Skip to content

A
alpha-mind
Commit c86610be authored by Dr.李's avatar Dr.李
Browse files
Options

update example

parent 265f1b2a
Expand all Show whitespace changes
Inline Side-by-side
Showing with 754 additions and 63 deletions
notebooks/Example 1 - factor IC analysis.ipynb
View file @ c86610be
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 1,
"metadata": { "metadata": {
"collapsed": true "collapsed": true
}, },
...@@ -21,7 +21,7 @@ ...@@ -21,7 +21,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 2,
"metadata": { "metadata": {
"collapsed": true "collapsed": true
}, },
...@@ -34,22 +34,23 @@ ...@@ -34,22 +34,23 @@
"start_date = '2010-01-01'\n", "start_date = '2010-01-01'\n",
"end_date = '2018-02-14'\n", "end_date = '2018-02-14'\n",
"\n", "\n",
"frequency = '20b'\n", "frequency = '10b'\n",
"method = 'risk_neutral'\n", "method = 'risk_neutral'\n",
"neutralize_risk = industry_styles\n", "neutralize_risk = industry_styles\n",
"turn_over_target_base = 2.0\n", "industry_name = 'sw_adj'\n",
"benchmark_total_lower = 1.0\n", "industry_level = 1\n",
"benchmark_total_lower = 0.8\n",
"benchmark_total_upper = 1.0\n", "benchmark_total_upper = 1.0\n",
"horizon = map_freq(frequency)\n", "horizon = map_freq(frequency)\n",
"weight_gap = 0.300\n", "weight_gap = 0.01\n",
"benchmark_code = 905\n", "benchmark_code = 905\n",
"universe_name = ['hs300']\n", "universe_name = ['zz800']\n",
"universe = Universe('custom', universe_name)\n", "universe = Universe('custom', universe_name)\n",
"ref_dates = makeSchedule(start_date, end_date, frequency, 'china.sse')\n", "ref_dates = makeSchedule(start_date, end_date, frequency, 'china.sse')\n",
"\n", "\n",
"executor = NaiveExecutor()\n", "executor = NaiveExecutor()\n",
"connect_str = 'postgres+psycopg2://postgres:we083826@192.168.0.102/alpha'\n", "data_source = 'postgres+psycopg2://postgres:we083826@192.168.0.102/alpha'\n",
"engine = SqlEngine(connect_str)" "engine = SqlEngine(data_source)"
] ]
}, },
{ {
...@@ -64,7 +65,8 @@ ...@@ -64,7 +65,8 @@
"Constraints settings\n", "Constraints settings\n",
"\"\"\"\n", "\"\"\"\n",
"\n", "\n",
"constraint_risk = ['SIZE', 'SIZENL', 'BETA']\n", "industry_names = industry_list(industry_name, industry_level)\n",
"constraint_risk = ['SIZE', 'SIZENL', 'BETA'] + industry_names\n",
"total_risk_names = constraint_risk + ['benchmark', 'total']\n", "total_risk_names = constraint_risk + ['benchmark', 'total']\n",
"\n", "\n",
"b_type = []\n", "b_type = []\n",
...@@ -76,10 +78,6 @@ ...@@ -76,10 +78,6 @@
" b_type.append(BoundaryType.RELATIVE)\n", " b_type.append(BoundaryType.RELATIVE)\n",
" l_val.append(benchmark_total_lower)\n", " l_val.append(benchmark_total_lower)\n",
" u_val.append(benchmark_total_upper)\n", " u_val.append(benchmark_total_upper)\n",
" elif name == 'total':\n",
" b_type.append(BoundaryType.RELATIVE)\n",
" l_val.append(1.0)\n",
" u_val.append(1.0)\n",
" else:\n", " else:\n",
" b_type.append(BoundaryType.ABSOLUTE)\n", " b_type.append(BoundaryType.ABSOLUTE)\n",
" l_val.append(0.0)\n", " l_val.append(0.0)\n",
...@@ -91,7 +89,9 @@ ...@@ -91,7 +89,9 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"\"\"\"\n", "\"\"\"\n",
...@@ -105,7 +105,10 @@ ...@@ -105,7 +105,10 @@
" dates=ref_dates,\n", " dates=ref_dates,\n",
" horizon=horizon,\n", " horizon=horizon,\n",
" offset=1)\n", " offset=1)\n",
"return_groups = codes_return.groupby('trade_date')" "\n",
"return_groups = codes_return.groupby('trade_date')\n",
"industry_total = engine.fetch_industry_matrix_range(universe, dates=ref_dates, category=industry_name, level=industry_level)\n",
"industry_groups = industry_total.groupby('trade_date')"
] ]
}, },
{ {
...@@ -146,11 +149,12 @@ ...@@ -146,11 +149,12 @@
" date = value[0]\n", " date = value[0]\n",
" data = value[1]\n", " data = value[1]\n",
" index_dates.append(date)\n", " index_dates.append(date)\n",
"\n", " \n",
" industry_matrix = industry_groups.get_group(date)\n",
" total_data = data.fillna(data[alpha_name].median())\n", " total_data = data.fillna(data[alpha_name].median())\n",
" total_data = pd.merge(total_data, industry_matrix, on=['code'])\n",
" alpha_logger.info('{0}: {1}'.format(date, len(total_data)))\n", " alpha_logger.info('{0}: {1}'.format(date, len(total_data)))\n",
" risk_exp = total_data[neutralize_risk].values.astype(float)\n", " risk_exp = total_data[neutralize_risk].values.astype(float)\n",
" industry = total_data.industry_code.values\n",
" benchmark_w = total_data.weight.values\n", " benchmark_w = total_data.weight.values\n",
" is_in_benchmark = (benchmark_w > 0.).astype(float).reshape(-1, 1)\n", " is_in_benchmark = (benchmark_w > 0.).astype(float).reshape(-1, 1)\n",
"\n", "\n",
...@@ -174,7 +178,7 @@ ...@@ -174,7 +178,7 @@
"\n", "\n",
" alpha_logger.info('{0} full re-balance'.format(date))\n", " alpha_logger.info('{0} full re-balance'.format(date))\n",
" target_pos, _ = er_portfolio_analysis(er,\n", " target_pos, _ = er_portfolio_analysis(er,\n",
" industry,\n", " total_data.industry_name.values,\n",
" None,\n", " None,\n",
" constraints,\n", " constraints,\n",
" False,\n", " False,\n",
...@@ -217,13 +221,13 @@ ...@@ -217,13 +221,13 @@
"\n", "\n",
"def worker_func_positive(factor_name):\n", "def worker_func_positive(factor_name):\n",
" from alphamind.api import SqlEngine\n", " from alphamind.api import SqlEngine\n",
" engine = SqlEngine(connect_str)\n", " engine = SqlEngine(data_source)\n",
" return factor_analysis(engine, factor_name, universe, benchmark_code, positive=True)\n", " return factor_analysis(engine, factor_name, universe, benchmark_code, positive=True)\n",
"\n", "\n",
"\n", "\n",
"def worker_func_negative(factor_name):\n", "def worker_func_negative(factor_name):\n",
" from alphamind.api import SqlEngine\n", " from alphamind.api import SqlEngine\n",
" engine = SqlEngine(connect_str)\n", " engine = SqlEngine(data_source)\n",
" return factor_analysis(engine, factor_name, universe, benchmark_code, positive=False)" " return factor_analysis(engine, factor_name, universe, benchmark_code, positive=False)"
] ]
}, },
...@@ -237,7 +241,7 @@ ...@@ -237,7 +241,7 @@
"source": [ "source": [
"df = engine.fetch_factor_coverage(start_date='2011-01-01',\n", "df = engine.fetch_factor_coverage(start_date='2011-01-01',\n",
" end_date='2018-02-12',\n", " end_date='2018-02-12',\n",
" universe='hs300')\n", " universe=universe_name[0])\n",
"df = df[df.source != 'risk_exposure']\n", "df = df[df.source != 'risk_exposure']\n",
"df = df.groupby('factor').mean()\n", "df = df.groupby('factor').mean()\n",
"df = df[df.coverage >= 0.98]" "df = df[df.coverage >= 0.98]"
...@@ -246,40 +250,41 @@ ...@@ -246,40 +250,41 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"%%time\n", "%%time\n",
"\n", "\n",
"from dask.distributed import Client\n", "from dask.distributed import Client\n",
"from dask.diagnostics import ProgressBar\n",
"\n", "\n",
"client = Client('192.168.0.102:8786')\n", "client = Client('192.168.0.102:8786')\n",
"\n", "\n",
"tasks = client.map(worker_func_positive, df.index.tolist(), pure=False)\n", "tasks = client.map(worker_func_positive, df.index.tolist(), pure=False)\n",
"with ProgressBar():\n", "res1 = client.gather(tasks)\n",
" res1 = client.gather(tasks)\n",
"\n", "\n",
"tasks = client.map(worker_func_negative, df.index.tolist(), pure=False)\n", "tasks = client.map(worker_func_negative, df.index.tolist(), pure=False)\n",
"with ProgressBar():\n", "res2 = client.gather(tasks)\n",
" res2 = client.gather(tasks)\n",
"\n", "\n",
"factor_df = pd.DataFrame()\n", "factor_df = pd.DataFrame()\n",
"ic_df = pd.DataFrame()\n", "ic_df = pd.DataFrame()\n",
"\n", "\n",
"for f_name, df in res1:\n", "for f_name, res in res1:\n",
" factor_df[f_name] = df['returns']\n", " factor_df[f_name] = res['returns']\n",
" ic_df[f_name] = df['IC']\n", " ic_df[f_name] = res['IC']\n",
"\n", "\n",
"for f_name, df in res2:\n", "for f_name, res in res2:\n",
" factor_df[f_name] = df['returns']\n", " factor_df[f_name] = res['returns']\n",
" ic_df[f_name] = df['IC']" " ic_df[f_name] = res['IC']"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"writer = pd.ExcelWriter(f'{universe_name[0]}.xlsx', engine='xlsxwriter')\n", "writer = pd.ExcelWriter(f'{universe_name[0]}.xlsx', engine='xlsxwriter')\n",
...@@ -288,33 +293,6 @@ ...@@ -288,33 +293,6 @@
"writer.close()" "writer.close()"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ic_df.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
...@@ -350,7 +328,7 @@ ...@@ -350,7 +328,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.4" "version": "3.6.3"
} }
}, },
"nbformat": 4, "nbformat": 4,
......
notebooks/Example 2 - Strategy Analysis.ipynb 0 → 100644
View file @ c86610be
This diff is collapsed.
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