Feature 342 tcdiag tcmpr plotter

metplotpy/plots/config/tcmpr_defaults.yaml

@@ -145,3 +145,5 @@ subtitle: ''
 prefix:
 baseline_file: ./hfip_baseline.dat
 column_info_file: ./plot_tcmpr_hdr.dat
+is_tcdiag_linetype: False
+connect_points: False

metplotpy/plots/tcmpr_plots/box/tcmpr_point.py

@@ -1,37 +1,45 @@
 import os
+from datetime import datetime
 
 import plotly.graph_objects as go
 
+from metplotpy.plots import util
 from metplotpy.plots.tcmpr_plots.box.tcmpr_box_point import TcmprBoxPoint
 from metplotpy.plots.tcmpr_plots.tcmpr_series import TcmprSeries
 
 
 class TcmprPoint(TcmprBoxPoint):
-    def __init__(self, config_obj, column_info, col, case_data, input_df, baseline_data):
-        super().__init__(config_obj, column_info, col, case_data, input_df, baseline_data)
-        print("--------------------------------------------------------")
-        print(f"Plotting POINT time series by {self.config_obj.series_val_names[0]}")
+    def __init__(self, config_obj, column_info, col, case_data, input_df, baseline_data, stat_name):
+        super().__init__(config_obj, column_info, col, case_data, input_df, baseline_data, stat_name)
+        # Set up Logging
+        self.point_logger = util.get_common_logger(self.config_obj.log_level, self.config_obj.log_filename)
 
-        self._adjust_titles()
-        self.series_list = self._create_series(self.input_df)
+        self.point_logger.info("--------------------------------------------------------")
+        self.point_logger.info(f"Plotting POINT time series by {self.config_obj.series_val_names[0]}")
+        start = datetime.now()
+
+        self._adjust_titles(stat_name)
+        self.series_list = self._create_series(self.input_df, stat_name)
         self.case_data = None
         self.cur_baseline = baseline_data['cur_baseline']
         self.cur_baseline_data = baseline_data['cur_baseline_data']
         self._init_hfip_baseline_for_plot()
 
         if self.config_obj.prefix is None or len(self.config_obj.prefix) == 0:
-            self.plot_filename = f"{self.config_obj.plot_dir}{os.path.sep}{self.config_obj.list_stat_1[0]}_pointplot.png"
+            self.plot_filename = f"{self.config_obj.plot_dir}{os.path.sep}{stat_name}_pointplot.png"
         else:
-            self.plot_filename = f"{self.config_obj.plot_dir}{os.path.sep}{self.config_obj.prefix}_pointplot.png"
+            self.plot_filename = f"{self.config_obj.plot_dir}{os.path.sep}{self.config_obj.prefix}_{stat_name}_pointplot.png"
+        # remove the old file if it exists
 
-        # remove the old file if it exist
         if os.path.exists(self.plot_filename):
             os.remove(self.plot_filename)
         self._create_figure()
 
-    def _adjust_titles(self):
+        self.point_logger.info(f"Finished generating the TCMPR points  in {datetime.now() - start} ms")
+
+    def _adjust_titles(self, stat_name):
         if self.yaxis_1 is None or len(self.yaxis_1) == 0:
-            self.yaxis_1 = self.config_obj.list_stat_1[0] + '(' + self.col['units'] + ')'
+            self.yaxis_1 = stat_name + '(' + self.col['units'] + ')'
 
         if self.title is None or len(self.title) == 0:
             self.title = 'Point Plots  of ' + self.col['desc'] + ' by ' \
@@ -57,28 +65,78 @@ def _draw_series(self, series: TcmprSeries) -> None:
         boxpoints = 'all'
 
         # create a trace
-        self.figure.add_trace(
-            go.Box(x=series.series_data['LEAD_HR'],
-                   y=series.series_data['PLOT'],
-                   mean=series.series_points['mean'],
-                   notched=self.config_obj.box_notch,
-                   line=line_color,
-                   fillcolor=fillcolor,
-                   name=series.user_legends,
-                   showlegend=True,
-                   # quartilemethod='linear', #"exclusive", "inclusive", or "linear"
-                   boxmean=self.config_obj.box_avg,
-                   boxpoints=boxpoints,  # outliers, all, False
-                   pointpos=0,
-                   marker=dict(size=4,
-                               color=marker_color,
+
+        # line plot, when connect_points is False in config file
+        if 'point' in self.config_obj.plot_type_list:
+            if self.config_obj.connect_points:
+                # line plot
+                mode = 'lines+markers'
+            else:
+                # points only
+                mode = 'markers'
+            # Create a point plot
+
+            # Ensure that the size of the list of x and y values
+            # are the same, or the resulting plot will be incorrect.
+            # This mismatch occurs when the x_list represents the
+            # available lead hours in the series data and the
+            # series_points has None where there isn't data corresponding
+            # to lead hours in the series_points dataframe.
+            #
+            y_list = series.series_points['mean']
+            x_list = series.series_data['LEAD_HR']
+            if len(x_list) != len(y_list):
+                # Clean up None values in the series.series_points['mean'] list
+                # The None values are assigned by the _create_series_points() method.
+                y_list = [y_values for y_values in y_list if y_values is not None]
+
+            self.figure.add_trace(
+                go.Scatter(x=x_list,
+                           y=y_list,
+                           showlegend=True,
+                           mode=mode,
+                           name=self.config_obj.user_legends[series.idx],
+                           marker=dict(
+                               color=marker_line_color,
+                               size=8,
+                               opacity=0.7,
                                line=dict(
-                                   width=1,
-                                   color=marker_line_color
-                               ),
-                               symbol=marker_symbol,
-                               ),
-                   jitter=0
-                   ),
-            secondary_y=series.y_axis != 1
-        )
+                                   color=self.config_obj.colors_list[series.idx],
+                                   width=1
+                               )
+                           ),
+                           ),
+                secondary_y=series.y_axis != 1
+            )
+
+            # When a line plot is requested, connect any gaps
+            if self.config_obj.connect_points:
+                self.figure.update_traces(connectgaps=True)
+
+        else:
+            # Boxplot
+            self.figure.add_trace(
+                go.Box(x=series.series_data['LEAD_HR'],
+                       y=series.series_data['PLOT'],
+                       mean=series.series_points['mean'],
+                       notched=self.config_obj.box_notch,
+                       line=line_color,
+                       fillcolor=fillcolor,
+                       name=series.user_legends,
+                       showlegend=True,
+                       boxmean=self.config_obj.box_avg,
+                       boxpoints=boxpoints,  # outliers, all, False
+                       pointpos=0,
+                       marker=dict(size=4,
+                                   color=marker_color,
+                                   line=dict(
+                                       width=1,
+                                       color=marker_line_color
+                                   ),
+                                   symbol=marker_symbol,
+                                   ),
+                       jitter=0
+                       ),
+                secondary_y=series.y_axis != 1
+            )
+

metplotpy/plots/tcmpr_plots/tcmpr.py

@@ -420,8 +420,11 @@ def save_to_file(self):
 
         # Create the directory for the output plot if it doesn't already exist
         dirname = os.path.dirname(os.path.abspath(self.plot_filename))
-        if not os.path.exists(dirname):
-            os.mkdir(dirname)
+        try:
+           os.makedirs(dirname, exist_ok=True)
+        except FileExistsError:
+            pass
+
         self.logger.info(f'Saving the image file: {self.plot_filename}')
         if self.figure:
             try:
@@ -511,8 +514,6 @@ def perform_event_equalization(input_df:pd.DataFrame, is_skill:bool, config_obj:
     return output_data
 
 
-
-
 def main(config_filename=None):
     """
         Generates a sample, default, TCMPR plot using a combination of
@@ -553,6 +554,24 @@ def main(config_filename=None):
 
     config_obj = TcmprConfig(docs)
 
+    # Create the requested plot(s)
+    create_plot(config_obj)
+
+
+def create_plot(config_obj: dict) -> None:
+    """
+        One or more TCMPR plots is generated. Event equalization is performed if
+        it was requested by a setting in the yaml configuration file.
+
+        Args:
+           @param config_obj:  The config object containing all the necessary information obtained
+                               from the yaml configuration file.
+
+        Returns: None, creates one or more plots as specified in the yaml config file
+    """
+
+    # Find input files, they must have the .tcst extension and filename must have
+    # the prefix "tc_pairs" (e.g. tc_pairs_gfso_20220401.tcst)
     tcst_files = []
     # list all .tcst files in tcst_dir
     if config_obj.tcst_dir is not None and len(config_obj.tcst_dir) > 0 and os.path.exists(config_obj.tcst_dir):
@@ -566,7 +585,9 @@ def main(config_filename=None):
     input_df = orig_input_df.copy(deep=True)
 
     # Define a demo and retro column
-    # TODO these values never get used comment out for now
+
+    # Note: Currently not supported, leave commented out for now.
+
     # input_df = orig_input_df.copy(deep=True)
     # if config_obj.demo_yr is not None and config_obj.demo_yr != 'NA':
     #     demo_yr_obj = datetime.strptime(str(config_obj.demo_yr), '%Y')
@@ -579,18 +600,19 @@ def main(config_filename=None):
                               quotechar='"', skipinitialspace=True, encoding='utf-8')
 
     logger = util.get_common_logger(config_obj.log_level, config_obj.log_filename)
+\
     for plot_type in config_obj.plot_type_list:
 
         # Apply event equalization, if requested
         # Event equalization is different for the skill_mn and skill_md
         is_skill = False
         if config_obj.use_ee:
             if plot_type == 'skill_mn' or plot_type == 'skill_md':
-               is_skill = True
-               # perform event equalization on the skill_mn|skill_md plot type
-               logger.info(f"Perform event equalization for {plot_type}: {datetime.now()}")
-               output_result = perform_event_equalization(orig_input_df, is_skill, config_obj)
-               input_df = output_result
+                is_skill = True
+                # perform event equalization on the skill_mn|skill_md plot type
+                logger.info(f"Perform event equalization for {plot_type}: {datetime.now()}")
+                output_result = perform_event_equalization(orig_input_df, is_skill, config_obj)
+                input_df = output_result
             else:
                 logger.info(f"Perform event equalization for {plot_type}: {datetime.now()}")
                 output_result = perform_event_equalization(orig_input_df, is_skill, config_obj)
@@ -641,7 +663,7 @@ def main(config_filename=None):
                 elif plot_type == 'skill_mn':
                     from metplotpy.plots.tcmpr_plots.skill.mean.tcmpr_skill_mean import TcmprSkillMean
                     plot = TcmprSkillMean(config_obj, column_info, col_to_plot, common_case_data, input_df,
-                                         cur_stat,  baseline_data)
+                                          cur_stat, baseline_data)
                 elif plot_type == 'skill_md':
                     from metplotpy.plots.tcmpr_plots.skill.median.tcmpr_skill_median import TcmprSkillMedian
                     plot = TcmprSkillMedian(config_obj, column_info, col_to_plot, common_case_data, input_df, cur_stat)
@@ -683,7 +705,10 @@ def read_tcst_files(config_obj, tcst_files):
     for file in tcst_files:
         if os.path.exists(file):
             print(f'Reading track data:{file}')
-            file_df = pd.read_csv(file, sep=r'\s+|;|:', header='infer', engine="python")
+            if config_obj.is_tcdiag:
+                file_df = pd.read_csv(file, sep='\t')
+            else:
+                file_df = pd.read_csv(file, sep=r'\s+|;|:', header='infer', engine="python")
             file_df['LEAD_HR'] = file_df['LEAD'] / 10000
             file_df['LEAD_HR'] = file_df['LEAD_HR'].astype('int')
             all_filters = []
@@ -704,7 +729,10 @@ def read_tcst_files(config_obj, tcst_files):
             # use numpy to select the rows where any record evaluates to True
             mask = np.array(all_filters).all(axis=0)
 
-            file_df['VALID_TIME'] = pd.to_datetime(file_df['VALID'], format='%Y%m%d_%H%M%S')  # 20170417_060000
+            if config_obj.is_tcdiag:
+                file_df['VALID_TIME'] = file_df['VALID']
+            else:
+                file_df['VALID_TIME'] = pd.to_datetime(file_df['VALID'], format='%Y%m%d_%H%M%S')  # 20170417_060000
             # Define a case column
             file_df['equalize'] = file_df.loc[:, 'BMODEL'].astype(str) \
                                   + ':' + file_df.loc[:, 'STORM_ID'].astype(str) \

metplotpy/plots/tcmpr_plots/tcmpr_config.py

@@ -28,6 +28,7 @@ class TcmprConfig(Config):
     Prepares and organises Line plot parameters
     """
     SUPPORTED_PLOT_TYPES = ['boxplot', 'point', 'mean', 'median', 'relperf', 'rank', 'skill_mn', 'skill_md']
+
     def __init__(self, parameters: dict) -> None:
         """ Reads in the plot settings from a box plot config file.
 
@@ -37,6 +38,9 @@ def __init__(self, parameters: dict) -> None:
         """
         super().__init__(parameters)
 
+        self.is_tcdiag = self._get_bool('is_tcdiag_linetype')
+        self.connect_points = self._get_bool('connect_points')
+
         # Logging
         self.log_filename = self.get_config_value('log_filename')
         self.log_level = self.get_config_value('log_level')
@@ -251,7 +255,8 @@ def _get_hfip_bsln(self) -> str:
         """
 
         hfip_bsln = str(self.get_config_value('hfip_bsln'))
-        hfip_bsln = hfip_bsln.lower()
+        hfip_bsln_lower = hfip_bsln.lower()
+
 
         # Validate that hfip_bsln is one of the following; (no, 0, 5, 10 year goal)
         supported_bsln = ['no', '0', '5', '10']

metplotpy/plots/util.py

@@ -13,9 +13,8 @@
 __author__ = 'Minna Win'
 
 import argparse
-from typing import Tuple
 import sys
-import getpass
+import os
 import logging
 import gc
 import re
@@ -316,6 +315,13 @@ def get_common_logger(log_level, log_filename):
                         currently in use by a plot type.
     '''
 
+    # If directory for logfile doesn't exist, create it
+    log_dir = os.path.dirname(log_filename)
+    try:
+       os.makedirs(log_dir, exist_ok=True)
+    except OSError:
+        pass
+
     # Supported log levels.
     log_level = log_level.upper()
     log_levels = {'DEBUG': logging.DEBUG, 'INFO': logging.INFO,
@@ -338,7 +344,7 @@ def get_common_logger(log_level, log_filename):
                             datefmt='%Y-%m-%d %H:%M:%S',
                             filename=log_filename,
                             filemode='w')
-    mpl_logger = logging.getLogger(name='matplotlib').setLevel(logging.CRITICAL)
+    logging.getLogger(name='matplotlib').setLevel(logging.CRITICAL)
     common_logger = logging.getLogger(__name__)
     f = cf()
     common_logger.addFilter(f)