From 7d0c68f55134dbcfb98564548e4fff695ac51227 Mon Sep 17 00:00:00 2001
From: Michael Reuscher <michael.reuscher@desy.de>
Date: Tue, 25 Jul 2023 10:32:09 +0200
Subject: [PATCH] create dataframes refactored
---
visualizer/visualizer/DataFrameCreator.py | 99 +++++++++++------------
visualizer/visualizer/SeabornPlotter.py | 14 ----
visualizer/visualizer/main.py | 4 +-
3 files changed, 50 insertions(+), 67 deletions(-)
diff --git a/visualizer/visualizer/DataFrameCreator.py b/visualizer/visualizer/DataFrameCreator.py
index 2975f7c..5815510 100644
--- a/visualizer/visualizer/DataFrameCreator.py
+++ b/visualizer/visualizer/DataFrameCreator.py
@@ -17,67 +17,64 @@ class DataFrameCreator:
merged_dfs[outer_key] = merged_dataframe_sorted
return merged_dfs
- def read_various_data(self, root, folder):
- for filename in folder:
- if filename.endswith('.dat'):
- file_path = os.path.join(root, filename)
- dataframe_name = os.path.splitext(filename)[0]
- dataframe_type = dataframe_name.split('-')[1]
- dataframe = pd.read_csv(file_path, delimiter=" ", header=0)
+ @staticmethod
+ def _set_dataframe(root, filename):
+ if filename.endswith('.dat'):
+ file_path = os.path.join(root, filename)
+ dataframe_name = os.path.splitext(filename)[0]
+ dataframe_type = dataframe_name.split('-')[1]
+ dataframe = pd.read_csv(file_path, delimiter=" ", header=0)
+ return dataframe, dataframe_type, dataframe_name
- if dataframe_type in self.v_dfs:
- inner_dict = self.v_dfs[dataframe_type]
- if dataframe_name in inner_dict:
- # DataFrame hinzufügen
- inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe],
- ignore_index=True)
- else:
- inner_dict[dataframe_name] = dataframe
- else:
- self.v_dfs[dataframe_type] = {
- dataframe_name: dataframe
- }
+ def read_various_data(self, root, filename):
+ dataframe, dataframe_type, dataframe_name = self._set_dataframe(root, filename)
+ if dataframe_type in self.v_dfs:
+ inner_dict = self.v_dfs[dataframe_type]
+ if dataframe_name in inner_dict:
+ # DataFrame hinzufügen
+ inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe],
+ ignore_index=True)
+ else:
+ inner_dict[dataframe_name] = dataframe
+ else:
+ self.v_dfs[dataframe_type] = {
+ dataframe_name: dataframe
+ }
- def read_long_data(self, root, folder):
- for filename in folder:
- if filename.endswith('.dat'):
- file_path = os.path.join(root, filename)
- dataframe_name = os.path.splitext(filename)[0]
- dataframe_type = dataframe_name.split('-')[1]
- dataframe = pd.read_csv(file_path, delimiter=" ", header=0)
- # Berechnung der Zeitdifferenz in Sekunden ab dem ersten Wert
- if not dataframe.empty:
- dataframe['start'] = pd.to_datetime(dataframe['start'], unit='s')
- start_time = dataframe['start'].iloc[0]
- dataframe['seconds_since_start'] = (dataframe['start'] - start_time).dt.total_seconds()
+ def read_long_data(self, root, filename):
+ dataframe, dataframe_type, dataframe_name = self._set_dataframe(root, filename)
+ # Berechnung der Zeitdifferenz in Sekunden ab dem ersten Wert
+ if not dataframe.empty:
+ dataframe['start'] = pd.to_datetime(dataframe['start'], unit='s')
+ start_time = dataframe['start'].iloc[0]
+ dataframe['seconds_since_start'] = (dataframe['start'] - start_time).dt.total_seconds()
- if dataframe_type in self.l_dfs:
- inner_dict = self.l_dfs[dataframe_type]
- if dataframe_name in inner_dict:
- # DataFrame hinzufügen
- inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe],
- ignore_index=True)
- else:
- inner_dict[dataframe_name] = dataframe
- else:
- self.l_dfs[dataframe_type] = {
- dataframe_name: dataframe
- }
+ if dataframe_type in self.l_dfs:
+ inner_dict = self.l_dfs[dataframe_type]
+ if dataframe_name in inner_dict:
+ # DataFrame hinzufügen
+ inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe],
+ ignore_index=True)
+ else:
+ inner_dict[dataframe_name] = dataframe
+ else:
+ self.l_dfs[dataframe_type] = {
+ dataframe_name: dataframe
+ }
def create(self):
- dfs = {}
for root, _, folder in os.walk(self.folder_path):
if os.path.basename(root) == "statistics":
- print("this was statistic")
- continue
+ for filename in folder:
+ print("this was statistic" + filename)
+ continue
elif os.path.basename(root) == "Data_Set_Long":
- self.read_long_data(root, folder)
+ for filename in folder:
+ self.read_long_data(root, filename)
else:
- self.read_various_data(root, folder)
+ for filename in folder:
+ self.read_various_data(root, filename)
various_dfs = self._merge_dataframes(self.v_dfs)
long_dfs = self._merge_dataframes(self.l_dfs)
return various_dfs, long_dfs
-
-
-
diff --git a/visualizer/visualizer/SeabornPlotter.py b/visualizer/visualizer/SeabornPlotter.py
index 740dfc0..940c0a0 100644
--- a/visualizer/visualizer/SeabornPlotter.py
+++ b/visualizer/visualizer/SeabornPlotter.py
@@ -3,8 +3,6 @@ import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib.offsetbox import OffsetImage, AnnotationBbox
import os
-import pandas as pd
-
sns.set_theme()
@@ -68,15 +66,3 @@ class SeabornPlotter:
plt.xticks(rotation=45)
plt.savefig(title + ".svg", format='svg')
plt.show()
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/visualizer/visualizer/main.py b/visualizer/visualizer/main.py
index 2647010..489cc2a 100644
--- a/visualizer/visualizer/main.py
+++ b/visualizer/visualizer/main.py
@@ -17,12 +17,13 @@ def main():
# Import Data
creator = DataFrameCreator(data_path)
v_dataframes, l_dataframes = creator.create()
+
+ # Plot
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)
-
# Plotter run
v_plotter.plot_histogram_various()
@@ -31,7 +32,6 @@ def main():
# Setup Plotter
frame_name = frame
l_plotter = SeabornPlotter(l_dataframes[frame], frame_name)
-
# Plotter run
l_plotter.plot_histogram_long()
--
GitLab