{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib as plt\nimport cufflinks as cf\nfrom plotly.offline import download_plotlyjs,init_notebook_mode,plot,iplot\ninit_notebook_mode(connected=True)\ncf.go_offline()\nfrom plotly.subplots import make_subplots\nimport plotly.express as px\nimport plotly.graph_objects as go\n\nimport tensorflow as tf\nimport tensorflow.keras.backend as K\nimport tensorflow.keras.layers as L\nimport tensorflow.keras.models as M\n\nfrom sklearn.metrics import mean_absolute_error\nfrom sklearn.model_selection import KFold","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/train.csv')\ndf_test = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.pairplot(df_train,hue=\"Sex\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.pairplot(df_train,hue=\"SmokingStatus\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.boxplot(x='SmokingStatus',y='Age',data=df_train,palette='rainbow')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(df_train['Sex'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(df_train['SmokingStatus'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set(rc={'figure.figsize':(11.7,8.27)})\nsns.countplot(df_train['Age'],hue=df_train['Sex'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set(rc={'figure.figsize':(11.7,8.27)})\nsns.countplot(df_train['Age'],hue=df_train['SmokingStatus'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# sns.barplot(x=df_train.Percent,y=df_train.FVC,hue=df_train.Sex)\nsns.jointplot(x=df_train.Percent,y=df_train.FVC,data=df_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.scatterplot(x=df_train.Percent,y=df_train.FVC,data=df_train,hue='Sex')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.scatterplot(x=df_train.Percent,y=df_train.FVC,data=df_train,hue='SmokingStatus')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"parallel_diagram = df_train[['Weeks', 'Patient', 'FVC', 'Percent', 'Age', 'Sex', 'SmokingStatus']]\n\nfig = px.parallel_categories(parallel_diagram, color_continuous_scale=px.colors.sequential.Inferno)\nfig.update_layout(title='Parallel category diagram on trainset')\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Code","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.drop_duplicates(keep=False, inplace=True, subset=['Patient','Weeks'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission = pd.read_csv(\"../input/osic-pulmonary-fibrosis-progression/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission['Patient'] = df_submission['Patient_Week'].apply(lambda x:x.split('_')[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission.head(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission['Weeks'] = df_submission['Patient_Week'].apply(lambda x: int(x.split('_')[-1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission.head(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission =  df_submission[['Patient','Weeks','Confidence','Patient_Week']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ndf_submission = df_submission.merge(df_test.drop('Weeks', axis=1), on=\"Patient\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train['WHERE'] = 'train'\ndf_test['WHERE'] = 'val'\ndf_submission['WHERE'] = 'test'\ndata = df_train.append([df_test, df_submission])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df_train.shape, df_test.shape, df_submission.shape, data.shape)\nprint(df_train.Patient.nunique(), df_test.Patient.nunique(), df_submission.Patient.nunique(), \n      data.Patient.nunique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data['min_week'] = data['Weeks']\ndata.loc[data.WHERE=='test','min_week'] = np.nan\ndata['min_week'] = data.groupby('Patient')['min_week'].transform('min')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base = data.loc[data.Weeks == data.min_week]\nbase = base[['Patient','FVC']].copy()\nbase.columns = ['Patient','min_FVC']\nbase['nb'] = 1\nbase['nb'] = base.groupby('Patient')['nb'].transform('cumsum')\nbase = base[base.nb==1]\nbase.drop('nb', axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# base.head() ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = data.merge(base, on='Patient', how='left')\ndata['base_week'] = data['Weeks'] - data['min_week']\ndel base","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"COLS = ['Sex','SmokingStatus'] #,'Age'\nFE = []\nfor col in COLS:\n    for mod in data[col].unique():\n        FE.append(mod)\n        data[mod] = (data[col] == mod).astype(int)\n#=================","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data['age'] = (data['Age'] - data['Age'].min() ) / ( data['Age'].max() - data['Age'].min() )\ndata['BASE'] = (data['min_FVC'] - data['min_FVC'].min() ) / ( data['min_FVC'].max() - data['min_FVC'].min() )\ndata['week'] = (data['base_week'] - data['base_week'].min() ) / ( data['base_week'].max() - data['base_week'].min() )\ndata['percent'] = (data['Percent'] - data['Percent'].min() ) / ( data['Percent'].max() - data['Percent'].min() )\nFE += ['age','percent','week','BASE']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tr = data.loc[data.WHERE=='train']\nchunk = data.loc[data.WHERE=='val']\nsub = data.loc[data.WHERE=='test']\ndel data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tr.shape, chunk.shape, sub.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# BASELINE NN","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"C1, C2 = tf.constant(70, dtype='float32'), tf.constant(1000, dtype=\"float32\")\n#=============================#\ndef score(y_true, y_pred):\n    tf.dtypes.cast(y_true, tf.float32)\n    tf.dtypes.cast(y_pred, tf.float32)\n    sigma = y_pred[:, 2] - y_pred[:, 0]\n    fvc_pred = y_pred[:, 1]\n    \n    #sigma_clip = sigma + C1\n    sigma_clip = tf.maximum(sigma, C1)\n    delta = tf.abs(y_true[:, 0] - fvc_pred)\n    delta = tf.minimum(delta, C2)\n    sq2 = tf.sqrt( tf.dtypes.cast(2, dtype=tf.float32) )\n    metric = (delta / sigma_clip)*sq2 + tf.math.log(sigma_clip* sq2)\n    return K.mean(metric)\n#============================#\ndef qloss(y_true, y_pred):\n    # Pinball loss for multiple quantiles\n    qs = [0.2, 0.50, 0.8]\n    q = tf.constant(np.array([qs]), dtype=tf.float32)\n    e = y_true - y_pred\n    v = tf.maximum(q*e, (q-1)*e)\n    return K.mean(v)\n#=============================#\ndef mloss(_lambda):\n    def loss(y_true, y_pred):\n        return _lambda * qloss(y_true, y_pred) + (1 - _lambda)*score(y_true, y_pred)\n    return loss\n#=================\ndef make_model(nh):\n    z = L.Input((nh,), name=\"Patient\")\n    x = L.Dense(100, activation=\"relu\", name=\"d1\")(z)\n    x = L.Dense(100, activation=\"relu\", name=\"d2\")(x)\n    #x = L.Dense(100, activation=\"relu\", name=\"d3\")(x)\n    p1 = L.Dense(3, activation=\"linear\", name=\"p1\")(x)\n    p2 = L.Dense(3, activation=\"relu\", name=\"p2\")(x)\n    preds = L.Lambda(lambda x: x[0] + tf.cumsum(x[1], axis=1), \n                     name=\"preds\")([p1, p2])\n    \n    model = M.Model(z, preds, name=\"CNN\")\n    #model.compile(loss=qloss, optimizer=\"adam\", metrics=[score])\n    model.compile(loss=mloss(0.8), optimizer=tf.keras.optimizers.Adam(lr=0.1, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.01, amsgrad=False), metrics=[score])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = tr['FVC'].values\nz = tr[FE].values\nze = sub[FE].values\nnh = z.shape[1]\npe = np.zeros((ze.shape[0], 3))\npred = np.zeros((z.shape[0], 3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"net = make_model(nh)\nprint(net.summary())\nprint(net.count_params())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NFOLD = 5\nkf = KFold(n_splits=NFOLD)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tf.cast(y, tf.float32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z = z.astype(np.float32)\ny = y.astype(np.float32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\ncnt = 0\nEPOCHS = 800\nfor tr_idx, val_idx in kf.split(z):\n    cnt += 1\n    print(f\"FOLD {cnt}\")\n    net = make_model(nh)\n    net.fit(z[tr_idx], y[tr_idx], batch_size=128, epochs=500, \n            validation_data=(z[val_idx], y[val_idx]), verbose=0) #\n    print(\"train\", net.evaluate(z[tr_idx], y[tr_idx], verbose=0, batch_size=128))\n    print(\"val\", net.evaluate(z[val_idx], y[val_idx], verbose=0, batch_size=128))\n    print(\"predict val...\")\n    pred[val_idx] = net.predict(z[val_idx], batch_size=128, verbose=0)\n    print(\"predict test...\")\n    pe += net.predict(ze, batch_size=128, verbose=0) / NFOLD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sigma_opt = mean_absolute_error(y, pred[:, 1])\nunc = pred[:,2] - pred[:, 0]\nsigma_mean = np.mean(unc)\nprint(sigma_opt, sigma_mean)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# idxs = np.random.randint(0, y.shape[0], 100)\n# plt.plot(y[idxs], label=\"ground truth\")\n# plt.plot(pred[idxs, 0], label=\"q25\")\n# plt.plot(pred[idxs, 1], label=\"q50\")\n# plt.plot(pred[idxs, 2], label=\"q75\")\n# plt.legend(loc=\"best\")\n# plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(unc.min(), unc.mean(), unc.max(), (unc>=0).mean())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# PREDICTION","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['FVC1'] = 0.996*pe[:, 1]\nsub['Confidence1'] = pe[:, 2] - pe[:, 0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm = sub[['Patient_Week','FVC','Confidence','FVC1','Confidence1']].copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm.loc[~subm.FVC1.isnull()].head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm.loc[~subm.FVC1.isnull(),'FVC'] = subm.loc[~subm.FVC1.isnull(),'FVC1']\nif sigma_mean<70:\n    subm['Confidence'] = sigma_opt\nelse:\n    subm.loc[~subm.FVC1.isnull(),'Confidence'] = subm.loc[~subm.FVC1.isnull(),'Confidence1']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm.describe().T","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"otest = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/test.csv')\nfor i in range(len(otest)):\n    subm.loc[subm['Patient_Week']==otest.Patient[i]+'_'+str(otest.Weeks[i]), 'FVC'] = otest.FVC[i]\n    subm.loc[subm['Patient_Week']==otest.Patient[i]+'_'+str(otest.Weeks[i]), 'Confidence'] = 0.1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm[[\"Patient_Week\",\"FVC\",\"Confidence\"]].to_csv(\"../working/submission.csv\", index=False)","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":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}