chore: Restructure

# Conflicts:
#	config/measure.py
#	results/compression_results_auto_small.csv

config/measure.py

@@ -65,12 +65,12 @@ if __name__ == "__main__":
     ]
 
     models = [
-        ("auto-genome-full-256.pt", 256, "autoencoder", files_genome + files_genome_cnn),
-        ("auto-genome-full-128.pt", 128, "autoencoder", files_genome + files_genome_cnn),
+        ("auto-genome-full-256.pt", 256, "autoencoder", files_genome),
+        ("auto-genome-full-128.pt", 128, "autoencoder", files_genome),
         ("cnn-genome-full-256.pt", 256, "cnn", files_genome_cnn),
         ("cnn-genome-full-128.pt", 128, "cnn", files_genome_cnn),
-        ("auto-enwik9-full-256.pt", 256, "autoencoder", files_enwik9 + files_enwik9_cnn),
-        ("auto-enwik9-full-128.pt", 128, "autoencoder", files_enwik9 + files_enwik9_cnn),
+        ("auto-enwik9-full-256.pt", 256, "autoencoder", files_enwik9),
+        ("auto-enwik9-full-128.pt", 128, "autoencoder", files_enwik9),
         ("cnn-enwik9-full-256.pt", 256, "cnn", files_enwik9_cnn),
         ("cnn-enwik9-full-128.pt", 128, "cnn", files_enwik9_cnn),
     ]

pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
     "fsspec==2024.9.0",
     "lorem>=0.1.1",
     "arithmeticencodingpython",
-    "pandas-stubs~=2.3.3",
+    "pandas-stubs==2.3.3.251201",
     "seaborn>=0.13.2",
 ]
 

results/compress/compression_results_auto_small.csv

@@ -1,13 +0,0 @@
-model_type,model_name,context_length,dataset_type,input_file_name,original_file_size,compressed_file_size,mse_loss,compression_time,decompression_time
-autoencoder,auto-genome-full-256.pt,256,genome,genome_small.fna,1367,1392,220.29188537597656,237708436,29378622
-autoencoder,auto-genome-full-256.pt,256,genome,genome_xsmall.fna,1043,1160,263.97027587890625,5293080,4488761
-autoencoder,auto-genome-full-256.pt,256,genome,genome_xxsmall.fna,800,928,319.5350036621094,4873340,4381310
-autoencoder,auto-genome-full-128.pt,128,genome,genome_small.fna,1367,2816,120.52304077148438,251659317,5284661
-autoencoder,auto-genome-full-128.pt,128,genome,genome_xsmall.fna,1043,2304,133.8379669189453,152590538,4432469
-autoencoder,auto-genome-full-128.pt,128,genome,genome_xxsmall.fna,800,1792,159.2862548828125,153622653,4532139
-autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_small.txt,1022,976,746.8033447265625,6699780,22065927
-autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xsmall.txt,825,976,787.5345458984375,3715750,3665629
-autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xxsmall.txt,492,488,828.8658447265625,4892560,4176979
-autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_small.txt,1022,2016,231.42955017089844,5005880,4400159
-autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xsmall.txt,825,1764,236.55636596679688,5024449,4180100
-autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xxsmall.txt,492,1008,237.20529174804688,4856779,4145850

results/cpu_compression_graphs.py

@@ -110,5 +110,5 @@ def plot_compression_metrics(csv_path, output_dir="results/compress/plots"):
 
 if __name__ == "__main__":
     # You can modify this path to point to your CSV file
-    csv_path = "results/compress/compression_metrics_20251216_182603.csv"
+    csv_path = "compression_metrics_20251216_182603.csv"
     plot_compression_metrics(csv_path)

results/make_graphs.py

@@ -5,7 +5,7 @@ import numpy as np
 
 if __name__ == "__main__":
     # read in the csv
-    df = pd.read_csv("./results/compress/compression_results.csv")
+    df = pd.read_csv("compression_results.csv")
 
     for dataset_type in df["dataset_type"].unique():
         for model_type in df["model_type"].unique():

uv.lock

@@ -1761,7 +1761,7 @@ requires-dist = [
     { name = "matplotlib", marker = "extra == 'dev'", specifier = ">=3.10.7" },
     { name = "memray", marker = "extra == 'dev'", specifier = ">=1.19.1" },
     { name = "optuna", marker = "extra == 'dev'", specifier = "==4.5.0" },
-    { name = "pandas-stubs", specifier = "~=2.3.3" },
+    { name = "pandas-stubs", specifier = "==2.3.3.251201" },
     { name = "regex", marker = "extra == 'dataset'", specifier = ">=2025.11.3" },
     { name = "seaborn", specifier = ">=0.13.2" },
     { name = "torch", marker = "extra == 'dev'", specifier = "==2.9.0" },