finished water quality monitoring project

src/clean_data.py

@@ -1,7 +1,6 @@
-def clean_sensor_data(df: pd.DataFrame) -> pd.DataFrame:
-    """
-    Clean sensor data by handling missing or invalid values.
-
-    Returns:
-        pd.DataFrame: Cleaned data.
-    """
+def clean_data(df):
+    df = df.copy()
+    df = df.dropna(subset=["pH", "turbidity"])
+    df["temperature"] = df["temperature"].fillna(df["temperature"].mean())
+    df["dissolved_oxygen"] = df["dissolved_oxygen"].fillna(df["dissolved_oxygen"].mean())
+    return df

src/evaluate.py

@@ -1,9 +1,12 @@
 class WaterQualityEvaluator:
     def __init__(self, ph_range=(6.5, 8.5), turbidity_threshold=1.0):
-        self.ph_range = ph_range
+        self.ph_min, self.ph_max = ph_range
         self.turbidity_threshold = turbidity_threshold
 
-    def is_safe(self, row: pd.Series) -> bool:
-        """
-        Determine if a row of water data is safe.
-        """
+    def is_safe(self, row):
+        return self.ph_min <= row["pH"] <= self.ph_max and row["turbidity"] <= self.turbidity_threshold
+
+    def evaluate(self, df):
+        df = df.copy()
+        df["is_safe"] = df.apply(self.is_safe, axis=1)
+        return df

src/load_data.py

@@ -1,10 +1,15 @@
-def load_csv(filepath: str) -> pd.DataFrame:
-    """
-    Load sensor data from a CSV file.
+import pandas as pd
 
-    Args:
-        filepath (str): Path to the CSV file.
+def load_data(file_path):
+    try:
+        df = pd.read_csv(file_path)
+        return df
+    except FileNotFoundError:
+        print(f"File not found: {file_path}")
+        return None
 
-    Returns:
-        pd.DataFrame: Loaded data as a pandas DataFrame.
-    """
+    df = df.copy()
+    df = df.dropna(subset=["pH", "turbidity"])
+    df["temperature"] = df["temperature"].fillna(df["temperature"].mean())
+    df["dissolved_oxygen"] = df["dissolved_oxygen"].fillna(df["dissolved_oxygen"].mean())
+    return df

src/main.py

@@ -0,0 +1,20 @@
+from load_data import load_data
+from clean_data import clean_data
+from evaluate import WaterQualityEvaluator
+
+def main():
+    file_path = "C:/Users/Administrator/Desktop/water_quality_monitoring/data/sensor_data.csv"  
+    df = load_data(file_path)
+    if df is not None:
+        df = clean_data(df)
+        evaluator = WaterQualityEvaluator()
+        results = evaluator.evaluate(df)
+        results.to_csv("evaluated_results.csv", index=False)
+        print(results[['sensor_id', 'pH', 'turbidity', 'is_safe']].head(10))
+        print("✅ Results saved to evaluated_results.csv")
+    else:
+        print("❌ Failed to load the dataset.")
+
+if __name__ == "__main__":
+    main()
+