Merge pull request #40 from SPF-OST/38-add-improvements-suggested-by-…

…alex

addressed most improvements suggested by alex in : #32

examples/ready-to-run/processing_example.py

@@ -19,42 +19,48 @@ def processing_of_monthly_data(simulation: api.Simulation):
 
     # modify label for the y axis
     ax.set_ylabel("Power [kW]")
-    # make label fit inside your plot
+
+    # This is also done by api.save_plot, but if you want to see your plot before saving it.
+    # For example with _plt.show(). Calling this function is required, to make the plot look as expected.
     _plt.tight_layout()
 
     # create plots folder inside simulation directory and save plot in configured formats
-    api.save_plot(fig, simulation.path, "monthly-bar-chart")
+    api.export_plots_in_configured_formats(
+        fig, simulation.path, "monthly-bar-chart"
+    )
 
 
 def processing_of_hourly_data(simulation: api.Simulation):
     # create line plot using hourly data
     fig, ax = api.line_plot(simulation.hourly, ["QSrc1TIn", "QSrc1TOut"])
 
-    # modify label for the y axis
+    # Here you can modify anything to do with your plot, according to the matplotlib.pyplot standard
     ax.set_ylabel("Temperature [°C]")
     # make label fit inside your plot
     _plt.tight_layout()
 
     # create plots folder inside simulation directory and save plot in configured formats
-    api.save_plot(fig, simulation.path, "hourly-line-plot")
+    api.export_plots_in_configured_formats(
+        fig, simulation.path, "hourly-line-plot"
+    )
 
 
 def processing_for_histogram(simulation: api.Simulation):
     # create histogram using hourly data
     fig, _ = api.histogram(simulation.hourly, ["QSrc1TIn"])
 
-    # create plots folder inside simulation directory and save plot in configured formats
-    api.save_plot(fig, simulation.path, "histogram")
+    # if you don't want to export your plot, you can also just show it by calling this function
+    _plt.show()
 
 
 if __name__ == "__main__":
     # This is the entry point to your script.
-    # In here you can decide how you would like to run your processing steps.
+    # Here, you can decide how you would like to run your processing steps.
     # In the example below we run both processing steps on a whole result set.
     # Or a single processing step on a single simulation.
     # Make sure to remove the lines you do not want to run.
 
-    # bundle the scenarios into a list
+    # bundle the steps into a list
     processing_scenarios = [
         processing_of_monthly_data,
         processing_of_hourly_data,

pytrnsys_process/api.py

@@ -21,9 +21,13 @@
 )
 from pytrnsys_process.process_sim.process_sim import Simulation
 
+# ============================================================
 # this lives here, because it needs to be available everywhere
 from pytrnsys_process.settings import settings
-from pytrnsys_process.utils import save_plot
+
+# ============================================================
+
+from pytrnsys_process.utils import export_plots_in_configured_formats
 
 __all__ = [
     "line_plot",
@@ -35,6 +39,6 @@
     "process_single_simulation",
     "process_whole_result_set",
     "Simulation",
-    "save_plot",
+    "export_plots_in_configured_formats",
     "settings",
 ]

pytrnsys_process/converter.py → pytrnsys_process/file_converter.py

@@ -55,7 +55,7 @@ def convert_sim_results_to_csv(
         )
 
         for input_file in input_files:
-            if not input_file.is_file():
+            if input_file.is_dir():
                 continue
 
             if ftd.has_pattern(input_file, const.FileType.MONTHLY):
@@ -130,12 +130,12 @@ def _refactor_filename(
         filename: str, patterns: list[str], prefix: str
     ) -> str:
         """Process filename by removing patterns and adding appropriate prefix.
-        
+
         Args:
             filename: The original filename to process
             patterns: List of regex patterns to remove from filename
             prefix: Prefix to add to the processed filename
-            
+
         Returns:
             The processed filename with patterns removed and prefix added
         """

pytrnsys_process/logger.py

@@ -1,3 +1,18 @@
+"""
+Configures logging for the pytrnsys_process package with three outputs:
+1. Console output (INFO level) - Shows basic messages without stacktrace
+2. Regular log file (INFO level) - Logs to pytrnsys_process.log without stacktrace
+3. Debug log file (DEBUG level) - Logs to pytrnsys_process_debug.log with full stacktrace
+
+The logging setup includes custom formatting for each handler and uses a TracebackInfoFilter
+to control stacktrace visibility in different outputs. The main logger is configured at DEBUG
+level to capture all logging events, while individual handlers control what gets displayed
+in each output.
+
+All handlers use the same log record.
+Once the log record is modified and anything removed from it, will not be available in the other handlers.
+"""
+
 import logging
 import sys
 

pytrnsys_process/plotting/plot_wrappers.py

@@ -32,12 +32,19 @@ def line_plot(
         >>>
         >>> def create_line_plot(simulation: api.Simulation):
         >>>     fig, ax = api.line_plot(simulation.hourly, columns=['var1', 'var2'])
-        Customize the plot using the returned axes object:
+        >>>     # Customize the plot using the returned axes object:
         >>>     ax.set_xlabel('Time')
         >>>     ax.set_ylabel('Value')
         >>>     ax.set_title('My Plot')
         >>>     ax.grid(True)
         >>>     _plt.show()
+        >>>
+        >>> # run the single scenario on a single simulation
+        >>> api.process_single_simulation(
+        >>>     _pl.Path("data/results/complete-0-SnkScale0.6000-StoreScale8"),
+        >>>     create_line_plot,
+        >>>     )
+
     For additional customization options, refer to:
     - Matplotlib documentation: https://matplotlib.org/stable/api/
     - Pandas plotting: https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.plot.html
@@ -70,12 +77,19 @@ def bar_chart(
 
     Example:
         >>> from pytrnsys_process import api
-        >>> fig, ax = api.bar_chart(simulation.monthly, columns=['var1', 'var2'])
-        Customize the plot using the returned axes object:
-        >>> ax.set_xlabel('Time')
-        >>> ax.set_ylabel('Value')
-        >>> ax.set_title('My Plot')
-        >>> ax.grid(True)
+        >>> def create_bar_chart(simulation: api.Simulation):
+        >>>     fig, ax = api.bar_chart(simulation.monthly, columns=['var1', 'var2'])
+        >>>     # Customize the plot using the returned axes object:
+        >>>     ax.set_xlabel('Time')
+        >>>     ax.set_ylabel('Value')
+        >>>     ax.set_title('My Plot')
+        >>>     ax.grid(True)
+        >>>
+        >>> # run the single scenario on a single simulation
+        >>> api.process_single_simulation(
+        >>>     _pl.Path("data/results/complete-0-SnkScale0.6000-StoreScale8"),
+        >>>     create_bar_chart,
+        >>>     )
 
     For additional customization options, refer to:
     - Matplotlib documentation: https://matplotlib.org/stable/api/
@@ -109,12 +123,19 @@ def stacked_bar_chart(
 
     Example:
         >>> from pytrnsys_process import api
-        >>> fig, ax = api.stacked_bar_chart(simulation.monthly, columns=['var1', 'var2', 'var3'])
-        Customize the plot using the returned axes object:
-        >>> ax.set_xlabel('Time')
-        >>> ax.set_ylabel('Value')
-        >>> ax.set_title('My Plot')
-        >>> ax.grid(True)
+        >>> def create_stacked_bar_chart(simulation: api.Simulation):
+        >>>     fig, ax = api.stacked_bar_chart(simulation.monthly, columns=['var1', 'var2', 'var3'])
+        >>>     # Customize the plot using the returned axes object:
+        >>>     ax.set_xlabel('Time')
+        >>>     ax.set_ylabel('Value')
+        >>>     ax.set_title('My Plot')
+        >>>     ax.grid(True)
+        >>>
+        >>> # run the single scenario on a single simulation
+        >>> api.process_single_simulation(
+        >>>     _pl.Path("data/results/complete-0-SnkScale0.6000-StoreScale8"),
+        >>>     create_stacked_bar_chart,
+        >>>     )
 
     For additional customization options, refer to:
     - Matplotlib documentation: https://matplotlib.org/stable/api/
@@ -148,12 +169,19 @@ def histogram(
 
     Example:
         >>> from pytrnsys_process import api
-        >>> fig, ax = api.histogram(simulation.hourly, columns=['var1', 'var2'])
-        Customize the plot using the returned axes object:
-        >>> ax.set_xlabel('Value')
-        >>> ax.set_ylabel('Frequency')
-        >>> ax.set_title('My Histogram')
-        >>> ax.grid(True)
+        >>> def create_histogram(simulation: api.Simulation):
+        >>>     fig, ax = api.histogram(simulation.hourly, columns=['var1', 'var2'])
+        >>>     # Customize the plot using the returned axes object:
+        >>>     ax.set_xlabel('Value')
+        >>>     ax.set_ylabel('Frequency')
+        >>>     ax.set_title('My Histogram')
+        >>>     ax.grid(True)
+        >>>
+        >>> # run the single scenario on a single simulation
+        >>> api.process_single_simulation(
+        >>>     _pl.Path("data/results/complete-0-SnkScale0.6000-StoreScale8"),
+        >>>     create_histogram,
+        >>>     )
 
     For additional customization options, refer to:
     - Matplotlib documentation: https://matplotlib.org/stable/api/
@@ -190,17 +218,24 @@ def scatter_plot(
 
     Example:
         >>> from pytrnsys_process import api
-        >>> fig, ax = api.scatter_plot(
-        ...     simulation.hourly,
-        ...     columns=["var1", "var2", "var3"],
-        ...     x_column="var1",
-        ...     y_column="var2",
-        ... )
-        Customize the plot using the returned axes object:
-        >>> ax.set_xlabel('Time')
-        >>> ax.set_ylabel('Value')
-        >>> ax.set_title('My Scatter Plot')
-        >>> ax.grid(True)
+        >>> def create_scatter_plot(simulation: api.Simulation):
+        >>>     fig, ax = api.scatter_plot(
+        ...         simulation.hourly,
+        ...         columns=["var1", "var2", "var3"],
+        ...         x_column="var1",
+        ...         y_column="var2",
+        ...     )
+        >>>     # Customize the plot using the returned axes object:
+        >>>     ax.set_xlabel('Time')
+        >>>     ax.set_ylabel('Value')
+        >>>     ax.set_title('My Scatter Plot')
+        >>>     ax.grid(True)
+        >>>
+        >>> # run the single scenario on a single simulation
+        >>> api.process_single_simulation(
+        >>>     _pl.Path("data/results/complete-0-SnkScale0.6000-StoreScale8"),
+        >>>     create_scatter_plot,
+        >>>     )
 
     For additional customization options, refer to:
     - Matplotlib documentation: https://matplotlib.org/stable/api/

pytrnsys_process/plotting/plotters.py

@@ -15,6 +15,7 @@
 # TODO: deal with legends (curve names, fonts, colors, linestyles) # pylint: disable=fixme
 # TODO: clean up old stuff by refactoring # pylint: disable=fixme
 # TODO: make issue for docstrings of plotting # pylint: disable=fixme
+# TODO: Add colormap support # pylint: disable=fixme
 
 
 @dataclass
@@ -113,32 +114,6 @@ def _do_plot(
 
         return fig, ax
 
-    # TODO: Add colormap support # pylint: disable=fixme
-    # def _do_plot(
-    #     self,
-    #     df: _pd.DataFrame,
-    #     columns: list[str],
-    #     use_legend: bool = True,
-    #     size: tuple[float, float] = const.PlotSizes.A4.value,
-    #     **kwargs: _tp.Any,
-    # ) -> _plt.Figure:
-    #     """The matplot date formatter does not work when using df.plot func.
-    #     This is an example to plot a stacked bar chart without df.plot"""
-    #     fig, ax = _plt.subplots(figsize=size)
-    #     x = _np.arange(len(df.index))
-    #     bottom = _np.zeros(len(df.index))
-    #     for col in columns:
-    #         ax.bar(x, df[col], label=col, bottom=bottom, width=0.35)
-    #         bottom += df[col]
-    #     if use_legend:
-    #         ax.legend()
-    #     ax.set_xticks(x)
-    #     ax.set_xticklabels(
-    #         _pd.to_datetime(df.index).strftime(self.DATE_FORMAT)
-    #     )
-    #     self.configure(ax)
-    #     return fig
-
     # TODO Idea for what an energy balance plot method could look like # pylint: disable=fixme
     @staticmethod
     def create_energy_balance_monthly(
@@ -237,6 +212,8 @@ def _do_plot(
     ) -> tuple[_plt.Figure, _plt.Axes]:
         fig, ax = _plt.subplots(figsize=size)
         # TODO: cleanup the other Plotters to remove the stringy dictionary.
-        df[columns].plot.scatter(colormap=self.COLOR_MAP, legend=use_legend, ax=ax, **kwargs)
+        df[columns].plot.scatter(
+            colormap=self.COLOR_MAP, legend=use_legend, ax=ax, **kwargs
+        )
         ax = self.configure(ax)
         return fig, ax

pytrnsys_process/process_sim/process_sim.py

@@ -43,6 +43,8 @@ class Simulation:
 def process_sim(
         sim_files: _abc.Sequence[_pl.Path], sim_folder: _pl.Path
 ) -> Simulation:
+    # Used to store the array of dataframes for each file type.
+    # Later used to concatenate all into one dataframe and saving as Sim object
     simulation_data_collector = _SimulationDataCollector()
     for sim_file in sim_files:
         try:
@@ -192,25 +194,16 @@ def _process_file(
 def _merge_dataframes_into_simulation(
         simulation_data_collector: _SimulationDataCollector, sim_folder: _pl.Path
 ) -> Simulation:
-    monthly_df = (
-        handle_duplicate_columns(
-            _pd.concat(simulation_data_collector.monthly, axis=1)
-        )
-        if simulation_data_collector.monthly
-        else _pd.DataFrame()
-    )
-    hourly_df = (
-        handle_duplicate_columns(
-            _pd.concat(simulation_data_collector.hourly, axis=1)
-        )
-        if simulation_data_collector.hourly
-        else _pd.DataFrame()
-    )
-    timestep_df = (
-        handle_duplicate_columns(
-            _pd.concat(simulation_data_collector.step, axis=1)
-        )
-        if simulation_data_collector.step
-        else _pd.DataFrame()
-    )
+
+    monthly_df = get_df_without_duplicates(simulation_data_collector.monthly)
+    hourly_df = get_df_without_duplicates(simulation_data_collector.hourly)
+    timestep_df = get_df_without_duplicates(simulation_data_collector.step)
+
     return Simulation(sim_folder, monthly_df, hourly_df, timestep_df)
+
+
+def get_df_without_duplicates(dfs: _abc.Sequence[_pd.DataFrame]):
+    if len(dfs) > 0:
+        return handle_duplicate_columns(_pd.concat(dfs, axis=1))
+
+    return _pd.DataFrame()

pytrnsys_process/settings.py

@@ -28,7 +28,7 @@ class Plot:
 
 @dataclass
 class Reader:
-    folder_name_for_printer_files_loc: str = "temp"
+    folder_name_for_printer_files: str = "temp"
     read_step_files: bool = True