Merge

examples/workflow_by_code.ipynb

@@ -1,11 +1,11 @@
 {
  "cells": [
   {
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "<a href=\"https://colab.research.google.com/github/microsoft/qlib/blob/main/examples/workflow_by_code.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
-   ],
-   "cell_type": "markdown",
-   "metadata": {}
+   ]
   },
   {
    "cell_type": "code",
@@ -28,16 +28,17 @@
     "import sys, site\n",
     "from pathlib import Path\n",
     "\n",
-    "TEMP_CODE_DIR = str(Path(\"~/tmp/qlib_code\").expanduser().resolve())\n",
     "\n",
     "try:\n",
     "    import qlib\n",
-    "    scripts_dir = Path.cwd().parent.joinpath(\"scripts\")\n",
     "except ImportError:\n",
     "    # install qlib\n",
     "    ! pip install pyqlib\n",
     "    # reload\n",
     "    site.main()\n",
+    "\n",
+    "scripts_dir = Path.cwd().parent.joinpath(\"scripts\")\n",
+    "if not scripts_dir.joinpath(\"get_data.py\").exists():\n",
     "    # download get_data.py script\n",
     "    scripts_dir = Path(\"~/tmp/qlib_code/scripts\").expanduser().resolve()\n",
     "    scripts_dir.mkdir(parents=True, exist_ok=True)\n",
@@ -376,4 +377,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}

examples/workflow_by_code_finetune.py

@@ -1,128 +0,0 @@
-#  Copyright (c) Microsoft Corporation.
-#  Licensed under the MIT License.
-
-import sys
-from pathlib import Path
-
-import qlib
-import pandas as pd
-from qlib.config import REG_CN
-from qlib.contrib.model.gbdt import LGBModel
-from qlib.contrib.data.handler import Alpha158
-from qlib.contrib.strategy.strategy import TopkDropoutStrategy
-from qlib.contrib.evaluate import (
-    backtest as normal_backtest,
-    risk_analysis,
-)
-from qlib.utils import exists_qlib_data, init_instance_by_config
-from qlib.workflow import R
-from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
-
-
-if __name__ == "__main__":
-
-    # use default data
-    provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
-    if not exists_qlib_data(provider_uri):
-        print(f"Qlib data is not found in {provider_uri}")
-        sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
-        from get_data import GetData
-
-        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
-
-    qlib.init(provider_uri=provider_uri, region=REG_CN)
-
-    market = "csi300"
-    benchmark = "SH000300"
-
-    ###################################
-    # train model
-    ###################################
-    data_handler_config = {
-        "start_time": "2008-01-01",
-        "end_time": "2020-08-01",
-        "fit_start_time": "2008-01-01",
-        "fit_end_time": "2014-12-31",
-        "instruments": market,
-    }
-
-    task = {
-        "model": {
-            "class": "LGBModel",
-            "module_path": "qlib.contrib.model.gbdt",
-            "kwargs": {
-                "loss": "mse",
-                "colsample_bytree": 0.8879,
-                "learning_rate": 0.0421,
-                "subsample": 0.8789,
-                "lambda_l1": 205.6999,
-                "lambda_l2": 580.9768,
-                "max_depth": 8,
-                "num_leaves": 210,
-                "num_threads": 20,
-            },
-        },
-        "dataset": {
-            "class": "DatasetH",
-            "module_path": "qlib.data.dataset",
-            "kwargs": {
-                "handler": {
-                    "class": "Alpha158",
-                    "module_path": "qlib.contrib.data.handler",
-                    "kwargs": data_handler_config,
-                },
-                "segments": {
-                    "train": ("2008-01-01", "2014-12-31"),
-                    "valid": ("2015-01-01", "2016-12-31"),
-                    "test": ("2017-01-01", "2020-08-01"),
-                },
-            },
-        },
-    }
-
-    port_analysis_config = {
-        "strategy": {
-            "class": "TopkDropoutStrategy",
-            "module_path": "qlib.contrib.strategy.strategy",
-            "kwargs": {
-                "topk": 50,
-                "n_drop": 5,
-            },
-        },
-        "backtest": {
-            "verbose": False,
-            "limit_threshold": 0.095,
-            "account": 100000000,
-            "benchmark": benchmark,
-            "deal_price": "close",
-            "open_cost": 0.0005,
-            "close_cost": 0.0015,
-            "min_cost": 5,
-        },
-    }
-
-    # model initiaiton
-    model = init_instance_by_config(task["model"])
-    dataset = init_instance_by_config(task["dataset"])
-
-    # start exp to train init model
-    with R.start(experiment_name="init models"):
-        model.fit(dataset)
-        R.save_objects(init_model=model)
-        rid = R.get_recorder().id
-
-    # Finetune model based on previous trained model
-    with R.start(experiment_name="finetune model"):
-        recorder = R.get_recorder(rid, experiment_name="init models")
-        model = recorder.load_object("init_model")
-        model.finetune(dataset, num_boost_round=10)
-        R.save_objects(model=model)
-
-        # prediction
-        recorder = R.get_recorder()
-        sr = SignalRecord(model, dataset, recorder)
-        sr.generate()
-
-        # backtest
-        par = PortAnaRecord(recorder, port_analysis_config)
-        par.generate()