{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport gc\nfrom statistics import mean\n\nimport os\n\nimport random\nfrom tqdm import tqdm_notebook as tqdm\nfrom tqdm import tqdm_pandas\n\nimport warnings\nwarnings.filterwarnings('ignore')","execution_count":33,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"step = 100000000\nstop = 100000000\nX = pd.DataFrame(dtype = np.float32,columns = ['mean','std','99quat','50quat','25quat','1quat','time_to_failure'])\nj = 0\nfor i in tqdm(range(0, stop, step)):\n train_df = pd.read_csv(\"../input/train.csv\",\n skiprows = i,\n nrows = step,\n dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32}\n )\n train_df.columns = ['acoustic_data','time_to_failure']\n seg_len = 5000\n segments = int(np.floor(train_df.shape[0] / seg_len))\n for segment in range(segments):\n x = train_df.acoustic_data[segment*seg_len:segment*seg_len+seg_len]\n X.loc[j,'mean'] = np.mean(x)\n X.loc[j,'std'] = np.std(x)\n X.loc[j,'99quat'] = np.quantile(x,0.99)\n X.loc[j,'50quat'] = np.quantile(x,0.5)\n X.loc[j,'25quat'] = np.quantile(x,0.25)\n X.loc[j,'1quat'] = np.quantile(x,0.01)\n X.loc[j,'time_to_failure'] = train_df.time_to_failure.values[segment*seg_len+seg_len-1]\n j +=1\n del train_df\n gc.collect()\n ","execution_count":3,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=1), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"c10e58f75dc34a48a12dcaa55527ad14"}},"metadata":{}},{"output_type":"stream","text":"\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import MinMaxScaler\nscaler = MinMaxScaler() \nX.iloc[:,:-1] = scaler.fit_transform(X.iloc[:,:-1])","execution_count":4,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def getTrainBatch(dfl,seg_len,batch_size):\n x = np.empty([batch_size,seg_len,6])\n y = np.empty([batch_size,1])\n for i,rn in enumerate(np.random.randint(dfl.shape[0]-seg_len, size=batch_size)):\n df = dfl.loc[rn:rn+seg_len-1,:]\n x[i,:,:] = df.iloc[:,:-1]\n y[i] = df.iloc[-1,-1]\n return x,y","execution_count":5,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Dropout, CuDNNLSTM\nfrom keras.optimizers import Adam\nfrom keras.losses import mean_squared_error\nfrom keras.callbacks import History","execution_count":6,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(CuDNNLSTM(64 ,return_sequences=True ,input_shape=(30, 6)))\nmodel.add(CuDNNLSTM(64))\nmodel.add(Dropout(rate=0.5))\nmodel.add(Dense(1, activation='linear'))\n\nprint(model.summary())","execution_count":7,"outputs":[{"output_type":"stream","text":"WARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\nInstructions for updating:\nColocations handled automatically by placer.\nWARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.\nInstructions for updating:\nPlease use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ncu_dnnlstm_1 (CuDNNLSTM) (None, 30, 64) 18432 \n_________________________________________________________________\ncu_dnnlstm_2 (CuDNNLSTM) (None, 64) 33280 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 64) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 1) 65 \n=================================================================\nTotal params: 51,777\nTrainable params: 51,777\nNon-trainable params: 0\n_________________________________________________________________\nNone\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='mean_absolute_error',optimizer='adam',metrics=['mae'])","execution_count":8,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss = []\nval_loss = []\nfor j in tqdm(range(101)):\n #print('Generating training batch :',j)\n x_train,y_train = getTrainBatch(X,30,batch_size=1024)\n history = model.fit(x_train,\n y_train,\n batch_size=16,\n epochs=10,\n validation_split=0.1,\n verbose=0)\n loss = loss + history.history['loss']\n val_loss = val_loss + history.history['val_loss']\n #mae = mae + history.history['mean_absolute_error']\n if (j%10==0):\n print('loss :',mean(loss[-10:]),' val_loss :',mean(val_loss[-10:])) #, ' val_mae :',mean(mae[-10:])*16)\n del x_train, y_train\n gc.collect()","execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=11), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"87cb9590f9214fd68dc9944b8567ef98"}},"metadata":{}},{"output_type":"stream","text":"WARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\nInstructions for updating:\nUse tf.cast instead.\nloss : 3.430697639317259 val_loss : 2.983592477122557\nloss : 3.453736361955069 val_loss : 3.242035299828909\nloss : 3.3415056794008136 val_loss : 3.3557125237381573\nloss : 3.2525093650714325 val_loss : 3.007265317440033\nloss : 2.6481271572014666 val_loss : 2.464331022628303\nloss : 2.2769491619318236 val_loss : 1.9408699969643528\n\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predicting the submission\ndef predictSubmission(seg_id):\n X_test = pd.DataFrame(dtype = np.float32,columns = ['mean','std','99quat','50quat','25quat','1quat'])\n test_df = pd.read_csv('../input/test/' + seg_id + '.csv')\n seg_len = 5000\n segments = int(np.floor(test_df.shape[0] / seg_len))\n for i,segment in enumerate(range(segments)):\n x = test_df.acoustic_data[segment*seg_len:segment*seg_len+seg_len]\n X_test.loc[i,'mean'] = np.mean(x)\n X_test.loc[i,'std'] = np.std(x)\n X_test.loc[i,'99quat'] = np.quantile(x,0.99)\n X_test.loc[i,'50quat'] = np.quantile(x,0.5)\n X_test.loc[i,'25quat'] = np.quantile(x,0.25)\n X_test.loc[i,'1quat'] = np.quantile(x,0.01)\n y = model.predict(scaler.transform(X_test).reshape(1,30,6))\n return y[0][0]","execution_count":26,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tqdm_pandas(tqdm())\nsubmission = pd.read_csv('../input/sample_submission.csv')\nsubmission.loc[:,'time_to_failure']=submission.loc[:,'seg_id'].progress_apply(predictSubmission)\nsubmission.to_csv('submission_10.csv',index=False)","execution_count":35,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"8d3937cb3a554c63a227a5072a01e120"}},"metadata":{}},{"output_type":"stream","text":"\nTqdmDeprecationWarning: Please use `tqdm.pandas(...)` instead of `tqdm_pandas(tqdm(...))`.\n","name":"stdout"},{"output_type":"error","ename":"KeyboardInterrupt","evalue":"","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mtqdm_pandas\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtqdm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0msubmission\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../input/sample_submission.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0msubmission\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'time_to_failure'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msubmission\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'seg_id'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprogress_apply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpredictSubmission\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0msubmission\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'submission_10.csv'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/tqdm/_tqdm.py\u001b[0m in \u001b[0;36minner\u001b[0;34m(df, func, *args, **kwargs)\u001b[0m\n\u001b[1;32m 677\u001b[0m \u001b[0;31m# Apply the provided function (in **kwargs)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 678\u001b[0m \u001b[0;31m# on the df using our wrapper (which provides bar updating)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 679\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdf_function\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwrapper\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 680\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 681\u001b[0m \u001b[0;31m# Close bar and return pandas calculation result\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self, func, convert_dtype, args, **kwds)\u001b[0m\n\u001b[1;32m 3192\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3193\u001b[0m \u001b[0mvalues\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobject\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3194\u001b[0;31m \u001b[0mmapped\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap_infer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconvert_dtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3195\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3196\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmapped\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmapped\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mSeries\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/src/inference.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/tqdm/_tqdm.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 673\u001b[0m \u001b[0;31m# take a fast or slow code path; so stop when t.total==t.n\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 674\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtotal\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtotal\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 675\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 676\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 677\u001b[0m \u001b[0;31m# Apply the provided function (in **kwargs)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m\u001b[0m in \u001b[0;36mpredictSubmission\u001b[0;34m(seg_id)\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mpredictSubmission\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mseg_id\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mX_test\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdtype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfloat32\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'mean'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'std'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'99quat'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'50quat'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'25quat'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'1quat'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mtest_df\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../input/test/'\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mseg_id\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0mseg_len\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m5000\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0msegments\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfloor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_df\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0mseg_len\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, doublequote, delim_whitespace, low_memory, memory_map, float_precision)\u001b[0m\n\u001b[1;32m 676\u001b[0m skip_blank_lines=skip_blank_lines)\n\u001b[1;32m 677\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 678\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 679\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 680\u001b[0m \u001b[0mparser_f\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 444\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 445\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 446\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 447\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1034\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'skipfooter not supported for iteration'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1035\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1036\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1037\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1038\u001b[0m \u001b[0;31m# May alter columns / col_dict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1846\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1847\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1848\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1849\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1850\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_first_chunk\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader.read\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_low_memory\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_rows\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_column_data\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_tokens\u001b[0;34m()\u001b[0m\n","\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._convert_with_dtype\u001b[0;34m()\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/dtypes/common.py\u001b[0m in \u001b[0;36mis_integer_dtype\u001b[0;34m(arr_or_dtype)\u001b[0m\n\u001b[1;32m 809\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 810\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 811\u001b[0;31m \u001b[0;32mdef\u001b[0m \u001b[0mis_integer_dtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marr_or_dtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 812\u001b[0m \"\"\"\n\u001b[1;32m 813\u001b[0m \u001b[0mCheck\u001b[0m \u001b[0mwhether\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mprovided\u001b[0m \u001b[0marray\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mdtype\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mof\u001b[0m \u001b[0man\u001b[0m \u001b[0minteger\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "]}]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":36,"outputs":[{"output_type":"execute_result","execution_count":36,"data":{"text/plain":" seg_id time_to_failure\n0 seg_00030f 0\n1 seg_0012b5 0\n2 seg_00184e 0\n3 seg_003339 0\n4 seg_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 \n \n
seg_idtime_to_failure
0seg_00030f0
1seg_0012b50
2seg_00184e0
3seg_0033390
4seg_0042cc0
\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}