Completed the month 3 exam project

src/clean_data.py

@@ -1,7 +1,19 @@
+import pandas as pd
 def clean_sensor_data(df: pd.DataFrame) -> pd.DataFrame:
     """
     Clean sensor data by handling missing or invalid values.
-
+    
     Returns:
         pd.DataFrame: Cleaned data.
     """
+    cleaned_df = df.copy()
+
+    #Handle missing values - replace with None
+    cleaned_df = cleaned_df.replace(['', 'NULL', 'null', 'NAN'], None)
+
+    #Convert numeric columns
+    numeric_columns = ['pH', 'turbidity', 'temperature', 'dissolved_oxygen']
+    for col in numeric_columns:
+        cleaned_df[col] = pd.to_numeric(cleaned_df[col], errors='coerce')
+
+    return cleaned_df

src/evaluate.py

@@ -1,9 +1,43 @@
+import pandas as pd
 class WaterQualityEvaluator:
     def __init__(self, ph_range=(6.5, 8.5), turbidity_threshold=1.0):
         self.ph_range = ph_range
         self.turbidity_threshold = turbidity_threshold
 
-    def is_safe(self, row: pd.Series) -> bool:
+    def is_safe(self, row: pd.Series, location_name) -> bool:
         """
         Determine if a row of water data is safe.
         """
+        sensor_id = row['sensor_id']
+        ph = row['pH']
+        turbidity = row['turbidity']
+
+        #check for missing values
+        if pd.isna(ph):
+            return f"Sensor {sensor_id} at {location_name}: ❌ Unsafe (missing pH)"
+        if pd.isna(turbidity):
+            return f"Sensor {sensor_id} at {location_name}: ❌ Unsafe (missing turbidity)"
+
+        #check ph range
+        min_ph, max_ph = self.ph_range
+        if ph < min_ph:
+            return f"Sensor {sensor_id} at {location_name}: ❌ Unsafe (pH too low)"
+        elif ph > max_ph:
+            return f"Sensor {sensor_id} at {location_name}: ❌ Unsafe (pH too high)"
+
+        # Check turbidity
+        if turbidity > self.turbidity_threshold:
+            return f"Sensor {sensor_id} at {location_name}: ❌ Unsafe (turbidity too high)"
+
+        # If all checks pass
+        return f"Sensor {sensor_id} at {location_name}: ✅ Safe"
+
+    def evaluate_dataframe(self, df, location_name):
+        """
+        Evaluate all rows in the dataframe
+        """
+        results = []
+        for index, row in df.iterrows():
+            result = self.is_safe(row, location_name)
+            results.append(result)
+        return results

src/load_data.py

@@ -1,3 +1,4 @@
+import pandas as pd
 def load_csv(filepath: str) -> pd.DataFrame:
     """
     Load sensor data from a CSV file.
@@ -8,3 +9,5 @@ def load_csv(filepath: str) -> pd.DataFrame:
     Returns:
         pd.DataFrame: Loaded data as a pandas DataFrame.
     """
+    df = pd.read_csv(filepath)
+    return df

src/main.py

@@ -0,0 +1,50 @@
+import pandas as pd
+from load_data import load_csv
+from clean_data import clean_sensor_data
+from evaluate import WaterQualityEvaluator
+
+def main():
+    # Get input from user
+    file_path = input("Enter the path to your CSV file: ")
+    location_name = input("Enter the location name (e.g., Lake A): ")
+
+    # Load data
+    print("Loading data...")
+    df = load_csv(file_path)
+
+    if df is None:
+        print("Failed to load data. Exiting.")
+        return
+
+    print(f"Loaded {len(df)} rows of data")
+
+    # Clean data
+    print("Cleaning data...")
+    cleaned_df = clean_sensor_data(df)
+
+    # Evaluate data
+    print("Evaluating water safety...")
+    evaluator = WaterQualityEvaluator()
+    results = evaluator.evaluate_dataframe(cleaned_df, location_name)
+
+    # Print results
+    print("\n--- Water Safety Results ---")
+    for result in results:
+        print(result)
+
+    # Bonus: Count safe vs unsafe
+    safe_count = sum(1 for result in results if "✅ Safe" in result)
+    unsafe_count = len(results) - safe_count
+
+    print(f"\nSummary: {safe_count} safe, {unsafe_count} unsafe")
+
+    # Bonus: Save to CSV
+    results_df = pd.DataFrame({
+        'sensor_id': cleaned_df['sensor_id'],
+        'result': [r.split(': ')[1] for r in results]
+    })
+    results_df.to_csv('results.csv', index=False)
+    print("Results saved to results.csv")
+
+
+main()