hydroanomaly 0.7.3__py3-none-any.whl → 1.2.0__py3-none-any.whl

hydroanomaly/__init__.py

@@ -5,17 +5,20 @@ A simple Python package with just 3 modules:
 1. USGS turbidity data retrieval (returns data and site coordinates)
 2. Sentinel satellite bands retrieval  
 3. Time series visualization
+4. Machine learning anomaly detection (One-Class SVM and Isolation Forest)
 
 That's it - nothing else!
 """
 
-__version__ = "0.7.3"
+__version__ = "1.2.0"
 __author__ = "Ehsan Kahrizi (Ehsan.kahrizi@usu.edu)"
 
 # Import the 3 simple modules
 from .usgs_turbidity import get_turbidity, get_usgs_turbidity
-from .sentinel_bands import get_sentinel_bands, get_satellite_data, get_sentinel, get_sentinel_bands_gee
+from .sentinel_bands import get_sentinel_bands, get_satellite_data, get_sentinel, get_sentinel_bands_gee, show_sentinel_ndwi_map
 from .visualize import plot_timeseries, plot_turbidity, plot_sentinel, plot_comparison, plot, visualize
+from .ml import run_oneclass_svm, run_isolation_forest
+
 
 # Export everything
 __all__ = [
@@ -28,7 +31,7 @@ __all__ = [
     'get_sentinel_bands',
     'get_satellite_data', 
     'get_sentinel',
-
+    'show_sentinel_ndwi_map',
 
     # Visualization functions
     'plot_timeseries',
@@ -36,7 +39,11 @@ __all__ = [
     'plot_sentinel', 
     'plot_comparison',
     'plot',
-    'visualize'
+    'visualize',
+    
+    # Machine learning functions
+    'run_oneclass_svm',
+    'run_isolation_forest'  
 ]
 
 print(f"HydroAnomaly v{__version__} - Simple Water Data Package")

hydroanomaly/ml.py

@@ -0,0 +1,170 @@
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+from sklearn.svm import OneClassSVM
+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['date']
+    same_day = usgs[usgs['date'] == target_time.date()]
+    if same_day.empty:
+        return np.nan
+    delta = (same_day['datetime'] - target_time).abs()
+    return same_day.loc[delta.idxmin(), 'Turbidity']
+
+
+
+# ============= Preprocessing and Feature Engineering ========================================================
+def preprocess_data(sentinel, usgs):
+    # Add matched turbidity
+    sentinel['Turbidity'] = sentinel.apply(lambda row: match_nearest(row, usgs), axis=1)
+    df = sentinel.dropna(subset=['Turbidity'])
+
+    # Water pixels filtering
+    if 'SCL' in df.columns and (df['SCL'] == 6).sum() > 0:
+        df = df[df['SCL'] == 6].drop_duplicates(subset=['B2', 'B3', 'B4'])
+
+    # Feature engineering
+    bands = ['B2','B3','B4','B5','B6','B7','B8','B8A','B9','B11','B12']
+    df['NDVI'] = (df['B8'] - df['B4']) / (df['B8'] + df['B4'])
+    df['NDWI'] = (df['B3'] - df['B8']) / (df['B3'] + df['B8'])
+    df['NDSI'] = (df['B3'] - df['B11']) / (df['B3'] + df['B11'])
+
+    df = df.sort_values('date').reset_index(drop=True)
+    df['Turbidity_diff1'] = df['Turbidity'].diff()
+    df['Turbidity_diff2'] = df['Turbidity_diff1'].diff()
+    thresh = 2 * df['Turbidity_diff2'].std()
+    df['spike'] = (df['Turbidity_diff2'].abs() > thresh).astype(int)
+    df = df.dropna()
+
+    # Class label
+    df['Classe'] = (df['Turbidity'] > 20).astype(int)
+    return df, bands
+
+
+# ============= Anomaly Detection Methods ================================================================
+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.
+    """
+    df, bands = preprocess_data(sentinel, usgs)
+    features = bands + ['NDVI','NDWI','NDSI','Turbidity_diff1','Turbidity_diff2','spike']
+    X = df[features].fillna(df[features].mean()).values
+    y = df['Classe'].values
+
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
+
+    X_class0 = X_scaled[y == 0]
+    X_class1 = X_scaled[y == 1]
+
+    train_size = max(1, int(0.8 * len(X_class0)))
+    X_train = X_class0[:train_size]
+    X_test = np.vstack([X_class0[train_size:], X_class1])
+    y_test = np.array([0]*(len(X_class0)-train_size) + [1]*len(X_class1))
+
+    best_f1 = -1
+    best_model, best_y_pred, best_params = None, None, None
+    for gamma in ['auto', 'scale']:
+        for nu in [0.01, 0.05, 0.1, 0.2]:
+            model = OneClassSVM(kernel='rbf', gamma=gamma, nu=nu)
+            model.fit(X_train)
+            y_pred = np.where(model.predict(X_test) == 1, 0, 1)
+            if len(np.unique(y_pred)) > 1:
+                f1 = f1_score(y_test, y_pred)
+                if f1 > best_f1:
+                    best_f1 = f1
+                    best_model = model
+                    best_y_pred = y_pred
+                    best_params = {'gamma': gamma, 'nu': nu}
+
+    if best_f1 > -1:
+        df_out = df.iloc[-len(y_test):].copy()
+        df_out['predicted'] = best_y_pred
+        if plot:
+            plt.figure(figsize=(15,6))
+            plt.plot(df_out['date'], df_out['Turbidity'], label='Turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1]['date'], df_out[df_out['Classe']==1]['Turbidity'],
+                        color='red', marker='x', label='True Anomaly', s=100)
+            plt.scatter(df_out[df_out['predicted']==1]['date'], 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("Date")
+            plt.ylabel("Turbidity")
+            plt.legend()
+            plt.grid(True)
+            plt.tight_layout()
+            plt.show()
+        return df_out, best_params, best_f1
+    else:
+        print("Could not find a good model. Try different hyperparameters.")
+        return None, None, None
+
+
+# ============= Isolation Forest Method ================================================================
+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.
+    """
+    df, bands = preprocess_data(sentinel, usgs)
+    features = bands + ['NDVI','NDWI','NDSI','Turbidity_diff1','Turbidity_diff2','spike']
+    X = df[features].fillna(df[features].mean()).values
+    y = df['Classe'].values
+
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
+
+    X_class0 = X_scaled[y == 0]
+    X_class1 = X_scaled[y == 1]
+
+    train_size = max(1, int(0.8 * len(X_class0)))
+    X_train = X_class0[:train_size]
+    X_test = np.vstack([X_class0[train_size:], X_class1])
+    y_test = np.array([0]*(len(X_class0)-train_size) + [1]*len(X_class1))
+
+    best_f1 = -1
+    best_model, best_y_pred, best_params = None, None, None
+    for contamination in [0.01, 0.05, 0.1, 0.15, 0.2, 0.3]:
+        model = IsolationForest(
+            n_estimators=100,
+            contamination=contamination,
+            max_samples='auto',
+            bootstrap=True,
+            random_state=42
+        )
+        model.fit(X_train)
+        y_pred = np.where(model.predict(X_test) == 1, 0, 1)
+        if len(np.unique(y_pred)) > 1:
+            f1 = f1_score(y_test, y_pred)
+            if f1 > best_f1:
+                best_f1 = f1
+                best_model = model
+                best_y_pred = y_pred
+                best_params = {'contamination': contamination}
+
+    if best_f1 > -1:
+        df_out = df.iloc[-len(y_test):].copy()
+        df_out['predicted'] = best_y_pred
+        if plot:
+            plt.figure(figsize=(15,6))
+            plt.plot(df_out['date'], df_out['Turbidity'], label='Turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1]['date'], df_out[df_out['Classe']==1]['Turbidity'],
+                        color='red', marker='x', label='True Anomaly', s=100)
+            plt.scatter(df_out[df_out['predicted']==1]['date'], 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("Date")
+            plt.ylabel("Turbidity")
+            plt.legend()
+            plt.grid(True)
+            plt.tight_layout()
+            plt.show()
+        return df_out, best_params, best_f1
+    else:
+        print("Could not find a good model. Try different hyperparameters.")
+        return None, None, None

hydroanomaly/sentinel_bands.py

@@ -4,13 +4,15 @@ Sentinel-2 Satellite Data Retrieval using Google Earth Engine (GEE)
 This module provides a function to retrieve Sentinel-2 satellite band data
 for a specified location and time period, with masking and cloud filtering.
 """
-import ee 
+import ee
+import geemap 
 import pandas as pd
 import numpy as np
 from datetime import datetime, timedelta
 import requests
 import warnings
 
+# Retrive data from Google Earth Engine ========================================================
 def get_sentinel_bands_gee(
     latitude: float,
     longitude: float,
@@ -98,6 +100,54 @@ def get_sentinel_bands_gee(
         df = df.set_index('date')
     return df
 
+
+# Showing map with NDWI (Normalized Difference Water Index) ========================================================
+def show_sentinel_ndwi_map(
+    latitude: float,
+    longitude: float,
+    start_date: str,
+    end_date: str,
+    buffer_meters: int = 20,
+    cloudy_pixel_percentage: int = 20,
+    zoom: int = 15
+):
+    """
+    Display an interactive map showing the NDWI, point, and buffer.
+
+    Args:
+        latitude (float): Latitude of the center point.
+        longitude (float): Longitude of the center point.
+        start_date (str): Start date as "YYYY-MM-DD".
+        end_date (str): End date as "YYYY-MM-DD".
+        buffer_meters (int): Buffer radius in meters.
+        cloudy_pixel_percentage (int): Max allowed cloud percentage.
+        zoom (int): Zoom level for map.
+    """
+    point = ee.Geometry.Point([longitude, latitude])
+    buffer = point.buffer(buffer_meters)
+
+    image = (ee.ImageCollection("COPERNICUS/S2_SR_HARMONIZED")
+             .filterBounds(buffer)
+             .filterDate(start_date, end_date)
+             .filter(ee.Filter.lt("CLOUDY_PIXEL_PERCENTAGE", cloudy_pixel_percentage))
+             .median())
+
+    ndwi = image.normalizedDifference(["B3", "B8"]).rename("NDWI")
+
+    ndwi_vis = {
+        'min': 0,
+        'max': 1,
+        'palette': ['white', 'cyan', 'blue']}
+
+    Map = geemap.Map()
+    Map.centerObject(buffer, zoom=zoom)
+    Map.addLayer(ndwi, ndwi_vis, "NDWI (Water)")
+    Map.addLayer(point, {'color': 'yellow'}, 'Point')
+    Map.addLayer(buffer, {'color': 'red'}, 'Buffer')
+    Map.add_colorbar(ndwi_vis, label="NDWI", layer_name="NDWI (Water)")
+    return Map
+
+
 # Aliases for user convenience
 get_sentinel_bands = get_sentinel_bands_gee
 get_satellite_data = get_sentinel_bands_gee

hydroanomaly/visualize.py

@@ -11,7 +11,7 @@ import pandas as pd
 import numpy as np
 from datetime import datetime
 
-
+# ==============================================================================================
 def plot_timeseries(data: pd.DataFrame, title: str = "Time Series Data", save_file: str = None) -> None:
     """
     Create a simple time series plot.
@@ -26,10 +26,10 @@ def plot_timeseries(data: pd.DataFrame, title: str = "Time Series Data", save_fi
     """
     
     if data.empty:
-        print("❌ No data to plot")
+        print("No data to plot")
         return
     
-    print(f"📊 Creating plot: {title}")
+    print(f"Creating plot: {title}")
     
     # Create figure
     plt.figure(figsize=(12, 6))
@@ -59,12 +59,12 @@ def plot_timeseries(data: pd.DataFrame, title: str = "Time Series Data", save_fi
     # Save if requested
     if save_file:
         plt.savefig(save_file, dpi=300, bbox_inches='tight')
-        print(f"💾 Plot saved as {save_file}")
+        print(f"Plot saved as {save_file}")
     
     plt.show()
-    print("✅ Plot created successfully!")
-
+    print("Plot created successfully!")
 
+# ==============================================================================================
 def plot_turbidity(turbidity_data: pd.DataFrame, save_file: str = None) -> None:
     """
     Create a turbidity-specific plot with appropriate formatting.
@@ -75,10 +75,10 @@ def plot_turbidity(turbidity_data: pd.DataFrame, save_file: str = None) -> None:
     """
     
     if turbidity_data.empty:
-        print("❌ No turbidity data to plot")
+        print("No turbidity data to plot")
         return
     
-    print("🌫️  Creating turbidity plot")
+    print("Creating turbidity plot")
     
     plt.figure(figsize=(12, 6))
     
@@ -92,7 +92,7 @@ def plot_turbidity(turbidity_data: pd.DataFrame, save_file: str = None) -> None:
     plt.axhline(y=25, color='red', linestyle='--', alpha=0.7, label='High (25 NTU)')
     
     # Format plot
-    plt.title('💧 Turbidity Time Series', fontsize=14, fontweight='bold', pad=20)
+    plt.title('Turbidity Time Series', fontsize=14, fontweight='bold', pad=20)
     plt.xlabel('Date', fontsize=12)
     plt.ylabel('Turbidity (NTU)', fontsize=12)
     plt.grid(True, alpha=0.3)
@@ -107,12 +107,12 @@ def plot_turbidity(turbidity_data: pd.DataFrame, save_file: str = None) -> None:
     # Save if requested
     if save_file:
         plt.savefig(save_file, dpi=300, bbox_inches='tight')
-        print(f"💾 Turbidity plot saved as {save_file}")
+        print(f"Turbidity plot saved as {save_file}")
     
     plt.show()
-    print("✅ Turbidity plot created!")
-
+    print("Turbidity plot created!")
 
+# ==============================================================================================
 def plot_sentinel(sentinel_data: pd.DataFrame, save_file: str = None) -> None:
     """
     Create a Sentinel satellite data plot.
@@ -123,10 +123,10 @@ def plot_sentinel(sentinel_data: pd.DataFrame, save_file: str = None) -> None:
     """
     
     if sentinel_data.empty:
-        print("❌ No Sentinel data to plot")
+        print("No Sentinel data to plot")
         return
     
-    print("🛰️  Creating Sentinel bands plot")
+    print("Creating Sentinel bands plot")
     
     plt.figure(figsize=(12, 8))
     
@@ -146,7 +146,7 @@ def plot_sentinel(sentinel_data: pd.DataFrame, save_file: str = None) -> None:
                 label=column, color=color, linewidth=2, marker='o', markersize=4)
     
     # Format plot
-    plt.title('🛰️ Sentinel Satellite Data', fontsize=14, fontweight='bold', pad=20)
+    plt.title('Sentinel Satellite Data', fontsize=14, fontweight='bold', pad=20)
     plt.xlabel('Date', fontsize=12)
     plt.ylabel('Digital Number / Index Value', fontsize=12)
     plt.grid(True, alpha=0.3)
@@ -161,12 +161,12 @@ def plot_sentinel(sentinel_data: pd.DataFrame, save_file: str = None) -> None:
     # Save if requested
     if save_file:
         plt.savefig(save_file, dpi=300, bbox_inches='tight')
-        print(f"💾 Sentinel plot saved as {save_file}")
+        print(f"Sentinel plot saved as {save_file}")
     
     plt.show()
-    print("✅ Sentinel plot created!")
-
+    print("Sentinel plot created!")
 
+# ==============================================================================================
 def plot_comparison(data1: pd.DataFrame, data2: pd.DataFrame, 
                    label1: str = "Dataset 1", label2: str = "Dataset 2",
                    title: str = "Data Comparison", save_file: str = None) -> None:
@@ -183,10 +183,10 @@ def plot_comparison(data1: pd.DataFrame, data2: pd.DataFrame,
     """
     
     if data1.empty and data2.empty:
-        print("❌ No data to plot")
+        print("No data to plot")
         return
     
-    print(f"📊 Creating comparison plot: {title}")
+    print(f"Creating comparison plot: {title}")
     
     fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10), sharex=True)
     
@@ -215,10 +215,10 @@ def plot_comparison(data1: pd.DataFrame, data2: pd.DataFrame,
     # Save if requested
     if save_file:
         plt.savefig(save_file, dpi=300, bbox_inches='tight')
-        print(f"💾 Comparison plot saved as {save_file}")
+        print(f"Comparison plot saved as {save_file}")
     
     plt.show()
-    print("✅ Comparison plot created!")
+    print("Comparison plot created!")
 
 
 # Simple aliases

{hydroanomaly-0.7.3.dist-info → hydroanomaly-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydroanomaly
-Version: 0.7.3
+Version: 1.2.0
 Summary: A Python package for hydro anomaly detection with simple USGS data retrieval
 Author-email: Ehsan Kahrizi <ehsan.kahrizi@usu.edu>
 License: MIT License
@@ -28,7 +28,7 @@ License: MIT License
 Project-URL: Homepage, https://github.com/yourusername/hydroanomaly
 Project-URL: Bug Reports, https://github.com/yourusername/hydroanomaly/issues
 Project-URL: Source, https://github.com/yourusername/hydroanomaly
-Keywords: python,package,hydro,anomaly,detection
+Keywords: python,package,hydrology,anomaly detection,remote sensing
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6

hydroanomaly-1.2.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+hydroanomaly/__init__.py,sha256=IGPsOv-xfQGQpr_HxhrcZXjvVVkAfMBxh97e6S8Rfac,1664
+hydroanomaly/ml.py,sha256=vqfnmGijjxGgtqJ2rzOmnMMrrVAVlYOPe1AnuX4EuG4,7018
+hydroanomaly/sentinel_bands.py,sha256=Y6RAunVJDYLs13WemSSQNEu07GqmhR64fC2mLPxwh2k,5371
+hydroanomaly/usgs_turbidity.py,sha256=k0cXRXpTe1YgjfR0Htw77SLD8hM--43jiEiJwx1vRg0,5664
+hydroanomaly/visualize.py,sha256=d_Ou1sTr648TdAW-94NXwNbLPL4rvYVYb5pw4Xux3aE,7228
+hydroanomaly-1.2.0.dist-info/licenses/LICENSE,sha256=OphKV48tcMv6ep-7j-8T6nycykPT0g8ZlMJ9zbGvdPs,1066
+hydroanomaly-1.2.0.dist-info/METADATA,sha256=bh51WnUxEbk3azZY2IN9a9Io1Pav7knU90qMiiiTGDU,12981
+hydroanomaly-1.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hydroanomaly-1.2.0.dist-info/top_level.txt,sha256=t-5Lc-eTLlkxIhR_N1Cpp6_YZafKS3xLLk9D2CtbE7o,13
+hydroanomaly-1.2.0.dist-info/RECORD,,

hydroanomaly-0.7.3.dist-info/RECORD

@@ -1,9 +0,0 @@
-hydroanomaly/__init__.py,sha256=blfdU8RYTU_JTMgD_OUEx6YNEZW_Xi6Nn6vqgOdgbt8,1388
-hydroanomaly/sentinel_bands.py,sha256=LL_ChqpN6d_aJ0nq0YPWkL_vp9ns5bkSRp0UcKYe3o8,3637
-hydroanomaly/usgs_turbidity.py,sha256=k0cXRXpTe1YgjfR0Htw77SLD8hM--43jiEiJwx1vRg0,5664
-hydroanomaly/visualize.py,sha256=gkLgI3agx291jK5o08nYEbEpGpr6cD-6aAKn2Ha2Lqk,6937
-hydroanomaly-0.7.3.dist-info/licenses/LICENSE,sha256=OphKV48tcMv6ep-7j-8T6nycykPT0g8ZlMJ9zbGvdPs,1066
-hydroanomaly-0.7.3.dist-info/METADATA,sha256=yRZiu7Pea2bWa42QUcfkxTTtgBRRD2AOAPLsThwqXSw,12962
-hydroanomaly-0.7.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hydroanomaly-0.7.3.dist-info/top_level.txt,sha256=t-5Lc-eTLlkxIhR_N1Cpp6_YZafKS3xLLk9D2CtbE7o,13
-hydroanomaly-0.7.3.dist-info/RECORD,,