{"cells":[{"metadata":{},"cell_type":"markdown","source":"### Overview\n\nThis kernel implements a CNN with a squeeze-and-excitation mechanism. The rationale is using sigmoid gates to reduce the effects of noise  from the original inputs. The gate parameters are learned to differentiate useful filters and less useful ones, and hopefully less useful ones are more suppressed with lower sigmoid coefficients.\n\nThe original paper for the squeeze-and-excitation mechanism:\n\nhttps://arxiv.org/abs/1709.01507\n\nSome codes were borrowed from these kernels (Great thanks!):\n\nhttps://www.kaggle.com/gpreda/lanl-earthquake-eda-and-prediction\n\nhttps://www.kaggle.com/friedchips/how-to-reduce-the-training-data-to-400mb\n\nhttps://www.kaggle.com/tandonarpit6/lanl-earthquake-prediction-fast-ai\n\nhttps://www.kaggle.com/rtatman/download-a-csv-file-from-a-kernel\n\n"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"## Read in training data (from https://www.kaggle.com/gpreda/lanl-earthquake-eda-and-prediction)\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom tqdm import tqdm_notebook\n\n%time train = pd.read_csv(\"../input/train.csv\", dtype={\"acoustic_data\": np.int16, \"time_to_failure\": np.float32})","execution_count":1,"outputs":[{"output_type":"stream","text":"CPU times: user 2min 6s, sys: 9.17 s, total: 2min 15s\nWall time: 2min 16s\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"### Sample Data Generation\n\nTo evaluate the squeeze-and-excitation mechanism with a subset of data, in total 2,550 samples with 15,0000 consecutive points were generated from 17 pre-failure periods. The model was trained with 5-fold cross validation and test data was predicted with the average outputs from the five models of each cv."},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Split the whole training segments into five cross-folds.\n# There are 17 pre-failure periods in the training data, so samples for five cross folds were randomly selected \n# from pre-failure periods with index 0 - 3, 4 - 6, 7 - 9, 10 - 12, and 13 - 16.\n\nsample_num = 150\ninput_len = 150000\nnp.random.seed(7898)\n\n# From https://www.kaggle.com/friedchips/how-to-reduce-the-training-data-to-400mb\nttf = train[\"time_to_failure\"].values\nindex_start = np.nonzero(np.diff(ttf) > 0)[0] + 1\nindex_start = np.insert(index_start, 0, 0) # insert 1st period start manually\nchunk_length = np.diff(np.append(index_start, train.shape[0]))\n\nX_series = []\ny_series = []\n# Split 17 pre-failure periods into five cross-folds, where the last four folds starts at index of 4, 7, 10 and 13th pre-failure period\ncv_assign = [4, 7, 10, 13]\nX, y = None, None\nfor i in range(len(index_start)):\n    if i in cv_assign:\n        X_series.append(X)\n        y_series.append(y)\n        X, y = None, None\n    index_set = np.random.randint(low=index_start[i], high=index_start[i] + chunk_length[i] - input_len, size=sample_num)\n    ac_data = np.zeros((sample_num,input_len, 1), dtype=np.int16)\n    ac_label = np.zeros((sample_num,), dtype=np.float32)\n    for j in range(sample_num):\n        ac_data[j, :, 0] = train[\"acoustic_data\"].values[index_set[j]:index_set[j] + input_len]\n        ac_label[j] = train[\"time_to_failure\"].values[index_set[j] + input_len]\n    if X is None: X, y = ac_data, ac_label\n    else:\n        X, y = np.concatenate((X, ac_data), axis=0), np.concatenate((y, ac_label), axis=0)\nX_series.append(X)\ny_series.append(y)\ndel train # Just to save space\n\n# From https://www.kaggle.com/tandonarpit6/lanl-earthquake-prediction-fast-ai\nsubmission = pd.read_csv(\"../input/sample_submission.csv\", index_col=\"seg_id\")\nX_test = np.zeros((2624, 150000, 1), dtype=np.int32)\ni = 0\nfor seg_id in tqdm_notebook(submission.index):\n    seg = pd.read_csv(\"../input/test/{}.csv\".format(seg_id))\n    X_test[i, :, :] = seg.values\n    i += 1","execution_count":2,"outputs":[{"output_type":"display_data","data":{"text/plain":"HBox(children=(IntProgress(value=0, max=2624), HTML(value='')))","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"113a2e519d4d4a3b8fb62e398c114ce9"}},"metadata":{}},{"output_type":"stream","text":"\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"### Model Architecture\n\nThe input into the model is a segment with length 15,0000. The model first reduces all signals by 100 fold, and followed by two convolutional layers. Squeeze-and-excitation mechanism and a max-pooling layer are filled in between two conv layers. The final output is calculated with an intermediate dense layer from the second conv layer."},{"metadata":{"trusted":true,"_uuid":"84b9a9e92b164eceb89a232a7d689d39a59a47e2"},"cell_type":"code","source":"#Generate CNN model with a squeeze-and-excitation mechanism\nfrom keras.models import Sequential, Model\nfrom keras.layers import Input, Conv1D, MaxPooling1D, Dense, Flatten, Multiply, Dropout, Lambda, GlobalAveragePooling1D\nfrom keras.optimizers import Adam\n\ndef squeeze_block(x, filter_num):\n    squeeze = GlobalAveragePooling1D()(x)\n    squeeze = Dense(int(filter_num / 2), activation=\"relu\", kernel_initializer=\"he_normal\")(squeeze)\n    squeeze = Dense(filter_num, activation=\"sigmoid\", kernel_initializer=\"he_normal\", name=\"squeeze_coef\")(squeeze)\n    c = Multiply()([x, squeeze])\n    return c\n\ndef model_gen(InputDim):\n    print(\"Building model ...\")\n    inputs = Input((InputDim, 1))\n    c = Lambda(lambda x: x / 100.0)(inputs)\n    c = Conv1D(filters=16, kernel_size=(10,), strides=1, padding=\"valid\", \n               kernel_initializer=\"he_normal\", activation=\"relu\", name=\"conv_before_squeeze\")(c)\n    c = squeeze_block(c, 16)\n    c = MaxPooling1D(pool_size=10, strides=10, padding=\"valid\")(c)\n    c = Conv1D(filters=16, kernel_size=(10,), strides=5, padding=\"valid\", \n               kernel_initializer=\"he_normal\", activation='relu', name=\"conv_after_squeeze\")(c)\n    f = Flatten()(c)\n    d = Dense(64, activation=\"relu\", kernel_initializer=\"he_normal\")(f)\n    d = Dropout(rate=0.5)(d)\n    outputs = Dense(1, activation=\"elu\", kernel_initializer=\"he_normal\")(d)\n    model = Model(inputs=[inputs], outputs=[outputs])\n    optim = Adam(lr=0.005)\n    model.compile(loss=\"mean_absolute_error\", optimizer=optim)\n    return model\nmodel = model_gen(150000)\nmodel.summary()","execution_count":3,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"},{"output_type":"stream","text":"Building model ...\nWARNING: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 #     Connected to                     \n==================================================================================================\ninput_1 (InputLayer)            (None, 150000, 1)    0                                            \n__________________________________________________________________________________________________\nlambda_1 (Lambda)               (None, 150000, 1)    0           input_1[0][0]                    \n__________________________________________________________________________________________________\nconv_before_squeeze (Conv1D)    (None, 149991, 16)   176         lambda_1[0][0]                   \n__________________________________________________________________________________________________\nglobal_average_pooling1d_1 (Glo (None, 16)           0           conv_before_squeeze[0][0]        \n__________________________________________________________________________________________________\ndense_1 (Dense)                 (None, 8)            136         global_average_pooling1d_1[0][0] \n__________________________________________________________________________________________________\nsqueeze_coef (Dense)            (None, 16)           144         dense_1[0][0]                    \n__________________________________________________________________________________________________\nmultiply_1 (Multiply)           (None, 149991, 16)   0           conv_before_squeeze[0][0]        \n                                                                 squeeze_coef[0][0]               \n__________________________________________________________________________________________________\nmax_pooling1d_1 (MaxPooling1D)  (None, 14999, 16)    0           multiply_1[0][0]                 \n__________________________________________________________________________________________________\nconv_after_squeeze (Conv1D)     (None, 2998, 16)     2576        max_pooling1d_1[0][0]            \n__________________________________________________________________________________________________\nflatten_1 (Flatten)             (None, 47968)        0           conv_after_squeeze[0][0]         \n__________________________________________________________________________________________________\ndense_2 (Dense)                 (None, 64)           3070016     flatten_1[0][0]                  \n__________________________________________________________________________________________________\ndropout_1 (Dropout)             (None, 64)           0           dense_2[0][0]                    \n__________________________________________________________________________________________________\ndense_3 (Dense)                 (None, 1)            65          dropout_1[0][0]                  \n==================================================================================================\nTotal params: 3,073,113\nTrainable params: 3,073,113\nNon-trainable params: 0\n__________________________________________________________________________________________________\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"### Model Training\n\nA decaying learning rate scheduler was applied.\n\nFor each cross-fold, the model was trained for 30 epochs, and the model from the last epoch was used to predict the test data."},{"metadata":{"trusted":true,"_uuid":"ecbab3c71227eb649d17ec93dac57768f282c73d","collapsed":true},"cell_type":"code","source":"# Model training with 5-cv\n\nimport numpy as np\nfrom keras.callbacks import LearningRateScheduler\n\nbatch_size = 50\nepochs_number = 30\n\ndef step_decay(epoch):\n    initial_lrate = 0.005\n    drop = 0.8\n    epochs_drop = 5.0\n    lrate = initial_lrate * np.power(drop, np.floor((1 + epoch) / epochs_drop))\n    return lrate\nlrate = LearningRateScheduler(step_decay)\n\nmodel_loss = np.zeros((5,), dtype=np.float32)\ny_pred_series = []\ny_test = np.zeros((2624, 1), dtype=np.float32)\n\nfor i in range(len(X_series)):\n    model = model_gen(input_len)\n    X_fit, y_fit = None, None\n    for j in range(len(X_series)):\n        if j != i:\n            if X_fit is None: X_fit, y_fit = X_series[j], y_series[j]\n            else:\n                X_fit, y_fit = np.concatenate((X_fit, X_series[j]), axis=0), np.concatenate((y_fit, y_series[j]), axis=0)\n    X_val, y_val = X_series[i], y_series[i]\n    model.fit(X_fit, y_fit, batch_size=batch_size, epochs=epochs_number, \n              validation_data=(X_val, y_val), shuffle=True, callbacks=[lrate])\n    model_loss[i] = model.evaluate(X_val, y_val)\n    y_pred_series.append(model.predict(X_val))\n    y_test += model.predict(X_test)\nmodel.save_weights(filepath=\"model_param.hdf5\")\n    \nmodel_loss_mean = np.mean(model_loss)\nmodel_loss_std = np.std(model_loss)\nprint(\"CV Score for the model is {:.3f} +/- {:.3f}\".format(model_loss_mean, model_loss_std))\nsubmission.time_to_failure = y_test / 5\nsubmission.to_csv(\"submission.csv\", index=True)","execution_count":4,"outputs":[{"output_type":"stream","text":"Building model ...\nWARNING: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.\nTrain on 1950 samples, validate on 600 samples\nEpoch 1/30\n1950/1950 [==============================] - 7s 4ms/step - loss: 4.7129 - val_loss: 3.3340\nEpoch 2/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.8747 - val_loss: 2.7317\nEpoch 3/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.5878 - val_loss: 2.5728\nEpoch 4/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.4555 - val_loss: 2.7359\nEpoch 5/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.3873 - val_loss: 2.4761\nEpoch 6/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.2871 - val_loss: 2.5560\nEpoch 7/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.1311 - val_loss: 2.6136\nEpoch 8/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.1586 - val_loss: 2.5187\nEpoch 9/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 2.0224 - val_loss: 2.5357\nEpoch 10/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.9288 - val_loss: 2.7099\nEpoch 11/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.9567 - val_loss: 2.4892\nEpoch 12/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.9374 - val_loss: 2.4787\nEpoch 13/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.8567 - val_loss: 2.4882\nEpoch 14/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.8247 - val_loss: 2.5385\nEpoch 15/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.7897 - val_loss: 2.5065\nEpoch 16/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.7035 - val_loss: 2.4838\nEpoch 17/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.6576 - val_loss: 2.4831\nEpoch 18/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.6210 - val_loss: 2.5194\nEpoch 19/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.6574 - val_loss: 2.5083\nEpoch 20/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.5704 - val_loss: 2.5183\nEpoch 21/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.5536 - val_loss: 2.5719\nEpoch 22/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.5111 - val_loss: 2.5203\nEpoch 23/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.5619 - val_loss: 2.5582\nEpoch 24/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4871 - val_loss: 2.5447\nEpoch 25/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4706 - val_loss: 2.5556\nEpoch 26/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4205 - val_loss: 2.5304\nEpoch 27/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4767 - val_loss: 2.5637\nEpoch 28/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4160 - val_loss: 2.6306\nEpoch 29/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.4339 - val_loss: 2.5566\nEpoch 30/30\n1950/1950 [==============================] - 4s 2ms/step - loss: 1.3849 - val_loss: 2.5701\n600/600 [==============================] - 1s 1ms/step\nBuilding model ...\nTrain on 2100 samples, validate on 450 samples\nEpoch 1/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 4.3936 - val_loss: 1.8583\nEpoch 2/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.5568 - val_loss: 1.6482\nEpoch 3/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.4070 - val_loss: 2.3953\nEpoch 4/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.3688 - val_loss: 2.4250\nEpoch 5/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.2356 - val_loss: 1.7738\nEpoch 6/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.2648 - val_loss: 1.8403\nEpoch 7/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.2840 - val_loss: 1.9673\nEpoch 8/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.1227 - val_loss: 1.9778\nEpoch 9/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.0264 - val_loss: 1.8772\nEpoch 10/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.0532 - val_loss: 1.8612\nEpoch 11/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.9336 - val_loss: 1.9353\nEpoch 12/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.9804 - val_loss: 2.0082\nEpoch 13/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.9284 - val_loss: 2.0971\nEpoch 14/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.8316 - val_loss: 2.1683\nEpoch 15/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.8754 - val_loss: 1.8924\nEpoch 16/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7820 - val_loss: 2.0646\nEpoch 17/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7016 - val_loss: 2.2584\nEpoch 18/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.6644 - val_loss: 2.0111\nEpoch 19/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.6265 - val_loss: 1.9864\nEpoch 20/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.5634 - val_loss: 2.0085\nEpoch 21/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.5515 - val_loss: 2.1930\nEpoch 22/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.5855 - val_loss: 2.3303\nEpoch 23/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.6070 - val_loss: 2.0032\nEpoch 24/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.5225 - val_loss: 2.1002\nEpoch 25/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.4719 - val_loss: 1.9509\nEpoch 26/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.4999 - val_loss: 2.0495\nEpoch 27/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.4351 - val_loss: 1.9675\nEpoch 28/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.3726 - val_loss: 2.1446\nEpoch 29/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.4420 - val_loss: 2.0205\nEpoch 30/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.4407 - val_loss: 2.1038\n450/450 [==============================] - 0s 1ms/step\nBuilding model ...\nTrain on 2100 samples, validate on 450 samples\nEpoch 1/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 4.4839 - val_loss: 3.3496\nEpoch 2/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 3.1494 - val_loss: 2.6167\nEpoch 3/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.9362 - val_loss: 2.4005\nEpoch 4/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.6862 - val_loss: 2.6254\nEpoch 5/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.5751 - val_loss: 2.3405\nEpoch 6/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.4757 - val_loss: 2.3823\nEpoch 7/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.3983 - val_loss: 2.4328\nEpoch 8/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.4003 - val_loss: 2.4283\nEpoch 9/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.2340 - val_loss: 2.4177\nEpoch 10/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.1605 - val_loss: 2.5206\nEpoch 11/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.1331 - val_loss: 2.4494\nEpoch 12/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.0199 - val_loss: 2.5783\nEpoch 13/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 2.0381 - val_loss: 2.5557\nEpoch 14/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.9578 - val_loss: 2.4715\nEpoch 15/30\n","name":"stdout"},{"output_type":"stream","text":"2100/2100 [==============================] - 4s 2ms/step - loss: 1.8494 - val_loss: 2.4452\nEpoch 16/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.9362 - val_loss: 2.4337\nEpoch 17/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.8715 - val_loss: 2.4827\nEpoch 18/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7948 - val_loss: 2.5901\nEpoch 19/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.8414 - val_loss: 2.4758\nEpoch 20/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.8163 - val_loss: 2.4622\nEpoch 21/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7341 - val_loss: 2.5161\nEpoch 22/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7481 - val_loss: 2.4596\nEpoch 23/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7456 - val_loss: 2.5027\nEpoch 24/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7058 - val_loss: 2.5395\nEpoch 25/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7493 - val_loss: 2.4692\nEpoch 26/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7131 - val_loss: 2.5045\nEpoch 27/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7066 - val_loss: 2.4868\nEpoch 28/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.6756 - val_loss: 2.5021\nEpoch 29/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.7240 - val_loss: 2.5981\nEpoch 30/30\n2100/2100 [==============================] - 4s 2ms/step - loss: 1.6700 - val_loss: 2.5296\n450/450 [==============================] - 0s 982us/step\nBuilding model ...\nTrain on 2100 samples, validate on 450 samples\nEpoch 1/30\n2100/2100 [==============================] - 6s 3ms/step - loss: 3.9701 - val_loss: 2.1411\nEpoch 2/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 3.0646 - val_loss: 2.2981\nEpoch 3/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 2.7524 - val_loss: 1.6301\nEpoch 4/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 2.5028 - val_loss: 1.9894\nEpoch 5/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 2.2395 - val_loss: 1.3908\nEpoch 6/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 2.0425 - val_loss: 1.6335\nEpoch 7/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 2.1393 - val_loss: 1.8919\nEpoch 8/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.9063 - val_loss: 1.5512\nEpoch 9/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.8415 - val_loss: 1.6281\nEpoch 10/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.7064 - val_loss: 1.5467\nEpoch 11/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.6866 - val_loss: 1.6394\nEpoch 12/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.5582 - val_loss: 1.6908\nEpoch 13/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.5850 - val_loss: 1.9010\nEpoch 14/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.5665 - val_loss: 1.6600\nEpoch 15/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.5236 - val_loss: 1.7660\nEpoch 16/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.5108 - val_loss: 1.7197\nEpoch 17/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.4949 - val_loss: 2.0301\nEpoch 18/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.4699 - val_loss: 1.7693\nEpoch 19/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.4160 - val_loss: 1.8472\nEpoch 20/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.3548 - val_loss: 1.7744\nEpoch 21/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.3525 - val_loss: 1.8239\nEpoch 22/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.3776 - val_loss: 1.8070\nEpoch 23/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.3287 - val_loss: 1.7539\nEpoch 24/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.3190 - val_loss: 1.8312\nEpoch 25/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2397 - val_loss: 1.8970\nEpoch 26/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2691 - val_loss: 1.8481\nEpoch 27/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2220 - val_loss: 1.9326\nEpoch 28/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2168 - val_loss: 1.9563\nEpoch 29/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2134 - val_loss: 1.9898\nEpoch 30/30\n2100/2100 [==============================] - 5s 2ms/step - loss: 1.2482 - val_loss: 2.0132\n450/450 [==============================] - 0s 1ms/step\nBuilding model ...\nTrain on 1950 samples, validate on 600 samples\nEpoch 1/30\n1950/1950 [==============================] - 6s 3ms/step - loss: 5.7073 - val_loss: 4.7288\nEpoch 2/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.7991 - val_loss: 3.0299\nEpoch 3/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 2.6125 - val_loss: 3.4321\nEpoch 4/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.4434 - val_loss: 3.4578\nEpoch 5/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 2.3908 - val_loss: 2.8635\nEpoch 6/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.1936 - val_loss: 2.5927\nEpoch 7/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.1697 - val_loss: 2.4320\nEpoch 8/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.2768 - val_loss: 2.8269\nEpoch 9/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.1385 - val_loss: 2.4296\nEpoch 10/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.0437 - val_loss: 2.7939\nEpoch 11/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 2.1114 - val_loss: 2.9672\nEpoch 12/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 1.9256 - val_loss: 2.5884\nEpoch 13/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 1.8690 - val_loss: 2.5726\nEpoch 14/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.8184 - val_loss: 2.8788\nEpoch 15/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.7260 - val_loss: 2.4678\nEpoch 16/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.7000 - val_loss: 2.5966\nEpoch 17/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.6727 - val_loss: 2.7924\nEpoch 18/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.7137 - val_loss: 2.7787\nEpoch 19/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.6258 - val_loss: 2.5647\nEpoch 20/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.6045 - val_loss: 2.5912\nEpoch 21/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.4943 - val_loss: 2.4952\nEpoch 22/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.4512 - val_loss: 2.3793\nEpoch 23/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.4840 - val_loss: 2.5876\nEpoch 24/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.4909 - val_loss: 2.5711\nEpoch 25/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.3440 - val_loss: 2.6493\nEpoch 26/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.4103 - val_loss: 2.4370\nEpoch 27/30\n1950/1950 [==============================] - 5s 2ms/step - loss: 1.3341 - val_loss: 2.8098\nEpoch 28/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 1.3358 - val_loss: 2.6176\nEpoch 29/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 1.3722 - val_loss: 2.4923\nEpoch 30/30\n1950/1950 [==============================] - 5s 3ms/step - loss: 1.2818 - val_loss: 2.6794\n600/600 [==============================] - 1s 1ms/step\nCV Score for the model is 2.379 +/- 0.268\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"### Model Evaluation\n\nModel from each cross-fold was used to predict the validation fold to have a comparison with ground truth. The model tends to overestimate small failure time and underestimate large failure time."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"CV Score for the model is {:.3f} +/- {:.3f}\".format(model_loss_mean, model_loss_std))\nfig, ax = plt.subplots(5, 1, figsize=(15, 10))\nfor i in range(len(y_pred_series)):\n    index = np.argsort(y_series[i])\n    ax[i].plot(np.arange(y_series[i].shape[0]), y_series[i][index], \"b-\")\n    ax[i].plot(np.arange(y_pred_series[i].shape[0]), y_pred_series[i][index], \"r.\")\n    ax[i].set_ylabel(\"Time in CV {}\".format(i + 1))\n    if i == 0:\n        ax[i].set_title(\"Truth (Blue) versus Prediction (Red)\")\n    ax[-1].set_xlabel(\"Samples ranked with increasing failure time\")","execution_count":8,"outputs":[{"output_type":"stream","text":"CV Score for the model is 2.379 +/- 0.268\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"<Figure size 1080x720 with 5 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"To evaluate the efficiency of the squeeze-and-excitation mechanism, one sample with the largest failure time from the last cross-fold was picked to generate the outputs of convolutional layers. Note that each conv layer has 16 filters, so the outputs of first conv layer were shown in left four columns (start from second row), and ones for second conv layer were in right four columns.\n\nIt seems all squeeze coefficients for 16 filters in first conv layer were around 0.50. While it could mean the squeeze-and-excitation didn't do the job as expected, interestingly, the CNN model without it performs consistently WORSE than with it (didn't show in current kernel)."},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import backend as K\n\nI = y_val.argsort()[-1] # Pick some sample with the largest failure time\nx = X_val[I, :, :]\ny = y_val[I]\nx = np.expand_dims(x, axis=0)\ny_pred = model.predict(x)[0][0]\n\nget_pre_squeeze_conv_layer_output = K.function([model.layers[0].input],\n                                  [model.get_layer(\"conv_before_squeeze\").output])\nget_post_squeeze_conv_layer_output = K.function([model.layers[0].input],\n                                      [model.get_layer(\"conv_before_squeeze\").output])\nget_squeeze_coefficients = K.function([model.layers[0].input],\n                                      [model.get_layer(\"squeeze_coef\").output])\n\nconv_output = np.array(get_pre_squeeze_conv_layer_output([x])[0])\nconv2_output = np.array(get_post_squeeze_conv_layer_output([x])[0])\nsqueeze_coefs = np.array(get_squeeze_coefficients([x])[0])\n\nr, c = 5, 8\nfig, ax = plt.subplots(r, c, figsize=(30, 10))\nfor i in range(r):\n    for j in range(c):\n        ax[i][j].set_xticks([])\n        if i == 0:\n            if j == 0:\n                ax[i][j].plot(np.arange(x.shape[1]), x[0, :, 0], \"b-\")\n                ax[i][j].set_title(\"True/Pred = {:.2f}/{:.2f}\".format(y, y_pred))\n            else:\n                ax[i][j].set_visible(False)\n        else:\n            if j <= 3:\n                k = c // 2 * (i - 1) + j\n                ax[i][j].plot(np.arange(conv_output.shape[1]), conv_output[0, :, k], \"b-\")\n                ax[i][j].set_title(\"Squeeze Coef: {:.2f}\".format(squeeze_coefs[0, k]))\n            else:\n                k = c // 2 * (i - 1) + j - 4\n                ax[i][j].plot(np.arange(conv2_output.shape[1]), conv2_output[0, :, k], \"b-\")\nax[2][0].set_ylabel(\"First Conv Outputs Before Squeezing\")\nax[2][4].set_ylabel(\"Second Conv Outputs After Squeezing\")","execution_count":20,"outputs":[{"output_type":"execute_result","execution_count":20,"data":{"text/plain":"Text(0, 0.5, 'Second Conv Outputs After Squeezing')"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 2160x720 with 40 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"One can download the submission.csv from the following codes. The PL score with predictions from this kernel was 1.922. I expect some better scores when one trains the model with the whole set of training data."},{"metadata":{"trusted":true},"cell_type":"code","source":"# From https://www.kaggle.com/rtatman/download-a-csv-file-from-a-kernel\nfrom IPython.display import HTML\nimport base64\n\n# function that takes in a dataframe and creates a text link to  \n# download it (will only work for files < 2MB or so)\ndef create_download_link(df, title = \"Download CSV file\", filename = \"submission.csv\"):  \n    csv = df.to_csv()\n    b64 = base64.b64encode(csv.encode())\n    payload = b64.decode()\n    html = '<a download=\"{filename}\" href=\"data:text/csv;base64,{payload}\" target=\"_blank\">{title}</a>'\n    html = html.format(payload=payload,title=title,filename=filename)\n    return HTML(html)\n\n# create a link to download the dataframe\ncreate_download_link(submission)","execution_count":21,"outputs":[{"output_type":"execute_result","execution_count":21,"data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"<a download=\"submission.csv\" href=\"data:text/csv;base64,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\" target=\"_blank\">Download CSV file</a>"},"metadata":{}}]}],"metadata":{"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":1}