Upload folder using huggingface_hub

.gitattributes

@@ -32,4 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,203 @@
----
-license: mit
----
+---
+language: en
+license: mit
+model-index:
+- name: aai540-group3/diabetes-readmission
+  results:
+  - task:
+      type: binary-classification
+    dataset:
+      name: Diabetes 130-US Hospitals
+      type: hospital-readmission
+    metrics:
+    - type: accuracy
+      value: 0.8865474882652552
+      name: accuracy
+    - type: auc
+      value: 0.6467403398083669
+      name: auc
+---
+
+# aai540-group3/diabetes-readmission
+
+## Model Description
+
+This model predicts 30-day hospital readmissions for diabetic patients using historical patient data
+and machine learning techniques. The model aims to identify high-risk individuals enabling targeted
+interventions and improved healthcare resource allocation.
+
+## Overview
+
+- **Task:** Binary Classification (Hospital Readmission Prediction)
+- **Model Type:** autogluon
+- **Framework:** Python Autogluon
+- **License:** MIT
+- **Last Updated:** 2024-10-29
+
+## Performance Metrics
+
+- **Test Accuracy:** 0.8865
+- **Test ROC-AUC:** 0.6467
+
+## Feature Importance
+
+Significant features and their importance scores:
+
+| Feature | Importance | p-value | 99% CI |
+|---------|------------|----------|----------|
+| 0 | 0.0563 | 3.24e-04 | [0.0294, 0.0832] |
+| 1 | 0.0358 | 8.45e-06 | [0.0290, 0.0426] |
+| 2 | 0.0080 | 0.0083 | [-0.0013, 0.0173] |
+| 3 | 0.0046 | 1.96e-04 | [0.0027, 0.0065] |
+| 4 | 0.0023 | 0.0055 | [-0.0001, 0.0046] |
+| 5 | 0.0008 | 0.1840 | [-0.0027, 0.0043] |
+
+*Note: Only features with non-zero importance are shown. The confidence intervals (CI) are calculated at the 99% level. Features with p-value < 0.05 are considered statistically significant.*
+
+## Features
+
+### Numeric Features
+- Patient demographics (age)
+- Hospital stay metrics (time_in_hospital, num_procedures, num_lab_procedures)
+- Medication metrics (num_medications, total_medications)
+- Service utilization (number_outpatient, number_emergency, number_inpatient)
+- Diagnostic information (number_diagnoses)
+
+### Binary Features
+- Patient characteristics (gender)
+- Medication flags (diabetesmed, change, insulin_with_oral)
+
+### Interaction Features
+- Time-based interactions (medications × time, procedures × time)
+- Complexity indicators (age × diagnoses, medications × procedures)
+- Resource utilization (lab procedures × time, medications × changes)
+
+### Ratio Features
+- Resource efficiency (procedure/medication ratio, lab/procedure ratio)
+- Diagnostic density (diagnosis/procedure ratio)
+
+## Intended Use
+
+This model is designed for healthcare professionals to assess the risk of 30-day readmission
+for diabetic patients. It should be used as a supportive tool in conjunction with clinical judgment.
+
+### Primary Intended Uses
+- Predict likelihood of 30-day hospital readmission
+- Support resource allocation and intervention planning
+- Aid in identifying high-risk patients
+- Assist in care management decision-making
+
+### Out-of-Scope Uses
+- Non-diabetic patient populations
+- Predicting readmissions beyond 30 days
+- Making final decisions without clinical oversight
+- Use as sole determinant for patient care decisions
+- Emergency or critical care decision-making
+
+## Training Data
+
+The model was trained on the [Diabetes 130-US Hospitals Dataset](https://doi.org/10.24432/C5230J)
+(1999-2008) from UCI ML Repository. This dataset includes:
+
+- Over 100,000 hospital admissions
+- 50+ features including patient demographics, diagnoses, procedures
+- Binary outcome: readmission within 30 days
+- Comprehensive medication tracking
+- Detailed hospital utilization metrics
+
+## Training Procedure
+
+### Data Preprocessing
+- Missing value imputation using mean/mode
+- Outlier handling using 5-sigma clipping
+- Feature scaling using StandardScaler
+- Categorical encoding using one-hot encoding
+- Log transformation for skewed features
+
+### Feature Engineering
+- Created interaction terms between key variables
+- Generated resource utilization ratios
+- Aggregated medication usage metrics
+- Developed time-based interaction features
+- Constructed diagnostic density metrics
+
+### Model Training
+- Data split: 70% training, 15% validation, 15% test
+- Cross-validation for model selection
+- Hyperparameter optimization via grid search
+- Early stopping to prevent overfitting
+- Model selection based on ROC-AUC performance
+
+## Limitations & Biases
+
+### Known Limitations
+- Model performance depends on data quality and completeness
+- Limited to the scope of training data timeframe (1999-2008)
+- May not generalize to significantly different healthcare systems
+- Requires standardized input data format
+
+### Potential Biases
+- May exhibit demographic biases present in training data
+- Performance may vary across different hospital systems
+- Could be influenced by regional healthcare practices
+- Might show temporal biases due to historical data
+
+### Recommendations
+- Regular model monitoring and retraining
+- Careful validation in new deployment contexts
+- Assessment of performance across demographic groups
+- Integration with existing clinical workflows
+
+## Monitoring & Maintenance
+
+### Monitoring Requirements
+- Track prediction accuracy across different patient groups
+- Monitor input data distribution shifts
+- Assess feature importance stability
+- Evaluate performance metrics over time
+
+### Maintenance Schedule
+- Quarterly performance reviews recommended
+- Annual retraining with updated data
+- Regular bias assessments
+- Ongoing validation against current practices
+
+## Citation
+
+```bibtex
+@misc{diabetes-readmission-model,
+  title = {Hospital Readmission Prediction Model for Diabetic Patients},
+  author = {Agustin, Jonathan and Robertson, Zack and Vo, Lisa},
+  year = {2024},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/{REPO_ID}}}
+}
+
+@misc{diabetes-dataset,
+  title = {Diabetes 130-US Hospitals for Years 1999-2008 Data Set},
+  author = {Strack, B. and DeShazo, J. and Gennings, C. and Olmo, J. and
+            Ventura, S. and Cios, K. and Clore, J.},
+  year = {2014},
+  publisher = {UCI Machine Learning Repository},
+  doi = {10.24432/C5230J}
+}
+```
+
+## Model Card Authors
+
+Jonathan Agustin, Zack Robertson, Lisa Vo
+
+## For Questions, Issues, or Feedback
+
+- GitHub Issues: [Repository Issues](https://github.com/aai540-group3/diabetes-readmission/issues)
+- Email: [team contact information]
+
+## Updates and Versions
+
+- {pd.Timestamp.now().strftime('%Y-%m-%d')}: Initial model release
+- Feature engineering pipeline implemented
+- Comprehensive preprocessing system added
+- Model evaluation and selection completed
+
+---
+Last updated: {pd.Timestamp.now().strftime('%Y-%m-%d')}

autogluon/metrics/feature_importance.csv

@@ -0,0 +1,98 @@
+,importance,stddev,p_value,n,p99_high,p99_low
+total_encounters,0.05633188246384744,0.01306857727918546,0.0003239944497075829,5,0.08324026370862368,0.029423501219071196
+discharge_disposition_id_2.0,0.03579614353303893,0.0032878240066241274,8.445030543368168e-06,5,0.042565818605235,0.029026468460842857
+encounter_per_time,0.008011873284703586,0.004518928602209438,0.008307777731853096,5,0.017316409734883593,-0.0012926631654764202
+age_x_number_diagnoses,0.004567182369341038,0.0009303464717592386,0.00019566488400355028,5,0.006482778613448061,0.002651586125234015
+number_diagnoses_x_time_in_hospital,0.0022883946798970545,0.00114142152620697,0.005482230034090644,5,0.0046385973784792405,-6.180801868513114e-05
+age_x_num_medications,0.0007673725098147121,0.0016926127397477618,0.1840177606988291,5,0.004252485535349559,-0.002717740515720135
+gender,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_numchange,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_5,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_4,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_3,0.0,0.0,0.5,5,0.0,0.0
+diagnosis_procedure_ratio,0.0,0.0,0.5,5,0.0,0.0
+lab_procedure_ratio,0.0,0.0,0.5,5,0.0,0.0
+procedure_medication_ratio,0.0,0.0,0.5,5,0.0,0.0
+time_in_hospital_x_num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+change_x_num_medications,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_4,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_num_procedures,0.0,0.0,0.5,5,0.0,0.0
+total_medications_x_number_diagnoses,0.0,0.0,0.5,5,0.0,0.0
+num_lab_procedures_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+num_procedures_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_3.5,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_7,0.0,0.0,0.5,5,0.0,0.0
+number_emergency_log1p,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_8,0.0,0.0,0.5,5,0.0,0.0
+event_timestamp,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_8.0,0.0,0.0,0.5,5,0.0,0.0
+A1Cresult_1,0.0,0.0,0.5,5,0.0,0.0
+A1Cresult_0,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum_1,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum_0,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_18,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_10,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_7,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_2,0.0,0.0,0.5,5,0.0,0.0
+gender_1,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_7.5,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_7.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_6.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_5.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_4.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_3.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_2.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_1.0,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_11,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_9,0.0,0.0,0.5,5,0.0,0.0
+number_inpatient_log1p,0.0,0.0,0.5,5,0.0,0.0
+diagnoses_per_encounter,0.0,0.0,0.5,5,0.0,0.0
+number_outpatient_log1p,0.0,0.0,0.5,5,0.0,0.0
+metformin,0.0,0.0,0.5,5,0.0,0.0
+pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+tolbutamide,0.0,0.0,0.5,5,0.0,0.0
+glyburide,0.0,0.0,0.5,5,0.0,0.0
+glipizide,0.0,0.0,0.5,5,0.0,0.0
+acetohexamide,0.0,0.0,0.5,5,0.0,0.0
+glimepiride,0.0,0.0,0.5,5,0.0,0.0
+chlorpropamide,0.0,0.0,0.5,5,0.0,0.0
+nateglinide,0.0,0.0,0.5,5,0.0,0.0
+repaglinide,0.0,0.0,0.5,5,0.0,0.0
+a1cresult,0.0,0.0,0.5,5,0.0,0.0
+acarbose,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum,0.0,0.0,0.5,5,0.0,0.0
+number_diagnoses,0.0,0.0,0.5,5,0.0,0.0
+diag_3,0.0,0.0,0.5,5,0.0,0.0
+diag_2,0.0,0.0,0.5,5,0.0,0.0
+diag_1,0.0,0.0,0.5,5,0.0,0.0
+num_medications,0.0,0.0,0.5,5,0.0,0.0
+num_procedures,0.0,0.0,0.5,5,0.0,0.0
+num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+rosiglitazone,0.0,0.0,0.5,5,0.0,0.0
+miglitol,0.0,0.0,0.5,5,0.0,0.0
+age,0.0,0.0,0.5,5,0.0,0.0
+level1_diag2,0.0,0.0,0.5,5,0.0,0.0
+procedures_to_medications,0.0,0.0,0.5,5,0.0,0.0
+lab_procedures_per_day,0.0,0.0,0.5,5,0.0,0.0
+procedures_per_day,0.0,0.0,0.5,5,0.0,0.0
+nummed,0.0,0.0,0.5,5,0.0,0.0
+numchange,0.0,0.0,0.5,5,0.0,0.0
+insulin_with_oral,0.0,0.0,0.5,5,0.0,0.0
+medication_density,0.0,0.0,0.5,5,0.0,0.0
+total_medications,0.0,0.0,0.5,5,0.0,0.0
+level1_diag3,0.0,0.0,0.5,5,0.0,0.0
+id,0.0,0.0,0.5,5,0.0,0.0
+troglitazone,0.0,0.0,0.5,5,0.0,0.0
+diabetesmed,0.0,0.0,0.5,5,0.0,0.0
+change,0.0,0.0,0.5,5,0.0,0.0
+metformin-pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+metformin-rosiglitazone,0.0,0.0,0.5,5,0.0,0.0
+glimepiride-pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+glipizide-metformin,0.0,0.0,0.5,5,0.0,0.0
+glyburide-metformin,0.0,0.0,0.5,5,0.0,0.0
+insulin,0.0,0.0,0.5,5,0.0,0.0
+tolazamide,0.0,0.0,0.5,5,0.0,0.0
+created_timestamp,0.0,0.0,0.5,5,0.0,0.0

autogluon/metrics/metrics.json

@@ -0,0 +1,8 @@
+{
+    "test_accuracy": 0.8865474882652552,
+    "test_precision": 0.0,
+    "test_recall": 0.0,
+    "test_f1": 0.0,
+    "test_auc": 0.6467403398083669,
+    "test_pr_auc": 0.18117429407499608
+}

autogluon/model/feature_importance.csv

@@ -0,0 +1,98 @@
+,importance,stddev,p_value,n,p99_high,p99_low
+total_encounters,0.05633188246384744,0.01306857727918546,0.0003239944497075829,5,0.08324026370862368,0.029423501219071196
+discharge_disposition_id_2.0,0.03579614353303893,0.0032878240066241274,8.445030543368168e-06,5,0.042565818605235,0.029026468460842857
+encounter_per_time,0.008011873284703586,0.004518928602209438,0.008307777731853096,5,0.017316409734883593,-0.0012926631654764202
+age_x_number_diagnoses,0.004567182369341038,0.0009303464717592386,0.00019566488400355028,5,0.006482778613448061,0.002651586125234015
+number_diagnoses_x_time_in_hospital,0.0022883946798970545,0.00114142152620697,0.005482230034090644,5,0.0046385973784792405,-6.180801868513114e-05
+age_x_num_medications,0.0007673725098147121,0.0016926127397477618,0.1840177606988291,5,0.004252485535349559,-0.002717740515720135
+gender,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_numchange,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_5,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_4,0.0,0.0,0.5,5,0.0,0.0
+admission_type_id_3,0.0,0.0,0.5,5,0.0,0.0
+diagnosis_procedure_ratio,0.0,0.0,0.5,5,0.0,0.0
+lab_procedure_ratio,0.0,0.0,0.5,5,0.0,0.0
+procedure_medication_ratio,0.0,0.0,0.5,5,0.0,0.0
+time_in_hospital_x_num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+change_x_num_medications,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_4,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_num_procedures,0.0,0.0,0.5,5,0.0,0.0
+total_medications_x_number_diagnoses,0.0,0.0,0.5,5,0.0,0.0
+num_lab_procedures_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+num_procedures_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+num_medications_x_time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_3.5,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_7,0.0,0.0,0.5,5,0.0,0.0
+number_emergency_log1p,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_8,0.0,0.0,0.5,5,0.0,0.0
+event_timestamp,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_8.0,0.0,0.0,0.5,5,0.0,0.0
+A1Cresult_1,0.0,0.0,0.5,5,0.0,0.0
+A1Cresult_0,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum_1,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum_0,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_18,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_10,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_7,0.0,0.0,0.5,5,0.0,0.0
+discharge_disposition_id_2,0.0,0.0,0.5,5,0.0,0.0
+gender_1,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_7.5,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_7.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_6.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_5.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_4.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_3.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_2.0,0.0,0.0,0.5,5,0.0,0.0
+level1_diag1_1.0,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_11,0.0,0.0,0.5,5,0.0,0.0
+admission_source_id_9,0.0,0.0,0.5,5,0.0,0.0
+number_inpatient_log1p,0.0,0.0,0.5,5,0.0,0.0
+diagnoses_per_encounter,0.0,0.0,0.5,5,0.0,0.0
+number_outpatient_log1p,0.0,0.0,0.5,5,0.0,0.0
+metformin,0.0,0.0,0.5,5,0.0,0.0
+pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+tolbutamide,0.0,0.0,0.5,5,0.0,0.0
+glyburide,0.0,0.0,0.5,5,0.0,0.0
+glipizide,0.0,0.0,0.5,5,0.0,0.0
+acetohexamide,0.0,0.0,0.5,5,0.0,0.0
+glimepiride,0.0,0.0,0.5,5,0.0,0.0
+chlorpropamide,0.0,0.0,0.5,5,0.0,0.0
+nateglinide,0.0,0.0,0.5,5,0.0,0.0
+repaglinide,0.0,0.0,0.5,5,0.0,0.0
+a1cresult,0.0,0.0,0.5,5,0.0,0.0
+acarbose,0.0,0.0,0.5,5,0.0,0.0
+max_glu_serum,0.0,0.0,0.5,5,0.0,0.0
+number_diagnoses,0.0,0.0,0.5,5,0.0,0.0
+diag_3,0.0,0.0,0.5,5,0.0,0.0
+diag_2,0.0,0.0,0.5,5,0.0,0.0
+diag_1,0.0,0.0,0.5,5,0.0,0.0
+num_medications,0.0,0.0,0.5,5,0.0,0.0
+num_procedures,0.0,0.0,0.5,5,0.0,0.0
+num_lab_procedures,0.0,0.0,0.5,5,0.0,0.0
+time_in_hospital,0.0,0.0,0.5,5,0.0,0.0
+rosiglitazone,0.0,0.0,0.5,5,0.0,0.0
+miglitol,0.0,0.0,0.5,5,0.0,0.0
+age,0.0,0.0,0.5,5,0.0,0.0
+level1_diag2,0.0,0.0,0.5,5,0.0,0.0
+procedures_to_medications,0.0,0.0,0.5,5,0.0,0.0
+lab_procedures_per_day,0.0,0.0,0.5,5,0.0,0.0
+procedures_per_day,0.0,0.0,0.5,5,0.0,0.0
+nummed,0.0,0.0,0.5,5,0.0,0.0
+numchange,0.0,0.0,0.5,5,0.0,0.0
+insulin_with_oral,0.0,0.0,0.5,5,0.0,0.0
+medication_density,0.0,0.0,0.5,5,0.0,0.0
+total_medications,0.0,0.0,0.5,5,0.0,0.0
+level1_diag3,0.0,0.0,0.5,5,0.0,0.0
+id,0.0,0.0,0.5,5,0.0,0.0
+troglitazone,0.0,0.0,0.5,5,0.0,0.0
+diabetesmed,0.0,0.0,0.5,5,0.0,0.0
+change,0.0,0.0,0.5,5,0.0,0.0
+metformin-pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+metformin-rosiglitazone,0.0,0.0,0.5,5,0.0,0.0
+glimepiride-pioglitazone,0.0,0.0,0.5,5,0.0,0.0
+glipizide-metformin,0.0,0.0,0.5,5,0.0,0.0
+glyburide-metformin,0.0,0.0,0.5,5,0.0,0.0
+insulin,0.0,0.0,0.5,5,0.0,0.0
+tolazamide,0.0,0.0,0.5,5,0.0,0.0
+created_timestamp,0.0,0.0,0.5,5,0.0,0.0

autogluon/model/leaderboard.csv

@@ -0,0 +1,3 @@
+model,score_test,score_val,eval_metric,pred_time_test,pred_time_val,fit_time,pred_time_test_marginal,pred_time_val_marginal,fit_time_marginal,stack_level,can_infer,fit_order
+LightGBMBasic,0.6467403398083669,0.6342024393654344,roc_auc,0.03393197059631348,0.03538703918457031,1.146812915802002,0.03393197059631348,0.03538703918457031,1.146812915802002,1,True,1
+WeightedEnsemble_L2,0.6467403398083669,0.6342024393654344,roc_auc,0.0435791015625,0.035985708236694336,1.149925947189331,0.009647130966186523,0.0005986690521240234,0.0031130313873291016,2,True,2

autogluon/model/learner.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ff306c94de1c67d7c49887f2ddda86584e9575df3afdac54b8c4008c615cfa
+size 6740

autogluon/model/metadata.json

@@ -0,0 +1,352 @@
+{
+  "system": "Linux",
+  "version": "1.1.1",
+  "lite": false,
+  "py_version": "3.10",
+  "py_version_micro": "3.10.15",
+  "packages": {
+    "gitpython": "3.1.43",
+    "mako": "1.3.6",
+    "markdown": "3.7",
+    "markupsafe": "3.0.2",
+    "pydrive2": "1.20.0",
+    "pyjwt": "2.9.0",
+    "pysocks": "1.7.1",
+    "pyyaml": "6.0.2",
+    "sqlalchemy": "2.0.36",
+    "absl-py": "2.1.0",
+    "accelerate": "0.21.0",
+    "adlfs": "2024.7.0",
+    "aiobotocore": "2.15.2",
+    "aiohappyeyeballs": "2.4.3",
+    "aiohttp": "3.10.10",
+    "aiohttp-cors": "0.7.0",
+    "aiohttp-retry": "2.9.0",
+    "aioitertools": "0.12.0",
+    "aiooss2": "0.2.10",
+    "aiosignal": "1.3.1",
+    "alembic": "1.13.3",
+    "aliyun-python-sdk-core": "2.16.0",
+    "aliyun-python-sdk-kms": "2.16.5",
+    "amqp": "5.2.0",
+    "annotated-types": "0.7.0",
+    "antlr4-python3-runtime": "4.9.3",
+    "anyio": "4.6.2.post1",
+    "appdirs": "1.4.4",
+    "argcomplete": "3.5.1",
+    "async-timeout": "4.0.3",
+    "asyncssh": "2.18.0",
+    "atpublic": "5.0",
+    "attrs": "24.2.0",
+    "autogluon": "1.1.1",
+    "autogluon.common": "1.1.1",
+    "autogluon.core": "1.1.1",
+    "autogluon.features": "1.1.1",
+    "autogluon.multimodal": "1.1.1",
+    "autogluon.tabular": "1.1.1",
+    "autogluon.timeseries": "1.1.1",
+    "azure-core": "1.31.0",
+    "azure-datalake-store": "0.0.53",
+    "azure-identity": "1.19.0",
+    "azure-storage-blob": "12.23.1",
+    "bcrypt": "4.2.0",
+    "beautifulsoup4": "4.12.3",
+    "billiard": "4.2.1",
+    "blis": "0.7.11",
+    "boto3": "1.35.36",
+    "botocore": "1.35.36",
+    "cachetools": "5.5.0",
+    "catalogue": "2.0.10",
+    "catboost": "1.2.7",
+    "celery": "5.4.0",
+    "certifi": "2024.8.30",
+    "cffi": "1.17.1",
+    "charset-normalizer": "3.4.0",
+    "click": "8.1.7",
+    "click-didyoumean": "0.3.1",
+    "click-plugins": "1.1.1",
+    "click-repl": "0.3.0",
+    "cloudpathlib": "0.20.0",
+    "cloudpickle": "3.1.0",
+    "colorama": "0.4.6",
+    "coloredlogs": "15.0.1",
+    "colorful": "0.5.6",
+    "colorlog": "6.8.2",
+    "confection": "0.1.5",
+    "configobj": "5.0.9",
+    "contourpy": "1.3.0",
+    "crcmod": "1.7",
+    "cryptography": "43.0.3",
+    "cycler": "0.12.1",
+    "cymem": "2.0.8",
+    "datasets": "2.14.4",
+    "decorator": "5.1.1",
+    "defusedxml": "0.7.1",
+    "dictdiffer": "0.9.0",
+    "dill": "0.3.7",
+    "diskcache": "5.6.3",
+    "distlib": "0.3.9",
+    "distro": "1.9.0",
+    "dpath": "2.2.0",
+    "dulwich": "0.22.3",
+    "dvc": "3.56.0",
+    "dvc-azure": "3.1.0",
+    "dvc-data": "3.16.6",
+    "dvc-gdrive": "3.0.1",
+    "dvc-gs": "3.0.1",
+    "dvc-hdfs": "3.0.0",
+    "dvc-http": "2.32.0",
+    "dvc-objects": "5.1.0",
+    "dvc-oss": "3.0.0",
+    "dvc-render": "1.0.2",
+    "dvc-s3": "3.2.0",
+    "dvc-ssh": "4.1.1",
+    "dvc-studio-client": "0.21.0",
+    "dvc-task": "0.40.2",
+    "dvc-webdav": "3.0.0",
+    "dvc-webhdfs": "3.1.0",
+    "dvclive": "3.48.0",
+    "entrypoints": "0.4",
+    "evaluate": "0.4.3",
+    "exceptiongroup": "1.2.2",
+    "fastai": "2.7.18",
+    "fastcore": "1.7.19",
+    "fastdownload": "0.0.7",
+    "fastprogress": "1.0.3",
+    "filelock": "3.16.1",
+    "flatbuffers": "24.3.25",
+    "flatten-dict": "0.4.2",
+    "flufl-lock": "8.1.0",
+    "fonttools": "4.54.1",
+    "frozenlist": "1.5.0",
+    "fsspec": "2024.10.0",
+    "funcy": "2.0",
+    "future": "1.0.0",
+    "gcsfs": "2024.10.0",
+    "gdown": "5.2.0",
+    "gitdb": "4.0.11",
+    "gluonts": "0.15.1",
+    "google-api-core": "2.22.0",
+    "google-api-python-client": "2.149.0",
+    "google-auth": "2.35.0",
+    "google-auth-httplib2": "0.2.0",
+    "google-auth-oauthlib": "1.2.1",
+    "google-cloud-core": "2.4.1",
+    "google-cloud-storage": "2.18.2",
+    "google-crc32c": "1.6.0",
+    "google-resumable-media": "2.7.2",
+    "googleapis-common-protos": "1.65.0",
+    "grandalf": "0.8",
+    "graphviz": "0.20.3",
+    "greenlet": "3.1.1",
+    "grpcio": "1.67.1",
+    "gto": "1.7.1",
+    "h11": "0.14.0",
+    "httpcore": "1.0.6",
+    "httplib2": "0.22.0",
+    "httpx": "0.27.2",
+    "huggingface-hub": "0.26.2",
+    "humanfriendly": "10.0",
+    "hydra-core": "1.3.2",
+    "hyperopt": "0.2.7",
+    "idna": "3.10",
+    "imageio": "2.36.0",
+    "isodate": "0.7.2",
+    "iterative-telemetry": "0.0.9",
+    "jinja2": "3.1.4",
+    "jmespath": "0.10.0",
+    "joblib": "1.4.2",
+    "jsonschema": "4.21.1",
+    "jsonschema-specifications": "2024.10.1",
+    "kiwisolver": "1.4.7",
+    "knack": "0.12.0",
+    "kombu": "5.4.2",
+    "langcodes": "3.4.1",
+    "language-data": "1.2.0",
+    "lazy-loader": "0.4",
+    "lightgbm": "4.3.0",
+    "lightning": "2.3.3",
+    "lightning-utilities": "0.11.8",
+    "llvmlite": "0.43.0",
+    "marisa-trie": "1.2.1",
+    "markdown-it-py": "3.0.0",
+    "matplotlib": "3.9.2",
+    "mdurl": "0.1.2",
+    "mlforecast": "0.10.0",
+    "model-index": "0.1.11",
+    "mpmath": "1.3.0",
+    "msal": "1.31.0",
+    "msal-extensions": "1.2.0",
+    "msgpack": "1.1.0",
+    "multidict": "6.1.0",
+    "multiprocess": "0.70.15",
+    "murmurhash": "1.0.10",
+    "networkx": "3.4.2",
+    "nlpaug": "1.1.11",
+    "nltk": "3.9.1",
+    "nptyping": "2.4.1",
+    "numba": "0.60.0",
+    "numpy": "1.26.4",
+    "nvidia-cublas-cu12": "12.1.3.1",
+    "nvidia-cuda-cupti-cu12": "12.1.105",
+    "nvidia-cuda-nvrtc-cu12": "12.1.105",
+    "nvidia-cuda-runtime-cu12": "12.1.105",
+    "nvidia-cudnn-cu12": "8.9.2.26",
+    "nvidia-cufft-cu12": "11.0.2.54",
+    "nvidia-curand-cu12": "10.3.2.106",
+    "nvidia-cusolver-cu12": "11.4.5.107",
+    "nvidia-cusparse-cu12": "12.1.0.106",
+    "nvidia-ml-py3": "7.352.0",
+    "nvidia-nccl-cu12": "2.20.5",
+    "nvidia-nvjitlink-cu12": "12.6.77",
+    "nvidia-nvtx-cu12": "12.1.105",
+    "oauth2client": "4.1.3",
+    "oauthlib": "3.2.2",
+    "omegaconf": "2.2.3",
+    "onnx": "1.17.0",
+    "onnxruntime": "1.19.2",
+    "opencensus": "0.11.4",
+    "opencensus-context": "0.1.3",
+    "opendatalab": "0.0.10",
+    "openmim": "0.3.9",
+    "openxlab": "0.0.11",
+    "optimum": "1.17.1",
+    "optuna": "4.0.0",
+    "ordered-set": "4.1.0",
+    "orjson": "3.10.10",
+    "oss2": "2.18.1",
+    "ossfs": "2023.12.0",
+    "packaging": "24.1",
+    "pandas": "2.2.3",
+    "pathspec": "0.12.1",
+    "patsy": "0.5.6",
+    "pdf2image": "1.17.0",
+    "pillow": "10.4.0",
+    "pip": "24.3.1",
+    "platformdirs": "3.11.0",
+    "plotly": "5.24.1",
+    "portalocker": "2.10.1",
+    "preshed": "3.0.9",
+    "prometheus-client": "0.21.0",
+    "prompt-toolkit": "3.0.48",
+    "propcache": "0.2.0",
+    "proto-plus": "1.25.0",
+    "protobuf": "5.28.3",
+    "psutil": "5.9.8",
+    "py4j": "0.10.9.7",
+    "pyopenssl": "24.2.1",
+    "py-spy": "0.3.14",
+    "pyarrow": "18.0.0",
+    "pyasn1": "0.6.1",
+    "pyasn1-modules": "0.4.1",
+    "pycparser": "2.22",
+    "pycryptodome": "3.21.0",
+    "pydantic": "2.9.2",
+    "pydantic-core": "2.23.4",
+    "pydot": "3.0.2",
+    "pygit2": "1.16.0",
+    "pygments": "2.18.0",
+    "pygraphviz": "1.14",
+    "pygtrie": "2.5.0",
+    "pynvml": "11.5.3",
+    "pyparsing": "3.2.0",
+    "pytesseract": "0.3.10",
+    "python-dateutil": "2.9.0.post0",
+    "pytorch-lightning": "2.3.3",
+    "pytorch-metric-learning": "2.3.0",
+    "pytz": "2024.2",
+    "pywavelets": "1.7.0",
+    "ray": "2.10.0",
+    "referencing": "0.35.1",
+    "regex": "2024.9.11",
+    "requests": "2.32.3",
+    "requests-oauthlib": "2.0.0",
+    "rich": "13.9.3",
+    "rpds-py": "0.20.0",
+    "rsa": "4.9",
+    "ruamel.yaml": "0.18.6",
+    "ruamel.yaml.clib": "0.2.12",
+    "s3fs": "2024.10.0",
+    "s3transfer": "0.10.3",
+    "safetensors": "0.4.5",
+    "scikit-image": "0.20.0",
+    "scikit-learn": "1.4.0",
+    "scipy": "1.12.0",
+    "scmrepo": "3.3.8",
+    "seaborn": "0.13.2",
+    "semver": "3.0.2",
+    "sentencepiece": "0.2.0",
+    "seqeval": "1.2.2",
+    "setuptools": "75.2.0",
+    "shellingham": "1.5.4",
+    "shortuuid": "1.0.13",
+    "shtab": "1.7.1",
+    "six": "1.16.0",
+    "smart-open": "7.0.5",
+    "smmap": "5.0.1",
+    "sniffio": "1.3.1",
+    "soupsieve": "2.6",
+    "spacy": "3.7.5",
+    "spacy-legacy": "3.0.12",
+    "spacy-loggers": "1.0.5",
+    "sqltrie": "0.11.1",
+    "srsly": "2.4.8",
+    "sshfs": "2024.9.0",
+    "statsforecast": "1.4.0",
+    "statsmodels": "0.14.4",
+    "sympy": "1.13.3",
+    "tabulate": "0.9.0",
+    "tenacity": "9.0.0",
+    "tensorboard": "2.18.0",
+    "tensorboardx": "2.6.2.2",
+    "tensorboard-data-server": "0.7.2",
+    "text-unidecode": "1.3",
+    "thinc": "8.2.5",
+    "threadpoolctl": "3.5.0",
+    "tifffile": "2024.9.20",
+    "timm": "0.9.16",
+    "tokenizers": "0.19.1",
+    "tomlkit": "0.13.2",
+    "toolz": "0.12.1",
+    "torch": "2.3.1",
+    "torchmetrics": "1.2.1",
+    "torchvision": "0.18.1",
+    "tqdm": "4.66.6",
+    "transformers": "4.40.2",
+    "triton": "2.3.1",
+    "typer": "0.12.5",
+    "typing-extensions": "4.12.2",
+    "tzdata": "2024.2",
+    "uritemplate": "4.1.1",
+    "urllib3": "2.2.3",
+    "utilsforecast": "0.0.10",
+    "vine": "5.1.0",
+    "virtualenv": "20.27.1",
+    "voluptuous": "0.15.2",
+    "wasabi": "1.1.3",
+    "wcwidth": "0.2.13",
+    "weasel": "0.4.1",
+    "webdav4": "0.10.0",
+    "werkzeug": "3.0.6",
+    "window-ops": "0.0.15",
+    "wrapt": "1.16.0",
+    "xgboost": "2.0.3",
+    "xxhash": "3.5.0",
+    "yarl": "1.17.0",
+    "zc.lockfile": "3.0.post1",
+    "autocommand": "2.2.2",
+    "backports.tarfile": "1.2.0",
+    "importlib-metadata": "8.0.0",
+    "importlib-resources": "6.4.0",
+    "inflect": "7.3.1",
+    "jaraco.collections": "5.1.0",
+    "jaraco.context": "5.3.0",
+    "jaraco.functools": "4.0.1",
+    "jaraco.text": "3.12.1",
+    "more-itertools": "10.3.0",
+    "tomli": "2.0.1",
+    "typeguard": "4.3.0",
+    "wheel": "0.43.0",
+    "zipp": "3.19.2"
+  }
+}

autogluon/model/model_info.txt

@@ -0,0 +1,11 @@
+{
+    "type_of_learner": "",
+    "model_types": "[]",
+    "model_performance": "{}",
+    "model_best": "",
+    "model_paths": "{}",
+    "model_fit_times": "{}",
+    "model_pred_times": "{}",
+    "num_bag_folds": "0",
+    "max_stack_level": "2"
+}

autogluon/model/models/LightGBMBasic/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490527fd79d7ecb074d5629d05a7ed4684748df2a64284d49a6359833b0e2599
+size 18255

autogluon/model/models/WeightedEnsemble_L2/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1c58a255a92233bd6a40a3deedad052d8a33ab8f1a24ac99b6b2309f573b48
+size 6266

autogluon/model/models/trainer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ae12b06443f3b81b7bfb4c054957b48a823e49e21cafc7cf45f74fbe585e31
+size 4548

autogluon/model/predictor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b0e97edfad17ac8de2c788d60d0970dabc449b5d13d5bb94a21f92936ff57e
+size 498

autogluon/model/version.txt

@@ -0,0 +1 @@
+1.1.1

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "TabularBinaryClassification"
+  ],
+  "model_type": "autogluon",
+  "num_classes": 2,
+  "id2label": {
+    "0": "NO_READMISSION",
+    "1": "READMISSION"
+  },
+  "label2id": {
+    "NO_READMISSION": 0,
+    "READMISSION": 1
+  },
+  "task_specific_params": {
+    "classification": {
+      "problem_type": "binary_classification"
+    }
+  },
+  "preprocessing": {
+    "featurization_config": "preprocessing_config.json"
+  }
+}

logistic_regression/metrics/feature_importance.csv

@@ -0,0 +1,96 @@
+0
+0.006981576326524651
+-0.05324149411400925
+0.14520246099157075
+0.16641223168656358
+-0.1849432098152513
+-0.11971438258491879
+-0.6673136921817721
+0.0074340512164186865
+0.00710484910980806
+0.0208036887896313
+-0.06866704970640153
+0.02239663469454034
+-0.04780275329131699
+-0.001653654097302643
+-0.005213524709277947
+-0.038513975558627074
+-0.04872273341141308
+-0.021360986979047168
+-0.0034907486285829445
+-0.0357575743039899
+-0.01159127633728281
+-0.02893996449233495
+-0.025228955046709828
+-0.04067449776032111
+-0.030644765633352167
+-0.03515763759629512
+-0.016977946801395048
+0.09623559368069025
+-0.012484082699882501
+-0.0009575349297166111
+6.65410045567994e-20
+-0.028620120717707788
+-0.019723707791475878
+0.11631781014500936
+0.0
+-0.07245758942528399
+-0.0656703695598517
+-0.033527097500422244
+-0.013496060253957467
+-0.03848636989252564
+-0.06888678626860888
+-0.013496060253957467
+-0.013496060253957467
+0.4826929696848854
+-0.033688000688812766
+0.012021279187115997
+-0.10097152621946577
+-0.05616962767498837
+0.37548621562715806
+0.0
+0.0
+0.3189040988295721
+-0.033023665719576566
+0.16943919206646788
+-0.135015724007822
+-0.10070402041672873
+-0.1747234071221618
+-0.053920085325419025
+0.044547618656999764
+-0.0623980238417873
+-0.135015724007822
+0.109933062277
+-0.07844982806285462
+0.05400868882081664
+-0.05616962767498837
+-0.1295288236523361
+-0.01614939687456253
+0.7051654943458252
+0.021261903585148515
+0.2950273268755952
+0.49860678225720706
+0.20411937062125285
+0.3154294773153667
+0.8437534157758343
+0.017755007787785892
+0.2207871318828695
+-0.013672481533416214
+0.944583524149922
+0.73223783295433
+0.6556707014460541
+0.04423504672748837
+0.7594858589066283
+0.5685208571153414
+0.4973672369575105
+0.2100659929803077
+0.0
+0.0
+0.0
+0.0
+0.0
+0.0
+0.0
+0.0
+0.0
+0.0

logistic_regression/metrics/metrics.json

@@ -0,0 +1,14 @@
+{
+    "val_accuracy": 0.7306731921693967,
+    "val_precision": 0.17053609117771212,
+    "val_recall": 0.35579040070453544,
+    "val_f1": 0.23056070766157796,
+    "val_auc": 0.5940456525813896,
+    "val_avg_precision": 0.159584262357455,
+    "test_accuracy": 0.7294881398252184,
+    "test_precision": 0.1630248500428449,
+    "test_recall": 0.33509467195068254,
+    "test_f1": 0.21933996253062402,
+    "test_auc": 0.5861944545016542,
+    "test_avg_precision": 0.15440710835201596
+}

logistic_regression/model/model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f399e7348b5eb61e6baade37068ffa8d7a5e9445227e15a9294eb9f54b65e56
+size 1631

logistic_regression/model/model_summary.txt

@@ -0,0 +1,2 @@
+Model Parameters:
+{'C': 1.0, 'class_weight': None, 'dual': False, 'fit_intercept': True, 'intercept_scaling': 1, 'l1_ratio': None, 'max_iter': 1000, 'multi_class': 'deprecated', 'n_jobs': None, 'penalty': 'l2', 'random_state': 42, 'solver': 'saga', 'tol': 0.0001, 'verbose': 0, 'warm_start': False}

logistic_regression/model/params.json

@@ -0,0 +1,5 @@
+{
+    "C": 1.0,
+    "penalty": "l2",
+    "solver": "saga"
+}

logistic_regression/model/scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc54552b9983586c38e93f9623af8ecf307363a1083289b8b52260d5ac009c14
+size 5519

neural_network/metrics/metrics.json

@@ -0,0 +1,25 @@
+{
+    "train": {
+        "accuracy": 0.7377527952194214,
+        "auc": 0.8147459626197815,
+        "loss": 0.5141830444335938
+    },
+    "eval": {
+        "accuracy": 0.7731721997261047,
+        "auc": 0.6272097826004028,
+        "loss": 0.5016754269599915
+    },
+    "step": 0,
+    "val_accuracy": 0.7731721933679585,
+    "val_precision": 0.19533136570968607,
+    "val_recall": 0.32056362835755176,
+    "val_f1": 0.24274758252750916,
+    "val_auc": 0.6272456279863441,
+    "val_avg_precision": 0.17174880265376707,
+    "test_accuracy": 0.7703870162297128,
+    "test_precision": 0.18009348364036293,
+    "test_recall": 0.2884191985909291,
+    "test_f1": 0.22173324306025727,
+    "test_auc": 0.6234149477766672,
+    "test_avg_precision": 0.1627787212516569
+}

neural_network/model/model_summary.txt

@@ -0,0 +1,24 @@
+Model: "sequential_1"
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
+┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
+│ dense_3 (Dense)                      │ (None, 48)                  │           4,608 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ batch_normalization_2                │ (None, 48)                  │             192 │
+│ (BatchNormalization)                 │                             │                 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ dropout_2 (Dropout)                  │ (None, 48)                  │               0 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ dense_4 (Dense)                      │ (None, 38)                  │           1,862 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ batch_normalization_3                │ (None, 38)                  │             152 │
+│ (BatchNormalization)                 │                             │                 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ dropout_3 (Dropout)                  │ (None, 38)                  │               0 │
+├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
+│ dense_5 (Dense)                      │ (None, 1)                   │              39 │
+└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
+ Total params: 6,853 (26.77 KB)
+ Trainable params: 6,681 (26.10 KB)
+ Non-trainable params: 172 (688.00 B)
+

neural_network/model/params.json

@@ -0,0 +1,10 @@
+{
+    "n_layers": 2,
+    "units_first": 48,
+    "units_factor": 0.7950714306409916,
+    "dropout": 0.2731993941811405,
+    "learning_rate": 0.003968793330444372,
+    "batch_size": 32,
+    "activation": "relu",
+    "optimizer": "adam"
+}

neural_network/model/scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee48355f8a8cc48ceade28dc3ecd4944699c612fe75252bb66ddce52091ebb5
+size 5519

preprocessing_config.json

@@ -0,0 +1,189 @@
+{
+  "preprocessor": {
+    "numeric_features": [
+      "age",
+      "time_in_hospital",
+      "num_lab_procedures",
+      "num_procedures",
+      "num_medications",
+      "number_diagnoses",
+      "total_medications",
+      "medication_density",
+      "numchange",
+      "nummed",
+      "total_encounters",
+      "encounter_per_time",
+      "procedures_per_day",
+      "lab_procedures_per_day",
+      "procedures_to_medications",
+      "diagnoses_per_encounter",
+      "number_outpatient_log1p",
+      "number_emergency_log1p",
+      "number_inpatient_log1p"
+    ],
+    "binary_features": [
+      "gender",
+      "diabetesmed",
+      "change",
+      "insulin_with_oral"
+    ],
+    "medication_features": [
+      "metformin",
+      "repaglinide",
+      "nateglinide",
+      "chlorpropamide",
+      "glimepiride",
+      "glipizide",
+      "glyburide",
+      "pioglitazone",
+      "rosiglitazone",
+      "acarbose",
+      "miglitol",
+      "insulin",
+      "glyburide-metformin",
+      "tolazamide",
+      "metformin-pioglitazone",
+      "metformin-rosiglitazone",
+      "glimepiride-pioglitazone",
+      "glipizide-metformin",
+      "troglitazone",
+      "tolbutamide",
+      "acetohexamide"
+    ],
+    "interaction_features": [
+      "num_medications_x_time_in_hospital",
+      "num_procedures_x_time_in_hospital",
+      "num_lab_procedures_x_time_in_hospital",
+      "number_diagnoses_x_time_in_hospital",
+      "age_x_number_diagnoses",
+      "age_x_num_medications",
+      "total_medications_x_number_diagnoses",
+      "num_medications_x_num_procedures",
+      "time_in_hospital_x_num_lab_procedures",
+      "num_medications_x_num_lab_procedures",
+      "change_x_num_medications",
+      "num_medications_x_numchange"
+    ],
+    "ratio_features": [
+      "procedure_medication_ratio",
+      "lab_procedure_ratio",
+      "diagnosis_procedure_ratio"
+    ],
+    "categorical_features": {
+      "admission_type_id": [
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8
+      ],
+      "discharge_disposition_id": [
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19,
+        20,
+        21,
+        22,
+        23,
+        24,
+        25,
+        26
+      ],
+      "admission_source_id": [
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19,
+        20,
+        21,
+        22,
+        23,
+        24,
+        25
+      ],
+      "level1_diag1": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8
+      ]
+    },
+    "lab_features": {
+      "a1cresult": {
+        "mapping": {
+          ">7": 1,
+          ">8": 1,
+          "Norm": 0,
+          "None": -99
+        }
+      },
+      "max_glu_serum": {
+        "mapping": {
+          ">200": 1,
+          ">300": 1,
+          "Norm": 0,
+          "None": -99
+        }
+      }
+    }
+  },
+  "transformations": {
+    "numeric_scaling": "standard",
+    "outlier_handling": {
+      "method": "clip",
+      "std_multiplier": 5
+    },
+    "missing_values": {
+      "numeric": "mean",
+      "categorical": "mode"
+    }
+  },
+  "target": {
+    "name": "readmitted",
+    "type": "binary",
+    "mapping": {
+      ">30": 0,
+      "<30": 1,
+      "NO": 0
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "feature_extractor_type": "tabular",
+  "framework": "pt",
+  "num_features": null,
+  "requires_preprocessing": true,
+  "preprocessing_config": "preprocessing_config.json"
+}