rename data file

Makefile

@@ -1,10 +1,10 @@
 all: install data train eval
 
-city_distances_full.csv: check generate_data.py
+city_distances.csv: check generate_data.py
 	@echo "Generating distance data..."
 	@bash -c 'time python generate_data.py --country US --workers 8 --chunk-size 4200'
 
-data: city_distances_full.csv
+data: city_distances.csv
 
 train: check train.py
 	@echo "Training embeddings..."

eval.py

@@ -66,7 +66,7 @@ if __name__ == "__main__":
     model_name = "sentence-transformers/all-MiniLM-L6-v2"
     base_model = SentenceTransformer(model_name, device="cuda")
 
-    data = pd.read_csv("city_distances_full.csv")
+    data = pd.read_csv("city_distances.csv")
     # data_sample = data.sample(1_000)
     checkpoint_dir = "checkpoints_absmax_split"  # no slash
     for checkpoint in sorted(glob.glob(f"{checkpoint_dir}/*")):

generate_data.py

@@ -32,7 +32,7 @@ parser.add_argument(
     "--output-file",
     help="Specify the name of the output file (file.csv)",
     type=str,
-    default="city_distances_full.csv",
+    default="city_distances.csv",
 )
 parser.add_argument(
     "--shuffle",

train.py

@@ -32,7 +32,7 @@ model = SentenceTransformer(model_name, device="cuda")
 #     (fake.city(), fake.city(), np.random.rand())
 #     for _ in range(num_examples)
 # ]
-data = pd.read_csv("city_distances_full.csv")
+data = pd.read_csv("city_distances.csv")
 MAX_DISTANCE = 20_037.5  # global max distance
 # MAX_DISTANCE = data["distance"].max()  # about 5k