check documentation and notebooks

Author: zmek

notebooks/2b_Predict_using_patient_snapshots.ipynb

@@ -332,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -369,7 +369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -384,10 +384,10 @@
     {
      "data": {
       "text/plain": [
-       "TrainingResults(prediction_time=(9, 30), training_info={'cv_trials': [HyperParameterTrial(parameters={'n_estimators': 20}, cv_results={'train_auc': np.float64(0.9863488774220018), 'train_logloss': np.float64(0.2345235821107298), 'train_auprc': np.float64(0.9839960012755344), 'valid_auc': np.float64(0.7404647983595354), 'valid_logloss': np.float64(0.6777401688701863), 'valid_auprc': np.float64(0.732305765806727)}), HyperParameterTrial(parameters={'n_estimators': 30}, cv_results={'train_auc': np.float64(0.9934036840041577), 'train_logloss': np.float64(0.19339304359858095), 'train_auprc': np.float64(0.992275317414658), 'valid_auc': np.float64(0.7414445203918889), 'valid_logloss': np.float64(0.7224622072494462), 'valid_auprc': np.float64(0.739694204530856)}), HyperParameterTrial(parameters={'n_estimators': 40}, cv_results={'train_auc': np.float64(0.9966901551317282), 'train_logloss': np.float64(0.16839291934975475), 'train_auprc': np.float64(0.9957460357414476), 'valid_auc': np.float64(0.7385623148781044), 'valid_logloss': np.float64(0.7471921775214785), 'valid_auprc': np.float64(0.7319157690354547)})], 'features': {'names': ['age', 'latest_triage_score', 'num_urinalysis_orders_0', 'num_urinalysis_orders_1', 'num_troponin_orders_0', 'num_troponin_orders_1', 'num_bmp_orders_0', 'num_bmp_orders_1', 'num_cbc_orders_0', 'num_cbc_orders_1', 'num_d-dimer_orders_0', 'num_d-dimer_orders_1'], 'importances': [0.07901821285486221, 0.50030118227005, 0.10778335481882095, 0.0, 0.06226950138807297, 0.0, 0.08132454752922058, 0.0, 0.049338143318891525, 0.0, 0.11996506154537201, 0.0], 'has_importance_values': True}, 'dataset_info': {'train_valid_test_set_no': {'train_set_no': 412, 'valid_set_no': 141, 'test_set_no': None}, 'train_valid_test_class_balance': {'y_train_class_balance': {1: 0.29854368932038833, 0: 0.7014563106796117}, 'y_valid_class_balance': {0: 0.7021276595744681, 1: 0.2978723404255319}, 'y_test_class_balance': None}}}, calibration_info={'method': 'sigmoid'}, test_results=None, balance_info={'is_balanced': True, 'original_size': 412, 'balanced_size': 246, 'original_positive_rate': np.float64(0.29854368932038833), 'balanced_positive_rate': np.float64(0.5), 'majority_to_minority_ratio': 1.0})"
+       "TrainingResults(prediction_time=(9, 30), training_info={'cv_trials': [HyperParameterTrial(parameters={'n_estimators': 20}, cv_results={'train_auc': np.float64(0.9863488774220018), 'train_logloss': np.float64(0.23452358103155707), 'train_auprc': np.float64(0.9839960012755344), 'valid_auc': np.float64(0.7404647983595354), 'valid_logloss': np.float64(0.6777401687873552), 'valid_auprc': np.float64(0.732305765806727)}), HyperParameterTrial(parameters={'n_estimators': 30}, cv_results={'train_auc': np.float64(0.9934036840041577), 'train_logloss': np.float64(0.19339304380613956), 'train_auprc': np.float64(0.992275317414658), 'valid_auc': np.float64(0.7414445203918889), 'valid_logloss': np.float64(0.7224622070024668), 'valid_auprc': np.float64(0.739694204530856)}), HyperParameterTrial(parameters={'n_estimators': 40}, cv_results={'train_auc': np.float64(0.9966901551317282), 'train_logloss': np.float64(0.16839291733590328), 'train_auprc': np.float64(0.9957460357414476), 'valid_auc': np.float64(0.7385623148781044), 'valid_logloss': np.float64(0.7471921767090972), 'valid_auprc': np.float64(0.7319157690354547)})], 'features': {'names': ['age', 'latest_triage_score', 'num_urinalysis_orders', 'num_troponin_orders', 'num_bmp_orders', 'num_cbc_orders', 'num_d-dimer_orders'], 'importances': [0.07901820540428162, 0.50030118227005, 0.10778335481882095, 0.06226950138807297, 0.08132454752922058, 0.049338143318891525, 0.11996506154537201], 'has_importance_values': True}, 'dataset_info': {'train_valid_test_set_no': {'train_set_no': 412, 'valid_set_no': 141, 'test_set_no': None}, 'train_valid_test_class_balance': {'y_train_class_balance': {1: 0.29854368932038833, 0: 0.7014563106796117}, 'y_valid_class_balance': {0: 0.7021276595744681, 1: 0.2978723404255319}, 'y_test_class_balance': None}}}, calibration_info={'method': 'sigmoid'}, test_results=None, balance_info={'is_balanced': True, 'original_size': 412, 'balanced_size': 246, 'original_positive_rate': np.float64(0.29854368932038833), 'balanced_positive_rate': np.float64(0.5), 'majority_to_minority_ratio': 1.0})"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -408,7 +408,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -441,7 +441,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -465,7 +465,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -508,7 +508,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -522,7 +522,7 @@
        " 'majority_to_minority_ratio': 1.0}"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -540,7 +540,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -549,7 +549,7 @@
        "{'method': 'sigmoid'}"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -567,18 +567,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[HyperParameterTrial(parameters={'n_estimators': 20}, cv_results={'train_auc': np.float64(0.9863488774220018), 'train_logloss': np.float64(0.2345235821107298), 'train_auprc': np.float64(0.9839960012755344), 'valid_auc': np.float64(0.7404647983595354), 'valid_logloss': np.float64(0.6777401688701863), 'valid_auprc': np.float64(0.732305765806727)}),\n",
-       " HyperParameterTrial(parameters={'n_estimators': 30}, cv_results={'train_auc': np.float64(0.9934036840041577), 'train_logloss': np.float64(0.19339304359858095), 'train_auprc': np.float64(0.992275317414658), 'valid_auc': np.float64(0.7414445203918889), 'valid_logloss': np.float64(0.7224622072494462), 'valid_auprc': np.float64(0.739694204530856)}),\n",
-       " HyperParameterTrial(parameters={'n_estimators': 40}, cv_results={'train_auc': np.float64(0.9966901551317282), 'train_logloss': np.float64(0.16839291934975475), 'train_auprc': np.float64(0.9957460357414476), 'valid_auc': np.float64(0.7385623148781044), 'valid_logloss': np.float64(0.7471921775214785), 'valid_auprc': np.float64(0.7319157690354547)})]"
+       "[HyperParameterTrial(parameters={'n_estimators': 20}, cv_results={'train_auc': np.float64(0.9863488774220018), 'train_logloss': np.float64(0.23452358103155707), 'train_auprc': np.float64(0.9839960012755344), 'valid_auc': np.float64(0.7404647983595354), 'valid_logloss': np.float64(0.6777401687873552), 'valid_auprc': np.float64(0.732305765806727)}),\n",
+       " HyperParameterTrial(parameters={'n_estimators': 30}, cv_results={'train_auc': np.float64(0.9934036840041577), 'train_logloss': np.float64(0.19339304380613956), 'train_auprc': np.float64(0.992275317414658), 'valid_auc': np.float64(0.7414445203918889), 'valid_logloss': np.float64(0.7224622070024668), 'valid_auprc': np.float64(0.739694204530856)}),\n",
+       " HyperParameterTrial(parameters={'n_estimators': 40}, cv_results={'train_auc': np.float64(0.9966901551317282), 'train_logloss': np.float64(0.16839291733590328), 'train_auprc': np.float64(0.9957460357414476), 'valid_auc': np.float64(0.7385623148781044), 'valid_logloss': np.float64(0.7471921767090972), 'valid_auprc': np.float64(0.7319157690354547)})]"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -590,7 +590,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -619,7 +619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -655,7 +655,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {