water quality project

.gitignore

@@ -1,2 +1,4 @@
 index.py
-env/
+env/
+__pycache__/
+results/

src/clean_data.py

@@ -1,7 +1,26 @@
+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.copy()
+
+    # Remove duplicate rows that may come from repeated exports.
+    cleaned = cleaned.drop_duplicates().reset_index(drop=True)
+
+    text_columns = cleaned.select_dtypes(include="object").columns
+    cleaned[text_columns] = cleaned[text_columns].apply(lambda col: col.str.strip())
+
+    # Make sure numeric columns are floats so we can compare them.
+    numeric_columns = ["pH", "turbidity", "dissolved_oxygen", "temperature"]
+    for column in numeric_columns:
+        if column in cleaned.columns:
+            cleaned[column] = pd.to_numeric(cleaned[column], errors="coerce")
+
+    return cleaned

src/evaluate.py

@@ -1,3 +1,5 @@
+import pandas as pd
+
 class WaterQualityEvaluator:
     def __init__(self, ph_range=(6.5, 8.5), turbidity_threshold=1.0):
         self.ph_range = ph_range
@@ -7,3 +9,14 @@ def is_safe(self, row: pd.Series) -> bool:
         """
         Determine if a row of water data is safe.
         """
+        ph_min, ph_max = self.ph_range
+        ph_value = row.get("pH")
+        turbidity_value = row.get("turbidity")
+
+        if pd.isna(ph_value) or pd.isna(turbidity_value):
+            return False
+        if not (ph_min <= ph_value <= ph_max):
+            return False
+        if turbidity_value > self.turbidity_threshold:
+            return False
+        return True

src/load_data.py

@@ -1,3 +1,6 @@
+import pandas as pd
+
+
 def load_csv(filepath: str) -> pd.DataFrame:
     """
     Load sensor data from a CSV file.
@@ -8,3 +11,5 @@ def load_csv(filepath: str) -> pd.DataFrame:
     Returns:
         pd.DataFrame: Loaded data as a pandas DataFrame.
     """
+
+    return pd.read_csv(filepath, parse_dates=["timestamp"])

src/main.py

@@ -0,0 +1,42 @@
+import os
+
+from clean_data import clean_sensor_data
+from evaluate import WaterQualityEvaluator
+from load_data import load_csv
+
+INPUT_PATH = "data/sensor_data.csv"
+OUTPUT_PATH = "results/results.csv"
+ROWS_TO_SHOW = 5
+
+
+def main() -> None:
+    data = load_csv(INPUT_PATH)
+    cleaned = clean_sensor_data(data)
+
+    evaluator = WaterQualityEvaluator()
+    evaluated = evaluator.evaluate(cleaned)
+
+    os.makedirs(os.path.dirname(OUTPUT_PATH), exist_ok=True)
+    evaluated.to_csv(OUTPUT_PATH, index=False)
+
+    rows_to_show = evaluated.head(ROWS_TO_SHOW)
+    for _, row in rows_to_show.iterrows():
+        sensor = row.get("sensor_id", "Unknown sensor")
+        timestamp = row.get("timestamp", "Unknown time")
+        status = "✅ Safe" if row.get("is_safe") else "❌ Unsafe"
+        if status.startswith("❌") and row.get("issues"):
+            status = f"{status} ({row['issues']})"
+        print(f"Sensor {sensor} at {timestamp}: {status}")
+
+    total = len(evaluated)
+    safe = int(evaluated["is_safe"].sum())
+    unsafe = total - safe
+    print("\nSummary:")
+    print(f"  Total readings analysed: {total}")
+    print(f"  Safe readings:   {safe}")
+    print(f"  Unsafe readings: {unsafe}")
+    print(f"\nResults saved to {OUTPUT_PATH}")
+
+
+if __name__ == "__main__":
+    main()