From 4c86e6aa6750e28f1e0fbdd9cc3ab1ff110af85b Mon Sep 17 00:00:00 2001
From: Michael Reuscher <michael.reuscher@desy.de>
Date: Mon, 24 Jul 2023 12:13:11 +0200
Subject: [PATCH] bullshit in DataFrameCreator.py but i have to save
---
simrunner/simrunner.py | 1 -
visualizer/visualizer/DataFrameCreator.py | 86 ++++++++++++++++-------
visualizer/visualizer/SeabornPlotter.py | 60 ++++++++++------
visualizer/visualizer/main.py | 4 +-
4 files changed, 101 insertions(+), 50 deletions(-)
diff --git a/simrunner/simrunner.py b/simrunner/simrunner.py
index a6de2c7..851c2cd 100644
--- a/simrunner/simrunner.py
+++ b/simrunner/simrunner.py
@@ -139,4 +139,3 @@ event_list = create_event_list()
# Run detectorSimulation
run_sim(event_list, data_path, simulation_path, stat_path)
-
diff --git a/visualizer/visualizer/DataFrameCreator.py b/visualizer/visualizer/DataFrameCreator.py
index 50d3e94..4eaabcc 100644
--- a/visualizer/visualizer/DataFrameCreator.py
+++ b/visualizer/visualizer/DataFrameCreator.py
@@ -6,39 +6,73 @@ class DataFrameCreator:
def __init__(self, f_path):
self.folder_path = f_path
- def create_dataframes_data(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:
- 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)
-
- if dataframe_type in dfs:
- inner_dict = 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:
- dfs[dataframe_type] = {
- dataframe_name: dataframe
- }
-
+ @staticmethod
+ 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
+ return merged_dfs
+ def read_data(self, root, _, folder):
+ dataframe, dataframe_type, dataframe_name = "", "", ""
+ 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)
+ return dataframe, dataframe_type, dataframe_name
+
+ def create_dataframe_long(self, root, _, folder):
+ dfs = {}
+ for filename in folder:
+ if filename.endswith('.dat'):
+ dataframe, dataframe_type, dataframe_name = self.read_data(root, _, folder)
+ if dataframe_type in dfs:
+ inner_dict = dfs[dataframe_type]
+ if dataframe_name in inner_dict:
+ inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe],
+ ignore_index=True)
+ else:
+ inner_dict[dataframe_name] = dataframe
+ else:
+ dfs[dataframe_type] = {
+ dataframe_name: dataframe
+ }
+ print(dfs)
+ return dfs
+
+ def create_dataframe_statistics(self, root, _, folder):
+ print("statistics" + root + folder)
+
+ def create_dataframes_various(self, root, _, folder):
+ dfs = {}
+
+ dataframe, dataframe_type, dataframe_name = self.read_data(root, _, folder)
+ if dataframe_type in dfs:
+ inner_dict = dfs[dataframe_type]
+ if dataframe_name in inner_dict:
+ inner_dict[dataframe_name] = pd.concat([inner_dict[dataframe_name], dataframe], ignore_index=True)
+ else:
+ inner_dict[dataframe_name] = dataframe
+ else:
+ dfs[dataframe_type] = {
+ dataframe_name: dataframe
+ }
+ merged_dfs = self._merge_dataframes(dfs)
return merged_dfs
+ def create(self):
+ various_frames = {}
+ for root, _, folder in os.walk(self.folder_path):
+ if os.path.basename(root) == "statistics":
+ statistic_frames = self.create_dataframe_statistics(root, _, folder)
+ elif os.path.basename(root) == "Data_Set_Long":
+ long_frames = self.create_dataframe_long(root, _, folder)
+ else:
+ self.create_dataframes_various(root, _, folder)
+ return various_frames
diff --git a/visualizer/visualizer/SeabornPlotter.py b/visualizer/visualizer/SeabornPlotter.py
index 48a836f..186aae4 100644
--- a/visualizer/visualizer/SeabornPlotter.py
+++ b/visualizer/visualizer/SeabornPlotter.py
@@ -14,45 +14,63 @@ class SeabornPlotter:
self.name = name
self.current_plot = None
- def plot(self):
- df = self.dataframe
- x = df['size']
- y = df['duration']
- title = "Procedure: {}".format(self.name)
+ @staticmethod
+ def _add_logo(logo_path, logo_size, logo_x, logo_y):
+ current_directory = os.path.dirname(os.path.abspath(__file__))
+ logo_path = os.path.join(current_directory, logo_path)
+ logo_img = plt.imread(logo_path)
+ imagebox = OffsetImage(logo_img, zoom=logo_size)
+ ab = AnnotationBbox(imagebox, (logo_x, logo_y), xycoords='axes fraction', frameon=False)
+ plt.gca().add_artist(ab)
- # Bin Grenzen festlegen
+ @staticmethod
+ def _prepare_bins(df):
n = df['size'].nunique()
bins_x = np.zeros(n + 1, dtype=np.float64)
bins_x[0] = 0.75 * (1 << 4)
for i in range(1, n + 1):
bins_x[i] = bins_x[i - 1] * 2
bins_y = np.logspace(-6, 0, num=101)
+ return bins_x, bins_y
- # Achsen und Plot definieren
+ @staticmethod
+ def plot_histogram_various(x, y, title, bins_x, bins_y):
f, ax = plt.subplots(figsize=(16, 9))
- sns.histplot(x=x, y=y, color="blue", bins=[bins_x, bins_y],)
-
- # Setze die Skala der x-Achse auf logarithmisch
+ sns.histplot(x=x, y=y, color="blue", bins=[bins_x, bins_y])
ax.set_xscale('log')
ax.set_yscale('log')
+ ax.set_xlabel("Data size [Bytes]")
+ ax.set_ylabel("Time/Event [s]")
+ plt.title(title)
+ plt.grid(True)
+ plt.xticks(rotation=45)
- # Setze die Beschriftungen
+ @staticmethod
+ def plot_histogram_long(x, y, title, bins_x, bins_y):
+ f, ax = plt.subplots(figsize=(16, 9))
+ sns.histplot(x=x, y=y, color="blue", bins=[bins_x, bins_y])
+ ax.set_xscale('log')
+ ax.set_yscale('log')
ax.set_xlabel("Data size [Bytes]")
ax.set_ylabel("Time/Event [s]")
plt.title(title)
plt.grid(True)
plt.xticks(rotation=45)
- current_directory = os.path.dirname(os.path.abspath(__file__))
- logo_path = os.path.join(current_directory, "desy_logo.png")
- logo_img = plt.imread(logo_path)
- logo_size = 0.15
- logo_x = 1.065
- logo_y = 1.04
- imagebox = OffsetImage(logo_img, zoom=logo_size)
- ab = AnnotationBbox(imagebox, (logo_x, logo_y), xycoords='axes fraction', frameon=False)
- plt.gca().add_artist(ab)
- # Speichern und Anzeigen
+ def plot(self):
+ df = self.dataframe
+
+ # if self.name
+ x = df['size']
+ y = df['duration']
+ title = "Procedure: {}".format(self.name)
+
+ bins_x, bins_y = self._prepare_bins(df)
+ self.plot_histogram_various(x, y, title, bins_x, bins_y)
+
+ self._add_logo("desy_logo.png", logo_size=0.15, logo_x=1.065, logo_y=1.04)
+
+ # Save and View
plt.savefig(title + ".svg", format='svg')
plt.show()
diff --git a/visualizer/visualizer/main.py b/visualizer/visualizer/main.py
index 7235961..0742a25 100644
--- a/visualizer/visualizer/main.py
+++ b/visualizer/visualizer/main.py
@@ -16,12 +16,12 @@ def main():
# Import Data
creator = DataFrameCreator(data_path)
- dataframes = creator.create_dataframes_data()
+ dataframes = creator.create()
for frame in dataframes.keys():
if not dataframes[frame].empty:
# Setup Plotter
frame_name = frame
-
+ print(frame_name)
plotter = SeabornPlotter(dataframes[frame], frame_name)
# Plotter run
--
GitLab