Water_quality_control

src/clean_data.py

@@ -1,7 +1,23 @@
+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.
     """
+#handle missing values
+numeric_cols =['PH','turbidity','dissolved_oxygen','temperature']
+cleaned_df[numeric_cols] = cleaned_df[numeric_cols].fillna(cleaned_df[numeric_cols].mean())
+
+# Remove impossible values
+cleaned_df = cleaned_df[
+    (cleaned_df['pH'] > 0) & 
+    (cleaned_df['pH'] < 14) & 
+    (cleaned_df['turbidity'] >= 0) &
+    (cleaned_df['dissolved_oxygen'] >= 0) &
+    (cleaned_df['temperature'].between(-20, 60))]
+
+# Remove duplicates
+cleaned_df = cleaned_df.drop_duplicates()
+return cleaned_df

src/evaluate.py

@@ -1,3 +1,4 @@
+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 +8,6 @@ def is_safe(self, row: pd.Series) -> bool:
         """
         Determine if a row of water data is safe.
         """
+ph_ok = self.ph_range[0] <= row['pH'] <= self.ph_range[1]
+turbidity_ok = row['turbidity'] <= self.turbidity_threshold
+return ph_ok and turbidity_ok

src/load_data.py

@@ -1,10 +1,23 @@
-def load_csv(filepath: str) -> pd.DataFrame:
-    """
-    Load sensor data from a CSV file.
+import pandas as pd
+import csv
 
+def load_csv(filepath: str = 'data/sensor_data.csv') -> pd.DataFrame:
+    """
+    Load water quality sensor data from a CSV file.
+
     Args:
-        filepath (str): Path to the CSV file.
-
+        filepath: Path to the CSV file (default: 'data/sensor_data.csv')
+        
     Returns:
-        pd.DataFrame: Loaded data as a pandas DataFrame.
+        pd.DataFrame: Loaded sensor data or empty DataFrame if loading fails
     """
+    try:
+        df = pd.read_csv(filepath)
+        print(f"Successfully loaded data from {filepath}")
+        return df
+    except FileNotFoundError:
+        print(f"Error: File not found at {filepath}")
+        return pd.DataFrame()
+    except Exception as e:
+        print(f"Error loading data: {str(e)}")
+        return pd.DataFrame()

venv/Lib/site-packages/_distutils_hack/__init__.py

@@ -0,0 +1,128 @@
+import sys
+import os
+import re
+import importlib
+import warnings
+
+
+is_pypy = '__pypy__' in sys.builtin_module_names
+
+
+warnings.filterwarnings('ignore',
+                        r'.+ distutils\b.+ deprecated',
+                        DeprecationWarning)
+
+
+def warn_distutils_present():
+    if 'distutils' not in sys.modules:
+        return
+    if is_pypy and sys.version_info < (3, 7):
+        # PyPy for 3.6 unconditionally imports distutils, so bypass the warning
+        # https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
+        return
+    warnings.warn(
+        "Distutils was imported before Setuptools, but importing Setuptools "
+        "also replaces the `distutils` module in `sys.modules`. This may lead "
+        "to undesirable behaviors or errors. To avoid these issues, avoid "
+        "using distutils directly, ensure that setuptools is installed in the "
+        "traditional way (e.g. not an editable install), and/or make sure "
+        "that setuptools is always imported before distutils.")
+
+
+def clear_distutils():
+    if 'distutils' not in sys.modules:
+        return
+    warnings.warn("Setuptools is replacing distutils.")
+    mods = [name for name in sys.modules if re.match(r'distutils\b', name)]
+    for name in mods:
+        del sys.modules[name]
+
+
+def enabled():
+    """
+    Allow selection of distutils by environment variable.
+    """
+    which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'stdlib')
+    return which == 'local'
+
+
+def ensure_local_distutils():
+    clear_distutils()
+    distutils = importlib.import_module('setuptools._distutils')
+    distutils.__name__ = 'distutils'
+    sys.modules['distutils'] = distutils
+
+    # sanity check that submodules load as expected
+    core = importlib.import_module('distutils.core')
+    assert '_distutils' in core.__file__, core.__file__
+
+
+def do_override():
+    """
+    Ensure that the local copy of distutils is preferred over stdlib.
+
+    See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
+    for more motivation.
+    """
+    if enabled():
+        warn_distutils_present()
+        ensure_local_distutils()
+
+
+class DistutilsMetaFinder:
+    def find_spec(self, fullname, path, target=None):
+        if path is not None:
+            return
+
+        method_name = 'spec_for_{fullname}'.format(**locals())
+        method = getattr(self, method_name, lambda: None)
+        return method()
+
+    def spec_for_distutils(self):
+        import importlib.abc
+        import importlib.util
+
+        class DistutilsLoader(importlib.abc.Loader):
+
+            def create_module(self, spec):
+                return importlib.import_module('setuptools._distutils')
+
+            def exec_module(self, module):
+                pass
+
+        return importlib.util.spec_from_loader('distutils', DistutilsLoader())
+
+    def spec_for_pip(self):
+        """
+        Ensure stdlib distutils when running under pip.
+        See pypa/pip#8761 for rationale.
+        """
+        if self.pip_imported_during_build():
+            return
+        clear_distutils()
+        self.spec_for_distutils = lambda: None
+
+    @staticmethod
+    def pip_imported_during_build():
+        """
+        Detect if pip is being imported in a build script. Ref #2355.
+        """
+        import traceback
+        return any(
+            frame.f_globals['__file__'].endswith('setup.py')
+            for frame, line in traceback.walk_stack(None)
+        )
+
+
+DISTUTILS_FINDER = DistutilsMetaFinder()
+
+
+def add_shim():
+    sys.meta_path.insert(0, DISTUTILS_FINDER)
+
+
+def remove_shim():
+    try:
+        sys.meta_path.remove(DISTUTILS_FINDER)
+    except ValueError:
+        pass

venv/Lib/site-packages/_distutils_hack/override.py

@@ -0,0 +1 @@
+__import__('_distutils_hack').do_override()

venv/Lib/site-packages/dateutil/__init__.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+import sys
+
+try:
+    from ._version import version as __version__
+except ImportError:
+    __version__ = 'unknown'
+
+__all__ = ['easter', 'parser', 'relativedelta', 'rrule', 'tz',
+           'utils', 'zoneinfo']
+
+def __getattr__(name):
+    import importlib
+
+    if name in __all__:
+        return importlib.import_module("." + name, __name__)
+    raise AttributeError(
+        "module {!r} has not attribute {!r}".format(__name__, name)
+    )
+
+
+def __dir__():
+    # __dir__ should include all the lazy-importable modules as well.
+    return [x for x in globals() if x not in sys.modules] + __all__

venv/Lib/site-packages/dateutil/_common.py

@@ -0,0 +1,43 @@
+"""
+Common code used in multiple modules.
+"""
+
+
+class weekday(object):
+    __slots__ = ["weekday", "n"]
+
+    def __init__(self, weekday, n=None):
+        self.weekday = weekday
+        self.n = n
+
+    def __call__(self, n):
+        if n == self.n:
+            return self
+        else:
+            return self.__class__(self.weekday, n)
+
+    def __eq__(self, other):
+        try:
+            if self.weekday != other.weekday or self.n != other.n:
+                return False
+        except AttributeError:
+            return False
+        return True
+
+    def __hash__(self):
+        return hash((
+          self.weekday,
+          self.n,
+        ))
+
+    def __ne__(self, other):
+        return not (self == other)
+
+    def __repr__(self):
+        s = ("MO", "TU", "WE", "TH", "FR", "SA", "SU")[self.weekday]
+        if not self.n:
+            return s
+        else:
+            return "%s(%+d)" % (s, self.n)
+
+# vim:ts=4:sw=4:et

venv/Lib/site-packages/dateutil/_version.py

@@ -0,0 +1,4 @@
+# file generated by setuptools_scm
+# don't change, don't track in version control
+__version__ = version = '2.9.0.post0'
+__version_tuple__ = version_tuple = (2, 9, 0)

venv/Lib/site-packages/dateutil/easter.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+"""
+This module offers a generic Easter computing method for any given year, using
+Western, Orthodox or Julian algorithms.
+"""
+
+import datetime
+
+__all__ = ["easter", "EASTER_JULIAN", "EASTER_ORTHODOX", "EASTER_WESTERN"]
+
+EASTER_JULIAN = 1
+EASTER_ORTHODOX = 2
+EASTER_WESTERN = 3
+
+
+def easter(year, method=EASTER_WESTERN):
+    """
+    This method was ported from the work done by GM Arts,
+    on top of the algorithm by Claus Tondering, which was
+    based in part on the algorithm of Ouding (1940), as
+    quoted in "Explanatory Supplement to the Astronomical
+    Almanac", P.  Kenneth Seidelmann, editor.
+
+    This algorithm implements three different Easter
+    calculation methods:
+
+    1. Original calculation in Julian calendar, valid in
+       dates after 326 AD
+    2. Original method, with date converted to Gregorian
+       calendar, valid in years 1583 to 4099
+    3. Revised method, in Gregorian calendar, valid in
+       years 1583 to 4099 as well
+
+    These methods are represented by the constants:
+
+    * ``EASTER_JULIAN   = 1``
+    * ``EASTER_ORTHODOX = 2``
+    * ``EASTER_WESTERN  = 3``
+
+    The default method is method 3.
+
+    More about the algorithm may be found at:
+
+    `GM Arts: Easter Algorithms <http://www.gmarts.org/index.php?go=415>`_
+
+    and
+
+    `The Calendar FAQ: Easter <https://www.tondering.dk/claus/cal/easter.php>`_
+
+    """
+
+    if not (1 <= method <= 3):
+        raise ValueError("invalid method")
+
+    # g - Golden year - 1
+    # c - Century
+    # h - (23 - Epact) mod 30
+    # i - Number of days from March 21 to Paschal Full Moon
+    # j - Weekday for PFM (0=Sunday, etc)
+    # p - Number of days from March 21 to Sunday on or before PFM
+    #     (-6 to 28 methods 1 & 3, to 56 for method 2)
+    # e - Extra days to add for method 2 (converting Julian
+    #     date to Gregorian date)
+
+    y = year
+    g = y % 19
+    e = 0
+    if method < 3:
+        # Old method
+        i = (19*g + 15) % 30
+        j = (y + y//4 + i) % 7
+        if method == 2:
+            # Extra dates to convert Julian to Gregorian date
+            e = 10
+            if y > 1600:
+                e = e + y//100 - 16 - (y//100 - 16)//4
+    else:
+        # New method
+        c = y//100
+        h = (c - c//4 - (8*c + 13)//25 + 19*g + 15) % 30
+        i = h - (h//28)*(1 - (h//28)*(29//(h + 1))*((21 - g)//11))
+        j = (y + y//4 + i + 2 - c + c//4) % 7
+
+    # p can be from -6 to 56 corresponding to dates 22 March to 23 May
+    # (later dates apply to method 2, although 23 May never actually occurs)
+    p = i - j + e
+    d = 1 + (p + 27 + (p + 6)//40) % 31
+    m = 3 + (p + 26)//30
+    return datetime.date(int(y), int(m), int(d))