chore: Restructure
# Conflicts: # config/measure.py # results/compression_results_auto_small.csv
This commit is contained in:
parent
dd938489ef
commit
2f869a8a7a
GPG key ID:
38297DE43F75FFE2
41 changed files with 8 additions and 21 deletions
132
results/make_graphs.py
Normal file
132
results/make_graphs.py
Normal file
|
|
@ -0,0 +1,132 @@
|
|||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn as sns
|
||||
import numpy as np
|
||||
|
||||
if __name__ == "__main__":
|
||||
# read in the csv
|
||||
df = pd.read_csv("compression_results.csv")
|
||||
|
||||
for dataset_type in df["dataset_type"].unique():
|
||||
for model_type in df["model_type"].unique():
|
||||
dataset_df = df[df["dataset_type"] == dataset_type]
|
||||
model_df = dataset_df[dataset_df["model_type"] == model_type].copy()
|
||||
|
||||
# execution time
|
||||
plt.figure()
|
||||
model_df["original_file_size_mb"] = model_df["original_file_size"] / 1e6
|
||||
model_df["compression_time_s"] = model_df["compression_time"] / 1e9
|
||||
model_df["decompression_time_s"] = model_df["decompression_time"] / 1e9
|
||||
# compression
|
||||
sns.lineplot(
|
||||
data=model_df,
|
||||
x="original_file_size_mb",
|
||||
y="compression_time_s",
|
||||
hue="context_length",
|
||||
palette="Set1",
|
||||
markers=True,
|
||||
legend="brief",
|
||||
linestyle="-"
|
||||
)
|
||||
# decompression
|
||||
sns.lineplot(
|
||||
data=model_df,
|
||||
x="original_file_size_mb",
|
||||
y="decompression_time_s",
|
||||
hue="context_length",
|
||||
palette="Set1",
|
||||
markers=True,
|
||||
legend=False,
|
||||
linestyle="--"
|
||||
)
|
||||
plt.title(f"{model_type.capitalize()} compression and decompression time: {dataset_type}")
|
||||
plt.xlabel("file size [MB]")
|
||||
plt.ylabel("Time [s]")
|
||||
plt.yscale("log")
|
||||
plt.legend([f"{style}, {c_type}" for style, c_type in zip(["Solid", "Dashed"], ["compression", "decompression"])])
|
||||
plt.tight_layout()
|
||||
plt.savefig(f"./graphs/{model_type}_{dataset_type}_execution_time.png")
|
||||
|
||||
# compression ratio
|
||||
plt.figure()
|
||||
c256 = model_df[model_df["context_length"] == 256]
|
||||
c128 = model_df[model_df["context_length"] == 128]
|
||||
|
||||
plt.plot(c256["original_file_size"] / 1e6, c256["compressed_file_size"] / 1e6, label="256")
|
||||
plt.plot(c128["original_file_size"] / 1e6, c128["compressed_file_size"] / 1e6, label="128")
|
||||
plt.title(f"{model_type.capitalize()} compressed file evolution: {dataset_type}")
|
||||
plt.xlabel("Original file size [MB]")
|
||||
plt.ylabel("Compressed file size [MB]")
|
||||
plt.legend()
|
||||
plt.savefig(f"./graphs/{model_type}_{dataset_type}_compression_ratio.png")
|
||||
|
||||
|
||||
# if model_type == "cnn":
|
||||
# import numpy as np
|
||||
#
|
||||
# plt.figure()
|
||||
# for length, linestyle in [(128, '-'), (256, '--')]:
|
||||
# # extrapolate execution time to larger files
|
||||
# x = model_df[model_df["context_length"] == length]["original_file_size"] / 1e6
|
||||
# y = model_df[model_df["context_length"] == length]["compression_time"]
|
||||
# y_decom = model_df[model_df["context_length"] == length]["decompression_time"]
|
||||
#
|
||||
# b1, loga1 = np.polyfit(x, np.log(y), 1)
|
||||
# b2, loga2 = np.polyfit(x, np.log(y_decom), 1)
|
||||
#
|
||||
# x_comp = np.linspace(0, 40, 1000)
|
||||
# x_decomp = np.linspace(0, 40, 1000)
|
||||
# a1 = np.exp(loga1)
|
||||
# a2 = np.exp(loga2)
|
||||
#
|
||||
#
|
||||
# plt.plot(
|
||||
# x_comp, a1 * np.exp(x_comp),
|
||||
# label=f"{length} compression",
|
||||
# linestyle=linestyle
|
||||
# )
|
||||
# plt.plot(
|
||||
# x_decomp, a2 * np.exp(x_decomp),
|
||||
# label=f"{length} decompression",
|
||||
# linestyle=linestyle
|
||||
# )
|
||||
#
|
||||
#
|
||||
#
|
||||
# plt.legend()
|
||||
# plt.title(f"Extrapolated execution time for CNN compression and decompression")
|
||||
# plt.xlabel("File size [MB]")
|
||||
# plt.ylabel("Time [s]")
|
||||
# plt.tight_layout()
|
||||
# plt.savefig(f"./graphs/{model_type}_{dataset_type}_extrapolated_execution_time.png")
|
||||
|
||||
for model_type in df["model_type"].unique():
|
||||
model_df = df[df["model_type"] == model_type]
|
||||
|
||||
plt.figure(figsize=(10, 4))
|
||||
bar_height = 0.25
|
||||
files = model_df["input_file_name"].unique()
|
||||
y = np.arange(len(files))
|
||||
c256 = model_df[model_df["context_length"] == 256]
|
||||
c128 = model_df[model_df["context_length"] == 128]
|
||||
|
||||
plt.barh(
|
||||
y - bar_height / 2,
|
||||
c256["mse_loss"],
|
||||
height=bar_height,
|
||||
label="256"
|
||||
)
|
||||
|
||||
plt.barh(
|
||||
y + bar_height / 2,
|
||||
c128["mse_loss"],
|
||||
height=bar_height,
|
||||
label="128"
|
||||
)
|
||||
plt.yticks(y, files, rotation=45, ha="right")
|
||||
plt.title(f"MSE loss for different context lengths")
|
||||
plt.xlabel("MSE loss")
|
||||
plt.ylabel("Filename")
|
||||
plt.legend()
|
||||
plt.tight_layout()
|
||||
plt.savefig(f"./graphs/{model_type}_loss.png")
|
||||
Reference in a new issue