Skip to content

A
alpha-mind
Commit 0afa057f authored by Dr.李's avatar Dr.李
Browse files
Options

one more example

parent 4d6de4ea
Show whitespace changes
Inline Side-by-side
Showing with 1275 additions and 0 deletions
notebooks/production_factor_analysis.ipynb 0 → 100644
View file @ 0afa057f
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pylab inline\n",
"import matplotlib.pyplot as plt\n",
"plt.style.use('ggplot')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import sqlalchemy\n",
"import numpy as np\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"factor_table = 'prod_500'\n",
"risk_table = 'risk_factor_500'\n",
"trade_table = 'trade_data'\n",
"index_components = '500Weight'\n",
"benchmark = 'zz500'\n",
"\n",
"prod_factors = ['VAL', 'BDTO', 'RVOL', 'CFinc1', 'CHV']\n",
"product_weights = np.array([3., 1., 1., 0.5, 0.5])\n",
"\n",
"factor_list = ','.join([factor_table + '.' + f for f in prod_factors])\n",
"\n",
"server = '10.63.6.176'\n",
"user = 'sa'\n",
"pwd = 'we083826'\n",
"\n",
"engine = sqlalchemy.create_engine('mysql+pymysql://{0}:{1}@{2}/multifactor?charset=utf8'.format(user, pwd, server))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"sql_template = 'select {factor_list}, factor_data.申万一级行业, {trade_table}.Return as dailyReturn, {risk_table}.*, 1 as Market ' \\\n",
" 'from {factor_table}, factor_data, trade_data, {risk_table} ' \\\n",
" 'where factor_data.Date = {factor_table}.Date and factor_data.Code = {factor_table}.Code ' \\\n",
" 'and factor_data.Date = trade_data.Date and factor_data.Code = trade_data.Code ' \\\n",
" 'and factor_data.Date = {risk_table}.Date and factor_data.Code = {risk_table}.Code;'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"sql = sql_template.format(factor_list=factor_list,\n",
" factor_table=factor_table,\n",
" risk_table=risk_table,\n",
" trade_table=trade_table)\n",
"\n",
"factor_df = pd.read_sql(sql, engine)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"index_components_df = pd.read_sql('select Date, Code, {0} from index_components;'.format(index_components), engine)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"del factor_df['Bank']\n",
"del factor_df['NonBankFinancial']\n",
"factor_df.dropna(inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"raw_df = pd.merge(factor_df, index_components_df, on=['Date', 'Code'], how='left')\n",
"raw_df.fillna(0, inplace=True)\n",
"raw_df[index_components] = raw_df[index_components] / 100."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"risk_factor_cols = raw_df.columns[9:-1]\n",
"risk_factor_cols"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = raw_df.copy()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df['d1ret'] = df.dailyReturn.groupby(df.Code).shift(-2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"benchmark_data = pd.read_sql('select {0}, Date from index_data'.format(benchmark), engine)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"benchmark_data['ret'] = benchmark_data[benchmark] / benchmark_data[benchmark].shift(1) - 1.\n",
"benchmark_data['d1ret_b'] = benchmark_data['ret'] .shift(-1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.merge(df, benchmark_data[['Date', 'd1ret_b']], on='Date', how='left')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.dropna(inplace=True)\n",
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# to transform industry codes to int variable\n",
"old_ind_values = df['申万一级行业'].copy()\n",
"\n",
"ind_list = df['申万一级行业'].unique()\n",
"ind_dict = {}\n",
"for i, ind in enumerate(ind_list):\n",
" ind_dict[ind] = i\n",
"\n",
"df['申万一级行业'].replace(ind_dict, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Factor Date Preprocessing (Winsorize -> Standardize -> neutralize)\n",
"---------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import alphamind.data.neutralize as ne\n",
"import alphamind.data.winsorize as ws\n",
"import alphamind.data.standardize as st"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"total_data = df.copy()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"total_data.loc[:, risk_factor_cols] = total_data[risk_factor_cols].groupby(total_data.Date).transform(lambda x: x / x.sum())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"risk_factor_cols"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"y = total_data[prod_factors].values\n",
"groups = total_data.Date.values.astype(np.int)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"neutralized_values = ne.neutralize(total_data[risk_factor_cols].values,\n",
" st.standardize(ws.winsorize_normal(y, groups=groups),\n",
" groups=groups),\n",
" groups)\n",
"\n",
"total_data['res'] = neutralized_values @ product_weights"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data[['res', 'Date', 'Code']].tail()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Factor Performance (long_short)\n",
"------------------------------------------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"total_data['pos_long_short'] = total_data.res.groupby(groups).apply(lambda x: x / np.abs(x).sum())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data[['pos_long_short', 'res', 'dailyReturn', 'd1ret', 'd1ret_b', 'Code', 'Date']].tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"to_look_into = total_data[risk_factor_cols].multiply(total_data.pos_long_short, axis=0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().max()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().min()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_series = (total_data.pos_long_short * total_data.d1ret).groupby(total_data.Date).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series.cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series[-60:].cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data.pos_long_short.groupby(total_data.Date).apply(lambda x: x.sum()).head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Factor Performance (Long Only - Top 100 Equal Weighted)\n",
"------------------------------------------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import alphamind.portfolio.rankbuilder as rb"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"use_rank = 100\n",
"total_data['pos_100'] = rb.rank_build(total_data.res.values, use_rank, groups) / use_rank"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data[['pos_100', 'res', 'dailyReturn', 'd1ret', 'd1ret_b', 'Code', 'Date']].tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"to_look_into = total_data[risk_factor_cols].multiply(total_data.pos_100 - total_data[index_components], axis=0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().max()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().min()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_series = ((total_data.pos_100 - total_data[index_components]) * total_data.d1ret).groupby(total_data.Date).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series.cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series[-60:].cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data.pos_100.groupby(total_data.Date).sum().head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_pos_100 = ret_series.copy()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Factor Performance (Long Only - Top 100 Uniformly Distributed In Each Sector Equal Weighted)\n",
"-------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import alphamind.portfolio.percentbuilder as pb"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"factor_data_values = total_data[['Date', 'res', '申万一级行业']]\n",
"\n",
"def get_percent_pos(x):\n",
" res_values = x.res.values\n",
" percent = 115. / len(res_values)\n",
" ind_values = x['申万一级行业'].values.astype(int)\n",
" final_choosed = pb.percent_build(res_values, percent, ind_values)\n",
" return pd.Series(final_choosed / final_choosed.sum())\n",
"\n",
"total_data['pos_100_uind'] = factor_data_values.groupby('Date').apply(get_percent_pos).values"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(total_data['pos_100_uind'] > 0).groupby(total_data.Date).sum().plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"to_look_into = total_data[risk_factor_cols].multiply(total_data.pos_100_uind - total_data[index_components], axis=0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().max()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().min()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data[['pos_100_uind', 'res', 'dailyReturn', 'd1ret', 'd1ret_b', 'Code', 'Date']].tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_series = ((total_data.pos_100_uind - total_data[index_components]) * total_data.d1ret).groupby(total_data.Date).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series.cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series[-60:].cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data.pos_100_uind.groupby(total_data.Date).sum().head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_100_uind = ret_series.copy()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Factor Performance (Long Only - Match Benchark Sectors)\n",
"-------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import alphamind.portfolio.linearbuilder as lb"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"\n",
"lbound_exposure = -0.00001 * np.ones(len(risk_factor_cols))\n",
"ubound_exposure = 0.00001 * np.ones(len(risk_factor_cols))\n",
"lbound_exposure[-2] = -0.01\n",
"ubound_exposure[-2] = 0.01\n",
"\n",
"def get_benchmark_match_pos(x):\n",
" er = x.res.values\n",
" bm = x[index_components].values\n",
" lbound = 0.\n",
" ubound = 0.01 #+ bm\n",
" risk_exposure = x[risk_factor_cols].values\n",
" \n",
" status, value , ret = lb.linear_build(er,\n",
" lbound=lbound,\n",
" ubound=ubound,\n",
" risk_exposure=risk_exposure,\n",
" bm=bm,\n",
" risk_target=(lbound_exposure, ubound_exposure),\n",
" solver=None)\n",
" print(x.Date.unique()[0], ': ', status)\n",
" \n",
" if status != 'optimal':\n",
" return pd.Series(np.ones(len(er)) / len(er))\n",
" else:\n",
" return pd.Series(ret)\n",
"\n",
"res = total_data.groupby('Date').apply(get_benchmark_match_pos).values\n",
"total_data['pos_bmat'] = res"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(total_data['pos_bmat'] > 1e-4).groupby(total_data.Date).sum().plot(ylim=(50, 250), figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"to_look_into = total_data[risk_factor_cols].multiply(total_data.pos_bmat - total_data[index_components], axis=0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().max()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"to_look_into.groupby(total_data.Date).sum().min()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_data[['pos_bmat', 'res', 'dailyReturn', 'd1ret', 'd1ret_b', 'Code', 'Date']].tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_series = ((total_data.pos_bmat - total_data[index_components]) * total_data.d1ret).groupby(total_data.Date).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series.cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ret_series[-60:].cumsum().plot(figsize=(14,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_bmat = ret_series.copy()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Performance Analysis and Comparison\n",
"------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ret_mat = pd.DataFrame({'pos_100': ret_pos_100,\n",
" 'pos_100_uind': ret_100_uind,\n",
" 'pos_bmat': ret_bmat})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"sharp_mat = ret_mat.rolling(window=250).mean() / ret_mat.rolling(window=250).std() * np.sqrt(250)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sharp_mat.plot(figsize=(14, 7))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Postion Analysis and Comparison\n",
"----------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"pos_table = total_data[['Date', 'Code', '申万一级行业', 'pos_long_short', 'pos_100', 'pos_100_uind', 'pos_bmat', index_components]].copy()\n",
"pos_table.loc[:, '申万一级行业'] = old_ind_values.values\n",
"\n",
"for name in ['pos_100', 'pos_100_uind', 'pos_bmat']:\n",
" pos_table.loc[:, name] = pos_table[name] - pos_table[index_components]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"aggregated_pos_table = pos_table.groupby(['Date', '申万一级行业']).sum()\n",
"aggregated_pos_table.reset_index(level=1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_pos_table.loc[aggregated_pos_table['申万一级行业'] == '申万家用电器',['pos_long_short', 'pos_100', 'pos_100_uind', 'pos_bmat']].plot(figsize=(16,7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_pos_table[['pos_long_short', 'pos_100', 'pos_100_uind', 'pos_bmat']].corr()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"turn_over_table = {}\n",
"\n",
"for name in ['pos_long_short', 'pos_100', 'pos_100_uind', 'pos_bmat']:\n",
" pos_series = pos_table[['Date', 'Code', name]]\n",
" pivot_position = pos_series.pivot_table(name, index='Date', columns='Code').fillna(0.)\n",
" turn_over_series = pivot_position.diff().abs().sum(axis=1)\n",
" turn_over_table[name] = turn_over_series.values\n",
" \n",
"turn_over_table = pd.DataFrame(turn_over_table, index=pos_table.Date.unique())\n",
"turn_over_table.tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"turn_over_table.plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(turn_over_table * 0.0015).plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(turn_over_table[-60:].cumsum() * 0.0015).plot(figsize=(14, 7))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Risk Exposure (Long Short)\n",
"---------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import alphamind.analysis.riskanalysis as ra"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"net_weight = total_data.pos_long_short\n",
"next_bar_return_series = total_data.d1ret\n",
"risk_table = total_data[risk_factor_cols]\n",
"net_weight.index = total_data.Date\n",
"next_bar_return_series.index = total_data.Date\n",
"risk_table.index = total_data.Date"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"explained_table, exposure_table = ra.risk_analysis(net_weight, next_bar_return_series, risk_table)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"aggregated_bars = explained_table.groupby(level=0).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"top_sources = aggregated_bars.sum().abs().sort_values(ascending=False).index[:10]\n",
"aggregated_bars.sum().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].cumsum().plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].plot(figsize=(14, 7))\n",
"plt.legend(loc='upper center', ncol=int(len(top_sources[1:]) // 3) + 1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Risk Exposure (Long Only - Top 100)\n",
"-------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"net_weight = total_data.pos_100 - total_data[index_components]\n",
"net_weight.index = total_data.Date"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"explained_table, exposure_table = ra.risk_analysis(net_weight, next_bar_return_series, risk_table)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"aggregated_bars = explained_table.groupby(level=0).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"top_sources = aggregated_bars.sum().abs().sort_values(ascending=False).index[:10]\n",
"aggregated_bars.sum().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].cumsum().plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].plot(figsize=(14, 7))\n",
"plt.legend(loc='upper center', ncol=int(len(top_sources[1:]) // 3) + 1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Risk Exposure (Long Only - Top 100 Uniformly Distributed)\n",
"-------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"net_weight = total_data.pos_100_uind - total_data[index_components]\n",
"net_weight.index = total_data.Date"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"explained_table, exposure_table = ra.risk_analysis(net_weight, next_bar_return_series, risk_table)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"aggregated_bars = explained_table.groupby(level=0).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"top_sources = aggregated_bars.sum().abs().sort_values(ascending=False).index[:10]\n",
"aggregated_bars.sum().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].cumsum().plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].plot(figsize=(14, 7))\n",
"plt.legend(loc='upper center', ncol=int(len(top_sources[1:]) // 3) + 1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Risk Exposure (Long Only - Match Benchmark Sectors)\n",
"--------------------------------------------------------"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"net_weight = total_data.pos_bmat - total_data[index_components]\n",
"net_weight.index = total_data.Date"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"explained_table, exposure_table = ra.risk_analysis(net_weight, next_bar_return_series, risk_table)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"aggregated_bars = explained_table.groupby(level=0).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"top_sources = aggregated_bars.sum().abs().sort_values(ascending=False).index[:10]\n",
"aggregated_bars.sum().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].cumsum().plot(figsize=(14, 7))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"aggregated_bars[top_sources.difference(['idiosyncratic'])].plot(figsize=(14, 7))\n",
"plt.legend(loc='upper center', ncol=int(len(top_sources[1:]) // 3) + 1)"
]
},
{
"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",
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
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