Merge pull request #404 from jnsebgosselin/refactor_wldataset

PR: Rename WLDataFrame to WLDataset and WLDataset to WLDataFrame

gwhat/brf_mod/tests/test_brf_mod.py

@@ -20,7 +20,7 @@
 from gwhat.brf_mod.kgs_gui import (
     BRFManager, KGSBRFInstaller, QMessageBox, QFileDialog)
 from gwhat.projet.reader_projet import ProjetReader
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.config.main import CONF
 
 
@@ -40,7 +40,7 @@ def wldataset(project):
     # Create a wldset object from a file.
     rootpath = osp.dirname(osp.realpath(__file__))
     filepath = osp.join(rootpath, 'data', 'sample_water_level_datafile.csv')
-    wldset = WLDataFrame(filepath)
+    wldset = WLDataset(filepath)
 
     # Add the wldset to the project.
     project.add_wldset('test_brf_wldset', wldset)

gwhat/projet/manager_data.py

@@ -29,7 +29,7 @@
 from gwhat.utils import icons
 import gwhat.common.widgets as myqt
 from gwhat.common.utils import calc_dist_from_coord
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.projet.reader_projet import INVALID_CHARS, is_dsetname_valid
 from gwhat.meteo.weather_reader import WXDataFrame
 from gwhat.widgets.buttons import ToolBarWidget
@@ -707,7 +707,7 @@ def load_dataset(self, filename):
 
         try:
             if self._datatype == 'water level':
-                self._dataset = WLDataFrame(filename)
+                self._dataset = WLDataset(filename)
             elif self._datatype == 'daily weather':
                 self._dataset = WXDataFrame(filename)
         except Exception as e:

gwhat/projet/reader_projet.py

@@ -24,7 +24,7 @@
 
 # ---- Local library imports
 from gwhat.meteo.weather_reader import WXDataFrameBase, METEO_VARIABLES
-from gwhat.projet.reader_waterlvl import WLDataFrameBase, WLDataset
+from gwhat.projet.reader_waterlvl import WLDatasetBase, WLDataFrame
 from gwhat.gwrecharge.glue import GLUEDataFrameBase
 from gwhat.common.utils import save_content_to_file
 from gwhat.utils.math import nan_as_text_tolist, calcul_rmse
@@ -220,7 +220,7 @@ def get_wldset(self, name):
         if name in self.wldsets:
             self.set_last_opened_wldset(name)
             print('done')
-            return WLDataFrameHDF5(self.db['wldsets/%s' % name])
+            return WLDatasetHDF5(self.db['wldsets/%s' % name])
         else:
             print('failed')
             return None
@@ -282,7 +282,7 @@ def add_wldset(self, name, df):
             print('Unable to save dataset to project db')
             del self.db['wldsets'][name]
 
-        return WLDataFrameHDF5(grp)
+        return WLDatasetHDF5(grp)
 
     def del_wldset(self, name):
         """Delete the specified water level dataset."""
@@ -389,7 +389,7 @@ def del_wxdset(self, name):
         self.db.flush()
 
 
-class WLDataFrameHDF5(WLDataFrameBase):
+class WLDatasetHDF5(WLDatasetBase):
     """
     This is a wrapper around the h5py group that is used to store
     water level datasets. It mimick the structure of the DataFrame that
@@ -398,7 +398,7 @@ class WLDataFrameHDF5(WLDataFrameBase):
     """
 
     def __init__(self, hdf5group, *args, **kwargs):
-        super(WLDataFrameHDF5, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.__load_dataset__(hdf5group)
 
     def __load_dataset__(self, hdf5group):
@@ -413,7 +413,7 @@ def __load_dataset__(self, hdf5group):
                 columns.append(colname)
         data = np.vstack(tuple(data)).transpose()
         columns = tuple(columns)
-        self._dataf = WLDataset(data, columns)
+        self._dataf = WLDataFrame(data, columns)
 
         # Setup the structure for the Master Recession Curve
         if 'mrc' not in list(self.dset.keys()):

gwhat/projet/reader_waterlvl.py

@@ -39,9 +39,13 @@
     ])
 COLUMNS = list(COL_REGEX.keys())
 
-HEADER = {'Well': '', 'Well ID': '',
-          'Province': '', 'Municipality': '',
-          'Latitude': 0, 'Longitude': 0, 'Elevation': 0}
+HEADER = {'Well': '',
+          'Well ID': '',
+          'Province': '',
+          'Municipality': '',
+          'Latitude': 0,
+          'Longitude': 0,
+          'Elevation': 0}
 HEADER_REGEX = {
     'Well': r'(?<!\S)(wellname|name)(:|=)?(?!\S)',
     'Well ID': r'(?<!\S)(wellid|id)(:|=)?(?!\S)',
@@ -53,26 +57,27 @@
     }
 
 
-class EmptyWLDataset(pd.DataFrame):
-    def __init__(self):
-        super().__init__(np.empty((0, len(COLUMNS))), columns=COLUMNS)
+class WLDataFrame(pd.DataFrame):
+    def __init__(self, data: list = None, columns: list = None):
+        super().__init__(data=[], columns=COLUMNS)
         self.set_index([INDEX], drop=True, inplace=True)
 
-
-class WLDataset(EmptyWLDataset):
-    def __init__(self, data, columns):
-        super().__init__()
-        df = pd.DataFrame(data, columns=columns)
-        for column in columns:
-            for colname, regex in COL_REGEX.items():
-                str_ = column.replace(" ", "").replace("_", "")
-                if re.search(regex, str_, re.IGNORECASE):
-                    self[colname] = df[column].copy()
-                    break
-        del df
+        if data is not None and columns is not None:
+            df = pd.DataFrame(data, columns=columns)
+            for column in columns:
+                for colname, regex in COL_REGEX.items():
+                    str_ = column.replace(" ", "").replace("_", "")
+                    if re.search(regex, str_, re.IGNORECASE):
+                        self[colname] = df[column].copy()
+                        break
+            del df
         self.format_numeric_data()
         self.format_datetime_data()
 
+    @property
+    def _constructor(self):
+        return WLDataFrame
+
     def format_numeric_data(self):
         """Format the data to floats type."""
         for colname in COLUMNS:
@@ -139,8 +144,6 @@ def open_water_level_datafile(filename):
                     sheet.iter_rows(min_col=1, values_only=True)]
         finally:
             workbook.close()
-        print(data)
-
     return data
 
 
@@ -177,7 +180,7 @@ def read_water_level_datafile(filename):
         return None
 
     # Cast the data into a Pandas dataframe.
-    dataf = WLDataset(reader[i+1:], columns=row)
+    dataf = WLDataFrame(reader[i+1:], columns=row)
 
     # Add the metadata to the dataframe.
     for key in header.keys():
@@ -261,16 +264,16 @@ def generate_HTML_table(name, lat, lon, alt, mun):
     return table
 
 
-class WLDataFrameBase(Mapping):
+class WLDatasetBase(Mapping):
     """
     A water level data frame base class.
     """
 
     def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
+        super().__init__()
         self.dset = None
         self._undo_stack = []
-        self._dataf = EmptyWLDataset()
+        self._dataf = WLDataFrame()
 
     def __load_dataset__(self):
         """Loads the dataset and save it in a store."""
@@ -359,7 +362,7 @@ def _add_to_undo_stack(self, indexes):
             self._undo_stack.append(self._dataf['WL'].iloc[indexes].copy())
 
 
-class WLDataFrame(WLDataFrameBase):
+class WLDataset(WLDatasetBase):
     """
     A water level dataset container that loads its data from a csv
     or an Excel file.
@@ -389,9 +392,9 @@ def __load_dataset__(self, filename):
 
 if __name__ == "__main__":
     from gwhat import __rootdir__
-    df = WLDataFrame(
+    df = WLDataset(
         osp.join(__rootdir__, 'tests', "water_level_datafile.csv"))
-    df2 = WLDataFrame(
+    df2 = WLDataset(
         osp.join(__rootdir__, 'tests', "water_level_datafile.xls"))
-    df3 = WLDataFrame(
+    df3 = WLDataset(
         osp.join(__rootdir__, 'tests', "water_level_datafile.xlsx"))

gwhat/projet/tests/test_manager_data.py

@@ -19,7 +19,7 @@
 
 # ---- Local Libraries Imports
 from gwhat.meteo.weather_reader import WXDataFrame
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.projet.reader_projet import ProjetReader
 from gwhat.projet.manager_data import (DataManager, QFileDialog, QMessageBox,
                                        QCheckBox)
@@ -219,8 +219,8 @@ def test_delete_waterlevel_data(datamanager, mocker, qtbot):
     """
     Test deleting water level datasets from the project.
     """
-    datamanager.new_wldset_imported('wldset1', WLDataFrame(WLFILENAME))
-    datamanager.new_wldset_imported('wldset2', WLDataFrame(WLFILENAME))
+    datamanager.new_wldset_imported('wldset1', WLDataset(WLFILENAME))
+    datamanager.new_wldset_imported('wldset2', WLDataset(WLFILENAME))
     assert datamanager.wldataset_count() == 2
 
     # Click to delete the current water level dataset, but cancel.
@@ -262,7 +262,7 @@ def test_last_opened_datasets(qtbot, projectpath):
 
     # Add some water level dataset.
     for name in ['wldset1', 'wldset2', 'wldset3']:
-        datamanager.new_wldset_imported(name, WLDataFrame(WLFILENAME))
+        datamanager.new_wldset_imported(name, WLDataset(WLFILENAME))
     assert datamanager.get_current_wldset().name == 'wldset3'
 
     # Add some weather dataset.

gwhat/projet/tests/test_project.py

@@ -24,7 +24,7 @@
 from gwhat.projet.reader_projet import ProjetReader
 from gwhat.projet.manager_projet import (
     ProjetManager, QFileDialog, QMessageBox, CONF)
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.utils.math import nan_as_text_tolist
 
 NAME = "test @ prô'jèt!"
@@ -409,7 +409,7 @@ def test_store_mrc(project, testfile):
     Test that MRC data and results are saved and retrieved as expected
     in GWHAT project files.
     """
-    project.add_wldset('dataset_test', WLDataFrame(testfile))
+    project.add_wldset('dataset_test', WLDataset(testfile))
     wldset = project.get_wldset('dataset_test')
     assert wldset.mrc_exists() is False
 
@@ -449,7 +449,7 @@ def test_mrc_backward_compatibility(project, testfile):
     See jnsebgosselin/gwhat#377.
     """
     # Add the dataset to the project.
-    project.add_wldset('dataset_test', WLDataFrame(testfile))
+    project.add_wldset('dataset_test', WLDataset(testfile))
     wldset = project.get_wldset('dataset_test')
 
     # Make sure that the namespace was created automatically for the mrc

gwhat/recession/recession_calc.py

@@ -144,10 +144,10 @@ def calculate_mrc(t, h, periods: list(tuple), mrctype: int = 1):
 
 
 if __name__ == '__main__':
-    from gwhat.projet.reader_waterlvl import WLDataFrame
+    from gwhat.projet.reader_waterlvl import WLDataset
     import matplotlib.pyplot as plt
 
-    wldset = WLDataFrame(
+    wldset = WLDataset(
         "C:/Users/User/gwhat/gwhat/tests/data/sample_water_level_datafile.csv")
     periods = [
         (41384.260416666664, 41414.114583333336),

gwhat/tests/test_hydrocalc.py

@@ -20,7 +20,7 @@
 
 # ---- Local Libraries Imports
 from gwhat.meteo.weather_reader import WXDataFrame
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.HydroCalc2 import WLCalc
 from gwhat.projet.manager_data import DataManager
 from gwhat.projet.reader_projet import ProjetReader
@@ -50,7 +50,7 @@ def project(projectpath):
     project.add_wxdset(wxdset.metadata['Station Name'], wxdset)
 
     # Add the water level dataset to the project.
-    wldset = WLDataFrame(WLFILENAME)
+    wldset = WLDataset(WLFILENAME)
     project.add_wldset(wldset['Well'], wldset)
     return project
 

gwhat/tests/test_hydroprint.py

@@ -19,7 +19,7 @@
 
 # ---- Local Libraries Imports
 from gwhat.meteo.weather_reader import WXDataFrame
-from gwhat.projet.reader_waterlvl import WLDataFrame
+from gwhat.projet.reader_waterlvl import WLDataset
 from gwhat.HydroPrint2 import (HydroprintGUI, PageSetupWin, QFileDialog,
                                QMessageBox)
 from gwhat.projet.manager_data import DataManager
@@ -52,7 +52,7 @@ def project(projectpath):
         project.add_wxdset(wxdset.metadata['Station Name'], wxdset)
 
     # Add the water level dataset to the project.
-    wldset = WLDataFrame(WLFILENAME)
+    wldset = WLDataset(WLFILENAME)
     project.add_wldset(wldset['Well'], wldset)
     return project
 

gwhat/tests/test_read_waterlvl.py

@@ -18,7 +18,7 @@
 # ---- Local library imports
 from gwhat.common.utils import save_content_to_excel, save_content_to_csv
 from gwhat.projet.reader_waterlvl import (
-    load_waterlvl_measures, init_waterlvl_measures, WLDataFrame)
+    load_waterlvl_measures, init_waterlvl_measures, WLDataset)
 
 DATA = [['Well name = ', "êi!@':i*"],
         ['well id : ', '1234ABC'],
@@ -72,7 +72,7 @@ def datatmpdir(tmp_path):
 # =============================================================================
 @pytest.mark.parametrize("ext", ['.csv', '.xls', '.xlsx'])
 def test_reading_waterlvl(datatmpdir, ext):
-    df = WLDataFrame(osp.join(datatmpdir, 'water_level_datafile' + ext))
+    df = WLDataset(osp.join(datatmpdir, 'water_level_datafile' + ext))
 
     expected_results = {
         'Well': "êi!@':i*",