hydroanomaly 1.2.1__tar.gz → 1.2.2__tar.gz

{hydroanomaly-1.2.1 → hydroanomaly-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydroanomaly
-Version: 1.2.1
+Version: 1.2.2
 Summary: A Python package for hydro anomaly detection with simple USGS data retrieval
 Author-email: Ehsan Kahrizi <ehsan.kahrizi@usu.edu>
 License: MIT License

{hydroanomaly-1.2.1 → hydroanomaly-1.2.2}/hydroanomaly/__init__.py

@@ -10,7 +10,7 @@ A simple Python package with just 3 modules:
 That's it - nothing else!
 """
 
-__version__ = "1.2.1"
+__version__ = "1.2.2"
 __author__ = "Ehsan Kahrizi (Ehsan.kahrizi@usu.edu)"
 
 # Import the 3 simple modules

{hydroanomaly-1.2.1 → hydroanomaly-1.2.2}/hydroanomaly/ml.py

@@ -6,24 +6,30 @@ from sklearn.ensemble import IsolationForest
 from sklearn.metrics import f1_score, recall_score, precision_score
 import matplotlib.pyplot as plt
 
-# ============= Helper Functions =========================================================================
-def match_nearest(row, usgs):
-    target_time = row['datetime']
-    same_day = usgs[usgs['datetime'] == target_time.datetime()]
-    if same_day.empty:
+# ============= Helper Function: Match nearest USGS turbidity by datetime ================================
+def match_nearest_datetime(sentinel_dt, usgs):
+    # usgs is indexed by 'datetime'
+    if usgs.empty:
         return np.nan
-    delta = (same_day['datetime'] - target_time).abs()
-    return same_day.loc[delta.idxmin(), 'turbidity']
+    # Find the closest datetime in usgs to sentinel_dt
+    i = usgs.index.get_indexer([sentinel_dt], method='nearest')[0]
+    return usgs.iloc[i]['Turbidity']
 
-
-
-# ============= Preprocessing and Feature Engineering ========================================================
+# ============= Preprocessing and Feature Engineering ====================================================
 def preprocess_data(sentinel, usgs):
-    # Add matched turbidity
-    sentinel['turbidity'] = sentinel.apply(lambda row: match_nearest(row, usgs), axis=1)
+    # Expect both to have DatetimeIndex named 'datetime'
+    if sentinel.index.name != 'datetime':
+        raise ValueError("Sentinel dataframe must have DatetimeIndex named 'datetime'")
+    if usgs.index.name != 'datetime':
+        raise ValueError("USGS dataframe must have DatetimeIndex named 'datetime'")
+
+    # Add matched turbidity to sentinel (by nearest datetime)
+    sentinel = sentinel.copy()
+    usgs = usgs.copy()
+    sentinel['turbidity'] = [match_nearest_datetime(dt, usgs) for dt in sentinel.index]
     df = sentinel.dropna(subset=['turbidity'])
 
-    # Water pixels filtering
+    # Water pixel filtering
     if 'SCL' in df.columns and (df['SCL'] == 6).sum() > 0:
         df = df[df['SCL'] == 6].drop_duplicates(subset=['B2', 'B3', 'B4'])
 
@@ -33,7 +39,7 @@ def preprocess_data(sentinel, usgs):
     df['NDWI'] = (df['B3'] - df['B8']) / (df['B3'] + df['B8'])
     df['NDSI'] = (df['B3'] - df['B11']) / (df['B3'] + df['B11'])
 
-    df = df.sort_values('datetime').reset_index(drop=True)
+    df = df.sort_index()
     df['turbidity_diff1'] = df['turbidity'].diff()
     df['turbidity_diff2'] = df['turbidity_diff1'].diff()
     thresh = 2 * df['turbidity_diff2'].std()
@@ -44,12 +50,11 @@ def preprocess_data(sentinel, usgs):
     df['Classe'] = (df['turbidity'] > 20).astype(int)
     return df, bands
 
-
-# ============= Anomaly Detection Methods ================================================================
+# ============= Anomaly Detection: One-Class SVM ========================================================
 def run_oneclass_svm(sentinel, usgs, plot=True):
     """
     Apply One-Class SVM anomaly detection on Sentinel/USGS data.
-    Returns: DataFrame with predictions, and best model parameters.
+    Inputs must have DatetimeIndex named 'datetime'.
     """
     df, bands = preprocess_data(sentinel, usgs)
     features = bands + ['NDVI','NDWI','NDSI','turbidity_diff1','turbidity_diff2','spike']
@@ -87,14 +92,14 @@ def run_oneclass_svm(sentinel, usgs, plot=True):
         df_out['predicted'] = best_y_pred
         if plot:
             plt.figure(figsize=(15,6))
-            plt.plot(df_out['datetime'], df_out['turbidity'], label='turbidity', color='blue')
-            plt.scatter(df_out[df_out['Classe']==1]['datetime'], df_out[df_out['Classe']==1]['turbidity'],
+            plt.plot(df_out.index, df_out['turbidity'], label='Turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1].index, df_out[df_out['Classe']==1]['turbidity'],
                         color='red', marker='x', label='True Anomaly', s=100)
-            plt.scatter(df_out[df_out['predicted']==1]['datetime'], df_out[df_out['predicted']==1]['turbidity'],
+            plt.scatter(df_out[df_out['predicted']==1].index, df_out[df_out['predicted']==1]['turbidity'],
                         edgecolors='orange', facecolors='none', marker='o', label='Predicted Anomaly', s=80)
             plt.title("True vs Predicted Anomalies (OneClassSVM)")
-            plt.xlabel("datetime")
-            plt.ylabel("turbidity")
+            plt.xlabel("Datetime")
+            plt.ylabel("Turbidity")
             plt.legend()
             plt.grid(True)
             plt.tight_layout()
@@ -104,12 +109,11 @@ def run_oneclass_svm(sentinel, usgs, plot=True):
         print("Could not find a good model. Try different hyperparameters.")
         return None, None, None
 
-
-# ============= Isolation Forest Method ================================================================
+# ============= Anomaly Detection: Isolation Forest ======================================================
 def run_isolation_forest(sentinel, usgs, plot=True):
     """
     Apply Isolation Forest anomaly detection on Sentinel/USGS data.
-    Returns: DataFrame with predictions, and best model parameters.
+    Inputs must have DatetimeIndex named 'datetime'.
     """
     df, bands = preprocess_data(sentinel, usgs)
     features = bands + ['NDVI','NDWI','NDSI','turbidity_diff1','turbidity_diff2','spike']
@@ -152,14 +156,14 @@ def run_isolation_forest(sentinel, usgs, plot=True):
         df_out['predicted'] = best_y_pred
         if plot:
             plt.figure(figsize=(15,6))
-            plt.plot(df_out['datetime'], df_out['turbidity'], label='turbidity', color='blue')
-            plt.scatter(df_out[df_out['Classe']==1]['datetime'], df_out[df_out['Classe']==1]['turbidity'],
+            plt.plot(df_out.index, df_out['turbidity'], label='Turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1].index, df_out[df_out['Classe']==1]['turbidity'],
                         color='red', marker='x', label='True Anomaly', s=100)
-            plt.scatter(df_out[df_out['predicted']==1]['datetime'], df_out[df_out['predicted']==1]['turbidity'],
+            plt.scatter(df_out[df_out['predicted']==1].index, df_out[df_out['predicted']==1]['turbidity'],
                         edgecolors='orange', facecolors='none', marker='o', label='Predicted Anomaly', s=80)
             plt.title("True vs Predicted Anomalies (Isolation Forest)")
-            plt.xlabel("datetime")
-            plt.ylabel("turbidity")
+            plt.xlabel("Datetime")
+            plt.ylabel("Turbidity")
             plt.legend()
             plt.grid(True)
             plt.tight_layout()

{hydroanomaly-1.2.1 → hydroanomaly-1.2.2}/hydroanomaly.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydroanomaly
-Version: 1.2.1
+Version: 1.2.2
 Summary: A Python package for hydro anomaly detection with simple USGS data retrieval
 Author-email: Ehsan Kahrizi <ehsan.kahrizi@usu.edu>
 License: MIT License

{hydroanomaly-1.2.1 → hydroanomaly-1.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hydroanomaly"
-version = "1.2.1"
+version = "1.2.2"
 authors = [
     {name = "Ehsan Kahrizi", email = "ehsan.kahrizi@usu.edu"},
 ]