crypto_predictor
1bd9d25f60
- 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
33 lines
874 B
Bash
Executable File
33 lines
874 B
Bash
Executable File
#!/bin/bash
|
|
# 安装三个时间序列基础模型
|
|
|
|
echo "=================================="
|
|
echo "安装时间序列基础模型"
|
|
echo "=================================="
|
|
|
|
# 激活conda环境
|
|
source /Users/xxz/miniforge3/bin/activate
|
|
conda activate crypto_pred_312
|
|
|
|
echo ""
|
|
echo "[1/3] 安装 Google TimesFM 2.5..."
|
|
pip install git+https://github.com/google-research/timesfm.git
|
|
|
|
echo ""
|
|
echo "[2/3] 安装 IBM TTM-R2 (Granite TSFM)..."
|
|
pip install tsfm_public
|
|
|
|
echo ""
|
|
echo "[3/3] 安装 Lag-Llama 依赖..."
|
|
pip install gluonts[torch] torch
|
|
|
|
echo ""
|
|
echo "=================================="
|
|
echo "✓ 所有模型安装完成!"
|
|
echo "=================================="
|
|
echo ""
|
|
echo "模型位置："
|
|
echo " - TimesFM 2.5: HuggingFace自动下载"
|
|
echo " - TTM-R2: ibm-granite/granite-timeseries-ttm-r2"
|
|
echo " - Lag-Llama: time-series-foundation-models/lag-llama"
|