np.quantile(x,.82)\n X_train.loc[segment, 'q9'] = np.quantile(x,.9)\n X_train.loc[segment, 'q10'] = np.quantile(x,1) #81,82\n X_train.loc[segment, 'iqr'] = np.quantile(x,.75) - np.quantile (x,.25)\n #X_train.loc[segment, 'diff'] = np.max(x) - np.min (x)\n #X_train.loc[segment, 'hmean'] = stats.hmean(x)\n #X_train.loc[segment, 'gmean'] = stats.gmean(x)\n #X_train.loc[segment, 'abs_std'] = np.abs(x).std()\n #X_train.loc[segment, 'abs_min'] = np.abs(x).min() \n #X_train.loc[segment, 'trend'] = add_trend_feature(x)\n #X_train.loc[segment, 'abs_trend'] = add_trend_feature(x, abs_values=True)","execution_count":9,"outputs":[{"output_type":"stream","text":"100%|██████████| 4194/4194 [02:44<00:00, 24.36it/s]\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":10,"outputs":[{"output_type":"execute_result","execution_count":10,"data":{"text/plain":" ave std max ... gmean time_to_failure q2\n0 4.884113333333334 5.101089126891323 104.0 ... NaN 1.4307971859 2.0\n1 4.725766666666667 6.588801819164257 181.0 ... NaN 1.3914988931 2.0\n2 4.906393333333333 6.967373808828945 140.0 ... NaN 1.3531960947 2.0\n3 4.902240000000000 6.922282112791032 197.0 ... NaN 1.3137978019 2.0\n4 4.908720000000000 7.301085852684289 145.0 ... NaN 1.2743995091 2.0\n\n[5 rows x 30 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
avestdmaxminkurtskewmedianvarsumq1q19iqrdiffq2Q1q3q4Q2q6q7Q3q8q81q82q9q10abs_meanhmeangmeantime_to_failureq2
04.8841133333333345.101089126891323104.0-98.0-2.562764815176403e-19-1.184237892933500e-185.026.021110280488884732617.00.02.04.0NaN3.03.04.05.06.07.07.08.08.08.010.0104.0NaNNaNNaN1.43079718592.0
14.7257666666666676.588801819164257181.0-154.0-1.279532035880493e-19-7.005507285384737e-195.043.412309412222221708865.00.02.05.0NaN2.03.04.05.06.07.07.08.08.08.010.0181.0NaNNaNNaN1.39149889312.0
24.9063933333333336.967373808828945140.0-106.01.391479524196863e-191.113183619357490e-185.048.544297791955557735959.00.02.05.0NaN2.03.04.05.06.07.07.08.08.08.010.0140.0NaNNaNNaN1.35319609472.0
34.9022400000000006.922282112791032197.0-199.08.465450562766819e-204.884981308350689e-195.047.917989649066669735336.00.02.05.0NaN2.03.04.05.06.07.07.08.08.08.010.0197.0NaNNaNNaN1.31379780192.0
44.9087200000000007.301085852684289145.0-126.09.737581111816477e-207.286763784956444e-195.053.305854628266673736308.00.02.05.0NaN2.03.04.05.06.07.07.08.08.08.010.0145.0NaNNaNNaN1.27439950912.0
\n
"},"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)\n\n#7\npearson_coef, p_value = stats.pearsonr(X_train['sum'], X_train['time_to_failure'])\nprint(\"sum: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#8\npearson_coef, p_value = stats.pearsonr(X_train['median'], X_train['time_to_failure'])\nprint(\"median: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#9\npearson_coef, p_value = stats.pearsonr(X_train['var'], X_train['time_to_failure'])\nprint(\"var: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#9\npearson_coef, p_value = stats.pearsonr(X_train['gmean'], X_train['time_to_failure'])\nprint(\"gmean: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n","execution_count":13,"outputs":[{"output_type":"stream","text":"ave: The Pearson Correlation Coefficient is -0.03131485200929432 with a P-value of P = 0.042572800232409745\nstd: The Pearson Correlation Coefficient is -0.217068826179775 with a P-value of P = 6.564514537505289e-46\nkurt: The Pearson Correlation Coefficient is -0.03137478045305264 with a P-value of P = 0.04217798229575217\nmax: The Pearson Correlation Coefficient is -0.1896826701588192 with a P-value of P = 2.8493795430103317e-35\nmin: The Pearson Correlation Coefficient is 0.19408103734575255 with a P-value of P = 7.074292833901952e-37\nskew: The Pearson Correlation Coefficient is -0.024760831194503785 with a P-value of P = 0.10886701222756817\nsum: The Pearson Correlation Coefficient is -0.03131485200929434 with a P-value of P = 0.042572800232409745\nmedian: The Pearson Correlation Coefficient is -0.0044450029567653 with a P-value of P = 0.7735159958650007\nvar: The Pearson Correlation Coefficient is -0.10517513939091518 with a P-value of P = 8.600345532359949e-12\ngmean: The Pearson Correlation Coefficient is nan with a P-value of P = 1.0\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#10\npearson_coef, p_value = stats.pearsonr(X_train['q1'], X_train['time_to_failure'])\nprint(\"q1: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#11\npearson_coef, p_value = stats.pearsonr(X_train['q19'], X_train['time_to_failure'])\nprint(\"q19: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#12\npearson_coef, p_value = stats.pearsonr(X_train['q2'], X_train['time_to_failure'])\nprint(\"q2: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#13\npearson_coef, p_value = stats.pearsonr(X_train['Q1'], X_train['time_to_failure'])\nprint(\"Q1: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#14\npearson_coef, p_value = stats.pearsonr(X_train['q3'], X_train['time_to_failure'])\nprint(\"q3: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#15\npearson_coef, p_value = stats.pearsonr(X_train['q4'], X_train['time_to_failure'])\nprint(\"q4: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#16\npearson_coef, p_value = stats.pearsonr(X_train['Q2'], X_train['time_to_failure'])\nprint(\"Q2: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#17\npearson_coef, p_value = stats.pearsonr(X_train['q6'], X_train['time_to_failure'])\nprint(\"q6: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#18\npearson_coef, p_value = stats.pearsonr(X_train['q7'], X_train['time_to_failure'])\nprint(\"q7: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#19\npearson_coef, p_value = stats.pearsonr(X_train['Q3'], X_train['time_to_failure'])\nprint(\"Q3: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#20\npearson_coef, p_value = stats.pearsonr(X_train['q8'], X_train['time_to_failure'])\nprint(\"q8: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#21\npearson_coef, p_value = stats.pearsonr(X_train['q81'], X_train['time_to_failure'])\nprint(\"q81: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#22\npearson_coef, p_value = stats.pearsonr(X_train['q82'], X_train['time_to_failure'])\nprint(\"q82: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#23\npearson_coef, p_value = stats.pearsonr(X_train['q9'], X_train['time_to_failure'])\nprint(\"q9: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#24\npearson_coef, p_value = stats.pearsonr(X_train['q10'], X_train['time_to_failure'])\nprint(\"q10: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)\n\n#25\npearson_coef, p_value = stats.pearsonr(X_train['iqr'], X_train['time_to_failure'])\nprint(\"iqr: The Pearson Correlation Coefficient is\", pearson_coef, \" with a P-value of P =\", p_value)","execution_count":14,"outputs":[{"output_type":"stream","text":"q1: The Pearson Correlation Coefficient is 0.45472936704789013 with a P-value of P = 3.656259962449344e-213\nq19: The Pearson Correlation Coefficient is 0.46569147449333415 with a P-value of P = 7.937636347791565e-225\nq2: The Pearson Correlation Coefficient is 0.45261129991855875 with a P-value of P = 5.858858295270717e-211\nQ1: The Pearson Correlation Coefficient is 0.3588626305135062 with a P-value of P = 1.0978135212546844e-127\nq3: The Pearson Correlation Coefficient is 0.2834822256248399 with a P-value of P = 2.3870961725134474e-78\nq4: The Pearson Correlation Coefficient is 0.13836657148635756 with a P-value of P = 2.2280069420992113e-19\nQ2: The Pearson Correlation Coefficient is -0.0044450029567653 with a P-value of P = 0.7735159958650007\nq6: The Pearson Correlation Coefficient is -0.1695744241759776 with a P-value of P = 1.9889094673043306e-28\nq7: The Pearson Correlation Coefficient is -0.3338120112434793 with a P-value of P = 1.055846088709528e-109\nQ3: The Pearson Correlation Coefficient is -0.3878462847221366 with a P-value of P = 1.2839639295600133e-150\nq8: The Pearson Correlation Coefficient is -0.47710133131107896 with a P-value of P = 1.990053982483615e-237\nq81: The Pearson Correlation Coefficient is -0.4938696013644259 with a P-value of P = 7.766151193084308e-257\nq82: The Pearson Correlation Coefficient is -0.4745900019893077 with a P-value of P = 1.298817489822563e-234\nq9: The Pearson Correlation Coefficient is -0.46803310339510945 with a P-value of P = 2.251829320649944e-227\nq10: The Pearson Correlation Coefficient is -0.1896826701588192 with a P-value of P = 2.8493795430103317e-35\niqr: The Pearson Correlation Coefficient is -0.5069941406902863 with a P-value of P = 8.417843540889508e-273\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#X_train['std'].unique","execution_count":15,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#X_train['time_to_failure'].unique\nX_train['time_to_failure'].describe()","execution_count":16,"outputs":[{"output_type":"execute_result","execution_count":16,"data":{"text/plain":"count 4194.000000000000000\nmean 5.682698488340905\nstd 3.673144820066522\nmin 0.006397657167800\n25% 2.634173052750000\n50% 5.354846515149999\n75% 8.175924278749999\nmax 16.103195567000000\nName: time_to_failure, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#X_train=X_train[X_train['ave']<=5.20555]","execution_count":17,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Creating a cloumn featuring binary values on the basis of accident risks\nX_train['outcome'] =[1 if x<=5.682698488340905 else 0 for x in X_train['time_to_failure']]","execution_count":18,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head(2)","execution_count":19,"outputs":[{"output_type":"execute_result","execution_count":19,"data":{"text/plain":" ave std ... q2 outcome\n0 4.884113333333334 5.101089126891323 ... 2.0 1\n1 4.725766666666667 6.588801819164257 ... 2.0 1\n\n[2 rows x 31 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
avestdmaxminkurtskewmedianvarsumq1q19iqrdiffq2Q1q3q4Q2q6q7Q3q8q81q82q9q10abs_meanhmeangmeantime_to_failureq2outcome
04.8841133333333345.101089126891323104.0-98.0-2.562764815176403e-19-1.184237892933500e-185.026.021110280488884732617.00.02.04.0NaN3.03.04.05.06.07.07.08.08.08.010.0104.0NaNNaNNaN1.43079718592.01
14.7257666666666676.588801819164257181.0-154.0-1.279532035880493e-19-7.005507285384737e-195.043.412309412222221708865.00.02.05.0NaN2.03.04.05.06.07.07.08.08.08.010.0181.0NaNNaNNaN1.39149889312.01
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#x_train=X_train [['diff','ave', 'std', 'max', 'min','kurt','skew','median','var','sum','q1','q19','abs_mean',\\\n # 'q2','Q1','q3','q4','Q2','q6','q7','Q3','q8','q81','q82','q9','q10','iqr']]#=2.065\nx_train=X_train [['q1','q19','q2','Q1','q3','q4','Q2','q6','q7','Q3','q8','q81','q82','q9','q10','iqr']]#=2.062\n#x_train=X_train [['q1','q19','q2','q8','q81','q82','q9','min','max','std','iqr']]#=2.075\n#x_train=X_train [['q1','q19','q2','q8','q81','q82','q9','iqr']] # = 2.075\nx_train.head()","execution_count":20,"outputs":[{"output_type":"execute_result","execution_count":20,"data":{"text/plain":" q1 q19 q2 Q1 q3 q4 Q2 ... Q3 q8 q81 q82 q9 q10 iqr\n0 0.0 2.0 2.0 3.0 3.0 4.0 5.0 ... 7.0 8.0 8.0 8.0 10.0 104.0 4.0\n1 0.0 2.0 2.0 2.0 3.0 4.0 5.0 ... 7.0 8.0 8.0 8.0 10.0 181.0 5.0\n2 0.0 2.0 2.0 2.0 3.0 4.0 5.0 ... 7.0 8.0 8.0 8.0 10.0 140.0 5.0\n3 0.0 2.0 2.0 2.0 3.0 4.0 5.0 ... 7.0 8.0 8.0 8.0 10.0 197.0 5.0\n4 0.0 2.0 2.0 2.0 3.0 4.0 5.0 ... 7.0 8.0 8.0 8.0 10.0 145.0 5.0\n\n[5 rows x 16 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
q1q19q2Q1q3q4Q2q6q7Q3q8q81q82q9q10iqr
00.02.02.03.03.04.05.06.07.07.08.08.08.010.0104.04.0
10.02.02.02.03.04.05.06.07.07.08.08.08.010.0181.05.0
20.02.02.02.03.04.05.06.07.07.08.08.08.010.0140.05.0
30.02.02.02.03.04.05.06.07.07.08.08.08.010.0197.05.0
40.02.02.02.03.04.05.06.07.07.08.08.08.010.0145.05.0
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.isnull().sum()","execution_count":21,"outputs":[{"output_type":"execute_result","execution_count":21,"data":{"text/plain":"q1 0\nq19 0\nq2 0\nQ1 0\nq3 0\nq4 0\nQ2 0\nq6 0\nq7 0\nQ3 0\nq8 0\nq81 0\nq82 0\nq9 0\nq10 0\niqr 0\ndtype: int64"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape","execution_count":22,"outputs":[{"output_type":"execute_result","execution_count":22,"data":{"text/plain":"(4194, 16)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#y_train.head()\ny_train=X_train[['outcome']]\ny_train.head()","execution_count":23,"outputs":[{"output_type":"execute_result","execution_count":23,"data":{"text/plain":" outcome\n0 1\n1 1\n2 1\n3 1\n4 1","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
outcome
01
11
21
31
41
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":24,"outputs":[{"output_type":"execute_result","execution_count":24,"data":{"text/plain":"(4194, 1)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"scaler = StandardScaler()\nscaler.fit(x_train)\nX_train_scaled = scaler.transform(x_train)","execution_count":25,"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":26,"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()\n","execution_count":27,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","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":28,"outputs":[{"output_type":"stream","text":"Score: 0.208\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/sample_submission.csv', index_col='seg_id')","execution_count":29,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":30,"outputs":[{"output_type":"execute_result","execution_count":30,"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":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
time_to_failure
seg_id
seg_00030f0
seg_0012b50
seg_00184e0
seg_0033390
seg_0042cc0
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#X_train=X_train.drop(['time_to_failure'], axis=1)","execution_count":31,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = pd.DataFrame(columns=x_train.columns, dtype=np.float64, index=submission.index)","execution_count":32,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":33,"outputs":[{"output_type":"execute_result","execution_count":33,"data":{"text/plain":"(2624, 16)"},"metadata":{}}]},{"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'] = np.std(x)\n #X_test.loc[seg_id, 'max'] = np.max(x)\n #X_test.loc[seg_id, 'min'] = np.min(x)\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()\n #X_test.loc[seg_id, 'sum'] = x.sum()\n X_test.loc[seg_id, 'q1'] = np.quantile(x,.1)\n X_test.loc[seg_id, 'q19'] = np.quantile(x,.19)\n X_test.loc[seg_id, 'q2'] = np.quantile(x,.2)\n X_test.loc[seg_id, 'Q1'] = np.quantile(x,.25)\n X_test.loc[seg_id, 'q3'] = np.quantile(x,.3)\n X_test.loc[seg_id, 'q4'] = np.quantile(x,.4)\n X_test.loc[seg_id, 'Q2'] = np.quantile(x,.5)\n X_test.loc[seg_id, 'q6'] = np.quantile(x,.6)\n X_test.loc[seg_id, 'q7'] = np.quantile(x,.7)\n X_test.loc[seg_id, 'Q3'] = np.quantile(x,.75)\n X_test.loc[seg_id, 'q8'] = np.quantile(x,.8)\n X_test.loc[seg_id, 'q81'] = np.quantile(x,.81)\n X_test.loc[seg_id, 'q82'] = np.quantile(x,.82)\n X_test.loc[seg_id, 'q9'] = np.quantile(x,.9)\n X_test.loc[seg_id, 'q10'] = np.quantile(x,1)\n X_test.loc[seg_id, 'iqr'] = np.quantile(x,.75) - np.quantile (x,.25)","execution_count":34,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.shape","execution_count":35,"outputs":[{"output_type":"execute_result","execution_count":35,"data":{"text/plain":"(2624, 16)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.head()","execution_count":36,"outputs":[{"output_type":"execute_result","execution_count":36,"data":{"text/plain":" q1 q19 q2 Q1 q3 q4 ... q8 q81 q82 q9 q10 iqr\nseg_id ... \nseg_00030f 0.0 1.0 1.0 2.0 3.0 4.0 ... 7.0 8.0 8.0 9.0 115.0 5.0\nseg_0012b5 -1.0 1.0 1.0 2.0 2.0 3.0 ... 7.0 7.0 7.0 9.0 152.0 5.0\nseg_00184e 0.0 2.0 2.0 2.0 3.0 4.0 ... 7.0 8.0 8.0 9.0 248.0 5.0\nseg_003339 1.0 2.0 2.0 3.0 3.0 4.0 ... 7.0 7.0 7.0 8.0 85.0 4.0\nseg_0042cc 0.0 1.0 1.0 2.0 2.0 3.0 ... 7.0 7.0 7.0 9.0 177.0 4.0\n\n[5 rows x 16 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
q1q19q2Q1q3q4Q2q6q7Q3q8q81q82q9q10iqr
seg_id
seg_00030f0.01.01.02.03.04.04.05.06.07.07.08.08.09.0115.05.0
seg_0012b5-1.01.01.02.02.03.04.05.06.07.07.07.07.09.0152.05.0
seg_00184e0.02.02.02.03.04.05.05.06.07.07.08.08.09.0248.05.0
seg_0033391.02.02.03.03.04.05.05.06.07.07.07.07.08.085.04.0
seg_0042cc0.01.01.02.02.03.04.05.06.06.07.07.07.09.0177.04.0
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.isnull().sum()","execution_count":37,"outputs":[{"output_type":"execute_result","execution_count":37,"data":{"text/plain":"q1 0\nq19 0\nq2 0\nQ1 0\nq3 0\nq4 0\nQ2 0\nq6 0\nq7 0\nQ3 0\nq8 0\nq81 0\nq82 0\nq9 0\nq10 0\niqr 0\ndtype: int64"},"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":38,"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}