Merge pull request #10

Fix linter warnings

ExcelLayout.py

@@ -15,8 +15,8 @@
 
 import re
 import warnings
-import pandas as pd
 import math
+import pandas as pd
 
 
 class DataSource:
@@ -99,7 +99,7 @@ class DataSheet:
         create_custom_age_columns(self, age_ranges): Scans the column headers in the age category to build consistent
                                                      age columns.
     """
-    def __init__(self, sheet_name, data_source, custom_age_ranges, is_excel=False, file=None):
+    def __init__(self, sheet_name, data_source, custom_age_ranges, is_excel=False, file: pd.ExcelFile = None):
         """
         Initialize the DataSheet object.
 
@@ -116,34 +116,58 @@ def __init__(self, sheet_name, data_source, custom_age_ranges, is_excel=False, f
         self.columns = {}
         self.data_columns = []
 
-        if is_excel:
-            self.df = pd.read_excel(file, sheet_name, usecols=lambda x: '(%)' not in str(x), engine='openpyxl')
-            self.df.columns = self.df.columns.astype(str)
-            cols = [col for col in self.df.columns]
-
-            if data_source.get('date', None):
-                cols = ['date'] + cols[1:]
-                self.df.insert(0, 'date', data_source['date'], False)
-
-            self.df['date'] = pd.to_datetime(self.df['date'], errors='coerce')
+        if is_excel and file is not None:
+            self._load_excel_data(file, sheet_name, data_source)
 
-            if cols[-1].find('Not reported') == -1:
-                cols = cols + ['Not reported']
-                self.df['Not reported'] = 0
+        if custom_age_ranges and self.name in custom_age_ranges:
+            self.create_custom_age_columns(custom_age_ranges[self.name])
 
-            self.columns['date'] = cols[0]
-            for col in cols[1:]:
-                col_name = col
-                if data_source.get('remove column name text', None):
-                    for txt in data_source['remove column name text']:
-                        col_name = col.split(txt)[0]
-                        self.df[col_name.rstrip()] = self.df[col]
-                self.columns[col_name.rstrip()] = col
+    def _load_excel_data(self, file: pd.ExcelFile, sheet_name: str, data_source: dict):
+        """
+        Load and process data from an Excel file.
 
-            self.data_columns = list(self.columns.keys())[1:]
+        Args:
+            file (pd.ExcelFile): The Excel file to read the sheet from.
+            sheet_name (str): The name of the sheet to parse.
+            data_source (dict): The data source object containing additional settings.
 
-        if custom_age_ranges and self.name in custom_age_ranges:
-            self.create_custom_age_columns(custom_age_ranges[self.name])
+        Returns:
+            None
+        """
+        self.df = file.parse(sheet_name=sheet_name, usecols=lambda x: '(%)' not in str(x), engine='openpyxl')
+        self.df.columns = self.df.columns.astype(str)
+        self._process_date_column(data_source)
+        print(sheet_name)
+        print(self.df.columns)
+        self._process_columns(data_source)
+
+    def _process_date_column(self, data_source: dict):
+        """Process and format the date column."""
+
+        # This assumes that the first column is either the date column or does not have useful data
+        if data_source.get('date'):
+            self.df.drop(self.df.columns[0], axis=1, inplace=True)
+            self.df.insert(0, 'date', data_source['date'], False)
+
+        self.df['date'] = pd.to_datetime(self.df['date'], errors='coerce')
+
+        if 'Not reported' not in self.df.columns:
+            self.df['Not reported'] = 0
+
+        self.columns['date'] = self.df.columns[0]
+
+    def _process_columns(self, data_source: dict):
+        """Process and rename columns according to the data source settings."""
+        for col in self.df.columns[1:]:
+            col_name = col
+            if 'remove column name text' in data_source:
+                for txt in data_source['remove column name text']:
+                    col_name = col.split(txt)[0]
+            col_name = col_name.rstrip()
+            self.columns[col_name] = col
+            self.df[col_name] = self.df.pop(col)
+
+        self.data_columns = list(self.columns.keys())[1:]
 
     def create_custom_age_columns(self, age_ranges):
         """

README.md

@@ -53,7 +53,7 @@ There is a requirements.txt file available to install requirements
 #### Configure yaml
 First, configure your own jsdconfig.yaml file to select which data to load by default. There is a jsdconfig-example.yaml file provided that may be copied over or used as a template for your own config file.
 * The filename needs to be specified, and a human-readable name should be provided for use in the plots and figures. 
-* Please see the ***Generating custom excel files*** section for additional information.
+* Please see the ***Generating custom Excel files*** section for additional information.
 * On your first run, you may use ```cp jsdconfig-example.yaml jsdconfig.yaml``` to load the MIDRC data.
 
 #### Run application
@@ -70,7 +70,7 @@ To start the application, run `python main.py`
 - **Each attribute should have its own sheet** which will be automatically parsed by the application.
 - Column names within each sheet are parsed and compared between files
   - Where there is a matching column name within a worksheet of the same name, the JSD will be calculated using those values.
-  - ***A Date column is expected***, and it should be sorted. Please see how the census data is loaded using the example config file if your data does not have multiple dates and you do not have a date column.
+  - ***A Date column is expected***, and it should be sorted. Please see how the census data is loaded using the example config file if your data does not have multiple dates, and you do not have a date column.
 - The list of attributes provided in the GUI should be a list where worksheets with an identical name exist in both files. If it is not, please check your spelling
 - The ```remove column name text``` config parameter is due to how the MIDRC data is generated. There is a ```(CUSUM)``` suffix that needs to be removed to compare it to CDC and Census data.
 

excelparse.py

@@ -26,16 +26,16 @@ def excelparse(filename, sheet_name):
     """
 
     # This opens the file and creates a list of sheet names, along with necessary readers
-    # TODO: this should probably be separate in case we want multiple sheets
     xls = pd.ExcelFile(filename)
 
     # This reads all Excel sheets, probably not worth it
     # df_map = pd.read_excel(xls)
 
     # This reads in the specified worksheet
-    df = pd.read_excel(xls, sheet_name)
+    df = xls.parse(sheet_name=sheet_name, usecols=lambda x: '(%)' not in str(x), engine='openpyxl')
 
     # Find the columns that are percentages of the total distribution
-    pct_cols = [col for col in df.columns if '(%)' in col]
+    # pct_cols = [col for col in df.columns if '(%)' in col]
 
-    return df[['date'] + pct_cols]
+    # return df[['date'] + pct_cols]
+    return df

grabbablewidget.py

@@ -264,14 +264,14 @@ def _setup_buttons(self, layout):
         """
         button_layout = QHBoxLayout()
 
-        self.save_button = QPushButton("Save", self)
-        self.cancel_button = QPushButton("Cancel", self)
+        save_button = QPushButton("Save", self)
+        cancel_button = QPushButton("Cancel", self)
 
-        self.save_button.clicked.connect(self.save_image)
-        self.cancel_button.clicked.connect(self.cancel_save)
+        save_button.clicked.connect(self.save_image)
+        cancel_button.clicked.connect(self.cancel_save)
 
-        button_layout.addWidget(self.save_button)
-        button_layout.addWidget(self.cancel_button)
+        button_layout.addWidget(save_button)
+        button_layout.addWidget(cancel_button)
 
         layout.addLayout(button_layout)
 

jsdconfig.py

@@ -32,7 +32,7 @@ class JSDConfig:
         __init__(self, filename='jsdconfig.yaml'): Initializes a new instance of the JSDConfig class.
     """
     def __init__(self, filename='jsdconfig.yaml'):
-        stream = open(filename, 'r')
-        self.data = load(stream, Loader=Loader)
+        with open(filename, 'r', encoding='utf-8') as stream:
+            self.data = load(stream, Loader=Loader)
 
         # print(dump(self.data))

jsdcontroller.py

@@ -37,7 +37,7 @@ class JSDController(QObject):
     """
     modelChanged = Signal()
     fileChangedSignal = Signal()
-    
+
     def __init__(self, jsd_view, jsd_model, config):
         """
         Initialize the JSDController.
@@ -168,8 +168,8 @@ def get_file_sheets_from_combobox(self, index=0):
         """
         try:
             current_data = self.jsd_view.dataselectiongroupbox.file_comboboxes[index].currentData()
-        except IndexError:
-            raise IndexError("Index out of range")
+        except IndexError as exc:
+            raise IndexError("Index out of range") from exc
 
         sheets = self.jsd_model.data_sources[current_data].sheets
         return sheets
@@ -245,7 +245,7 @@ def update_file_based_charts(self):
 
         try:
             self.jsd_view.update_pie_chart_dock(sheet_dict)
-        except Exception:
+        except (ValueError, KeyError, TypeError):
             return False
 
         return True
@@ -262,13 +262,13 @@ def update_category_plots(self):
         sheet_dict = {}
         for i in range(len(self.jsd_view.dataselectiongroupbox.file_comboboxes)):
             if self.jsd_view.dataselectiongroupbox.file_checkboxes[i].isChecked():
-                sheet_dict[i] = (self.get_file_sheets_from_combobox(i))
+                sheet_dict[i] = self.get_file_sheets_from_combobox(i)
 
         try:
             self.jsd_view.update_jsd_timeline_plot(self.jsd_model)
             self.jsd_view.update_area_chart(sheet_dict)
             return True
-        except Exception as e:
+        except (ValueError, KeyError, TypeError) as e:
             print(f"An error occurred during the update of category plots: {e}")
             return False
 

jsdmodel.py

@@ -13,10 +13,10 @@
 #      limitations under the License.
 #
 
-from ExcelLayout import DataSource
+from typing import Optional, Any, List
 from PySide6.QtCore import QAbstractTableModel, QModelIndex, Qt, Signal
 from PySide6.QtGui import QColor
-from typing import Optional, Any, List
+from ExcelLayout import DataSource
 
 
 class JSDTableModel(QAbstractTableModel):
@@ -151,20 +151,20 @@ def update_input_data(self, new_input_data, new_column_infos):
         for c in range(self.columnCount()):
             self.max_row_count = max(self.max_row_count, len(self._input_data[c]))
 
-    def columnCount(self, parent: QModelIndex = None) -> int:
+    def columnCount(self, _parent: QModelIndex = None) -> int:
         """
         Returns the number of columns in the model.
 
         Args:
-            parent (QModelIndex): The parent index. Defaults to QModelIndex().
+            _parent (QModelIndex): The parent index. Defaults to QModelIndex(). This is unused.
 
         Returns:
             int: The number of columns in the model.
         """
         # return len(self.input_data[parent.row()])
         return len(self._input_data)
 
-    def headerData(self, section: int, orientation: int, role: int, *args, **kwargs) -> Any:
+    def headerData(self, section: int, orientation: Qt.Orientation, role: int = Qt.DisplayRole, *args, **kwargs) -> Any:
         """
         Returns the header data for the specified section, orientation, and role.
 

jsdview.py

@@ -12,12 +12,13 @@
 #      See the License for the specific language governing permissions and
 #      limitations under the License.
 #
-from typing import Type, Union, List, Tuple
+from typing import Type, Union, List, Tuple, Iterable
 import math
 import io
 import csv
+from functools import partial
 from PySide6.QtCore import (QRect, Qt, QDateTime, QTime, QPointF, QSignalBlocker, Signal,
-                            QFileInfo, QEvent, QDate)
+                            QFileInfo, QEvent, QDate, QObject)
 from PySide6.QtGui import QPainter, QAction, QKeySequence, QGuiApplication
 from PySide6.QtWidgets import (QHeaderView, QTableView, QWidget, QMainWindow, QGroupBox, QMenu, QFileDialog,
                                QVBoxLayout, QComboBox, QLabel, QHBoxLayout, QMenuBar, QDockWidget, QSplitter,
@@ -27,8 +28,6 @@
                               QPieSeries, QPolarChart, QAreaSeries, QCategoryAxis)
 from datetimetools import numpy_datetime64_to_qdate, convert_date_to_milliseconds
 from grabbablewidget import GrabbableChartView
-from functools import partial
-from typing import Iterable
 
 
 class JsdDataSelectionGroupBox(QGroupBox):
@@ -269,7 +268,6 @@ def __init__(self, data_sources):
         self.area_chart_widget = QWidget()
         # self.area_chart_layout = QVBoxLayout()
         self.area_chart_widget.setLayout(QVBoxLayout())
-        self.area_charts = {}
         self.spider_chart_vbox = QSplitter(Qt.Vertical)
         self.spider_chart_dock_widget = self.create_spider_chart_dock_widget(self.spider_chart_vbox,
                                                                          'Diversity Charts - ' + JsdWindow.WINDOW_TITLE)
@@ -346,7 +344,7 @@ def populate_dock_widget_menu(self, dock_widget_menu: QMenu) -> None:
         """
         Clear the dock widget menu and populate it with actions for each dock widget.
 
-        This method clears the existing menu items in the dock widget menu and creates a new action for each dock widget found.
+        This method clears the existing menu items in the menu and creates a new action for each dock widget found.
         Each action corresponds to a dock widget and allows the user to toggle the visibility of the dock widget.
         """
         dock_widget_menu.clear()
@@ -477,8 +475,7 @@ def update_pie_chart_dock(self, sheet_dict):
             label_text = file_comboboxes[index].currentText() + ':'
             label = QLabel(label_text)
             label_width = label.sizeHint().width()
-            if label_width > max_label_width:
-                max_label_width = label_width
+            max_label_width = max(max_label_width, label_width)
 
         for index, sheets in sheet_dict.items():
             row_layout = QHBoxLayout()
@@ -980,7 +977,7 @@ def __init__(self):
         super().__init__()
         self.installEventFilter(self)
 
-    def eventFilter(self, source, event):
+    def eventFilter(self, source: QObject, event):
         """
         Filters and handles key press events.
 

main.py

@@ -60,14 +60,14 @@ def _create_pixmap():
             painter.drawText(pixmap.rect(), Qt.AlignCenter, SPLASH_SCREEN_MESSAGE)
         return pixmap
 
-    def __init__(self, parent: Optional[QWidget] = None) -> None:
+    def __init__(self) -> None:
         """
         Initialize the object.
 
         Args:
-            parent: The parent widget.
+            None
         """
-        super().__init__(parent)
+        super().__init__()
         pixmap = self._create_pixmap()
         self.setPixmap(pixmap)