Skip to content

A
alpha-mind
Commit 46815cf9 authored by Dr.李's avatar Dr.李
Browse files
Options

cont. remove files

parent 4c0d86b0
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 4203 deletions
notebooks/machine learning/linear_regression_method.ipynb deleted 100644 → 0
View file @ 4c0d86b0
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/machine learning/tree_based_method.ipynb deleted 100644 → 0
View file @ 4c0d86b0
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/machine learning/xgboost_method.ipynb deleted 100644 → 0
View file @ 4c0d86b0
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import datetime as dt\n",
"import numpy as np\n",
"import pandas as pd\n",
"from matplotlib import pyplot as plt\n",
"from alphamind.api import *\n",
"from PyFin.api import *\n",
"import xgboost as xgb\n",
"from xgboost.sklearn import XGBRegressor\n",
"from sklearn.model_selection import GridSearchCV\n",
"\n",
"plt.style.use('fivethirtyeight')\n",
"engine = SqlEngine('postgres+psycopg2://postgres:A12345678!@10.63.6.220/alpha')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"u_name = 'zz500'\n",
"benchmark = 905\n",
"universe = Universe(u_name, [u_name])\n",
"factor_coverage = engine.fetch_factor_coverage()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"flitered_coverage = factor_coverage[((factor_coverage.source == 'uqer'))\n",
" & (factor_coverage.universe == u_name) \n",
" & (factor_coverage.trade_date >= '2012-01-01')]\n",
"coverage_report = flitered_coverage.groupby(['factor'])['coverage'].mean()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"risk_factors = engine.fetch_risk_meta()\n",
"risk_factors = risk_factors[risk_factors.type == 'style'].factor.tolist()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"alpha_factors = coverage_report[coverage_report >= 0.99].index.tolist()\n",
"\n",
"alpha_factors = {\n",
" f: DIFF(f) / (ABS(f) + 1e-4) / (DIFF('closePrice') / (LAST('closePrice') + 1e-4))\n",
" for f in alpha_factors if f != 'SIZE'\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"202"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"alpha_factors.__len__()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"frequency = '2w'\n",
"batch = 8\n",
"start_date = '2012-01-01'\n",
"end_date = '2017-10-25'\n",
"method = 'risk_neutral'\n",
"portfolio_risk_neutralize = ['SIZE']\n",
"neutralize_risk = industry_styles + portfolio_risk_neutralize\n",
"industry_lower = 1.\n",
"industry_upper = 1."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2017-10-30 15:59:06,085 - ALPHA_MIND - INFO - Starting data package fetching ...\n",
"D:\\ProgramData\\IntelPython3_2018\\lib\\site-packages\\alpha_mind-0.1.0-py3.6-win-amd64.egg\\alphamind\\data\\transformer.py:78: RuntimeWarning: invalid value encountered in true_divide\n",
" dropna=False)\n",
"D:\\ProgramData\\IntelPython3_2018\\lib\\site-packages\\alpha_mind-0.1.0-py3.6-win-amd64.egg\\alphamind\\data\\transformer.py:78: RuntimeWarning: divide by zero encountered in true_divide\n",
" dropna=False)\n",
"2017-10-30 16:00:44,156 - ALPHA_MIND - INFO - Loading data is finished\n",
"2017-10-30 16:01:02,368 - ALPHA_MIND - INFO - Data processing is finished\n"
]
}
],
"source": [
"data_package = fetch_data_package(engine,\n",
" alpha_factors=alpha_factors,\n",
" start_date=start_date,\n",
" end_date=end_date,\n",
" frequency=frequency,\n",
" universe=universe,\n",
" benchmark=benchmark,\n",
" batch=batch,\n",
" neutralized_risk=neutralize_risk,\n",
" pre_process=[winsorize_normal],\n",
" post_process=[winsorize_normal],\n",
" warm_start=batch)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"train_x = data_package['train']['x']\n",
"train_y = data_package['train']['y']\n",
"\n",
"predict_x = data_package['predict']['x']\n",
"predict_y = data_package['predict']['y']\n",
"\n",
"features = data_package['x_names']"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def plot_model_importance(model, features):\n",
" features = np.array(features)\n",
" n_features = len(features)\n",
" features_importance = model.feature_importances_\n",
" order = features_importance.argsort().argsort()\n",
" features = features[order >= n_features - 10]\n",
" features_importance = features_importance[order >= n_features - 10]\n",
" n_features = len(features)\n",
" plt.figure(figsize=(12, 6))\n",
" plt.barh(range(n_features), features_importance, align='center')\n",
" plt.yticks(np.arange(n_features), features)\n",
" plt.xlabel('Feature importance')\n",
" plt.ylabel('Feature')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 0. Train Score on a specific date\n",
"------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ref_date = list(train_x.keys())[-1]\n",
"sample_train_x = train_x[ref_date]\n",
"sample_train_y = train_y[ref_date].flatten()\n",
"\n",
"sample_test_x = predict_x[ref_date]\n",
"sample_test_y = predict_y[ref_date].flatten()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Wall time: 1min 22s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"param_grid = {\n",
" 'max_depth': [3, 5, 10],\n",
" 'min_child_weight': [1, 5, 10]\n",
"}\n",
"\n",
"\n",
"\n",
"inner_model = XGBRegressor(max_depth=5,\n",
" min_child_weight=20,\n",
" n_estimators=1000,\n",
" subsample=0.5,\n",
" colsample_bytree=0.05,\n",
" reg_alpha=1.,\n",
" reg_lambda=1.)\n",
"\n",
"model = GridSearchCV(estimator = inner_model,\n",
" param_grid=param_grid,\n",
" cv=5,\n",
" n_jobs=-1)\n",
"\n",
"model.fit(sample_train_x, sample_train_y)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.55783631412419776"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.score(sample_train_x, sample_train_y)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"-0.44341398453487768"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.score(sample_test_x, sample_test_y)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 0.0043753 , 0.00372711, 0.0043753 , 0.00453735, 0.00340301,\n",
" 0.00405121, 0.00599579, 0.00275482, 0.0046994 , 0.00550964,\n",
" 0.00648193, 0.00518555, 0.0046994 , 0.00615784, 0.00696808,\n",
" 0.00550964, 0.00988495, 0.00567169, 0.00307892, 0.0043753 ,\n",
" 0.00534759, 0.00356506, 0.00534759, 0.00518555, 0.0050235 ,\n",
" 0.00388916, 0.00486145, 0.00324097, 0.00307892, 0.00405121,\n",
" 0.00421326, 0.00794037, 0.00761627, 0.00324097, 0.00615784,\n",
" 0.00518555, 0.00405121, 0.00388916, 0.00291687, 0.00388916,\n",
" 0.00307892, 0.00631988, 0.00388916, 0.0050235 , 0.00453735,\n",
" 0.00275482, 0.00518555, 0.00226868, 0.00340301, 0.00421326,\n",
" 0.00324097, 0.00388916, 0.00453735, 0.00696808, 0.0046994 ,\n",
" 0.00372711, 0.00421326, 0.00761627, 0.0050235 , 0.00453735,\n",
" 0.00777832, 0.00599579, 0.00550964, 0.00372711, 0.00664398,\n",
" 0.00421326, 0.00534759, 0.00534759, 0.00567169, 0.0046994 ,\n",
" 0.00486145, 0.00826446, 0.0050235 , 0.00729217, 0.00810241,\n",
" 0.00275482, 0.00372711, 0.00356506, 0.0050235 , 0.00421326,\n",
" 0.0043753 , 0.00372711, 0.00583374, 0.00550964, 0.00583374,\n",
" 0.0050235 , 0.01069519, 0.00453735, 0.00388916, 0.00356506,\n",
" 0.00534759, 0.00696808, 0.00631988, 0.00534759, 0.00583374,\n",
" 0.00615784, 0.00599579, 0.01085724, 0.00615784, 0.00534759,\n",
" 0.00534759, 0.00388916, 0.0050235 , 0.00372711, 0.00534759,\n",
" 0.00486145, 0.00388916, 0.00486145, 0.00486145, 0.00518555,\n",
" 0.00324097, 0.00259277, 0.00356506, 0.00583374, 0.00324097,\n",
" 0.00340301, 0.00291687, 0.00405121, 0.00599579, 0.0046994 ,\n",
" 0.00486145, 0.00356506, 0.00421326, 0.00259277, 0.00518555,\n",
" 0.00307892, 0.00567169, 0.00388916, 0.0043753 , 0.00534759,\n",
" 0.00340301, 0.00599579, 0.00372711, 0.00324097, 0.00453735,\n",
" 0.00275482, 0.00567169, 0.00518555, 0.0050235 , 0.00340301,\n",
" 0.00405121, 0.0050235 , 0.00842651, 0.00421326, 0.00615784,\n",
" 0.0046994 , 0.00615784, 0.0046994 , 0.0050235 , 0.00664398,\n",
" 0.00243072, 0.00486145, 0.00453735, 0.0050235 , 0.00713012,\n",
" 0.00615784, 0.00486145, 0.00275482, 0.00615784, 0.00388916,\n",
" 0.00534759, 0.00713012, 0.00567169, 0.00340301, 0.00631988,\n",
" 0.00486145, 0.0046994 , 0.00421326, 0.0050235 , 0.00324097,\n",
" 0.00405121, 0.00615784, 0.00599579, 0.00761627, 0.00226868,\n",
" 0.00340301, 0.00324097, 0.00259277, 0.00486145, 0.00405121,\n",
" 0.00372711, 0.0043753 , 0.00307892, 0.00388916, 0.00307892,\n",
" 0.00340301, 0.00664398, 0.00453735, 0.00550964, 0.00745422,\n",
" 0.0043753 , 0.00615784, 0.00729217, 0.00842651, 0.0043753 ,\n",
" 0.00648193, 0.00453735, 0.00631988, 0.0090747 , 0.00826446,\n",
" 0.00631988, 0.0050235 ], dtype=float32)"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.best_estimator_.feature_importances_"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Train and test accuracy trend （XGBRegressor）\n",
"----------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dates = sorted(train_x.keys())\n",
"accuray_table = pd.DataFrame(columns=['train', 'test'])\n",
"\n",
"portfolio_industry_neutralize = True\n",
"\n",
"settlement = data_package['settlement']\n",
"industry_dummies = pd.get_dummies(settlement['industry'].values)\n",
"risk_styles = settlement[portfolio_risk_neutralize].values\n",
"total_risks = settlement[neutralize_risk].values\n",
"final_res = np.zeros(len(dates))\n",
"method = 'risk_neutral'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2017-10-30 16:03:43,756 - ALPHA_MIND - INFO - trade_date: 2012-01-30 00:00:00 training finished\n",
"2017-10-30 16:03:44,031 - ALPHA_MIND - INFO - trade_date: 2012-01-30 00:00:00 predicting finished\n",
"2017-10-30 16:05:05,734 - ALPHA_MIND - INFO - trade_date: 2012-02-08 00:00:00 training finished\n",
"2017-10-30 16:05:05,990 - ALPHA_MIND - INFO - trade_date: 2012-02-08 00:00:00 predicting finished\n",
"2017-10-30 16:06:15,716 - ALPHA_MIND - INFO - trade_date: 2012-02-22 00:00:00 training finished\n",
"2017-10-30 16:06:16,232 - ALPHA_MIND - INFO - trade_date: 2012-02-22 00:00:00 predicting finished\n",
"2017-10-30 16:07:26,617 - ALPHA_MIND - INFO - trade_date: 2012-03-07 00:00:00 training finished\n",
"2017-10-30 16:07:26,842 - ALPHA_MIND - INFO - trade_date: 2012-03-07 00:00:00 predicting finished\n",
"2017-10-30 16:08:34,769 - ALPHA_MIND - INFO - trade_date: 2012-03-21 00:00:00 training finished\n",
"2017-10-30 16:08:35,300 - ALPHA_MIND - INFO - trade_date: 2012-03-21 00:00:00 predicting finished\n",
"2017-10-30 16:09:42,546 - ALPHA_MIND - INFO - trade_date: 2012-04-05 00:00:00 training finished\n",
"2017-10-30 16:09:42,781 - ALPHA_MIND - INFO - trade_date: 2012-04-05 00:00:00 predicting finished\n",
"2017-10-30 16:10:45,327 - ALPHA_MIND - INFO - trade_date: 2012-04-18 00:00:00 training finished\n",
"2017-10-30 16:10:45,629 - ALPHA_MIND - INFO - trade_date: 2012-04-18 00:00:00 predicting finished\n",
"2017-10-30 16:11:55,708 - ALPHA_MIND - INFO - trade_date: 2012-05-02 00:00:00 training finished\n",
"2017-10-30 16:11:55,960 - ALPHA_MIND - INFO - trade_date: 2012-05-02 00:00:00 predicting finished\n",
"2017-10-30 16:13:14,065 - ALPHA_MIND - INFO - trade_date: 2012-05-16 00:00:00 training finished\n",
"2017-10-30 16:13:14,296 - ALPHA_MIND - INFO - trade_date: 2012-05-16 00:00:00 predicting finished\n",
"2017-10-30 16:14:36,442 - ALPHA_MIND - INFO - trade_date: 2012-05-30 00:00:00 training finished\n",
"2017-10-30 16:14:36,700 - ALPHA_MIND - INFO - trade_date: 2012-05-30 00:00:00 predicting finished\n",
"2017-10-30 16:15:50,418 - ALPHA_MIND - INFO - trade_date: 2012-06-13 00:00:00 training finished\n",
"2017-10-30 16:15:50,716 - ALPHA_MIND - INFO - trade_date: 2012-06-13 00:00:00 predicting finished\n",
"2017-10-30 16:16:59,918 - ALPHA_MIND - INFO - trade_date: 2012-06-27 00:00:00 training finished\n",
"2017-10-30 16:17:00,176 - ALPHA_MIND - INFO - trade_date: 2012-06-27 00:00:00 predicting finished\n",
"2017-10-30 16:18:12,672 - ALPHA_MIND - INFO - trade_date: 2012-07-11 00:00:00 training finished\n",
"2017-10-30 16:18:13,074 - ALPHA_MIND - INFO - trade_date: 2012-07-11 00:00:00 predicting finished\n",
"2017-10-30 16:19:18,565 - ALPHA_MIND - INFO - trade_date: 2012-07-25 00:00:00 training finished\n",
"2017-10-30 16:19:18,766 - ALPHA_MIND - INFO - trade_date: 2012-07-25 00:00:00 predicting finished\n",
"2017-10-30 16:20:24,549 - ALPHA_MIND - INFO - trade_date: 2012-08-08 00:00:00 training finished\n",
"2017-10-30 16:20:24,772 - ALPHA_MIND - INFO - trade_date: 2012-08-08 00:00:00 predicting finished\n",
"2017-10-30 16:21:29,819 - ALPHA_MIND - INFO - trade_date: 2012-08-22 00:00:00 training finished\n",
"2017-10-30 16:21:30,196 - ALPHA_MIND - INFO - trade_date: 2012-08-22 00:00:00 predicting finished\n",
"2017-10-30 16:22:39,143 - ALPHA_MIND - INFO - trade_date: 2012-09-05 00:00:00 training finished\n",
"2017-10-30 16:22:39,350 - ALPHA_MIND - INFO - trade_date: 2012-09-05 00:00:00 predicting finished\n",
"2017-10-30 16:23:48,277 - ALPHA_MIND - INFO - trade_date: 2012-09-19 00:00:00 training finished\n",
"2017-10-30 16:23:48,588 - ALPHA_MIND - INFO - trade_date: 2012-09-19 00:00:00 predicting finished\n",
"2017-10-30 16:24:55,873 - ALPHA_MIND - INFO - trade_date: 2012-10-08 00:00:00 training finished\n",
"2017-10-30 16:24:56,064 - ALPHA_MIND - INFO - trade_date: 2012-10-08 00:00:00 predicting finished\n",
"2017-10-30 16:25:58,817 - ALPHA_MIND - INFO - trade_date: 2012-10-17 00:00:00 training finished\n",
"2017-10-30 16:25:59,026 - ALPHA_MIND - INFO - trade_date: 2012-10-17 00:00:00 predicting finished\n",
"2017-10-30 16:27:00,816 - ALPHA_MIND - INFO - trade_date: 2012-10-31 00:00:00 training finished\n",
"2017-10-30 16:27:01,066 - ALPHA_MIND - INFO - trade_date: 2012-10-31 00:00:00 predicting finished\n",
"2017-10-30 16:28:07,181 - ALPHA_MIND - INFO - trade_date: 2012-11-14 00:00:00 training finished\n",
"2017-10-30 16:28:07,420 - ALPHA_MIND - INFO - trade_date: 2012-11-14 00:00:00 predicting finished\n",
"2017-10-30 16:29:16,637 - ALPHA_MIND - INFO - trade_date: 2012-11-28 00:00:00 training finished\n",
"2017-10-30 16:29:16,999 - ALPHA_MIND - INFO - trade_date: 2012-11-28 00:00:00 predicting finished\n",
"2017-10-30 16:30:21,593 - ALPHA_MIND - INFO - trade_date: 2012-12-12 00:00:00 training finished\n",
"2017-10-30 16:30:21,836 - ALPHA_MIND - INFO - trade_date: 2012-12-12 00:00:00 predicting finished\n",
"2017-10-30 16:31:30,018 - ALPHA_MIND - INFO - trade_date: 2012-12-26 00:00:00 training finished\n",
"2017-10-30 16:31:30,316 - ALPHA_MIND - INFO - trade_date: 2012-12-26 00:00:00 predicting finished\n",
"2017-10-30 16:32:35,963 - ALPHA_MIND - INFO - trade_date: 2013-01-09 00:00:00 training finished\n",
"2017-10-30 16:32:36,269 - ALPHA_MIND - INFO - trade_date: 2013-01-09 00:00:00 predicting finished\n",
"2017-10-30 16:33:44,180 - ALPHA_MIND - INFO - trade_date: 2013-01-23 00:00:00 training finished\n",
"2017-10-30 16:33:44,432 - ALPHA_MIND - INFO - trade_date: 2013-01-23 00:00:00 predicting finished\n",
"2017-10-30 16:34:52,341 - ALPHA_MIND - INFO - trade_date: 2013-02-06 00:00:00 training finished\n",
"2017-10-30 16:34:52,576 - ALPHA_MIND - INFO - trade_date: 2013-02-06 00:00:00 predicting finished\n",
"2017-10-30 16:36:01,845 - ALPHA_MIND - INFO - trade_date: 2013-02-20 00:00:00 training finished\n",
"2017-10-30 16:36:02,118 - ALPHA_MIND - INFO - trade_date: 2013-02-20 00:00:00 predicting finished\n",
"2017-10-30 16:37:10,073 - ALPHA_MIND - INFO - trade_date: 2013-03-06 00:00:00 training finished\n",
"2017-10-30 16:37:10,317 - ALPHA_MIND - INFO - trade_date: 2013-03-06 00:00:00 predicting finished\n",
"2017-10-30 16:38:23,873 - ALPHA_MIND - INFO - trade_date: 2013-03-20 00:00:00 training finished\n",
"2017-10-30 16:38:24,202 - ALPHA_MIND - INFO - trade_date: 2013-03-20 00:00:00 predicting finished\n",
"2017-10-30 16:39:30,761 - ALPHA_MIND - INFO - trade_date: 2013-04-03 00:00:00 training finished\n",
"2017-10-30 16:39:31,047 - ALPHA_MIND - INFO - trade_date: 2013-04-03 00:00:00 predicting finished\n",
"2017-10-30 16:40:34,583 - ALPHA_MIND - INFO - trade_date: 2013-04-17 00:00:00 training finished\n",
"2017-10-30 16:40:34,800 - ALPHA_MIND - INFO - trade_date: 2013-04-17 00:00:00 predicting finished\n",
"2017-10-30 16:41:36,855 - ALPHA_MIND - INFO - trade_date: 2013-05-02 00:00:00 training finished\n",
"2017-10-30 16:41:37,055 - ALPHA_MIND - INFO - trade_date: 2013-05-02 00:00:00 predicting finished\n",
"2017-10-30 16:42:42,062 - ALPHA_MIND - INFO - trade_date: 2013-05-15 00:00:00 training finished\n",
"2017-10-30 16:42:42,286 - ALPHA_MIND - INFO - trade_date: 2013-05-15 00:00:00 predicting finished\n",
"2017-10-30 16:43:48,501 - ALPHA_MIND - INFO - trade_date: 2013-05-29 00:00:00 training finished\n",
"2017-10-30 16:43:48,719 - ALPHA_MIND - INFO - trade_date: 2013-05-29 00:00:00 predicting finished\n",
"2017-10-30 16:44:56,528 - ALPHA_MIND - INFO - trade_date: 2013-06-13 00:00:00 training finished\n",
"2017-10-30 16:44:56,828 - ALPHA_MIND - INFO - trade_date: 2013-06-13 00:00:00 predicting finished\n",
"2017-10-30 16:46:08,251 - ALPHA_MIND - INFO - trade_date: 2013-06-26 00:00:00 training finished\n",
"2017-10-30 16:46:08,570 - ALPHA_MIND - INFO - trade_date: 2013-06-26 00:00:00 predicting finished\n",
"2017-10-30 16:47:17,948 - ALPHA_MIND - INFO - trade_date: 2013-07-10 00:00:00 training finished\n",
"2017-10-30 16:47:18,179 - ALPHA_MIND - INFO - trade_date: 2013-07-10 00:00:00 predicting finished\n",
"2017-10-30 16:48:28,189 - ALPHA_MIND - INFO - trade_date: 2013-07-24 00:00:00 training finished\n",
"2017-10-30 16:48:28,513 - ALPHA_MIND - INFO - trade_date: 2013-07-24 00:00:00 predicting finished\n",
"2017-10-30 16:49:37,966 - ALPHA_MIND - INFO - trade_date: 2013-08-07 00:00:00 training finished\n",
"2017-10-30 16:49:38,199 - ALPHA_MIND - INFO - trade_date: 2013-08-07 00:00:00 predicting finished\n",
"2017-10-30 16:50:47,164 - ALPHA_MIND - INFO - trade_date: 2013-08-21 00:00:00 training finished\n",
"2017-10-30 16:50:47,405 - ALPHA_MIND - INFO - trade_date: 2013-08-21 00:00:00 predicting finished\n",
"2017-10-30 16:51:59,466 - ALPHA_MIND - INFO - trade_date: 2013-09-04 00:00:00 training finished\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2017-10-30 16:51:59,771 - ALPHA_MIND - INFO - trade_date: 2013-09-04 00:00:00 predicting finished\n",
"2017-10-30 16:53:06,232 - ALPHA_MIND - INFO - trade_date: 2013-09-18 00:00:00 training finished\n",
"2017-10-30 16:53:06,504 - ALPHA_MIND - INFO - trade_date: 2013-09-18 00:00:00 predicting finished\n",
"2017-10-30 16:54:17,100 - ALPHA_MIND - INFO - trade_date: 2013-10-08 00:00:00 training finished\n",
"2017-10-30 16:54:17,349 - ALPHA_MIND - INFO - trade_date: 2013-10-08 00:00:00 predicting finished\n",
"2017-10-30 16:55:22,653 - ALPHA_MIND - INFO - trade_date: 2013-10-16 00:00:00 training finished\n",
"2017-10-30 16:55:22,904 - ALPHA_MIND - INFO - trade_date: 2013-10-16 00:00:00 predicting finished\n",
"2017-10-30 16:56:31,367 - ALPHA_MIND - INFO - trade_date: 2013-10-30 00:00:00 training finished\n",
"2017-10-30 16:56:31,650 - ALPHA_MIND - INFO - trade_date: 2013-10-30 00:00:00 predicting finished\n",
"2017-10-30 16:57:39,492 - ALPHA_MIND - INFO - trade_date: 2013-11-13 00:00:00 training finished\n",
"2017-10-30 16:57:39,751 - ALPHA_MIND - INFO - trade_date: 2013-11-13 00:00:00 predicting finished\n",
"2017-10-30 16:58:50,453 - ALPHA_MIND - INFO - trade_date: 2013-11-27 00:00:00 training finished\n",
"2017-10-30 16:58:50,712 - ALPHA_MIND - INFO - trade_date: 2013-11-27 00:00:00 predicting finished\n",
"2017-10-30 16:59:57,582 - ALPHA_MIND - INFO - trade_date: 2013-12-11 00:00:00 training finished\n",
"2017-10-30 16:59:57,957 - ALPHA_MIND - INFO - trade_date: 2013-12-11 00:00:00 predicting finished\n",
"2017-10-30 17:01:08,574 - ALPHA_MIND - INFO - trade_date: 2013-12-25 00:00:00 training finished\n",
"2017-10-30 17:01:08,786 - ALPHA_MIND - INFO - trade_date: 2013-12-25 00:00:00 predicting finished\n",
"2017-10-30 17:02:19,504 - ALPHA_MIND - INFO - trade_date: 2014-01-08 00:00:00 training finished\n",
"2017-10-30 17:02:19,757 - ALPHA_MIND - INFO - trade_date: 2014-01-08 00:00:00 predicting finished\n",
"2017-10-30 17:03:28,487 - ALPHA_MIND - INFO - trade_date: 2014-01-22 00:00:00 training finished\n",
"2017-10-30 17:03:28,702 - ALPHA_MIND - INFO - trade_date: 2014-01-22 00:00:00 predicting finished\n",
"2017-10-30 17:04:37,728 - ALPHA_MIND - INFO - trade_date: 2014-02-07 00:00:00 training finished\n",
"2017-10-30 17:04:37,962 - ALPHA_MIND - INFO - trade_date: 2014-02-07 00:00:00 predicting finished\n",
"2017-10-30 17:05:51,014 - ALPHA_MIND - INFO - trade_date: 2014-02-19 00:00:00 training finished\n",
"2017-10-30 17:05:51,237 - ALPHA_MIND - INFO - trade_date: 2014-02-19 00:00:00 predicting finished\n",
"2017-10-30 17:07:01,341 - ALPHA_MIND - INFO - trade_date: 2014-03-05 00:00:00 training finished\n",
"2017-10-30 17:07:01,560 - ALPHA_MIND - INFO - trade_date: 2014-03-05 00:00:00 predicting finished\n",
"2017-10-30 17:08:06,919 - ALPHA_MIND - INFO - trade_date: 2014-03-19 00:00:00 training finished\n",
"2017-10-30 17:08:07,263 - ALPHA_MIND - INFO - trade_date: 2014-03-19 00:00:00 predicting finished\n",
"2017-10-30 17:09:14,810 - ALPHA_MIND - INFO - trade_date: 2014-04-02 00:00:00 training finished\n",
"2017-10-30 17:09:15,045 - ALPHA_MIND - INFO - trade_date: 2014-04-02 00:00:00 predicting finished\n",
"2017-10-30 17:10:21,859 - ALPHA_MIND - INFO - trade_date: 2014-04-16 00:00:00 training finished\n",
"2017-10-30 17:10:22,073 - ALPHA_MIND - INFO - trade_date: 2014-04-16 00:00:00 predicting finished\n",
"2017-10-30 17:11:33,988 - ALPHA_MIND - INFO - trade_date: 2014-04-30 00:00:00 training finished\n",
"2017-10-30 17:11:34,238 - ALPHA_MIND - INFO - trade_date: 2014-04-30 00:00:00 predicting finished\n",
"2017-10-30 17:12:45,852 - ALPHA_MIND - INFO - trade_date: 2014-05-14 00:00:00 training finished\n",
"2017-10-30 17:12:46,122 - ALPHA_MIND - INFO - trade_date: 2014-05-14 00:00:00 predicting finished\n",
"2017-10-30 17:13:51,988 - ALPHA_MIND - INFO - trade_date: 2014-05-28 00:00:00 training finished\n",
"2017-10-30 17:13:52,200 - ALPHA_MIND - INFO - trade_date: 2014-05-28 00:00:00 predicting finished\n",
"2017-10-30 17:15:03,655 - ALPHA_MIND - INFO - trade_date: 2014-06-11 00:00:00 training finished\n",
"2017-10-30 17:15:04,208 - ALPHA_MIND - INFO - trade_date: 2014-06-11 00:00:00 predicting finished\n",
"2017-10-30 17:16:09,693 - ALPHA_MIND - INFO - trade_date: 2014-06-25 00:00:00 training finished\n",
"2017-10-30 17:16:10,029 - ALPHA_MIND - INFO - trade_date: 2014-06-25 00:00:00 predicting finished\n",
"2017-10-30 17:17:14,025 - ALPHA_MIND - INFO - trade_date: 2014-07-09 00:00:00 training finished\n",
"2017-10-30 17:17:14,280 - ALPHA_MIND - INFO - trade_date: 2014-07-09 00:00:00 predicting finished\n",
"2017-10-30 17:18:22,782 - ALPHA_MIND - INFO - trade_date: 2014-07-23 00:00:00 training finished\n",
"2017-10-30 17:18:23,174 - ALPHA_MIND - INFO - trade_date: 2014-07-23 00:00:00 predicting finished\n",
"2017-10-30 17:19:28,460 - ALPHA_MIND - INFO - trade_date: 2014-08-06 00:00:00 training finished\n",
"2017-10-30 17:19:28,675 - ALPHA_MIND - INFO - trade_date: 2014-08-06 00:00:00 predicting finished\n",
"2017-10-30 17:20:32,846 - ALPHA_MIND - INFO - trade_date: 2014-08-20 00:00:00 training finished\n",
"2017-10-30 17:20:33,059 - ALPHA_MIND - INFO - trade_date: 2014-08-20 00:00:00 predicting finished\n",
"2017-10-30 17:21:37,307 - ALPHA_MIND - INFO - trade_date: 2014-09-03 00:00:00 training finished\n",
"2017-10-30 17:21:37,585 - ALPHA_MIND - INFO - trade_date: 2014-09-03 00:00:00 predicting finished\n",
"2017-10-30 17:22:43,700 - ALPHA_MIND - INFO - trade_date: 2014-09-17 00:00:00 training finished\n",
"2017-10-30 17:22:43,922 - ALPHA_MIND - INFO - trade_date: 2014-09-17 00:00:00 predicting finished\n",
"2017-10-30 17:23:46,909 - ALPHA_MIND - INFO - trade_date: 2014-10-08 00:00:00 training finished\n",
"2017-10-30 17:23:47,124 - ALPHA_MIND - INFO - trade_date: 2014-10-08 00:00:00 predicting finished\n",
"2017-10-30 17:24:51,940 - ALPHA_MIND - INFO - trade_date: 2014-10-15 00:00:00 training finished\n",
"2017-10-30 17:24:52,162 - ALPHA_MIND - INFO - trade_date: 2014-10-15 00:00:00 predicting finished\n",
"2017-10-30 17:25:54,912 - ALPHA_MIND - INFO - trade_date: 2014-10-29 00:00:00 training finished\n",
"2017-10-30 17:25:55,272 - ALPHA_MIND - INFO - trade_date: 2014-10-29 00:00:00 predicting finished\n",
"2017-10-30 17:27:00,250 - ALPHA_MIND - INFO - trade_date: 2014-11-12 00:00:00 training finished\n",
"2017-10-30 17:27:00,462 - ALPHA_MIND - INFO - trade_date: 2014-11-12 00:00:00 predicting finished\n",
"2017-10-30 17:28:15,955 - ALPHA_MIND - INFO - trade_date: 2014-11-26 00:00:00 training finished\n",
"2017-10-30 17:28:16,477 - ALPHA_MIND - INFO - trade_date: 2014-11-26 00:00:00 predicting finished\n",
"2017-10-30 17:29:31,183 - ALPHA_MIND - INFO - trade_date: 2014-12-10 00:00:00 training finished\n",
"2017-10-30 17:29:31,748 - ALPHA_MIND - INFO - trade_date: 2014-12-10 00:00:00 predicting finished\n",
"2017-10-30 17:30:45,763 - ALPHA_MIND - INFO - trade_date: 2014-12-24 00:00:00 training finished\n",
"2017-10-30 17:30:46,076 - ALPHA_MIND - INFO - trade_date: 2014-12-24 00:00:00 predicting finished\n",
"2017-10-30 17:31:56,277 - ALPHA_MIND - INFO - trade_date: 2015-01-07 00:00:00 training finished\n",
"2017-10-30 17:31:56,520 - ALPHA_MIND - INFO - trade_date: 2015-01-07 00:00:00 predicting finished\n",
"2017-10-30 17:33:09,420 - ALPHA_MIND - INFO - trade_date: 2015-01-21 00:00:00 training finished\n",
"2017-10-30 17:33:09,700 - ALPHA_MIND - INFO - trade_date: 2015-01-21 00:00:00 predicting finished\n",
"2017-10-30 17:34:16,953 - ALPHA_MIND - INFO - trade_date: 2015-02-04 00:00:00 training finished\n",
"2017-10-30 17:34:17,174 - ALPHA_MIND - INFO - trade_date: 2015-02-04 00:00:00 predicting finished\n",
"2017-10-30 17:35:24,013 - ALPHA_MIND - INFO - trade_date: 2015-02-25 00:00:00 training finished\n",
"2017-10-30 17:35:24,358 - ALPHA_MIND - INFO - trade_date: 2015-02-25 00:00:00 predicting finished\n",
"2017-10-30 17:36:31,136 - ALPHA_MIND - INFO - trade_date: 2015-03-04 00:00:00 training finished\n",
"2017-10-30 17:36:31,414 - ALPHA_MIND - INFO - trade_date: 2015-03-04 00:00:00 predicting finished\n",
"2017-10-30 17:37:38,233 - ALPHA_MIND - INFO - trade_date: 2015-03-18 00:00:00 training finished\n",
"2017-10-30 17:37:38,467 - ALPHA_MIND - INFO - trade_date: 2015-03-18 00:00:00 predicting finished\n",
"2017-10-30 17:38:50,540 - ALPHA_MIND - INFO - trade_date: 2015-04-01 00:00:00 training finished\n",
"2017-10-30 17:38:50,981 - ALPHA_MIND - INFO - trade_date: 2015-04-01 00:00:00 predicting finished\n",
"2017-10-30 17:39:57,286 - ALPHA_MIND - INFO - trade_date: 2015-04-15 00:00:00 training finished\n",
"2017-10-30 17:39:57,495 - ALPHA_MIND - INFO - trade_date: 2015-04-15 00:00:00 predicting finished\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2017-10-30 17:41:02,621 - ALPHA_MIND - INFO - trade_date: 2015-04-29 00:00:00 training finished\n",
"2017-10-30 17:41:02,945 - ALPHA_MIND - INFO - trade_date: 2015-04-29 00:00:00 predicting finished\n",
"2017-10-30 17:42:10,267 - ALPHA_MIND - INFO - trade_date: 2015-05-13 00:00:00 training finished\n",
"2017-10-30 17:42:10,804 - ALPHA_MIND - INFO - trade_date: 2015-05-13 00:00:00 predicting finished\n",
"2017-10-30 17:43:20,729 - ALPHA_MIND - INFO - trade_date: 2015-05-27 00:00:00 training finished\n",
"2017-10-30 17:43:20,960 - ALPHA_MIND - INFO - trade_date: 2015-05-27 00:00:00 predicting finished\n",
"2017-10-30 17:44:32,601 - ALPHA_MIND - INFO - trade_date: 2015-06-10 00:00:00 training finished\n",
"2017-10-30 17:44:32,920 - ALPHA_MIND - INFO - trade_date: 2015-06-10 00:00:00 predicting finished\n",
"2017-10-30 17:45:42,142 - ALPHA_MIND - INFO - trade_date: 2015-06-24 00:00:00 training finished\n",
"2017-10-30 17:45:42,498 - ALPHA_MIND - INFO - trade_date: 2015-06-24 00:00:00 predicting finished\n",
"2017-10-30 17:46:51,160 - ALPHA_MIND - INFO - trade_date: 2015-07-08 00:00:00 training finished\n",
"2017-10-30 17:46:51,376 - ALPHA_MIND - INFO - trade_date: 2015-07-08 00:00:00 predicting finished\n",
"2017-10-30 17:48:04,098 - ALPHA_MIND - INFO - trade_date: 2015-07-22 00:00:00 training finished\n",
"2017-10-30 17:48:04,346 - ALPHA_MIND - INFO - trade_date: 2015-07-22 00:00:00 predicting finished\n",
"2017-10-30 17:49:12,908 - ALPHA_MIND - INFO - trade_date: 2015-08-05 00:00:00 training finished\n",
"2017-10-30 17:49:13,140 - ALPHA_MIND - INFO - trade_date: 2015-08-05 00:00:00 predicting finished\n",
"2017-10-30 17:50:26,135 - ALPHA_MIND - INFO - trade_date: 2015-08-19 00:00:00 training finished\n",
"2017-10-30 17:50:26,531 - ALPHA_MIND - INFO - trade_date: 2015-08-19 00:00:00 predicting finished\n",
"2017-10-30 17:51:34,916 - ALPHA_MIND - INFO - trade_date: 2015-09-02 00:00:00 training finished\n",
"2017-10-30 17:51:35,307 - ALPHA_MIND - INFO - trade_date: 2015-09-02 00:00:00 predicting finished\n",
"2017-10-30 17:52:44,581 - ALPHA_MIND - INFO - trade_date: 2015-09-16 00:00:00 training finished\n",
"2017-10-30 17:52:45,010 - ALPHA_MIND - INFO - trade_date: 2015-09-16 00:00:00 predicting finished\n",
"2017-10-30 17:53:58,147 - ALPHA_MIND - INFO - trade_date: 2015-09-30 00:00:00 training finished\n",
"2017-10-30 17:53:58,469 - ALPHA_MIND - INFO - trade_date: 2015-09-30 00:00:00 predicting finished\n",
"2017-10-30 17:55:13,364 - ALPHA_MIND - INFO - trade_date: 2015-10-14 00:00:00 training finished\n",
"2017-10-30 17:55:13,702 - ALPHA_MIND - INFO - trade_date: 2015-10-14 00:00:00 predicting finished\n",
"2017-10-30 17:56:21,040 - ALPHA_MIND - INFO - trade_date: 2015-10-28 00:00:00 training finished\n",
"2017-10-30 17:56:21,260 - ALPHA_MIND - INFO - trade_date: 2015-10-28 00:00:00 predicting finished\n",
"2017-10-30 17:57:32,846 - ALPHA_MIND - INFO - trade_date: 2015-11-11 00:00:00 training finished\n",
"2017-10-30 17:57:33,144 - ALPHA_MIND - INFO - trade_date: 2015-11-11 00:00:00 predicting finished\n",
"2017-10-30 17:58:46,159 - ALPHA_MIND - INFO - trade_date: 2015-11-25 00:00:00 training finished\n",
"2017-10-30 17:58:46,498 - ALPHA_MIND - INFO - trade_date: 2015-11-25 00:00:00 predicting finished\n",
"2017-10-30 17:59:52,634 - ALPHA_MIND - INFO - trade_date: 2015-12-09 00:00:00 training finished\n",
"2017-10-30 17:59:52,932 - ALPHA_MIND - INFO - trade_date: 2015-12-09 00:00:00 predicting finished\n",
"2017-10-30 18:01:01,254 - ALPHA_MIND - INFO - trade_date: 2015-12-23 00:00:00 training finished\n",
"2017-10-30 18:01:01,704 - ALPHA_MIND - INFO - trade_date: 2015-12-23 00:00:00 predicting finished\n",
"2017-10-30 18:02:14,769 - ALPHA_MIND - INFO - trade_date: 2016-01-06 00:00:00 training finished\n",
"2017-10-30 18:02:15,036 - ALPHA_MIND - INFO - trade_date: 2016-01-06 00:00:00 predicting finished\n",
"2017-10-30 18:03:20,459 - ALPHA_MIND - INFO - trade_date: 2016-01-20 00:00:00 training finished\n",
"2017-10-30 18:03:20,741 - ALPHA_MIND - INFO - trade_date: 2016-01-20 00:00:00 predicting finished\n",
"2017-10-30 18:04:16,460 - ALPHA_MIND - INFO - trade_date: 2016-02-03 00:00:00 training finished\n",
"2017-10-30 18:04:16,657 - ALPHA_MIND - INFO - trade_date: 2016-02-03 00:00:00 predicting finished\n",
"2017-10-30 18:05:15,056 - ALPHA_MIND - INFO - trade_date: 2016-02-17 00:00:00 training finished\n",
"2017-10-30 18:05:15,314 - ALPHA_MIND - INFO - trade_date: 2016-02-17 00:00:00 predicting finished\n"
]
}
],
"source": [
"for i, ref_date in enumerate(dates):\n",
" sample_train_x = train_x[ref_date]\n",
" sample_train_y = train_y[ref_date].flatten()\n",
"\n",
" model.fit(sample_train_x, sample_train_y)\n",
" accuray_table.loc[ref_date, 'train'] = model.score(sample_train_x, sample_train_y)\n",
" alpha_logger.info('trade_date: {0} training finished'.format(ref_date))\n",
" \n",
" ##---------------------------------##\n",
" \n",
" sample_test_x = predict_x[ref_date]\n",
" sample_test_y = predict_y[ref_date].flatten()\n",
" \n",
" cons = Constraints()\n",
" index = settlement.trade_date == ref_date\n",
" benchmark_w = settlement[index]['weight'].values\n",
" realized_r = settlement[index]['dx'].values\n",
" industry_names = settlement[index]['industry'].values\n",
" is_tradable = settlement[index]['isOpen'].values\n",
"\n",
" cons.add_exposure(['total'], np.ones((len(is_tradable), 1)))\n",
" cons.set_constraints('total', benchmark_w.sum(), benchmark_w.sum())\n",
"\n",
" if portfolio_industry_neutralize:\n",
" ind_exp = industry_dummies[index]\n",
"\n",
" risk_tags = ind_exp.columns\n",
" cons.add_exposure(risk_tags, ind_exp.values)\n",
" benchmark_exp = benchmark_w @ ind_exp.values\n",
"\n",
" for k, name in enumerate(risk_tags):\n",
" cons.set_constraints(name, benchmark_exp[k]*industry_lower, benchmark_exp[k]*industry_upper)\n",
"\n",
" if portfolio_risk_neutralize:\n",
" risk_exp = risk_styles[index]\n",
"\n",
" risk_tags = np.array(portfolio_risk_neutralize)\n",
" cons.add_exposure(risk_tags, risk_exp)\n",
"\n",
" benchmark_exp = benchmark_w @ risk_exp\n",
" for k, name in enumerate(risk_tags):\n",
" cons.set_constraints(name, benchmark_exp[k], benchmark_exp[k])\n",
"\n",
" risk_table = total_risks[index]\n",
" \n",
" y = model.predict(sample_test_x)\n",
" accuray_table.loc[ref_date, 'test'] = model.score(sample_test_x, sample_test_y)\n",
"\n",
" is_tradable[:] = True\n",
" weights, analysis = er_portfolio_analysis(y.astype(float),\n",
" industry_names,\n",
" realized_r,\n",
" constraints=cons,\n",
" detail_analysis=True,\n",
" benchmark=benchmark_w,\n",
" is_tradable=is_tradable,\n",
" method=method)\n",
" \n",
" final_res[i] = analysis['er']['total'] / benchmark_w.sum()\n",
" alpha_logger.info('trade_date: {0} predicting finished'.format(ref_date))\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"last_date = advanceDateByCalendar('china.sse', dates[-1], frequency)\n",
"\n",
"df = pd.Series(final_res, index=dates[1:] + [last_date])\n",
"df.sort_index(inplace=True)\n",
"df['2012-01-01':].cumsum().plot(figsize=(12, 6))\n",
"plt.title('Prod factors model {1} ({0})'.format(method, model.__class__.__name__))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"accuray_table.aggregate([np.mean, np.median, np.std])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
notebooks/machine learning/xgboost_method_v2.ipynb deleted 100644 → 0
View file @ 4c0d86b0
This source diff could not be displayed because it is too large. You can view the blob instead.
notebooks/notebook_utilities.py deleted 100644 → 0
View file @ 4c0d86b0
# -*- coding: utf-8 -*-
"""
Created on 2018-3-5
@author: cheng.li
"""
import numpy as np
import pandas as pd
import statsmodels.api as sm
from alphamind.api import (
SqlEngine, LinearConstraints, er_portfolio_analysis, alpha_logger
)
def cross_section_analysis(ref_date,
factor_name,
universe,
horizon,
constraint_risk,
linear_bounds,
lbound,
ubound,
engine):
codes = engine.fetch_codes(ref_date, universe)
risk_exposure = engine.fetch_risk_model(ref_date, codes)[1][['code'] + constraint_risk]
factor_data = engine.fetch_factor(ref_date, factor_name, codes)
industry_matrix = engine.fetch_industry_matrix(ref_date, codes, 'sw_adj', 1)
total_data = pd.merge(factor_data, risk_exposure, on='code')
total_data = pd.merge(total_data, industry_matrix, on='code').dropna()
total_risk_exp = total_data[constraint_risk]
constraints = LinearConstraints(linear_bounds, total_risk_exp)
er = total_data[factor_name].values
industry = total_data.industry_name.values
target_pos, _ = er_portfolio_analysis(er,
industry,
None,
constraints,
False,
None,
method='risk_neutral',
lbound=lbound*np.ones(len(er)),
ubound=ubound*np.ones(len(er)))
codes = total_data.code.tolist()
target_pos['code'] = codes
dx_returns = engine.fetch_dx_return(ref_date, codes, horizon=horizon, offset=1)
target_pos = pd.merge(target_pos, dx_returns, on=['code'])
activate_weight = target_pos.weight.values
excess_return = np.exp(target_pos.dx.values) - 1.
port_ret = np.log(activate_weight @ excess_return + 1.)
ic = np.corrcoef(excess_return, activate_weight)[0, 1]
x = sm.add_constant(activate_weight)
results = sm.OLS(excess_return, x).fit()
t_stats = results.tvalues[1]
alpha_logger.info(f"{ref_date} is finished with {len(target_pos)} stocks for {factor_name}")
return port_ret, ic, t_stats
if __name__ == '__main__':
from alphamind.api import (
Universe, map_freq, risk_styles, industry_styles, macro_styles, BoundaryType, create_box_bounds
)
"""
Back test parameter settings
"""
start_date = '2010-01-01'
end_date = '2018-02-28'
category = 'sw_adj'
level = 1
freq = '20b'
universe = Universe('custom', ['zz800'])
data_source = 'postgres+psycopg2://postgres:A12345678!@10.63.6.220/alpha'
engine = SqlEngine(data_source)
horizon = map_freq(freq)
"""
Factor Model
"""
factor_name = 'SIZE'
"""
Constraints
"""
risk_names = list(set(risk_styles).difference({factor_name}))
industry_names = list(set(industry_styles).difference({factor_name}))
constraint_risk = risk_names + industry_names + macro_styles
b_type = []
l_val = []
u_val = []
for name in constraint_risk:
if name in set(risk_styles):
b_type.append(BoundaryType.ABSOLUTE)
l_val.append(0.0)
u_val.append(0.0)
else:
b_type.append(BoundaryType.RELATIVE)
l_val.append(1.0)
u_val.append(1.0)
linear_bounds = create_box_bounds(constraint_risk, b_type, l_val, u_val)
ref_date = '2018-02-08'
df = pd.DataFrame(columns=['ret', 'ic', 't.'])
print(cross_section_analysis(ref_date,
factor_name,
universe,
horizon,
constraint_risk,
linear_bounds,
lbound=-0.01,
ubound=0.01,
engine=engine))
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment