hotsixman/fumen-measure-analyze
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

xgboost

Browse Source
This commit is contained in:
hotsixman
2026-04-25 03:04:52 +09:00
parent 8a8c0c9713
commit da4201fb20
11 changed files with 17829 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
train/train_xgboost.py
View File

@@ -3,11 +3,11 @@ import csv
import json
import math
import os
import random
import joblib
import numpy as np
from xgboost import XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_absolute_error
@@ -15,7 +15,9 @@ from sklearn.metrics import mean_absolute_error
# Hyper Parameters
# =========================================================
TEST_SIZE = 0.2
TRAIN_SIZE = 0
VALID_SIZE = 0
RANDOM_STATE = 42
N_ESTIMATORS = 500
@@ -27,7 +29,7 @@ COLSAMPLE_BYTREE = 0.8
CONTINUE_TRAINING = True
# 예측 성공으로 간주할 허용 오차
ERROR_TOLERANCE = 0.2
ERROR_TOLERANCE = 0.1
# =========================================================
# 파일명
@@ -50,6 +52,10 @@ IGNORE_KEYS = {
}
# =========================================================
# safe float
# =========================================================
def safe_float(value):
if value is None:
return 0.0
@@ -62,10 +68,16 @@ def safe_float(value):
return x
# =========================================================
# train
# =========================================================
def train_model(
working_dir: str,
data_dir: str
):
random.seed(RANDOM_STATE)
# =====================================================
# path
# =====================================================
@@ -129,14 +141,14 @@ def train_model(
])
# =====================================================
# measure.csv
# dataset build
# =====================================================
X = []
y = []
dataset = []
with open(measure_path, "r", encoding="utf-8") as f:
reader = csv.reader(f)
next(reader, None)
for row in reader:
@@ -163,29 +175,59 @@ def train_model(
for k in feature_names
]
X.append(features)
y.append(measure)
dataset.append((
features,
measure
))
if len(X) == 0:
raise ValueError("No training data")
# =====================================================
# shuffle
# =====================================================
X = np.array(X, dtype=np.float32)
y = np.array(y, dtype=np.float32)
random.shuffle(dataset)
print(f"Dataset Size: {len(X)}")
print(f"Feature Count: {len(feature_names)}")
required_size = TRAIN_SIZE + VALID_SIZE
if len(dataset) < required_size:
raise ValueError(
f"Not enough dataset "
f"({len(dataset)} < {required_size})"
)
# =====================================================
# split
# =====================================================
X_train, X_valid, y_train, y_valid = train_test_split(
X,
y,
test_size=TEST_SIZE,
random_state=RANDOM_STATE
train_dataset = dataset[:TRAIN_SIZE]
valid_dataset = dataset[
TRAIN_SIZE:
TRAIN_SIZE + VALID_SIZE
]
X_train = np.array(
[x for x, _ in train_dataset],
dtype=np.float32
)
y_train = np.array(
[y for _, y in train_dataset],
dtype=np.float32
)
X_valid = np.array(
[x for x, _ in valid_dataset],
dtype=np.float32
)
y_valid = np.array(
[y for _, y in valid_dataset],
dtype=np.float32
)
print(f"Train Size: {len(X_train)}")
print(f"Valid Size: {len(X_valid)}")
print(f"Feature Count: {len(feature_names)}")
# =====================================================
# scaler
# =====================================================
@@ -251,6 +293,7 @@ def train_model(
accuracy = correct / len(y_valid)
print(f"\nMAE: {mae:.4f}")
print(
f"Accuracy "
f"(±{ERROR_TOLERANCE}): "
@@ -304,8 +347,21 @@ if __name__ == "__main__":
"--dataDir",
required=True
)
parser.add_argument(
"--trainSize",
required=True
)
parser.add_argument(
"--validSize",
required=True
)
args = parser.parse_args()
TRAIN_SIZE = int(args.trainSize)
VALID_SIZE = int(args.validSize)
train_model(
args.workingDir,

94
train/train_xgboost_pick.py → train/train_xgboost_full.py
View File

@@ -3,11 +3,11 @@ import csv
import json
import math
import os
import random
import joblib
import numpy as np
from xgboost import XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_absolute_error
@@ -15,9 +15,7 @@ from sklearn.metrics import mean_absolute_error
# Hyper Parameters
# =========================================================
TRAIN_SIZE = 0
VALID_SIZE = 0
TEST_SIZE = 0.2
RANDOM_STATE = 42
N_ESTIMATORS = 500
@@ -29,7 +27,7 @@ COLSAMPLE_BYTREE = 0.8
CONTINUE_TRAINING = True
# 예측 성공으로 간주할 허용 오차
ERROR_TOLERANCE = 0.5
ERROR_TOLERANCE = 0.1
# =========================================================
# 파일명
@@ -52,10 +50,6 @@ IGNORE_KEYS = {
}
# =========================================================
# safe float
# =========================================================
def safe_float(value):
if value is None:
return 0.0
@@ -68,16 +62,10 @@ def safe_float(value):
return x
# =========================================================
# train
# =========================================================
def train_model(
working_dir: str,
data_dir: str
):
random.seed(RANDOM_STATE)
# =====================================================
# path
# =====================================================
@@ -141,14 +129,14 @@ def train_model(
])
# =====================================================
# dataset build
# measure.csv
# =====================================================
dataset = []
X = []
y = []
with open(measure_path, "r", encoding="utf-8") as f:
reader = csv.reader(f)
next(reader, None)
for row in reader:
@@ -175,59 +163,29 @@ def train_model(
for k in feature_names
]
dataset.append((
features,
measure
))
X.append(features)
y.append(measure)
# =====================================================
# shuffle
# =====================================================
if len(X) == 0:
raise ValueError("No training data")
random.shuffle(dataset)
X = np.array(X, dtype=np.float32)
y = np.array(y, dtype=np.float32)
required_size = TRAIN_SIZE + VALID_SIZE
if len(dataset) < required_size:
raise ValueError(
f"Not enough dataset "
f"({len(dataset)} < {required_size})"
)
print(f"Dataset Size: {len(X)}")
print(f"Feature Count: {len(feature_names)}")
# =====================================================
# split
# =====================================================
train_dataset = dataset[:TRAIN_SIZE]
valid_dataset = dataset[
TRAIN_SIZE:
TRAIN_SIZE + VALID_SIZE
]
X_train = np.array(
[x for x, _ in train_dataset],
dtype=np.float32
X_train, X_valid, y_train, y_valid = train_test_split(
X,
y,
test_size=TEST_SIZE,
random_state=RANDOM_STATE
)
y_train = np.array(
[y for _, y in train_dataset],
dtype=np.float32
)
X_valid = np.array(
[x for x, _ in valid_dataset],
dtype=np.float32
)
y_valid = np.array(
[y for _, y in valid_dataset],
dtype=np.float32
)
print(f"Train Size: {len(X_train)}")
print(f"Valid Size: {len(X_valid)}")
print(f"Feature Count: {len(feature_names)}")
# =====================================================
# scaler
# =====================================================
@@ -293,7 +251,6 @@ def train_model(
accuracy = correct / len(y_valid)
print(f"\nMAE: {mae:.4f}")
print(
f"Accuracy "
f"(±{ERROR_TOLERANCE}): "
@@ -347,21 +304,8 @@ if __name__ == "__main__":
"--dataDir",
required=True
)
parser.add_argument(
"--trainSize",
required=True
)
parser.add_argument(
"--validSize",
required=True
)
args = parser.parse_args()
TRAIN_SIZE = int(args.trainSize)
VALID_SIZE = int(args.validSize)
train_model(
args.workingDir,