refactor: 清理测试文件和2019相关代码
- 删除测试脚本: test_2026_classification.py, test_lagllama.py, test_timesfm.py, test_ttm.py - 删除2019相关文件: analyze_2019_*, apply_2019_*, dlinear_2019_*, three_models_2019_* - 添加集成模型相关代码和分析脚本 - 添加N-BEATS模型和CatBoost分类模型
This commit is contained in:
crypto_predictor committed
1 parent
c74f4f6949
commit
1bd9d25f60
33 files changed
+6557
-233
No files matched your search
@@ -0,0 +1,271 @@
|
||||
"""训练CatBoost二分类模型用于BTC 1小时涨跌预测"""
|
||||
|
||||
import sys
|
||||
import os
|
||||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import pandas_ta as ta
|
||||
from catboost import CatBoostClassifier, Pool
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import classification_report, accuracy_score, confusion_matrix
|
||||
from data.fetcher import BinanceDataFetcher
|
||||
import pickle
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
def add_technical_features(df):
|
||||
"""添加丰富的技术指标特征"""
|
||||
df = df.copy()
|
||||
|
||||
# 基础价格特征
|
||||
df['price_change'] = df['close'] - df['open']
|
||||
df['price_change_pct'] = (df['close'] - df['open']) / df['open']
|
||||
df['high_low_range'] = df['high'] - df['low']
|
||||
df['high_low_range_pct'] = (df['high'] - df['low']) / df['low']
|
||||
|
||||
# 移动平均线
|
||||
df['sma_7'] = ta.sma(df['close'], length=7)
|
||||
df['sma_25'] = ta.sma(df['close'], length=25)
|
||||
df['sma_99'] = ta.sma(df['close'], length=99)
|
||||
df['ema_12'] = ta.ema(df['close'], length=12)
|
||||
df['ema_26'] = ta.ema(df['close'], length=26)
|
||||
|
||||
# RSI
|
||||
df['rsi_14'] = ta.rsi(df['close'], length=14)
|
||||
df['rsi_7'] = ta.rsi(df['close'], length=7)
|
||||
|
||||
# MACD
|
||||
macd = ta.macd(df['close'])
|
||||
if macd is not None and not macd.empty:
|
||||
df['macd'] = macd.iloc[:, 0]
|
||||
df['macd_hist'] = macd.iloc[:, 1]
|
||||
df['macd_signal'] = macd.iloc[:, 2]
|
||||
|
||||
# 布林带
|
||||
bbands = ta.bbands(df['close'], length=20)
|
||||
if bbands is not None and not bbands.empty:
|
||||
df['bb_upper'] = bbands.iloc[:, 0]
|
||||
df['bb_mid'] = bbands.iloc[:, 1]
|
||||
df['bb_lower'] = bbands.iloc[:, 2]
|
||||
df['bb_width'] = (df['bb_upper'] - df['bb_lower']) / df['bb_mid']
|
||||
df['bb_position'] = (df['close'] - df['bb_lower']) / (df['bb_upper'] - df['bb_lower'])
|
||||
|
||||
# ATR (Average True Range)
|
||||
df['atr'] = ta.atr(df['high'], df['low'], df['close'], length=14)
|
||||
|
||||
# 成交量特征
|
||||
df['volume_sma_7'] = ta.sma(df['volume'], length=7)
|
||||
df['volume_ratio'] = df['volume'] / df['volume_sma_7']
|
||||
|
||||
# OBV (On-Balance Volume)
|
||||
df['obv'] = ta.obv(df['close'], df['volume'])
|
||||
|
||||
# Stochastic Oscillator
|
||||
stoch = ta.stoch(df['high'], df['low'], df['close'])
|
||||
if stoch is not None and not stoch.empty:
|
||||
df['stoch_k'] = stoch.iloc[:, 0]
|
||||
df['stoch_d'] = stoch.iloc[:, 1]
|
||||
|
||||
# ADX (Average Directional Index)
|
||||
adx = ta.adx(df['high'], df['low'], df['close'])
|
||||
if adx is not None and not adx.empty:
|
||||
df['adx'] = adx.iloc[:, 0]
|
||||
|
||||
# 价格动量
|
||||
df['momentum_1'] = df['close'].pct_change(1)
|
||||
df['momentum_3'] = df['close'].pct_change(3)
|
||||
df['momentum_7'] = df['close'].pct_change(7)
|
||||
|
||||
return df
|
||||
|
||||
|
||||
def create_labels(df, forecast_horizon=1):
|
||||
"""创建二分类标签"""
|
||||
df = df.copy()
|
||||
df['future_price'] = df['close'].shift(-forecast_horizon)
|
||||
df['future_return'] = (df['future_price'] - df['close']) / df['close']
|
||||
df['label'] = (df['future_return'] > 0).astype(int) # 1=涨, 0=跌
|
||||
return df[:-forecast_horizon]
|
||||
|
||||
|
||||
def prepare_data(df):
|
||||
"""准备训练数据"""
|
||||
# 添加技术指标
|
||||
df = add_technical_features(df)
|
||||
|
||||
# 创建标签
|
||||
df = create_labels(df, forecast_horizon=1)
|
||||
|
||||
# 删除NaN
|
||||
df = df.dropna().reset_index(drop=True)
|
||||
|
||||
# 选择特征列（排除原始时间戳和标签列）
|
||||
exclude_cols = ['timestamp', 'label', 'future_price', 'future_return']
|
||||
feature_cols = [col for col in df.columns if col not in exclude_cols]
|
||||
|
||||
X = df[feature_cols]
|
||||
y = df['label']
|
||||
|
||||
return X, y, feature_cols
|
||||
|
||||
|
||||
def main():
|
||||
print("="*80)
|
||||
print("训练CatBoost二分类模型 - BTC 1小时涨跌预测")
|
||||
print("="*80)
|
||||
|
||||
# ========== 步骤1: 获取数据 ==========
|
||||
print("\n[1/5] 获取历史数据...")
|
||||
|
||||
fetcher = BinanceDataFetcher()
|
||||
|
||||
# 获取训练数据 (2020-2024)
|
||||
df_train = fetcher.fetch_ohlcv('BTC', '1h', start_date='2020-01-01',
|
||||
end_date='2024-12-31', use_cache=True)
|
||||
|
||||
# 获取验证数据 (2025)
|
||||
df_val = fetcher.fetch_ohlcv('BTC', '1h', start_date='2025-01-01',
|
||||
end_date='2025-12-31', use_cache=True)
|
||||
|
||||
print(f"✓ 训练数据: {len(df_train)} 行 ({df_train['timestamp'].min()} 至 {df_train['timestamp'].max()})")
|
||||
print(f"✓ 验证数据: {len(df_val)} 行 ({df_val['timestamp'].min()} 至 {df_val['timestamp'].max()})")
|
||||
|
||||
# ========== 步骤2: 特征工程 ==========
|
||||
print("\n[2/5] 特征工程...")
|
||||
|
||||
X_train, y_train, feature_cols = prepare_data(df_train)
|
||||
X_val, y_val, _ = prepare_data(df_val)
|
||||
|
||||
print(f"✓ 特征数量: {len(feature_cols)}")
|
||||
print(f"✓ 训练样本: {len(X_train)} (涨: {(y_train==1).sum()}, 跌: {(y_train==0).sum()})")
|
||||
print(f"✓ 验证样本: {len(X_val)} (涨: {(y_val==1).sum()}, 跌: {(y_val==0).sum()})")
|
||||
|
||||
# 显示部分特征
|
||||
print(f"\n特征列表 (前20个):")
|
||||
for i, col in enumerate(feature_cols[:20], 1):
|
||||
print(f" {i:2d}. {col}")
|
||||
if len(feature_cols) > 20:
|
||||
print(f" ... 还有 {len(feature_cols)-20} 个特征")
|
||||
|
||||
# ========== 步骤3: 训练CatBoost模型 ==========
|
||||
print("\n[3/5] 训练CatBoost模型...")
|
||||
|
||||
# 创建CatBoost数据池
|
||||
train_pool = Pool(X_train, y_train)
|
||||
val_pool = Pool(X_val, y_val)
|
||||
|
||||
# 配置CatBoost参数
|
||||
model = CatBoostClassifier(
|
||||
iterations=1000,
|
||||
learning_rate=0.05,
|
||||
depth=6,
|
||||
l2_leaf_reg=3,
|
||||
loss_function='Logloss',
|
||||
eval_metric='Accuracy',
|
||||
random_seed=42,
|
||||
verbose=100,
|
||||
early_stopping_rounds=50,
|
||||
task_type='CPU', # 如果有GPU可改为'GPU'
|
||||
)
|
||||
|
||||
# 训练模型
|
||||
model.fit(
|
||||
train_pool,
|
||||
eval_set=val_pool,
|
||||
use_best_model=True,
|
||||
plot=False
|
||||
)
|
||||
|
||||
print(f"\n✓ 训练完成")
|
||||
print(f" 最佳迭代轮次: {model.get_best_iteration()}")
|
||||
print(f" 最佳验证准确率: {model.get_best_score()['validation']['Accuracy']:.4f}")
|
||||
|
||||
# ========== 步骤4: 评估模型 ==========
|
||||
print("\n[4/5] 评估模型性能...")
|
||||
|
||||
# 训练集预测
|
||||
y_train_pred = model.predict(X_train)
|
||||
train_acc = accuracy_score(y_train, y_train_pred)
|
||||
|
||||
# 验证集预测
|
||||
y_val_pred = model.predict(X_val)
|
||||
val_acc = accuracy_score(y_val, y_val_pred)
|
||||
|
||||
print(f"\n训练集性能：")
|
||||
print(f" 准确率: {train_acc*100:.2f}%")
|
||||
|
||||
print(f"\n验证集性能：")
|
||||
print(f" 准确率: {val_acc*100:.2f}%")
|
||||
|
||||
# 混淆矩阵
|
||||
cm = confusion_matrix(y_val, y_val_pred)
|
||||
print(f"\n混淆矩阵 (验证集):")
|
||||
print(f" 预测↓ 预测↑")
|
||||
print(f"真实↓ {cm[0,0]:4d} {cm[0,1]:4d}")
|
||||
print(f"真实↑ {cm[1,0]:4d} {cm[1,1]:4d}")
|
||||
|
||||
# 分类报告
|
||||
print(f"\n分类报告 (验证集):")
|
||||
print(classification_report(y_val, y_val_pred, target_names=['下跌', '上涨']))
|
||||
|
||||
# 特征重要性 (Top 20)
|
||||
feature_importance = model.get_feature_importance()
|
||||
importance_df = pd.DataFrame({
|
||||
'feature': feature_cols,
|
||||
'importance': feature_importance
|
||||
}).sort_values('importance', ascending=False)
|
||||
|
||||
print(f"\nTop 20 重要特征:")
|
||||
for i, (idx, row) in enumerate(importance_df.head(20).iterrows(), 1):
|
||||
print(f" {i:2d}. {row['feature']:<20s} {row['importance']:7.2f}")
|
||||
|
||||
# ========== 步骤5: 保存模型 ==========
|
||||
print("\n[5/5] 保存模型...")
|
||||
|
||||
checkpoint_dir = './models/checkpoints/catboost_classification_2026'
|
||||
os.makedirs(checkpoint_dir, exist_ok=True)
|
||||
|
||||
# 保存CatBoost模型
|
||||
model_path = f'{checkpoint_dir}/catboost_model.cbm'
|
||||
model.save_model(model_path, format='cbm')
|
||||
|
||||
# 保存特征列表和元数据
|
||||
metadata = {
|
||||
'feature_cols': feature_cols,
|
||||
'train_acc': float(train_acc),
|
||||
'val_acc': float(val_acc),
|
||||
'best_iteration': int(model.get_best_iteration()),
|
||||
'train_samples': len(X_train),
|
||||
'val_samples': len(X_val),
|
||||
'timestamp': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
|
||||
'train_date_range': f"{df_train['timestamp'].min()} - {df_train['timestamp'].max()}",
|
||||
'val_date_range': f"{df_val['timestamp'].min()} - {df_val['timestamp'].max()}",
|
||||
}
|
||||
|
||||
with open(f'{checkpoint_dir}/metadata.pkl', 'wb') as f:
|
||||
pickle.dump(metadata, f)
|
||||
|
||||
print(f"✓ 模型已保存到: {model_path}")
|
||||
print(f"✓ 元数据已保存到: {checkpoint_dir}/metadata.pkl")
|
||||
|
||||
# ========== 总结 ==========
|
||||
print("\n" + "="*80)
|
||||
print("✓ CatBoost二分类模型训练完成!")
|
||||
print("="*80)
|
||||
|
||||
print(f"\n模型性能总结：")
|
||||
print(f" 训练集准确率: {train_acc*100:.2f}%")
|
||||
print(f" 验证集准确率: {val_acc*100:.2f}%")
|
||||
print(f" 特征数量: {len(feature_cols)}")
|
||||
print(f" 最佳迭代: {model.get_best_iteration()}")
|
||||
|
||||
print(f"\n保存位置：")
|
||||
print(f" {checkpoint_dir}/")
|
||||
|
||||
print("\n" + "="*80)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in new issue
Block a user