feat: measuring code + graph generator code

2025-12-15 22:53:32 +01:00 · 2025-12-15 22:53:32 +01:00 · f3b07c1df3
commit f3b07c1df3
parent dd0b3d3945
6 changed files with 325 additions and 140 deletions
--- a/make_graphs.py
+++ b/make_graphs.py
@ -0,0 +1,78 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+
+if __name__ == "__main__":
+    # read in the csv
+    df = pd.read_csv("./results/compress/compression_results.csv")
+
+    for model_type in df["model_type"].unique():
+        model_df = df[df["model_type"] == model_type]
+
+        # execution time
+        plt.figure()
+        grouped = model_df.groupby("context_length")["compression_time"].mean() / 1e9
+        labels = grouped.index.astype(str)  # "128", "256"
+        x = np.arange(len(labels))  # [0, 1]
+
+        plt.bar(x, grouped.values, width=0.6)
+        plt.title(f"{model_type} mean compression time")
+        plt.xticks(x, labels)
+        plt.xlabel("Context length")
+        plt.ylabel("Mean compression time [s]")
+        plt.tight_layout()
+        plt.savefig(f"./graphs/{model_type}_{}_compression_time.png")
+
+        plt.figure()
+        grouped = model_df.groupby("context_length")["decompression_time"].mean() / 1e9
+        labels = grouped.index.astype(str)  # "128", "256"
+        x = np.arange(len(labels))  # [0, 1]
+
+        plt.bar(x, grouped.values, width=0.6)
+        plt.title(f"{model_type} mean decompression time")
+        plt.xticks(x, labels)
+        plt.xlabel("Context length")
+        plt.ylabel("Mean decompression time [s]")
+        plt.tight_layout()
+        plt.savefig(f"./graphs/{model_type}_{}_decompression_time.png")
+
+        # accuracy
+        plt.figure()
+        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["match_percentage"] * 100,
+            height=bar_height,
+            label="256"
+        )
+
+        plt.barh(
+            y + bar_height / 2,
+            c128["match_percentage"] * 100,
+            height=bar_height,
+            label="128"
+        )
+        plt.yticks(y, files)
+        plt.title(f"{model_type} time for different context lengths")
+        plt.xlabel("accuracy")
+        plt.ylabel("Filename")
+        plt.legend()
+        plt.savefig(f"./graphs/{model_type}_{}_accuracy.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"] / 1_000_000, c256["compressed_file_size"] / 1_000_000, label="256")
+        plt.plot(c128["original_file_size"] / 1_000_000, c128["compressed_file_size"] / 1_000_000, label="128")
+        plt.title(f"{model_type} compressed file evolution")
+        plt.xlabel("Original file size [MB]")
+        plt.ylabel("Compressed file size [MB]")
+        plt.legend()
+        plt.savefig(f"./graphs/{model_type}_{}_compression_ratio.png")