{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Found cached dataset text (C:/Users/WINSTON-ITX/.cache/huggingface/datasets/boomsss___text/boomsss--SPX_full_30min-37ae67efd8a1cc91/0.0.0/cb1e9bd71a82ad27976be3b12b407850fe2837d80c22c5e03a28949843a8ace2)\n", "getting econ tickers: 100%|██████████| 3/3 [00:00<00:00, 3.81it/s]\n", "Getting release dates: 100%|██████████| 8/8 [00:01<00:00, 5.02it/s]\n", "Making indicators: 100%|██████████| 8/8 [00:00<00:00, 7994.86it/s]\n", "Merging econ data: 100%|██████████| 8/8 [00:00<00:00, 1141.77it/s]\n", "Found cached dataset text (C:/Users/WINSTON-ITX/.cache/huggingface/datasets/boomsss___text/boomsss--SPX_full_30min-37ae67efd8a1cc91/0.0.0/cb1e9bd71a82ad27976be3b12b407850fe2837d80c22c5e03a28949843a8ace2)\n" ] } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "from datasets import load_dataset\n", "from model_day import get_data\n", "\n", "raw_data, df_final, final_date = get_data()\n", "\n", "data = load_dataset(\"boomsss/spx_intra\", split='train')\n", "\n", "rows = [d['text'] for d in data]\n", "rows = [x.split(',') for x in rows]\n", "\n", "fr = pd.DataFrame(columns=[\n", " 'Datetime','Open','High','Low','Close'\n", "], data = rows)\n", "\n", "fr['Datetime'] = pd.to_datetime(fr['Datetime'])\n", "fr['Datetime'] = fr['Datetime'].dt.tz_localize('America/New_York')\n", "fr = fr.set_index('Datetime')\n", "fr['Open'] = pd.to_numeric(fr['Open'])\n", "fr['High'] = pd.to_numeric(fr['High'])\n", "fr['Low'] = pd.to_numeric(fr['Low'])\n", "fr['Close'] = pd.to_numeric(fr['Close'])" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "gap_data = raw_data['CurrentGap']\n", "gap_data = gap_data.reset_index()\n", "gap_data.columns = ['Date','CurrentGap']" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "data = fr.loc['2007-04-28':]" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowClose
Datetime
2007-04-30 09:00:00-04:001494.071494.071494.071494.07
2007-04-30 09:30:00-04:001494.071495.361491.921493.42
2007-04-30 10:00:00-04:001493.911496.011492.171495.20
2007-04-30 10:30:00-04:001495.231497.161494.821497.00
2007-04-30 11:00:00-04:001496.891496.931495.711496.05
\n", "
" ], "text/plain": [ " Open High Low Close\n", "Datetime \n", "2007-04-30 09:00:00-04:00 1494.07 1494.07 1494.07 1494.07\n", "2007-04-30 09:30:00-04:00 1494.07 1495.36 1491.92 1493.42\n", "2007-04-30 10:00:00-04:00 1493.91 1496.01 1492.17 1495.20\n", "2007-04-30 10:30:00-04:00 1495.23 1497.16 1494.82 1497.00\n", "2007-04-30 11:00:00-04:00 1496.89 1496.93 1495.71 1496.05" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.head()" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\850442621.py:1: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data['Date'] = pd.to_datetime(data.index.date)\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\850442621.py:2: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data['HourMin'] = [f'{str(h).zfill(2)}{str(m).zfill(2)}' for h,m in zip(data.index.hour, data.index.minute)]\n" ] } ], "source": [ "data['Date'] = pd.to_datetime(data.index.date)\n", "data['HourMin'] = [f'{str(h).zfill(2)}{str(m).zfill(2)}' for h,m in zip(data.index.hour, data.index.minute)]\n", "# data = data.merge(gap_data, how = 'left', on ='Date')" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Open float64\n", "High float64\n", "Low float64\n", "Close float64\n", "Date datetime64[ns]\n", "HourMin object\n", "dtype: object" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.dtypes" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\3315939868.py:4: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data1['RowNumber'] = data1.groupby('Date').cumcount() + 1\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\3315939868.py:7: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data1['HighBar'] = data1['RowNumber'].where(data1.index.isin(high_idx)) > 0\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\3315939868.py:10: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data1['LowBar'] = data1['RowNumber'].where(data1.index.isin(low_idx)) > 0\n" ] } ], "source": [ "faulty = ['0900', '1600', '1630', '1700']\n", "data1 = data.loc[~data['HourMin'].isin(faulty)]\n", "\n", "data1['RowNumber'] = data1.groupby('Date').cumcount() + 1\n", "\n", "high_idx = data1.groupby('Date')['High'].idxmax()\n", "data1['HighBar'] = data1['RowNumber'].where(data1.index.isin(high_idx)) > 0\n", "\n", "low_idx = data1.groupby('Date')['High'].idxmin()\n", "data1['LowBar'] = data1['RowNumber'].where(data1.index.isin(low_idx)) > 0" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\1433357630.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n", " closes = data1.groupby('Date')['Date','Close'].tail(1)\n" ] } ], "source": [ "opens = data1.groupby('Date')[['Date','Open']].head(1)\n", "closes = data1.groupby('Date')['Date','Close'].tail(1)" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [], "source": [ "df_gaps = closes.merge(opens, on = 'Date')" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [], "source": [ "df_gaps['PrevClose'] = df_gaps['Close'].shift(1)" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [], "source": [ "df_gaps['CurrentGap'] = ((df_gaps['Open'] - df_gaps['PrevClose']) / df_gaps['PrevClose'])" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowCloseDateHourMinRowNumberHighBarLowBarCurrentGap
01494.071495.361491.921493.422007-04-3009301FalseFalseNaN
11493.911496.011492.171495.202007-04-3010002FalseFalseNaN
21495.231497.161494.821497.002007-04-3010303TrueFalseNaN
31496.891496.931495.711496.052007-04-3011004FalseFalseNaN
41496.101496.221493.631494.002007-04-3011305FalseFalseNaN
51493.991495.331493.731495.332007-04-3012006FalseFalseNaN
61495.551496.621495.291495.292007-04-3012307FalseFalseNaN
71495.011496.831495.011495.452007-04-3013008FalseFalseNaN
81495.421496.181494.481495.092007-04-3013309FalseFalseNaN
91495.221495.681492.811493.082007-04-30140010FalseFalseNaN
101493.051493.491489.311489.752007-04-30143011FalseFalseNaN
111490.171490.651487.551487.922007-04-30150012FalseFalseNaN
121487.871488.081482.311482.312007-04-30153013FalseTrueNaN
131483.001486.141482.261482.522007-05-0109301FalseFalse0.000465
141484.311485.001476.701478.152007-05-0110002FalseFalse0.000465
151477.861482.041477.411481.932007-05-0110303FalseFalse0.000465
161482.071482.721480.421481.942007-05-0111004FalseFalse0.000465
171481.771483.991480.611480.612007-05-0111305FalseFalse0.000465
181480.621482.151480.361480.702007-05-0112006FalseFalse0.000465
191480.721482.131480.331480.442007-05-0112307FalseFalse0.000465
201480.361480.361477.781479.682007-05-0113008FalseTrue0.000465
211479.611483.421479.551482.702007-05-0113309FalseFalse0.000465
221482.771484.671481.831484.162007-05-01140010FalseFalse0.000465
231484.101487.271483.971486.152007-05-01143011TrueFalse0.000465
241486.111486.811484.271484.272007-05-01150012FalseFalse0.000465
251484.051486.501483.971486.122007-05-01153013FalseFalse0.000465
261486.451491.901486.451491.472007-05-0209301FalseTrue0.000222
271491.761494.481491.761493.762007-05-0210002FalseFalse0.000222
281493.761497.561493.561496.942007-05-0210303FalseFalse0.000222
291496.921497.011495.681495.982007-05-0211004FalseFalse0.000222
301495.871496.081495.111495.582007-05-0211305FalseFalse0.000222
311495.691497.131495.151496.962007-05-0212006FalseFalse0.000222
321497.001497.321495.721496.262007-05-0212307FalseFalse0.000222
331496.491498.381496.491497.722007-05-0213008FalseFalse0.000222
341497.521498.371497.321497.882007-05-0213309FalseFalse0.000222
351497.821499.101497.111498.972007-05-02140010TrueFalse0.000222
361498.991499.001497.591497.762007-05-02143011FalseFalse0.000222
371497.731497.751495.641496.652007-05-02150012FalseFalse0.000222
381496.861496.971494.751495.772007-05-02153013FalseFalse0.000222
391496.021499.231496.021498.702007-05-0309301FalseTrue0.000167
401499.341500.511497.041499.222007-05-0310002FalseFalse0.000167
411498.841502.911498.311502.632007-05-0310303FalseFalse0.000167
421502.711502.921501.031502.092007-05-0311004FalseFalse0.000167
431502.081502.151500.541501.992007-05-0311305FalseFalse0.000167
441501.871502.451498.921498.922007-05-0312006FalseFalse0.000167
451498.851501.091498.781500.682007-05-0312307FalseFalse0.000167
461500.671501.421499.221499.832007-05-0313008FalseFalse0.000167
471499.861501.851499.511501.182007-05-0313309FalseFalse0.000167
481501.221502.351500.811501.722007-05-03140010FalseFalse0.000167
491502.211502.711500.551502.712007-05-03143011FalseFalse0.000167
\n", "
" ], "text/plain": [ " Open High Low Close Date HourMin RowNumber HighBar \\\n", "0 1494.07 1495.36 1491.92 1493.42 2007-04-30 0930 1 False \n", "1 1493.91 1496.01 1492.17 1495.20 2007-04-30 1000 2 False \n", "2 1495.23 1497.16 1494.82 1497.00 2007-04-30 1030 3 True \n", "3 1496.89 1496.93 1495.71 1496.05 2007-04-30 1100 4 False \n", "4 1496.10 1496.22 1493.63 1494.00 2007-04-30 1130 5 False \n", "5 1493.99 1495.33 1493.73 1495.33 2007-04-30 1200 6 False \n", "6 1495.55 1496.62 1495.29 1495.29 2007-04-30 1230 7 False \n", "7 1495.01 1496.83 1495.01 1495.45 2007-04-30 1300 8 False \n", "8 1495.42 1496.18 1494.48 1495.09 2007-04-30 1330 9 False \n", "9 1495.22 1495.68 1492.81 1493.08 2007-04-30 1400 10 False \n", "10 1493.05 1493.49 1489.31 1489.75 2007-04-30 1430 11 False \n", "11 1490.17 1490.65 1487.55 1487.92 2007-04-30 1500 12 False \n", "12 1487.87 1488.08 1482.31 1482.31 2007-04-30 1530 13 False \n", "13 1483.00 1486.14 1482.26 1482.52 2007-05-01 0930 1 False \n", "14 1484.31 1485.00 1476.70 1478.15 2007-05-01 1000 2 False \n", "15 1477.86 1482.04 1477.41 1481.93 2007-05-01 1030 3 False \n", "16 1482.07 1482.72 1480.42 1481.94 2007-05-01 1100 4 False \n", "17 1481.77 1483.99 1480.61 1480.61 2007-05-01 1130 5 False \n", "18 1480.62 1482.15 1480.36 1480.70 2007-05-01 1200 6 False \n", "19 1480.72 1482.13 1480.33 1480.44 2007-05-01 1230 7 False \n", "20 1480.36 1480.36 1477.78 1479.68 2007-05-01 1300 8 False \n", "21 1479.61 1483.42 1479.55 1482.70 2007-05-01 1330 9 False \n", "22 1482.77 1484.67 1481.83 1484.16 2007-05-01 1400 10 False \n", "23 1484.10 1487.27 1483.97 1486.15 2007-05-01 1430 11 True \n", "24 1486.11 1486.81 1484.27 1484.27 2007-05-01 1500 12 False \n", "25 1484.05 1486.50 1483.97 1486.12 2007-05-01 1530 13 False \n", "26 1486.45 1491.90 1486.45 1491.47 2007-05-02 0930 1 False \n", "27 1491.76 1494.48 1491.76 1493.76 2007-05-02 1000 2 False \n", "28 1493.76 1497.56 1493.56 1496.94 2007-05-02 1030 3 False \n", "29 1496.92 1497.01 1495.68 1495.98 2007-05-02 1100 4 False \n", "30 1495.87 1496.08 1495.11 1495.58 2007-05-02 1130 5 False \n", "31 1495.69 1497.13 1495.15 1496.96 2007-05-02 1200 6 False \n", "32 1497.00 1497.32 1495.72 1496.26 2007-05-02 1230 7 False \n", "33 1496.49 1498.38 1496.49 1497.72 2007-05-02 1300 8 False \n", "34 1497.52 1498.37 1497.32 1497.88 2007-05-02 1330 9 False \n", "35 1497.82 1499.10 1497.11 1498.97 2007-05-02 1400 10 True \n", "36 1498.99 1499.00 1497.59 1497.76 2007-05-02 1430 11 False \n", "37 1497.73 1497.75 1495.64 1496.65 2007-05-02 1500 12 False \n", "38 1496.86 1496.97 1494.75 1495.77 2007-05-02 1530 13 False \n", "39 1496.02 1499.23 1496.02 1498.70 2007-05-03 0930 1 False \n", "40 1499.34 1500.51 1497.04 1499.22 2007-05-03 1000 2 False \n", "41 1498.84 1502.91 1498.31 1502.63 2007-05-03 1030 3 False \n", "42 1502.71 1502.92 1501.03 1502.09 2007-05-03 1100 4 False \n", "43 1502.08 1502.15 1500.54 1501.99 2007-05-03 1130 5 False \n", "44 1501.87 1502.45 1498.92 1498.92 2007-05-03 1200 6 False \n", "45 1498.85 1501.09 1498.78 1500.68 2007-05-03 1230 7 False \n", "46 1500.67 1501.42 1499.22 1499.83 2007-05-03 1300 8 False \n", "47 1499.86 1501.85 1499.51 1501.18 2007-05-03 1330 9 False \n", "48 1501.22 1502.35 1500.81 1501.72 2007-05-03 1400 10 False \n", "49 1502.21 1502.71 1500.55 1502.71 2007-05-03 1430 11 False \n", "\n", " LowBar CurrentGap \n", "0 False NaN \n", "1 False NaN \n", "2 False NaN \n", "3 False NaN \n", "4 False NaN \n", "5 False NaN \n", "6 False NaN \n", "7 False NaN \n", "8 False NaN \n", "9 False NaN \n", "10 False NaN \n", "11 False NaN \n", "12 True NaN \n", "13 False 0.000465 \n", "14 False 0.000465 \n", "15 False 0.000465 \n", "16 False 0.000465 \n", "17 False 0.000465 \n", "18 False 0.000465 \n", "19 False 0.000465 \n", "20 True 0.000465 \n", "21 False 0.000465 \n", "22 False 0.000465 \n", "23 False 0.000465 \n", "24 False 0.000465 \n", "25 False 0.000465 \n", "26 True 0.000222 \n", "27 False 0.000222 \n", "28 False 0.000222 \n", "29 False 0.000222 \n", "30 False 0.000222 \n", "31 False 0.000222 \n", "32 False 0.000222 \n", "33 False 0.000222 \n", "34 False 0.000222 \n", "35 False 0.000222 \n", "36 False 0.000222 \n", "37 False 0.000222 \n", "38 False 0.000222 \n", "39 True 0.000167 \n", "40 False 0.000167 \n", "41 False 0.000167 \n", "42 False 0.000167 \n", "43 False 0.000167 \n", "44 False 0.000167 \n", "45 False 0.000167 \n", "46 False 0.000167 \n", "47 False 0.000167 \n", "48 False 0.000167 \n", "49 False 0.000167 " ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1 = data1.merge(df_gaps[['Date','CurrentGap']], how = 'left', on = 'Date')" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "data1.groupby('HourMin')['HighBar'].mean().plot(kind='bar');" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "\n", "hod_prob = data1.groupby('HourMin')['HighBar'].mean()\n", "\n", "hod_prob_sorted = hod_prob.sort_index()\n", "\n", "cumulative_prob = hod_prob_sorted.cumsum()\n", "\n", "# Plot the cumulative distribution curve\n", "plt.plot(cumulative_prob.index, cumulative_prob.values)\n", "plt.xlabel('Hour and Minute')\n", "plt.ylabel('Cumulative Probability of HOD Occurrence')\n", "plt.title('Cumulative Distribution of HOD Occurrence')\n", "plt.xticks(rotation=45)\n", "plt.grid()\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "data1.groupby('HourMin')['LowBar'].mean().plot(kind='bar');" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\1950565345.py:28: UserWarning: FixedFormatter should only be used together with FixedLocator\n", " axs[0, 0].set_xticklabels(hod_prob.index, rotation=45)\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\1950565345.py:42: UserWarning: FixedFormatter should only be used together with FixedLocator\n", " axs[0, 1].set_xticklabels(lod_prob.index, rotation=45)\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\1950565345.py:57: UserWarning: FixedFormatter should only be used together with FixedLocator\n", " axs[1, 0].set_xticklabels(cumulative_hod.index, rotation=45)\n", "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\1950565345.py:71: UserWarning: FixedFormatter should only be used together with FixedLocator\n", " axs[1, 1].set_xticklabels(cumulative_lod.index, rotation=45)\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "\n", "# Assuming you have a DataFrame 'data1' with the 'HourMin', 'HighBar', and 'LowBar' columns\n", "\n", "# Calculate the probability of High of Day (HOD) occurrence for each 'HourMin'\n", "hod_prob = data1.groupby('HourMin')['HighBar'].mean()\n", "\n", "# Calculate the probability of Low of Day (LOD) occurrence for each 'HourMin'\n", "lod_prob = data1.groupby('HourMin')['LowBar'].mean()\n", "\n", "# Sort the probabilities based on 'HourMin'\n", "hod_prob_sorted = hod_prob.sort_index()\n", "lod_prob_sorted = lod_prob.sort_index()\n", "\n", "# Calculate the cumulative distributions\n", "cumulative_hod = hod_prob_sorted.cumsum()\n", "cumulative_lod = lod_prob_sorted.cumsum()\n", "\n", "# Create a 2x4 grid of subplots with shared Y-axis\n", "fig, axs = plt.subplots(2, 2, figsize=(16, 8),)\n", "\n", "# Plot bar plot distributions of HOD and LOD\n", "axs[0, 0].bar(hod_prob.index, hod_prob.values)\n", "axs[0, 0].set_xlabel('Hour and Minute')\n", "axs[0, 0].set_ylabel('Probability of HOD Occurrence')\n", "axs[0, 0].set_title('Distribution of HOD Occurrence')\n", "axs[0, 0].set_xticklabels(hod_prob.index, rotation=45)\n", "axs[0, 0].grid()\n", "\n", "# Format labels as percentages\n", "axs[0, 0].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Add data labels to the graph\n", "for x, y in zip(hod_prob.index, hod_prob.values):\n", " axs[0, 0].text(x, y, f'{y:.0%}', ha='center', va='bottom')\n", "\n", "axs[0, 1].bar(lod_prob.index, lod_prob.values, color='orange')\n", "axs[0, 1].set_xlabel('Hour and Minute')\n", "axs[0, 1].set_ylabel('Probability of LOD Occurrence')\n", "axs[0, 1].set_title('Distribution of LOD Occurrence')\n", "axs[0, 1].set_xticklabels(lod_prob.index, rotation=45)\n", "axs[0, 1].grid()\n", "\n", "# Format labels as percentages\n", "axs[0, 1].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Add data labels to the graph\n", "for x, y in zip(lod_prob.index, lod_prob.values):\n", " axs[0, 1].text(x, y, f'{y:.0%}', ha='center', va='bottom')\n", "\n", "# Plot cumulative distributions of HOD and LOD\n", "axs[1, 0].plot(cumulative_hod.index, cumulative_hod.values)\n", "axs[1, 0].set_xlabel('Hour and Minute')\n", "axs[1, 0].set_ylabel('Cumulative Probability of HOD Occurrence')\n", "axs[1, 0].set_title('Cumulative Distribution of HOD Occurrence')\n", "axs[1, 0].set_xticklabels(cumulative_hod.index, rotation=45)\n", "axs[1, 0].grid()\n", "\n", "# Format labels as percentages\n", "axs[1, 0].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Add data labels to the graph\n", "for x, y in zip(cumulative_hod.index, cumulative_hod.values):\n", " axs[1, 0].text(x, y, f'{y:.0%}', ha='center', va='bottom')\n", "\n", "axs[1, 1].plot(cumulative_lod.index, cumulative_lod.values, color='orange')\n", "axs[1, 1].set_xlabel('Hour and Minute')\n", "axs[1, 1].set_ylabel('Cumulative Probability of LOD Occurrence')\n", "axs[1, 1].set_title('Cumulative Distribution of LOD Occurrence')\n", "axs[1, 1].set_xticklabels(cumulative_lod.index, rotation=45)\n", "axs[1, 1].grid()\n", "\n", "# Format labels as percentages\n", "axs[1, 1].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Add data labels to the graph\n", "for x, y in zip(cumulative_lod.index, cumulative_lod.values):\n", " axs[1, 1].text(x, y, f'{y:.0%}', ha='center', va='bottom')\n", "\n", "# # Remove unused subplots\n", "# fig.delaxes(axs[1, 2])\n", "# fig.delaxes(axs[1, 3])\n", "\n", "plt.tight_layout()\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['Open', 'High', 'Low', 'Close', 'Date', 'HourMin', 'CurrentGap',\n", " 'RowNumber', 'HighBar', 'LowBar'],\n", " dtype='object')" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1.columns" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\WINSTON-ITX\\AppData\\Local\\Temp\\ipykernel_24704\\2610222875.py:7: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " data1['CurrentGapCat'] = pd.qcut(data1['CurrentGap'], 4)\n" ] } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "\n", "# Assuming you have a DataFrame 'data1' with the 'HourMin', 'HighBar', and 'LowBar' columns\n", "\n", "# List of values to filter and plot\n", "data1['CurrentGapCat'] = pd.qcut(data1['CurrentGap'], 4)\n" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowCloseDateHourMinCurrentGapRowNumberHighBarLowBarCurrentGapCat
01492.191492.911492.191492.872007-04-271200NaN1FalseTrueNaN
11492.541494.461492.301493.322007-04-271230NaN2FalseFalseNaN
21493.301494.451493.071494.412007-04-271300NaN3FalseFalseNaN
31494.601496.551494.311495.042007-04-271330NaN4FalseFalseNaN
41495.011496.971494.651495.852007-04-271400NaN5FalseFalseNaN
....................................
571684565.234567.314562.064564.472023-07-191330-0.0024849FalseFalse(-0.0757, -0.00219]
571694564.454565.744557.484560.632023-07-191400-0.00248410FalseTrue(-0.0757, -0.00219]
571704560.614568.094560.614567.862023-07-191430-0.00248411FalseFalse(-0.0757, -0.00219]
571714567.824574.664567.614572.092023-07-191500-0.00248412FalseFalse(-0.0757, -0.00219]
571724572.044572.044565.594565.652023-07-191530-0.00248413FalseFalse(-0.0757, -0.00219]
\n", "

52956 rows × 11 columns

\n", "
" ], "text/plain": [ " Open High Low Close Date HourMin CurrentGap \\\n", "0 1492.19 1492.91 1492.19 1492.87 2007-04-27 1200 NaN \n", "1 1492.54 1494.46 1492.30 1493.32 2007-04-27 1230 NaN \n", "2 1493.30 1494.45 1493.07 1494.41 2007-04-27 1300 NaN \n", "3 1494.60 1496.55 1494.31 1495.04 2007-04-27 1330 NaN \n", "4 1495.01 1496.97 1494.65 1495.85 2007-04-27 1400 NaN \n", "... ... ... ... ... ... ... ... \n", "57168 4565.23 4567.31 4562.06 4564.47 2023-07-19 1330 -0.002484 \n", "57169 4564.45 4565.74 4557.48 4560.63 2023-07-19 1400 -0.002484 \n", "57170 4560.61 4568.09 4560.61 4567.86 2023-07-19 1430 -0.002484 \n", "57171 4567.82 4574.66 4567.61 4572.09 2023-07-19 1500 -0.002484 \n", "57172 4572.04 4572.04 4565.59 4565.65 2023-07-19 1530 -0.002484 \n", "\n", " RowNumber HighBar LowBar CurrentGapCat \n", "0 1 False True NaN \n", "1 2 False False NaN \n", "2 3 False False NaN \n", "3 4 False False NaN \n", "4 5 False False NaN \n", "... ... ... ... ... \n", "57168 9 False False (-0.0757, -0.00219] \n", "57169 10 False True (-0.0757, -0.00219] \n", "57170 11 False False (-0.0757, -0.00219] \n", "57171 12 False False (-0.0757, -0.00219] \n", "57172 13 False False (-0.0757, -0.00219] \n", "\n", "[52956 rows x 11 columns]" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "52956" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(data1)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Open 0\n", "High 0\n", "Low 0\n", "Close 0\n", "Date 0\n", "HourMin 0\n", "CurrentGap 36490\n", "RowNumber 0\n", "HighBar 0\n", "LowBar 0\n", "CurrentGapCat 36490\n", "dtype: int64" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[NaN, (0.000478, 0.00294], (0.00294, 0.0478], (-0.00219, 0.000478], (-0.0757, -0.00219]]\n", "Categories (4, interval[float64, right]): [(-0.0757, -0.00219] < (-0.00219, 0.000478] < (0.000478, 0.00294] < (0.00294, 0.0478]]" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data1['CurrentGapCat'].unique()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "# Function to convert a float to a percentage string with desired precision\n", "def float_to_percent(value, precision=2):\n", " return \"{:.{precision}%}\".format(value, precision=precision)\n", "\n", "# Loop through the categories and convert the float intervals to percentage format\n", "formatted_categories = []\n", "for category in data1['CurrentGapCat']:\n", " # Get the lower and upper bounds of the interval and convert them to percentage strings\n", " lower_bound = float_to_percent(category.left, precision=2)\n", " upper_bound = float_to_percent(category.right, precision=2)\n", " formatted_categories.append((lower_bound, upper_bound))\n", "\n", "print(formatted_categories)\n", "data1['Labels'] = formatted_categories\n", "\n", "tuples = sorted(list(set([s for s in zip(data1['CurrentGapCat'], data1['Labels'])])))\n", "\n", "# Create a 1x2 grid of subplots with shared Y-axis\n", "fig, axs = plt.subplots(1, 2, figsize=(15, 4), sharey=True)\n", "\n", "# Loop through the specified values and plot the cumulative distributions\n", "for t in tuples:\n", " # Filter the DataFrame based on the specified value\n", " gap = t[0]\n", " lbl = t[1]\n", " df_use = data1.loc[data1['CurrentGapCat'] == gap] # Replace 'column_to_filter' with the appropriate column name\n", " \n", " # Calculate the probability of High of Day (HOD) occurrence for each 'HourMin'\n", " hod_prob = df_use.groupby('HourMin')['HighBar'].mean()\n", " \n", " # Calculate the probability of Low of Day (LOD) occurrence for each 'HourMin'\n", " lod_prob = df_use.groupby('HourMin')['LowBar'].mean()\n", "\n", " # Sort the probabilities based on 'HourMin'\n", " hod_prob_sorted = hod_prob.sort_index()\n", " lod_prob_sorted = lod_prob.sort_index()\n", "\n", " # Calculate the cumulative distributions\n", " cumulative_hod = hod_prob_sorted.cumsum()\n", " cumulative_lod = lod_prob_sorted.cumsum()\n", "\n", " # Plot cumulative distributions of HOD and LOD and assign them to the legend\n", " axs[0].plot(cumulative_hod.index, cumulative_hod.values, label=lbl)\n", " axs[1].plot(cumulative_lod.index, cumulative_lod.values, label=lbl)\n", "\n", "# Set labels and title for the left plot (HOD)\n", "axs[0].set_xlabel('Hour and Minute')\n", "axs[0].set_ylabel('Cumulative Probability of HOD Occurrence')\n", "axs[0].set_title('Cumulative Distribution of HOD Occurrence')\n", "axs[0].set_xticklabels(cumulative_hod.index, rotation=45)\n", "axs[0].grid()\n", "\n", "# Format labels as percentages\n", "axs[0].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Set labels and title for the right plot (LOD)\n", "axs[1].set_xlabel('Hour and Minute')\n", "axs[1].set_ylabel('Cumulative Probability of LOD Occurrence')\n", "axs[1].set_title('Cumulative Distribution of LOD Occurrence')\n", "axs[1].set_xticklabels(cumulative_lod.index, rotation=45)\n", "axs[1].grid()\n", "\n", "# Format labels as percentages\n", "axs[1].yaxis.set_major_formatter('{:.0%}'.format)\n", "\n", "# Add legend to the plots\n", "axs[0].legend()\n", "axs[1].legend()\n", "\n", "plt.tight_layout()\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data1.query('HourMin == \"0930\" & HighBar == True')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "tuples" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "py39", "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": "3.9.12" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }