From 947985cee6ff90bc7a1b3518b920d76129f85c2d Mon Sep 17 00:00:00 2001
From: Michael Reuscher <michael.reuscher@desy.de>
Date: Tue, 25 Jul 2023 17:24:01 +0200
Subject: [PATCH] statistics plot 1.0
---
visualizer/visualizer/DataFrameCreator.py | 17 +++++++++---
visualizer/visualizer/SeabornPlotter.py | 33 +++++++++++++++++------
visualizer/visualizer/main.py | 20 +++++++-------
3 files changed, 48 insertions(+), 22 deletions(-)
diff --git a/visualizer/visualizer/DataFrameCreator.py b/visualizer/visualizer/DataFrameCreator.py
index 7f34309..f227893 100644
--- a/visualizer/visualizer/DataFrameCreator.py
+++ b/visualizer/visualizer/DataFrameCreator.py
@@ -1,6 +1,7 @@
import os
import pandas as pd
import re
+from collections import OrderedDict
class DataFrameCreator:
@@ -14,9 +15,9 @@ class DataFrameCreator:
def _merge_dataframes(dfs):
merged_dfs = {}
for outer_key in dfs:
- merged_dataframe = pd.concat(dfs[outer_key].values(), keys=dfs[outer_key].keys())
- merged_dataframe_sorted = merged_dataframe.sort_index()
- merged_dfs[outer_key] = merged_dataframe_sorted
+ # Concatenate and sort the DataFrames by their index
+ merged_dataframe = pd.concat(dfs[outer_key].values(), keys=dfs[outer_key].keys(), sort=True)
+ merged_dfs[outer_key] = merged_dataframe
return merged_dfs
@staticmethod
@@ -31,8 +32,15 @@ class DataFrameCreator:
@staticmethod
def _extract_statistics(data, filename):
result = {}
+ match = re.search(r'\d+(?=\.\w+$)', filename)
+ if match:
+ last_numbers = int(match.group())
+ datasize = last_numbers
+ else:
+ datasize = 0
group = re.search(r"(.*):", data).group(1)
result["Group"] = group
+ result["size"] = int(datasize)
values = re.findall(r"\d+\.\d+", data)
result["min"] = float(values[0])
@@ -74,7 +82,7 @@ class DataFrameCreator:
dataframe = pd.DataFrame(data_list)
dataframe_type = filename
- dataframe_name = filename.split('.')[0] # Verwende den Dateinamen ohne Erweiterung als DataFrame-Namen
+ dataframe_name = filename.split('.')[0]
if dataframe_type in self.s_dfs:
inner_dict = self.s_dfs[dataframe_type]
@@ -125,4 +133,5 @@ class DataFrameCreator:
various_dfs = self._merge_dataframes(self.v_dfs)
long_dfs = self._merge_dataframes(self.l_dfs)
statistics_dfs = self._merge_dataframes(self.s_dfs)
+
return various_dfs, long_dfs, statistics_dfs
diff --git a/visualizer/visualizer/SeabornPlotter.py b/visualizer/visualizer/SeabornPlotter.py
index f91b0a2..ef44dc7 100644
--- a/visualizer/visualizer/SeabornPlotter.py
+++ b/visualizer/visualizer/SeabornPlotter.py
@@ -68,13 +68,30 @@ class SeabornPlotter:
plt.show()
def plot_statistics(self):
- df = self.dataframe
- for frame in df
- plt.figure(figsize=(10, 6))
- sns.boxplot(data=df[['min', 'mean', '10%', 'med', '90%', 'max']], palette='pastel')
- plt.xlabel('Statistical Measures')
- plt.ylabel('Time (Y-Axis)')
- plt.title('Boxplot of Statistical Measures for Each Group')
- plt.grid(True)
+ dataframes = self.dataframe
+
+ # Sort the dataframes based on the 'size' column in ascending order
+ sorted_dataframes = sorted(dataframes.items(), key=lambda x: x[1]['size'].min())
+
+ num_plots = len(sorted_dataframes) # Number of DataFrames in the dictionary
+ rows = 6 # Number of rows in the grid
+ cols = (num_plots + 1) // rows # Number of columns in the grid
+
+ # Subplots creation
+ fig, axes = plt.subplots(rows, cols, figsize=(180, 120), constrained_layout=True)
+ fig.suptitle('Boxplot of Statistical Measures for Each Group', fontsize=14)
+
+ # For each DataFrame, create a boxplot and place it into the corresponding subplot
+ for idx, (df_key, df) in enumerate(sorted_dataframes):
+ sns.boxplot(data=df, ax=axes[idx // cols, idx % cols], palette='pastel')
+
+ axes[idx // cols, idx % cols].set_yscale('log')
+ axes[idx // cols, idx % cols].set_ylabel('Time (Y-Axis)')
+ axes[idx // cols, idx % cols].set_title(f'Group {df_key}', fontsize=12)
+ axes[idx // cols, idx % cols].grid(True)
+
+ # Hide empty subplots, if any
+ for idx in range(num_plots, rows * cols):
+ fig.delaxes(axes.flatten()[idx])
plt.show()
diff --git a/visualizer/visualizer/main.py b/visualizer/visualizer/main.py
index d6622fc..f204c88 100644
--- a/visualizer/visualizer/main.py
+++ b/visualizer/visualizer/main.py
@@ -23,21 +23,21 @@ def main():
s_plotter.plot_statistics()
# Plot Data
- for frame in v_dataframes.keys():
- if not v_dataframes[frame].empty:
+ #for frame in v_dataframes.keys():
+ #if not v_dataframes[frame].empty:
# Setup Plotter
- frame_name = frame
- v_plotter = SeabornPlotter(v_dataframes[frame], frame_name)
+ #frame_name = frame
+ #v_plotter = SeabornPlotter(v_dataframes[frame], frame_name)
# Plotter run
- v_plotter.plot_histogram_various()
+ #v_plotter.plot_histogram_various()
- for frame in l_dataframes.keys():
- if not v_dataframes[frame].empty:
+ #for frame in l_dataframes.keys():
+ #if not v_dataframes[frame].empty:
# Setup Plotter
- frame_name = frame
- l_plotter = SeabornPlotter(l_dataframes[frame], frame_name)
+ #frame_name = frame
+ #l_plotter = SeabornPlotter(l_dataframes[frame], frame_name)
# Plotter run
- l_plotter.plot_histogram_long()
+ #l_plotter.plot_histogram_long()
if __name__ == "__main__":
--
GitLab