dwker/strategy-lab
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

stumpy added

Browse Source
This commit is contained in:
David Brazda
2024-09-27 15:19:09 +02:00
parent a23834a938
commit 9c2e8b18a2
8 changed files with 1082743 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
output.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 21 KiB

932
research/strat_MARKOV_REGIME/v1_MULTI.ipynb Normal file
View File

@ -0,0 +1,932 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from v2realbot.tools.loadbatch import load_batch\n",
"from v2realbot.utils.utils import zoneNY\n",
"import pandas as pd\n",
"import numpy as np\n",
"import vectorbtpro as vbt\n",
"from itables import init_notebook_mode, show\n",
"import datetime\n",
"from itertools import product\n",
"from v2realbot.config import ACCOUNT1_PAPER_API_KEY, ACCOUNT1_PAPER_SECRET_KEY, DATA_DIR\n",
"\n",
"init_notebook_mode(all_interactive=True)\n",
"\n",
"vbt.settings.set_theme(\"dark\")\n",
"vbt.settings['plotting']['layout']['width'] = 1280\n",
"vbt.settings.plotting.auto_rangebreaks = True\n",
"# Set the option to display with pagination\n",
"pd.set_option('display.notebook_repr_html', True)\n",
"pd.set_option('display.max_rows', 10) # Number of rows per page\n",
"\n",
"# Define the market open and close times\n",
"market_open = datetime.time(9, 30)\n",
"market_close = datetime.time(16, 0)\n",
"entry_window_opens = 1\n",
"entry_window_closes = 370\n",
"\n",
"forced_exit_start = 380\n",
"forced_exit_end = 390\n",
"\n",
"#LOAD FROM PARQUET\n",
"#list all files is dir directory with parquet extension\n",
"dir = DATA_DIR + \"/notebooks/\"\n",
"import os\n",
"files = [f for f in os.listdir(dir) if f.endswith(\".parquet\")]\n",
"#print('\\n'.join(map(str, files)))\n",
"file_name = \"ohlcv_df-SPY-2024-01-01T09:30:00-2024-05-14T16:00:00.parquet\"\n",
"ohlcv_df = pd.read_parquet(dir+file_name,engine='pyarrow')\n",
"basic_data = vbt.Data.from_data(vbt.symbol_dict({\"SPY\": ohlcv_df}), tz_convert=zoneNY)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#parameters (primary y line, secondary y line, close)\n",
"def plot_2y_close(priminds, secinds, close):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"MOM\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False), trace_kwargs=dict(line=dict(color=\"blue\")))\n",
" for ind in priminds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" for ind in secinds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" return fig\n",
"\n",
"# close = basic_data.xloc[\"09:30\":\"10:00\"].close"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#PIPELINE - FOR - LOOP\n",
"\n",
"#indicator parameters\n",
"mom_timeperiod = list(range(2, 12))\n",
"\n",
"#uzavreni okna od 1 do 200\n",
"#entry_window_closes = list(range(2, 50, 3))\n",
"entry_window_closes = [5, 10, 30, 45]\n",
"#entry_window_closes = 30\n",
"#threshold entries parameters\n",
"#long\n",
"mom_th = np.round(np.arange(0.01, 0.5 + 0.02, 0.02),4).tolist()#-0.02\n",
"# short\n",
"#mom_th = np.round(np.arange(-0.01, -0.3 - 0.02, -0.02),4).tolist()#-0.02\n",
"roc_th = np.round(np.arange(-0.2, -0.8 - 0.05, -0.05),4).tolist()#-0.2\n",
"#print(mom_th, roc_th)\n",
"\n",
"#portfolio simulation parameters\n",
"sl_stop =np.round(np.arange(0.02/100, 0.7/100, 0.05/100),4).tolist()\n",
"tp_stop = np.round(np.arange(0.02/100, 0.7/100, 0.05/100),4).tolist()\n",
"\n",
"combs = list(product(mom_timeperiod, mom_th, roc_th, sl_stop, tp_stop))\n",
"\n",
"@vbt.parameterized(merge_func = \"concat\", random_subset = 2000, show_progress=True) \n",
"def test_strat(entry_window_closes=60,\n",
" mom_timeperiod=2,\n",
" mom_th=-0.04,\n",
" #roc_th=-0.2,\n",
" sl_stop=0.19/100,\n",
" tp_stop=0.19/100):\n",
" # mom_timeperiod=2\n",
" # mom_th=-0.06\n",
" # roc_th=-0.2\n",
" # sl_stop=0.04/100\n",
" # tp_stop=0.04/100\n",
"\n",
" momshort = vbt.indicator(\"talib:MOM\").run(basic_data.close, timeperiod=mom_timeperiod, short_name = \"slope_short\")\n",
" rocp = vbt.indicator(\"talib:ROC\").run(basic_data.close, short_name = \"rocp\")\n",
" #rate of change + momentum\n",
"\n",
" #momshort.plot rocp.real_crossed_below(roc_th) & \n",
" #short_signal = momshort.real_crossed_below(mom_th)\n",
" long_signal = momshort.real_crossed_above(mom_th)\n",
" # print(\"short signal\")\n",
" # print(short_signal.value_counts())\n",
"\n",
" #forced_exit = pd.Series(False, index=close.index)\n",
" forced_exit = basic_data.symbol_wrapper.fill(False)\n",
" #entry_window_open = pd.Series(False, index=close.index)\n",
" entry_window_open= basic_data.symbol_wrapper.fill(False)\n",
"\n",
" #print(entry_window_closes, \"entry window closes\")\n",
" # Calculate the time difference in minutes from market open for each timestamp\n",
" elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
" entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"\n",
" #print(entry_window_open.value_counts())\n",
"\n",
" forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
" #short_entries = (short_signal & entry_window_open)\n",
" #short_exits = forced_exit\n",
" entries = (long_signal & entry_window_open)\n",
" exits = forced_exit\n",
" #long_entries.info()\n",
" #number of trues and falses in long_entries\n",
" #print(short_exits.value_counts())\n",
" #print(short_entries.value_counts())\n",
"\n",
" #fig = plot_2y_close([],[momshort, rocp], close)\n",
" #short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" #print(sl_stop)\n",
" #tsl_th=sl_stop, \n",
" #short_entries=short_entries, short_exits=short_exits,\n",
" pf = vbt.Portfolio.from_signals(close=basic_data.close, entries=entries, exits=exits, tsl_stop=sl_stop, tp_stop = tp_stop, fees=0.0167/100, freq=\"1s\", price=\"close\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
" \n",
" return pf.stats([\n",
" 'total_return',\n",
" 'max_dd', \n",
" 'total_trades', \n",
" 'win_rate', \n",
" 'expectancy'\n",
" ])\n",
"\n",
"pf_results = test_strat(vbt.Param(entry_window_closes),\n",
" vbt.Param(mom_timeperiod),\n",
" vbt.Param(mom_th),\n",
" #vbt.Param(roc_th)\n",
" vbt.Param(sl_stop),\n",
" vbt.Param(tp_stop, condition=\"tp_stop > sl_stop\"))\n",
"pf_results = pf_results.unstack(level=-1)\n",
"pf_results.sort_values(by=[\"Total Return [%]\", \"Max Drawdown [%]\"], ascending=[False, True])\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#pf_results.load(\"10tiscomb.pickle\")\n",
"#pf_results.info()\n",
"\n",
"vbt.save(pf_results, \"8tiscomb_tsl.pickle\")\n",
"\n",
"# pf_results = vbt.load(\"8tiscomb_tsl.pickle\")\n",
"# pf_results\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# parallel_coordinates method¶\n",
"\n",
"# attach_px_methods.<locals>.plot_func(\n",
"# *args,\n",
"# layout=None,\n",
"# **kwargs\n",
"# )\n",
"\n",
"# pf_results.vbt.px.parallel_coordinates() #ocdf\n",
"\n",
"res = pf_results.reset_index()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf_results"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.preprocessing import StandardScaler\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Assuming pf_results is your DataFrame\n",
"# Convert columns to numeric, assuming NaNs where conversion fails\n",
"metrics = ['Total Return [%]', 'Max Drawdown [%]', 'Total Trades']\n",
"for metric in metrics:\n",
" pf_results[metric] = pd.to_numeric(pf_results[metric], errors='coerce')\n",
"\n",
"# Handle missing values, for example filling with the median\n",
"pf_results['Max Drawdown [%]'].fillna(pf_results['Max Drawdown [%]'].median(), inplace=True)\n",
"\n",
"# Extract the metrics into a new DataFrame\n",
"data_for_pca = pf_results[metrics]\n",
"\n",
"# Standardize the data before applying PCA\n",
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(data_for_pca)\n",
"\n",
"# Apply PCA\n",
"pca = PCA(n_components=2) # Adjust components as needed\n",
"principal_components = pca.fit_transform(data_scaled)\n",
"\n",
"# Create a DataFrame with the principal components\n",
"pca_results = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])\n",
"\n",
"# Visualize the results\n",
"plt.figure(figsize=(8,6))\n",
"plt.scatter(pca_results['PC1'], pca_results['PC2'], alpha=0.5)\n",
"plt.xlabel('Principal Component 1')\n",
"plt.ylabel('Principal Component 2')\n",
"plt.title('PCA of Strategy Optimization Results')\n",
"plt.grid(True)\n",
"plt.savefig(\"ddd.png\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check if there is any unnamed level and rename it\n",
"if None in df.index.names:\n",
" # Generate new names list replacing None with 'stat'\n",
" new_names = ['stat' if name is None else name for name in df.index.names]\n",
" df.index.set_names(new_names, inplace=True)\n",
"\n",
"rs= df\n",
"\n",
"rs.info()\n",
"\n",
"\n",
"# # Now, 'stat' is the name of the previously unnamed level\n",
"\n",
"# # Filter for 'Total Return' assuming it is a correct identifier in the 'stat' level\n",
"# total_return_series = df.xs('Total Return [%]', level='stat')\n",
"\n",
"# # Sort the Series to get the largest 'Total Return' values\n",
"# sorted_series = total_return_series.sort_values(ascending=False)\n",
"\n",
"# # Print the sorted filtered data\n",
"# sorted_series.head(20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted_series.vbt.save()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#df.info()\n",
"total_return_series = df.xs('Total Return [%]')\n",
"sorted_series = total_return_series.sort_values(ascending=False)\n",
"\n",
"# Display the top N entries, e.g., top 5\n",
"sorted_series.head(5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"comb_stats_df.nlargest(10, 'Total Return [%]')\n",
"#stats_df.info()\n",
"\n",
"\n",
"8\t-0.06\t-0.2\t0.0028\t0.0048\t4.156254\n",
"4 -0.02 -0.25 0.0028 0.0048 0.84433\n",
"3 -0.02 -0.25 0.0033 0.0023 Total Return [%] 0.846753\n",
"#2\t-0.04\t-0.2\t0.0019\t0.0019\n",
"# 2\t-0.04\t-0.2\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.25\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.3\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.35\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.4\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.2\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.25\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.3\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.35\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.4\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"basic_data.symbols"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
">>> def apply_func(ts, entries, exits, fastw, sloww, minp=None):\n",
"... fast_ma = vbt.nb.rolling_mean_nb(ts, fastw, minp=minp)\n",
"... slow_ma = vbt.nb.rolling_mean_nb(ts, sloww, minp=minp)\n",
"... entries[:] = vbt.nb.crossed_above_nb(fast_ma, slow_ma) \n",
"... exits[:] = vbt.nb.crossed_above_nb(slow_ma, fast_ma)\n",
"... return (fast_ma, slow_ma) \n",
"\n",
">>> CrossSig = vbt.IF(\n",
"... class_name=\"CrossSig\",\n",
"... input_names=['ts'],\n",
"... in_output_names=['entries', 'exits'],\n",
"... param_names=['fastw', 'sloww'],\n",
"... output_names=['fast_ma', 'slow_ma']\n",
"... ).with_apply_func(\n",
"... apply_func,\n",
"... in_output_settings=dict(\n",
"... entries=dict(dtype=np.bool_), #initialize output with bool\n",
"... exits=dict(dtype=np.bool_)\n",
"... )\n",
"... )\n",
">>> cross_sig = CrossSig.run(ts2, 2, 4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#PIPELINE - parameters in one go\n",
"\n",
"\n",
"#TOTO prepsat do FOR-LOOPu\n",
"\n",
"\n",
"#indicator parameters\n",
"mom_timeperiod = list(range(2, 6))\n",
"\n",
"#threshold entries parameters\n",
"mom_th = np.round(np.arange(-0.02, -0.1 - 0.02, -0.02),4).tolist()#-0.02\n",
"roc_th = np.round(np.arange(-0.2, -0.4 - 0.05, -0.05),4).tolist()#-0.2\n",
"#print(mom_th, roc_th)\n",
"#jejich product\n",
"# mom_th_prod, roc_th_prod = zip(*product(mom_th, roc_th))\n",
"\n",
"# #convert threshold to vbt param\n",
"# mom_th_index = vbt.Param(mom_th_prod, name='mom_th_th') \n",
"# roc_th_index = vbt.Param(roc_th_prod, name='roc_th_th')\n",
"\n",
"mom_th = vbt.Param(mom_th, name='mom_th')\n",
"roc_th = vbt.Param(roc_th, name='roc_th')\n",
"\n",
"#portfolio simulation parameters\n",
"sl_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"sl_stop = [round(val, 4) for val in sl_stop]\n",
"tp_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"tp_stop = [round(val, 4) for val in tp_stop]\n",
"sl_stop = vbt.Param(sl_stop) #np.nan mean s no stoploss\n",
"tp_stop = vbt.Param(tp_stop) #np.nan mean s no stoploss\n",
"\n",
"\n",
"#def test_mom(window=14, mom_th=0.2, roc_th=0.2, sl_stop=0.03/100, tp_stop=0.03/100):\n",
"#close = basic_data.xloc[\"09:30\":\"10:00\"].close\n",
"momshort = vbt.indicator(\"talib:MOM\").run(basic_data.get(\"Close\"), timeperiod=mom_timeperiod, short_name = \"slope_short\")\n",
"\n",
"#ht_trendline = vbt.indicator(\"talib:HT_TRENDLINE\").run(close, short_name = \"httrendline\")\n",
"rocp = vbt.indicator(\"talib:ROC\").run(basic_data.get(\"Close\"), short_name = \"rocp\")\n",
"#rate of change + momentum\n",
"\n",
"rocp_signal = rocp.real_crossed_below(mom_th)\n",
"mom_signal = momshort.real_crossed_below(roc_th)\n",
"\n",
"#mom_signal\n",
"print(rocp_signal.info())\n",
"print(mom_signal.info())\n",
"#print(rocp.real)\n",
"\n",
"\n",
"short_signal = (mom_signal.vbt & rocp_signal)\n",
"\n",
"# #short_signal = (rocp.real_crossed_below(roc_th_index) & momshort.real_crossed_below(mom_th_index))\n",
"# forced_exit = m1_data.symbol_wrapper.fill(False)\n",
"# entry_window_open= m1_data.symbol_wrapper.fill(False)\n",
"\n",
"\n",
"# # Calculate the time difference in minutes from market open for each timestamp\n",
"# elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
"# entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"# forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
"# short_entries = (short_signal & entry_window_open)\n",
"# short_exits = forced_exit\n",
"# #long_entries.info()\n",
"# #number of trues and falses in long_entries\n",
"# #short_exits.value_counts()\n",
"# #short_entries.value_counts()\n",
"\n",
"\n",
"# pf = vbt.Portfolio.from_signals(close=close, short_entries=short_entries, short_exits=short_exits, sl_stop=sl_stop, tp_stop = tp_stop, fees=0.0167/100, freq=\"1s\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# filter dates"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#filter na dny\n",
"dates_of_interest = pd.to_datetime(['2024-04-22']).tz_localize('US/Eastern')\n",
"filtered_df = df.loc[df.index.normalize().isin(dates_of_interest)]\n",
"\n",
"df = filtered_df\n",
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# import plotly.io as pio\n",
"# pio.renderers.default = 'notebook'\n",
"\n",
"#naloadujeme do vbt symbol as column\n",
"basic_data = vbt.Data.from_data({\"BAC\": df}, tz_convert=zoneNY)\n",
"\n",
"vbt.settings.plotting.auto_rangebreaks = True\n",
"#basic_data.data[\"BAC\"].vbt.ohlcv.plot()\n",
"\n",
"#basic_data.data[\"BAC\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"m1_data = basic_data[['Open', 'High', 'Low', 'Close', 'Volume']]\n",
"\n",
"m1_data.data[\"BAC\"]\n",
"#m5_data = m1_data.resample(\"5T\")\n",
"\n",
"#m5_data.data[\"BAC\"].head(10)\n",
"\n",
"# m15_data = m1_data.resample(\"15T\")\n",
"\n",
"# m15 = m15_data.data[\"BAC\"]\n",
"\n",
"# m15.vbt.ohlcv.plot()\n",
"\n",
"# m1_data.wrapper.index\n",
"\n",
"# m1_resampler = m1_data.wrapper.get_resampler(\"1T\")\n",
"# m1_resampler.index_difference(reverse=True)\n",
"\n",
"\n",
"# m5_resampler.prettify()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# MOM indicator"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"vbt.phelp(vbt.indicator(\"talib:ROCP\").run)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"vyuzití rychleho klesani na sekundove urovni behem open rush\n",
"- MOM + ROC during open rush\n",
"- short signal\n",
"- pipeline kombinace thresholdu pro vstup mom_th, roc_th + hodnota sl_stop a tp_stop (pripadne trailing) - nalezeni optimalni kombinace atributu"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# fig = plot_2y_close([ht_trendline],[momshort, rocp], close)\n",
"# short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
"\n",
"#parameters (primary y line, secondary y line, close)\n",
"def plot_2y_close(priminds, secinds, close):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"MOM\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False), trace_kwargs=dict(line=dict(color=\"blue\")))\n",
" for ind in priminds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" for ind in secinds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" return fig\n",
"\n",
"close = m1_data.xloc[\"09:30\":\"10:00\"].close\n",
"momshort = vbt.indicator(\"talib:MOM\").run(close, timeperiod=3, short_name = \"slope_short\")\n",
"ht_trendline = vbt.indicator(\"talib:HT_TRENDLINE\").run(close, short_name = \"httrendline\")\n",
"rocp = vbt.indicator(\"talib:ROC\").run(close, short_name = \"rocp\")\n",
"#rate of change + momentum\n",
"short_signal = (rocp.real_crossed_below(-0.2) & momshort.real_crossed_below(-0.02))\n",
"#indlong = vbt.indicator(\"talib:MOM\").run(close, timeperiod=10, short_name = \"slope_long\")\n",
"fig = plot_2y_close([ht_trendline],[momshort, rocp], close)\n",
"short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"close = m1_data.close\n",
"#vbt.phelp(vbt.OLS.run)\n",
"\n",
"#oer steepmnes of regression line\n",
"#talib.LINEARREG_SLOPE(close, timeperiod=timeperiod)\n",
"#a také ON BALANCE VOLUME - http://5.161.179.223:8000/static/js/vbt/api/indicators/custom/obv/index.html\n",
"\n",
"\n",
"\n",
"mom_ind = vbt.indicator(\"talib:MOM\") \n",
"#vbt.phelp(mom_ind.run)\n",
"\n",
"mom = mom_ind.run(close, timeperiod=10)\n",
"\n",
"plot_2y_close(mom, close)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# defining ENTRY WINDOW and forced EXIT window"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#m1_data.data[\"BAC\"].info()\n",
"import datetime\n",
"# Define the market open and close times\n",
"market_open = datetime.time(9, 30)\n",
"market_close = datetime.time(16, 0)\n",
"entry_window_opens = 2\n",
"entry_window_closes = 30\n",
"\n",
"forced_exit_start = 380\n",
"forced_exit_end = 390\n",
"\n",
"forced_exit = m1_data.symbol_wrapper.fill(False)\n",
"entry_window_open= m1_data.symbol_wrapper.fill(False)\n",
"\n",
"# Calculate the time difference in minutes from market open for each timestamp\n",
"elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
"entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
"\n",
"#entry_window_open.info()\n",
"# forced_exit.tail(100)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"close = m1_data.close\n",
"\n",
"#rsi = vbt.RSI.run(close, window=14)\n",
"\n",
"short_entries = (short_signal & entry_window_open)\n",
"short_exits = forced_exit\n",
"#long_entries.info()\n",
"#number of trues and falses in long_entries\n",
"#short_exits.value_counts()\n",
"short_entries.value_counts()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def plot_rsi(close, entries, exits):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"RSI\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" #rsi.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" entries.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
" exits.vbt.signals.plot_as_exits(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
" return fig\n",
"\n",
"plot_rsi(close, short_entries, short_exits)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"vbt.phelp(vbt.Portfolio.from_signals)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sl_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"sl_stop = [round(val, 4) for val in sl_stop]\n",
"print(sl_stop)\n",
"sl_stop = vbt.Param(sl_stop) #np.nan mean s no stoploss\n",
"\n",
"pf = vbt.Portfolio.from_signals(close=close, short_entries=short_entries, short_exits=short_exits, sl_stop=0.03/100, tp_stop = 0.03/100, fees=0.0167/100, freq=\"1s\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
"\n",
"#pf.stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#list of orders\n",
"#pf.orders.records_readable\n",
"#pf.orders.plots()\n",
"#pf.stats()\n",
"pf.stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[(0.0015,0.0013)].plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[0.03].plot_trade_signals()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# pristup k pf jako multi index"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#pf[0.03].plot()\n",
"#pf.order_records\n",
"pf[(0.03)].stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#zgrupovane statistiky\n",
"stats_df = pf.stats([\n",
" 'total_return',\n",
" 'total_trades',\n",
" 'win_rate',\n",
" 'expectancy'\n",
"], agg_func=None)\n",
"stats_df\n",
"\n",
"\n",
"stats_df.nlargest(10, 'Total Return [%]')\n",
"#stats_df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[(0.0011,0.0013000000000000002)].plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pandas.tseries.offsets import DateOffset\n",
"\n",
"temp_data = basic_data['2024-4-22']\n",
"temp_data\n",
"res1m = temp_data[[\"Open\", \"High\", \"Low\", \"Close\", \"Volume\"]]\n",
"\n",
"# Define a custom date offset that starts at 9:30 AM and spans 4 hours\n",
"custom_offset = DateOffset(hours=4, minutes=30)\n",
"\n",
"# res1m = res1m.get().resample(\"4H\").agg({ \n",
"# \"Open\": \"first\",\n",
"# \"High\": \"max\",\n",
"# \"Low\": \"min\",\n",
"# \"Close\": \"last\",\n",
"# \"Volume\": \"sum\"\n",
"# })\n",
"\n",
"res4h = res1m.resample(\"1h\", resample_kwargs=dict(origin=\"start\"))\n",
"\n",
"res4h.data\n",
"\n",
"res15m = res1m.resample(\"15T\", resample_kwargs=dict(origin=\"start\"))\n",
"\n",
"res15m.data[\"BAC\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"@vbt.njit\n",
"def long_entry_place_func_nb(c, low, close, time_in_ns, rsi14, window_open, window_close):\n",
" market_open_minutes = 570 # 9 hours * 60 minutes + 30 minutes\n",
"\n",
" for out_i in range(len(c.out)):\n",
" i = c.from_i + out_i\n",
"\n",
" current_minutes = vbt.dt_nb.hour_nb(time_in_ns[i]) * 60 + vbt.dt_nb.minute_nb(time_in_ns[i])\n",
" #print(\"current_minutes\", current_minutes)\n",
" # Calculate elapsed minutes since market open at 9:30 AM\n",
" elapsed_from_open = current_minutes - market_open_minutes\n",
" elapsed_from_open = elapsed_from_open if elapsed_from_open >= 0 else 0\n",
" #print( \"elapsed_from_open\", elapsed_from_open)\n",
"\n",
" #elapsed_from_open = elapsed_minutes_from_open_nb(time_in_ns) \n",
" in_window = elapsed_from_open > window_open and elapsed_from_open < window_close\n",
" #print(\"in_window\", in_window)\n",
" # if in_window:\n",
" # print(\"in window\")\n",
"\n",
" if in_window and rsi14[i] > 60: # and low[i, c.col] <= hit_price: # and hour == 9: # (4)!\n",
" return out_i\n",
" return -1\n",
"\n",
"@vbt.njit\n",
"def long_exit_place_func_nb(c, high, close, time_index, tp, sl): # (5)!\n",
" entry_i = c.from_i - c.wait\n",
" entry_price = close[entry_i, c.col]\n",
" hit_price = entry_price * (1 + tp)\n",
" stop_price = entry_price * (1 - sl)\n",
" for out_i in range(len(c.out)):\n",
" i = c.from_i + out_i\n",
" last_bar_of_day = vbt.dt_nb.day_changed_nb(time_index[i], time_index[i + 1])\n",
"\n",
" #print(next_day)\n",
" if last_bar_of_day: #pokud je dalsi next day, tak zavirame posledni\n",
" print(\"ted\",out_i)\n",
" return out_i\n",
" if close[i, c.col] >= hit_price or close[i, c.col] <= stop_price :\n",
" return out_i\n",
" return -1\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(np.random.random(size=(5, 10)), columns=list('abcdefghij'))\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.sum()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

1890
research/strat_MARKOV_REGIME/v2_SINGLE.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

7839
research/strat_STUMPY/STUMPY_OHLCV.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

445200
research/strat_STUMPY/STUMPY_OHLCV_animated.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

2038
research/strat_STUMPY/USREC.csv Normal file
View File

File diff suppressed because it is too large Load Diff

623912
research/strat_STUMPY/stumpy_test_shittles.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

932
research/strat_STUMPY/v1_MULTI.ipynb Normal file
View File

@ -0,0 +1,932 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from v2realbot.tools.loadbatch import load_batch\n",
"from v2realbot.utils.utils import zoneNY\n",
"import pandas as pd\n",
"import numpy as np\n",
"import vectorbtpro as vbt\n",
"from itables import init_notebook_mode, show\n",
"import datetime\n",
"from itertools import product\n",
"from v2realbot.config import ACCOUNT1_PAPER_API_KEY, ACCOUNT1_PAPER_SECRET_KEY, DATA_DIR\n",
"\n",
"init_notebook_mode(all_interactive=True)\n",
"\n",
"vbt.settings.set_theme(\"dark\")\n",
"vbt.settings['plotting']['layout']['width'] = 1280\n",
"vbt.settings.plotting.auto_rangebreaks = True\n",
"# Set the option to display with pagination\n",
"pd.set_option('display.notebook_repr_html', True)\n",
"pd.set_option('display.max_rows', 10) # Number of rows per page\n",
"\n",
"# Define the market open and close times\n",
"market_open = datetime.time(9, 30)\n",
"market_close = datetime.time(16, 0)\n",
"entry_window_opens = 1\n",
"entry_window_closes = 370\n",
"\n",
"forced_exit_start = 380\n",
"forced_exit_end = 390\n",
"\n",
"#LOAD FROM PARQUET\n",
"#list all files is dir directory with parquet extension\n",
"dir = DATA_DIR + \"/notebooks/\"\n",
"import os\n",
"files = [f for f in os.listdir(dir) if f.endswith(\".parquet\")]\n",
"#print('\\n'.join(map(str, files)))\n",
"file_name = \"ohlcv_df-SPY-2024-01-01T09:30:00-2024-05-14T16:00:00.parquet\"\n",
"ohlcv_df = pd.read_parquet(dir+file_name,engine='pyarrow')\n",
"basic_data = vbt.Data.from_data(vbt.symbol_dict({\"SPY\": ohlcv_df}), tz_convert=zoneNY)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#parameters (primary y line, secondary y line, close)\n",
"def plot_2y_close(priminds, secinds, close):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"MOM\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False), trace_kwargs=dict(line=dict(color=\"blue\")))\n",
" for ind in priminds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" for ind in secinds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" return fig\n",
"\n",
"# close = basic_data.xloc[\"09:30\":\"10:00\"].close"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#PIPELINE - FOR - LOOP\n",
"\n",
"#indicator parameters\n",
"mom_timeperiod = list(range(2, 12))\n",
"\n",
"#uzavreni okna od 1 do 200\n",
"#entry_window_closes = list(range(2, 50, 3))\n",
"entry_window_closes = [5, 10, 30, 45]\n",
"#entry_window_closes = 30\n",
"#threshold entries parameters\n",
"#long\n",
"mom_th = np.round(np.arange(0.01, 0.5 + 0.02, 0.02),4).tolist()#-0.02\n",
"# short\n",
"#mom_th = np.round(np.arange(-0.01, -0.3 - 0.02, -0.02),4).tolist()#-0.02\n",
"roc_th = np.round(np.arange(-0.2, -0.8 - 0.05, -0.05),4).tolist()#-0.2\n",
"#print(mom_th, roc_th)\n",
"\n",
"#portfolio simulation parameters\n",
"sl_stop =np.round(np.arange(0.02/100, 0.7/100, 0.05/100),4).tolist()\n",
"tp_stop = np.round(np.arange(0.02/100, 0.7/100, 0.05/100),4).tolist()\n",
"\n",
"combs = list(product(mom_timeperiod, mom_th, roc_th, sl_stop, tp_stop))\n",
"\n",
"@vbt.parameterized(merge_func = \"concat\", random_subset = 2000, show_progress=True) \n",
"def test_strat(entry_window_closes=60,\n",
" mom_timeperiod=2,\n",
" mom_th=-0.04,\n",
" #roc_th=-0.2,\n",
" sl_stop=0.19/100,\n",
" tp_stop=0.19/100):\n",
" # mom_timeperiod=2\n",
" # mom_th=-0.06\n",
" # roc_th=-0.2\n",
" # sl_stop=0.04/100\n",
" # tp_stop=0.04/100\n",
"\n",
" momshort = vbt.indicator(\"talib:MOM\").run(basic_data.close, timeperiod=mom_timeperiod, short_name = \"slope_short\")\n",
" rocp = vbt.indicator(\"talib:ROC\").run(basic_data.close, short_name = \"rocp\")\n",
" #rate of change + momentum\n",
"\n",
" #momshort.plot rocp.real_crossed_below(roc_th) & \n",
" #short_signal = momshort.real_crossed_below(mom_th)\n",
" long_signal = momshort.real_crossed_above(mom_th)\n",
" # print(\"short signal\")\n",
" # print(short_signal.value_counts())\n",
"\n",
" #forced_exit = pd.Series(False, index=close.index)\n",
" forced_exit = basic_data.symbol_wrapper.fill(False)\n",
" #entry_window_open = pd.Series(False, index=close.index)\n",
" entry_window_open= basic_data.symbol_wrapper.fill(False)\n",
"\n",
" #print(entry_window_closes, \"entry window closes\")\n",
" # Calculate the time difference in minutes from market open for each timestamp\n",
" elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
" entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"\n",
" #print(entry_window_open.value_counts())\n",
"\n",
" forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
" #short_entries = (short_signal & entry_window_open)\n",
" #short_exits = forced_exit\n",
" entries = (long_signal & entry_window_open)\n",
" exits = forced_exit\n",
" #long_entries.info()\n",
" #number of trues and falses in long_entries\n",
" #print(short_exits.value_counts())\n",
" #print(short_entries.value_counts())\n",
"\n",
" #fig = plot_2y_close([],[momshort, rocp], close)\n",
" #short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" #print(sl_stop)\n",
" #tsl_th=sl_stop, \n",
" #short_entries=short_entries, short_exits=short_exits,\n",
" pf = vbt.Portfolio.from_signals(close=basic_data.close, entries=entries, exits=exits, tsl_stop=sl_stop, tp_stop = tp_stop, fees=0.0167/100, freq=\"1s\", price=\"close\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
" \n",
" return pf.stats([\n",
" 'total_return',\n",
" 'max_dd', \n",
" 'total_trades', \n",
" 'win_rate', \n",
" 'expectancy'\n",
" ])\n",
"\n",
"pf_results = test_strat(vbt.Param(entry_window_closes),\n",
" vbt.Param(mom_timeperiod),\n",
" vbt.Param(mom_th),\n",
" #vbt.Param(roc_th)\n",
" vbt.Param(sl_stop),\n",
" vbt.Param(tp_stop, condition=\"tp_stop > sl_stop\"))\n",
"pf_results = pf_results.unstack(level=-1)\n",
"pf_results.sort_values(by=[\"Total Return [%]\", \"Max Drawdown [%]\"], ascending=[False, True])\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#pf_results.load(\"10tiscomb.pickle\")\n",
"#pf_results.info()\n",
"\n",
"vbt.save(pf_results, \"8tiscomb_tsl.pickle\")\n",
"\n",
"# pf_results = vbt.load(\"8tiscomb_tsl.pickle\")\n",
"# pf_results\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# parallel_coordinates method¶\n",
"\n",
"# attach_px_methods.<locals>.plot_func(\n",
"# *args,\n",
"# layout=None,\n",
"# **kwargs\n",
"# )\n",
"\n",
"# pf_results.vbt.px.parallel_coordinates() #ocdf\n",
"\n",
"res = pf_results.reset_index()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf_results"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.preprocessing import StandardScaler\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Assuming pf_results is your DataFrame\n",
"# Convert columns to numeric, assuming NaNs where conversion fails\n",
"metrics = ['Total Return [%]', 'Max Drawdown [%]', 'Total Trades']\n",
"for metric in metrics:\n",
" pf_results[metric] = pd.to_numeric(pf_results[metric], errors='coerce')\n",
"\n",
"# Handle missing values, for example filling with the median\n",
"pf_results['Max Drawdown [%]'].fillna(pf_results['Max Drawdown [%]'].median(), inplace=True)\n",
"\n",
"# Extract the metrics into a new DataFrame\n",
"data_for_pca = pf_results[metrics]\n",
"\n",
"# Standardize the data before applying PCA\n",
"scaler = StandardScaler()\n",
"data_scaled = scaler.fit_transform(data_for_pca)\n",
"\n",
"# Apply PCA\n",
"pca = PCA(n_components=2) # Adjust components as needed\n",
"principal_components = pca.fit_transform(data_scaled)\n",
"\n",
"# Create a DataFrame with the principal components\n",
"pca_results = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])\n",
"\n",
"# Visualize the results\n",
"plt.figure(figsize=(8,6))\n",
"plt.scatter(pca_results['PC1'], pca_results['PC2'], alpha=0.5)\n",
"plt.xlabel('Principal Component 1')\n",
"plt.ylabel('Principal Component 2')\n",
"plt.title('PCA of Strategy Optimization Results')\n",
"plt.grid(True)\n",
"plt.savefig(\"ddd.png\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check if there is any unnamed level and rename it\n",
"if None in df.index.names:\n",
" # Generate new names list replacing None with 'stat'\n",
" new_names = ['stat' if name is None else name for name in df.index.names]\n",
" df.index.set_names(new_names, inplace=True)\n",
"\n",
"rs= df\n",
"\n",
"rs.info()\n",
"\n",
"\n",
"# # Now, 'stat' is the name of the previously unnamed level\n",
"\n",
"# # Filter for 'Total Return' assuming it is a correct identifier in the 'stat' level\n",
"# total_return_series = df.xs('Total Return [%]', level='stat')\n",
"\n",
"# # Sort the Series to get the largest 'Total Return' values\n",
"# sorted_series = total_return_series.sort_values(ascending=False)\n",
"\n",
"# # Print the sorted filtered data\n",
"# sorted_series.head(20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted_series.vbt.save()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#df.info()\n",
"total_return_series = df.xs('Total Return [%]')\n",
"sorted_series = total_return_series.sort_values(ascending=False)\n",
"\n",
"# Display the top N entries, e.g., top 5\n",
"sorted_series.head(5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"comb_stats_df.nlargest(10, 'Total Return [%]')\n",
"#stats_df.info()\n",
"\n",
"\n",
"8\t-0.06\t-0.2\t0.0028\t0.0048\t4.156254\n",
"4 -0.02 -0.25 0.0028 0.0048 0.84433\n",
"3 -0.02 -0.25 0.0033 0.0023 Total Return [%] 0.846753\n",
"#2\t-0.04\t-0.2\t0.0019\t0.0019\n",
"# 2\t-0.04\t-0.2\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.25\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.3\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.35\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.4\t0.0019\t0.0019\t0.556919\t91\t60.43956\t0.00612\n",
"# 2\t-0.04\t-0.2\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.25\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.3\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.35\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853\n",
"# 2\t-0.04\t-0.4\t0.0019\t0.0017\t0.451338\t93\t63.44086\t0.004853"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"basic_data.symbols"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
">>> def apply_func(ts, entries, exits, fastw, sloww, minp=None):\n",
"... fast_ma = vbt.nb.rolling_mean_nb(ts, fastw, minp=minp)\n",
"... slow_ma = vbt.nb.rolling_mean_nb(ts, sloww, minp=minp)\n",
"... entries[:] = vbt.nb.crossed_above_nb(fast_ma, slow_ma) \n",
"... exits[:] = vbt.nb.crossed_above_nb(slow_ma, fast_ma)\n",
"... return (fast_ma, slow_ma) \n",
"\n",
">>> CrossSig = vbt.IF(\n",
"... class_name=\"CrossSig\",\n",
"... input_names=['ts'],\n",
"... in_output_names=['entries', 'exits'],\n",
"... param_names=['fastw', 'sloww'],\n",
"... output_names=['fast_ma', 'slow_ma']\n",
"... ).with_apply_func(\n",
"... apply_func,\n",
"... in_output_settings=dict(\n",
"... entries=dict(dtype=np.bool_), #initialize output with bool\n",
"... exits=dict(dtype=np.bool_)\n",
"... )\n",
"... )\n",
">>> cross_sig = CrossSig.run(ts2, 2, 4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#PIPELINE - parameters in one go\n",
"\n",
"\n",
"#TOTO prepsat do FOR-LOOPu\n",
"\n",
"\n",
"#indicator parameters\n",
"mom_timeperiod = list(range(2, 6))\n",
"\n",
"#threshold entries parameters\n",
"mom_th = np.round(np.arange(-0.02, -0.1 - 0.02, -0.02),4).tolist()#-0.02\n",
"roc_th = np.round(np.arange(-0.2, -0.4 - 0.05, -0.05),4).tolist()#-0.2\n",
"#print(mom_th, roc_th)\n",
"#jejich product\n",
"# mom_th_prod, roc_th_prod = zip(*product(mom_th, roc_th))\n",
"\n",
"# #convert threshold to vbt param\n",
"# mom_th_index = vbt.Param(mom_th_prod, name='mom_th_th') \n",
"# roc_th_index = vbt.Param(roc_th_prod, name='roc_th_th')\n",
"\n",
"mom_th = vbt.Param(mom_th, name='mom_th')\n",
"roc_th = vbt.Param(roc_th, name='roc_th')\n",
"\n",
"#portfolio simulation parameters\n",
"sl_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"sl_stop = [round(val, 4) for val in sl_stop]\n",
"tp_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"tp_stop = [round(val, 4) for val in tp_stop]\n",
"sl_stop = vbt.Param(sl_stop) #np.nan mean s no stoploss\n",
"tp_stop = vbt.Param(tp_stop) #np.nan mean s no stoploss\n",
"\n",
"\n",
"#def test_mom(window=14, mom_th=0.2, roc_th=0.2, sl_stop=0.03/100, tp_stop=0.03/100):\n",
"#close = basic_data.xloc[\"09:30\":\"10:00\"].close\n",
"momshort = vbt.indicator(\"talib:MOM\").run(basic_data.get(\"Close\"), timeperiod=mom_timeperiod, short_name = \"slope_short\")\n",
"\n",
"#ht_trendline = vbt.indicator(\"talib:HT_TRENDLINE\").run(close, short_name = \"httrendline\")\n",
"rocp = vbt.indicator(\"talib:ROC\").run(basic_data.get(\"Close\"), short_name = \"rocp\")\n",
"#rate of change + momentum\n",
"\n",
"rocp_signal = rocp.real_crossed_below(mom_th)\n",
"mom_signal = momshort.real_crossed_below(roc_th)\n",
"\n",
"#mom_signal\n",
"print(rocp_signal.info())\n",
"print(mom_signal.info())\n",
"#print(rocp.real)\n",
"\n",
"\n",
"short_signal = (mom_signal.vbt & rocp_signal)\n",
"\n",
"# #short_signal = (rocp.real_crossed_below(roc_th_index) & momshort.real_crossed_below(mom_th_index))\n",
"# forced_exit = m1_data.symbol_wrapper.fill(False)\n",
"# entry_window_open= m1_data.symbol_wrapper.fill(False)\n",
"\n",
"\n",
"# # Calculate the time difference in minutes from market open for each timestamp\n",
"# elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
"# entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"# forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
"# short_entries = (short_signal & entry_window_open)\n",
"# short_exits = forced_exit\n",
"# #long_entries.info()\n",
"# #number of trues and falses in long_entries\n",
"# #short_exits.value_counts()\n",
"# #short_entries.value_counts()\n",
"\n",
"\n",
"# pf = vbt.Portfolio.from_signals(close=close, short_entries=short_entries, short_exits=short_exits, sl_stop=sl_stop, tp_stop = tp_stop, fees=0.0167/100, freq=\"1s\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# filter dates"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#filter na dny\n",
"dates_of_interest = pd.to_datetime(['2024-04-22']).tz_localize('US/Eastern')\n",
"filtered_df = df.loc[df.index.normalize().isin(dates_of_interest)]\n",
"\n",
"df = filtered_df\n",
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# import plotly.io as pio\n",
"# pio.renderers.default = 'notebook'\n",
"\n",
"#naloadujeme do vbt symbol as column\n",
"basic_data = vbt.Data.from_data({\"BAC\": df}, tz_convert=zoneNY)\n",
"\n",
"vbt.settings.plotting.auto_rangebreaks = True\n",
"#basic_data.data[\"BAC\"].vbt.ohlcv.plot()\n",
"\n",
"#basic_data.data[\"BAC\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"m1_data = basic_data[['Open', 'High', 'Low', 'Close', 'Volume']]\n",
"\n",
"m1_data.data[\"BAC\"]\n",
"#m5_data = m1_data.resample(\"5T\")\n",
"\n",
"#m5_data.data[\"BAC\"].head(10)\n",
"\n",
"# m15_data = m1_data.resample(\"15T\")\n",
"\n",
"# m15 = m15_data.data[\"BAC\"]\n",
"\n",
"# m15.vbt.ohlcv.plot()\n",
"\n",
"# m1_data.wrapper.index\n",
"\n",
"# m1_resampler = m1_data.wrapper.get_resampler(\"1T\")\n",
"# m1_resampler.index_difference(reverse=True)\n",
"\n",
"\n",
"# m5_resampler.prettify()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# MOM indicator"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"vbt.phelp(vbt.indicator(\"talib:ROCP\").run)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"vyuzití rychleho klesani na sekundove urovni behem open rush\n",
"- MOM + ROC during open rush\n",
"- short signal\n",
"- pipeline kombinace thresholdu pro vstup mom_th, roc_th + hodnota sl_stop a tp_stop (pripadne trailing) - nalezeni optimalni kombinace atributu"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# fig = plot_2y_close([ht_trendline],[momshort, rocp], close)\n",
"# short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
"\n",
"#parameters (primary y line, secondary y line, close)\n",
"def plot_2y_close(priminds, secinds, close):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"MOM\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False), trace_kwargs=dict(line=dict(color=\"blue\")))\n",
" for ind in priminds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" for ind in secinds:\n",
" ind.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" return fig\n",
"\n",
"close = m1_data.xloc[\"09:30\":\"10:00\"].close\n",
"momshort = vbt.indicator(\"talib:MOM\").run(close, timeperiod=3, short_name = \"slope_short\")\n",
"ht_trendline = vbt.indicator(\"talib:HT_TRENDLINE\").run(close, short_name = \"httrendline\")\n",
"rocp = vbt.indicator(\"talib:ROC\").run(close, short_name = \"rocp\")\n",
"#rate of change + momentum\n",
"short_signal = (rocp.real_crossed_below(-0.2) & momshort.real_crossed_below(-0.02))\n",
"#indlong = vbt.indicator(\"talib:MOM\").run(close, timeperiod=10, short_name = \"slope_long\")\n",
"fig = plot_2y_close([ht_trendline],[momshort, rocp], close)\n",
"short_signal.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"close = m1_data.close\n",
"#vbt.phelp(vbt.OLS.run)\n",
"\n",
"#oer steepmnes of regression line\n",
"#talib.LINEARREG_SLOPE(close, timeperiod=timeperiod)\n",
"#a také ON BALANCE VOLUME - http://5.161.179.223:8000/static/js/vbt/api/indicators/custom/obv/index.html\n",
"\n",
"\n",
"\n",
"mom_ind = vbt.indicator(\"talib:MOM\") \n",
"#vbt.phelp(mom_ind.run)\n",
"\n",
"mom = mom_ind.run(close, timeperiod=10)\n",
"\n",
"plot_2y_close(mom, close)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# defining ENTRY WINDOW and forced EXIT window"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#m1_data.data[\"BAC\"].info()\n",
"import datetime\n",
"# Define the market open and close times\n",
"market_open = datetime.time(9, 30)\n",
"market_close = datetime.time(16, 0)\n",
"entry_window_opens = 2\n",
"entry_window_closes = 30\n",
"\n",
"forced_exit_start = 380\n",
"forced_exit_end = 390\n",
"\n",
"forced_exit = m1_data.symbol_wrapper.fill(False)\n",
"entry_window_open= m1_data.symbol_wrapper.fill(False)\n",
"\n",
"# Calculate the time difference in minutes from market open for each timestamp\n",
"elapsed_min_from_open = (forced_exit.index.hour - market_open.hour) * 60 + (forced_exit.index.minute - market_open.minute)\n",
"\n",
"entry_window_open[(elapsed_min_from_open >= entry_window_opens) & (elapsed_min_from_open < entry_window_closes)] = True\n",
"forced_exit[(elapsed_min_from_open >= forced_exit_start) & (elapsed_min_from_open < forced_exit_end)] = True\n",
"\n",
"#entry_window_open.info()\n",
"# forced_exit.tail(100)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"close = m1_data.close\n",
"\n",
"#rsi = vbt.RSI.run(close, window=14)\n",
"\n",
"short_entries = (short_signal & entry_window_open)\n",
"short_exits = forced_exit\n",
"#long_entries.info()\n",
"#number of trues and falses in long_entries\n",
"#short_exits.value_counts()\n",
"short_entries.value_counts()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def plot_rsi(close, entries, exits):\n",
" fig = vbt.make_subplots(rows=1, cols=1, shared_xaxes=True, specs=[[{\"secondary_y\": True}]], vertical_spacing=0.02, subplot_titles=(\"RSI\", \"Price\" ))\n",
" close.vbt.plot(fig=fig, add_trace_kwargs=dict(secondary_y=True))\n",
" #rsi.plot(fig=fig, add_trace_kwargs=dict(secondary_y=False))\n",
" entries.vbt.signals.plot_as_entries(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
" exits.vbt.signals.plot_as_exits(close, fig=fig, add_trace_kwargs=dict(secondary_y=False)) \n",
" return fig\n",
"\n",
"plot_rsi(close, short_entries, short_exits)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"vbt.phelp(vbt.Portfolio.from_signals)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sl_stop = np.arange(0.03/100, 0.2/100, 0.02/100).tolist()\n",
"# Using the round function\n",
"sl_stop = [round(val, 4) for val in sl_stop]\n",
"print(sl_stop)\n",
"sl_stop = vbt.Param(sl_stop) #np.nan mean s no stoploss\n",
"\n",
"pf = vbt.Portfolio.from_signals(close=close, short_entries=short_entries, short_exits=short_exits, sl_stop=0.03/100, tp_stop = 0.03/100, fees=0.0167/100, freq=\"1s\") #sl_stop=sl_stop, tp_stop = sl_stop,\n",
"\n",
"#pf.stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#list of orders\n",
"#pf.orders.records_readable\n",
"#pf.orders.plots()\n",
"#pf.stats()\n",
"pf.stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[(0.0015,0.0013)].plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[0.03].plot_trade_signals()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# pristup k pf jako multi index"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#pf[0.03].plot()\n",
"#pf.order_records\n",
"pf[(0.03)].stats()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#zgrupovane statistiky\n",
"stats_df = pf.stats([\n",
" 'total_return',\n",
" 'total_trades',\n",
" 'win_rate',\n",
" 'expectancy'\n",
"], agg_func=None)\n",
"stats_df\n",
"\n",
"\n",
"stats_df.nlargest(10, 'Total Return [%]')\n",
"#stats_df.info()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pf[(0.0011,0.0013000000000000002)].plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pandas.tseries.offsets import DateOffset\n",
"\n",
"temp_data = basic_data['2024-4-22']\n",
"temp_data\n",
"res1m = temp_data[[\"Open\", \"High\", \"Low\", \"Close\", \"Volume\"]]\n",
"\n",
"# Define a custom date offset that starts at 9:30 AM and spans 4 hours\n",
"custom_offset = DateOffset(hours=4, minutes=30)\n",
"\n",
"# res1m = res1m.get().resample(\"4H\").agg({ \n",
"# \"Open\": \"first\",\n",
"# \"High\": \"max\",\n",
"# \"Low\": \"min\",\n",
"# \"Close\": \"last\",\n",
"# \"Volume\": \"sum\"\n",
"# })\n",
"\n",
"res4h = res1m.resample(\"1h\", resample_kwargs=dict(origin=\"start\"))\n",
"\n",
"res4h.data\n",
"\n",
"res15m = res1m.resample(\"15T\", resample_kwargs=dict(origin=\"start\"))\n",
"\n",
"res15m.data[\"BAC\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"@vbt.njit\n",
"def long_entry_place_func_nb(c, low, close, time_in_ns, rsi14, window_open, window_close):\n",
" market_open_minutes = 570 # 9 hours * 60 minutes + 30 minutes\n",
"\n",
" for out_i in range(len(c.out)):\n",
" i = c.from_i + out_i\n",
"\n",
" current_minutes = vbt.dt_nb.hour_nb(time_in_ns[i]) * 60 + vbt.dt_nb.minute_nb(time_in_ns[i])\n",
" #print(\"current_minutes\", current_minutes)\n",
" # Calculate elapsed minutes since market open at 9:30 AM\n",
" elapsed_from_open = current_minutes - market_open_minutes\n",
" elapsed_from_open = elapsed_from_open if elapsed_from_open >= 0 else 0\n",
" #print( \"elapsed_from_open\", elapsed_from_open)\n",
"\n",
" #elapsed_from_open = elapsed_minutes_from_open_nb(time_in_ns) \n",
" in_window = elapsed_from_open > window_open and elapsed_from_open < window_close\n",
" #print(\"in_window\", in_window)\n",
" # if in_window:\n",
" # print(\"in window\")\n",
"\n",
" if in_window and rsi14[i] > 60: # and low[i, c.col] <= hit_price: # and hour == 9: # (4)!\n",
" return out_i\n",
" return -1\n",
"\n",
"@vbt.njit\n",
"def long_exit_place_func_nb(c, high, close, time_index, tp, sl): # (5)!\n",
" entry_i = c.from_i - c.wait\n",
" entry_price = close[entry_i, c.col]\n",
" hit_price = entry_price * (1 + tp)\n",
" stop_price = entry_price * (1 - sl)\n",
" for out_i in range(len(c.out)):\n",
" i = c.from_i + out_i\n",
" last_bar_of_day = vbt.dt_nb.day_changed_nb(time_index[i], time_index[i + 1])\n",
"\n",
" #print(next_day)\n",
" if last_bar_of_day: #pokud je dalsi next day, tak zavirame posledni\n",
" print(\"ted\",out_i)\n",
" return out_i\n",
" if close[i, c.col] >= hit_price or close[i, c.col] <= stop_price :\n",
" return out_i\n",
" return -1\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(np.random.random(size=(5, 10)), columns=list('abcdefghij'))\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df.sum()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}