Upload folder using huggingface_hub

README.md

@@ -1,3 +1,80 @@
----
-license: mit
----
+---
+license: mit
+library_name: scikit-learn
+tags:
+- flood-risk
+- tabular-classification
+- environmental-risk
+- singapore
+- lightgbm
+pipeline_tag: tabular-classification
+---
+
+# weijuinlee/coastal-risk-ai
+
+`coastal-risk-ai` predicts whether a flood alert will occur in the next 60 minutes for a location using rainfall, wind speed, tide level, and location metadata.
+
+## Model Summary
+
+- Task: binary classification
+- Target: `flood_event_next_60m`
+- Forecast horizon: 60 minutes
+- Model type: lightgbm
+
+## Risk Output
+
+- Probability: `0.0` to `1.0`
+- Risk labels:
+  - `low` for probability < 0.35
+  - `medium` for probability >= 0.35 and < 0.7
+  - `high` for probability >= 0.7
+
+## Evaluation
+
+Validation:
+- PR-AUC: 0.5146026360944063
+- ROC-AUC: 0.6092489137181875
+- F1: 0.5399534522885958
+
+Test:
+- PR-AUC: 0.5376358213531683
+- ROC-AUC: 0.6483611055375994
+- F1: 0.6011466011466011
+- Precision: 0.5628834355828221
+- Recall: 0.6449912126537786
+
+## Expected Input Schema
+
+- `location_id`
+- `rainfall_mm`
+- `wind_speed`
+- `tide_level_m`
+- `flood_prone_flag`
+- `hour_of_day`
+- `day_of_week` optional
+- `month` optional
+
+## Training Data
+
+This artifact was trained from the normalized coastal risk schema used in the repository:
+
+- `timestamp`
+- `location_id`
+- `latitude`
+- `longitude`
+- `rainfall_mm`
+- `wind_speed`
+- `tide_level_m`
+- `flood_alert`
+- `flood_prone_flag`
+
+The bundled sample dataset is synthetic and intended for pipeline validation and demo use.
+
+## Files
+
+- `model.joblib`: trained model artifact
+- `features.json`: ordered model feature list
+- `metrics.json`: train and evaluation metrics
+- `config.json`: pipeline configuration used for training
+- `sample_inference_single.json`: example inference payload
+- `sample_inference_batch.csv`: example batch inference payload

config.json

@@ -0,0 +1,34 @@
+{
+  "paths": {
+    "project_root": "/Users/leeweijuin/Development/coastal-risk-ai",
+    "raw_data_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/raw",
+    "processed_data_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/processed",
+    "artifacts_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts",
+    "model_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/model.joblib",
+    "features_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/features.json",
+    "metrics_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/metrics.json",
+    "evaluation_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/evaluation.json",
+    "dataset_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/raw/sample_environment_data.csv"
+  },
+  "features": {
+    "forecast_horizon_minutes": 60,
+    "rolling_windows_minutes": [
+      15,
+      30,
+      60,
+      180
+    ],
+    "high_tide_threshold_m": 2.8
+  },
+  "model": {
+    "model_type": "lightgbm",
+    "random_seed": 42,
+    "decision_threshold": 0.5,
+    "test_size": 0.15,
+    "val_size": 0.15
+  },
+  "risk": {
+    "medium_threshold": 0.35,
+    "high_threshold": 0.7
+  }
+}

features.json

@@ -0,0 +1,21 @@
+[
+  "rainfall_current",
+  "rainfall_15min_sum",
+  "rainfall_30min_sum",
+  "rainfall_60min_sum",
+  "rainfall_180min_sum",
+  "rainfall_60min_max",
+  "rainfall_trend",
+  "wind_current",
+  "wind_30min_mean",
+  "wind_60min_max",
+  "tide_current",
+  "tide_60min_mean",
+  "tide_trend",
+  "high_tide_flag",
+  "hour_of_day",
+  "day_of_week",
+  "month",
+  "location_code",
+  "flood_prone_flag"
+]

metrics.json

@@ -0,0 +1,92 @@
+{
+  "target": "flood_event_next_60m",
+  "model_type": "lightgbm",
+  "class_weight_scale": 1.29498861047836,
+  "validation": {
+    "pr_auc": 0.5146026360944063,
+    "roc_auc": 0.6092489137181875,
+    "f1": 0.5399534522885958,
+    "precision": 0.4627659574468085,
+    "recall": 0.6480446927374302,
+    "confusion_matrix": [
+      [
+        358,
+        404
+      ],
+      [
+        189,
+        348
+      ]
+    ]
+  },
+  "test": {
+    "pr_auc": 0.5376358213531683,
+    "roc_auc": 0.6483611055375994,
+    "f1": 0.6011466011466011,
+    "precision": 0.5628834355828221,
+    "recall": 0.6449912126537786,
+    "confusion_matrix": [
+      [
+        442,
+        285
+      ],
+      [
+        202,
+        367
+      ]
+    ]
+  },
+  "split_sizes": {
+    "train": 6045,
+    "validation": 1299,
+    "test": 1296
+  },
+  "split_time_ranges": {
+    "train": [
+      "2025-01-01 00:00:00+00:00",
+      "2025-01-07 23:50:00+00:00"
+    ],
+    "validation": [
+      "2025-01-07 23:55:00+00:00",
+      "2025-01-09 11:55:00+00:00"
+    ],
+    "test": [
+      "2025-01-09 12:00:00+00:00",
+      "2025-01-10 23:55:00+00:00"
+    ]
+  },
+  "config": {
+    "paths": {
+      "project_root": "/Users/leeweijuin/Development/coastal-risk-ai",
+      "raw_data_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/raw",
+      "processed_data_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/processed",
+      "artifacts_dir": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts",
+      "model_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/model.joblib",
+      "features_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/features.json",
+      "metrics_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/metrics.json",
+      "evaluation_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/artifacts/evaluation.json",
+      "dataset_path": "/Users/leeweijuin/Development/coastal-risk-ai/data/raw/sample_environment_data.csv"
+    },
+    "features": {
+      "forecast_horizon_minutes": 60,
+      "rolling_windows_minutes": [
+        15,
+        30,
+        60,
+        180
+      ],
+      "high_tide_threshold_m": 2.8
+    },
+    "model": {
+      "model_type": "lightgbm",
+      "random_seed": 42,
+      "decision_threshold": 0.5,
+      "test_size": 0.15,
+      "val_size": 0.15
+    },
+    "risk": {
+      "medium_threshold": 0.35,
+      "high_threshold": 0.7
+    }
+  }
+}

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4135bfb53e3e41bb363ee40dc83a2c2a27d5b7bfe7832432851606c2c4556166
+size 679712

sample_inference_batch.csv

@@ -0,0 +1,3 @@
+location_id,rainfall_mm,wind_speed,tide_level_m,flood_prone_flag,hour_of_day,day_of_week,month
+SG-001,22.0,13.0,2.95,1,18,2,1
+SG-002,2.5,6.5,1.7,0,11,2,1

sample_inference_single.json

@@ -0,0 +1,10 @@
+{
+  "location_id": "SG-001",
+  "rainfall_mm": 22.0,
+  "wind_speed": 13.0,
+  "tide_level_m": 2.95,
+  "flood_prone_flag": 1,
+  "hour_of_day": 18,
+  "day_of_week": 2,
+  "month": 1
+}