jreadey/query_select_example.ipynb

## query_select_example.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Example of using dataset query function in h5pyd/HSDS.\n",
    "\n",
    "To run, setup HSDS if you haven't alreay (see: http://github.com/HDFGroup/hsds/READMe.md).\n",
    "Then download the sample data file:  `wget https://s3.amazonaws.com/hdfgroup/data/hdf5test/snp500.h5`.\n",
    "Finally, load the file into hsds: `hsload snp500.h5 /home/test_user1/`  (adjust to the actually location desired)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import h5pyd\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Open a file containing stock quote data\n",
    "f = h5pyd.File(\"/home/test_user1/snp500.h5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "h5pyd._hl.table.Table"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The h5pyd Table class is a subclass of Dataset with methods specific for one-dimensional\n",
    "# datasets of compound type\n",
    "dset = f[\"dset\"]\n",
    "type(dset)  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3207353"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# nrows is a table property - number of rows in the dataset\n",
    "dset.nrows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype([('date', 'S10'), ('symbol', 'S4'), ('sector', 'i1'), ('open', '<f4'), ('high', '<f4'), ('low', '<f4'), ('volume', '<f4'), ('close', '<f4')])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dtype is a list of field names and sub-types\n",
    "dset.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([b'1970.01.02', b'1970.01.02', b'1970.01.02', b'1970.01.02',\n",
       "       b'1970.01.02', b'1970.01.02', b'1970.01.02', b'1970.01.02',\n",
       "       b'1970.01.02', b'1970.01.02'], dtype='|S10')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The date field starts in 1970...\n",
    "arr = dset[:10]  # get first 10 elements\n",
    "arr['date']  # date starts in 1970"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([b'2015.11.20', b'2015.11.20', b'2015.11.20', b'2015.11.20',\n",
       "       b'2015.11.20', b'2015.11.20', b'2015.11.20', b'2015.11.20',\n",
       "       b'2015.11.20', b'2015.11.20'], dtype='|S10')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr = dset[-10:]  # get last 10 elements\n",
    "arr['date']  # and ends in 2015"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 112 ms, sys: 539 µs, total: 113 ms\n",
      "Wall time: 903 ms\n"
     ]
    }
   ],
   "source": [
    "# If we wanted to extract all stock quotes with the symbol AAPL\n",
    "# We could read the dataset in chunks and filter out anything \n",
    "# other than that symbol, but it would be rather slow\n",
    "#\n",
    "# More efficient is to use the dset query operator which can just \n",
    "# return rows matching the specification\n",
    "symbol = \"AAPL\"\n",
    "query = f\"symbol == b'{symbol}'\"  # query just on exact match for the symbol\n",
    "# query = f\"(symbol == b'{symbol}') & (open > 100)\"  # boolean query\n",
    "%time arr = dset.read_where(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8813,)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>index</th>\n",
       "      <th>date</th>\n",
       "      <th>symbol</th>\n",
       "      <th>sector</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>volume</th>\n",
       "      <th>close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>128912</td>\n",
       "      <td>b'1980.12.12'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>0.436339</td>\n",
       "      <td>0.438236</td>\n",
       "      <td>0.436339</td>\n",
       "      <td>117258400.0</td>\n",
       "      <td>0.436339</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>128982</td>\n",
       "      <td>b'1980.12.15'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>0.415471</td>\n",
       "      <td>0.415471</td>\n",
       "      <td>0.413574</td>\n",
       "      <td>43971200.0</td>\n",
       "      <td>0.413574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>129052</td>\n",
       "      <td>b'1980.12.16'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>0.385117</td>\n",
       "      <td>0.385117</td>\n",
       "      <td>0.383220</td>\n",
       "      <td>26432000.0</td>\n",
       "      <td>0.383220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>129122</td>\n",
       "      <td>b'1980.12.17'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>0.392705</td>\n",
       "      <td>0.394602</td>\n",
       "      <td>0.392705</td>\n",
       "      <td>21610400.0</td>\n",
       "      <td>0.392705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>129192</td>\n",
       "      <td>b'1980.12.18'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>0.404088</td>\n",
       "      <td>0.405985</td>\n",
       "      <td>0.404088</td>\n",
       "      <td>18362400.0</td>\n",
       "      <td>0.404088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8808</th>\n",
       "      <td>3205203</td>\n",
       "      <td>b'2015.11.16'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>111.379997</td>\n",
       "      <td>114.239998</td>\n",
       "      <td>111.000000</td>\n",
       "      <td>37651000.0</td>\n",
       "      <td>114.180000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8809</th>\n",
       "      <td>3205708</td>\n",
       "      <td>b'2015.11.17'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>114.919998</td>\n",
       "      <td>115.050003</td>\n",
       "      <td>113.320000</td>\n",
       "      <td>27254000.0</td>\n",
       "      <td>113.690002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8810</th>\n",
       "      <td>3206213</td>\n",
       "      <td>b'2015.11.18'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>115.760002</td>\n",
       "      <td>117.489998</td>\n",
       "      <td>115.500000</td>\n",
       "      <td>46163400.0</td>\n",
       "      <td>117.290001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8811</th>\n",
       "      <td>3206718</td>\n",
       "      <td>b'2015.11.19'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>117.639999</td>\n",
       "      <td>119.750000</td>\n",
       "      <td>116.760002</td>\n",
       "      <td>42908200.0</td>\n",
       "      <td>118.779999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8812</th>\n",
       "      <td>3207223</td>\n",
       "      <td>b'2015.11.20'</td>\n",
       "      <td>b'AAPL'</td>\n",
       "      <td>6</td>\n",
       "      <td>119.199997</td>\n",
       "      <td>119.919998</td>\n",
       "      <td>118.849998</td>\n",
       "      <td>34103500.0</td>\n",
       "      <td>119.300003</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8813 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        index           date   symbol  sector        open        high  \\\n",
       "0      128912  b'1980.12.12'  b'AAPL'       6    0.436339    0.438236   \n",
       "1      128982  b'1980.12.15'  b'AAPL'       6    0.415471    0.415471   \n",
       "2      129052  b'1980.12.16'  b'AAPL'       6    0.385117    0.385117   \n",
       "3      129122  b'1980.12.17'  b'AAPL'       6    0.392705    0.394602   \n",
       "4      129192  b'1980.12.18'  b'AAPL'       6    0.404088    0.405985   \n",
       "...       ...            ...      ...     ...         ...         ...   \n",
       "8808  3205203  b'2015.11.16'  b'AAPL'       6  111.379997  114.239998   \n",
       "8809  3205708  b'2015.11.17'  b'AAPL'       6  114.919998  115.050003   \n",
       "8810  3206213  b'2015.11.18'  b'AAPL'       6  115.760002  117.489998   \n",
       "8811  3206718  b'2015.11.19'  b'AAPL'       6  117.639999  119.750000   \n",
       "8812  3207223  b'2015.11.20'  b'AAPL'       6  119.199997  119.919998   \n",
       "\n",
       "             low       volume       close  \n",
       "0       0.436339  117258400.0    0.436339  \n",
       "1       0.413574   43971200.0    0.413574  \n",
       "2       0.383220   26432000.0    0.383220  \n",
       "3       0.392705   21610400.0    0.392705  \n",
       "4       0.404088   18362400.0    0.404088  \n",
       "...          ...          ...         ...  \n",
       "8808  111.000000   37651000.0  114.180000  \n",
       "8809  113.320000   27254000.0  113.690002  \n",
       "8810  115.500000   46163400.0  117.290001  \n",
       "8811  116.760002   42908200.0  118.779999  \n",
       "8812  118.849998   34103500.0  119.300003  \n",
       "\n",
       "[8813 rows x 9 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert numpy result to Pandas dataframe\n",
    "df = pd.DataFrame(arr)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7dd2abd10bb0>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x900 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Calculate the 20 and 100 days moving averages of the closing prices\n",
    "close = df['close']\n",
    "short_rolling = close.rolling(window=20).mean()\n",
    "long_rolling = close.rolling(window=100).mean()\n",
    "\n",
    "# Plot everything by leveraging the very powerful matplotlib package\n",
    "fig, ax = plt.subplots(figsize=(16,9))\n",
    "\n",
    "ax.plot(close.index, close, label=symbol)\n",
    "ax.plot(short_rolling.index, short_rolling, label='20 days rolling')\n",
    "ax.plot(long_rolling.index, long_rolling, label='100 days rolling')\n",
    "\n",
    "ax.set_xlabel('Date')\n",
    "ax.set_ylabel('Adjusted closing price ($)')\n",
    "ax.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>index</th>\n",
       "      <th>sector</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>volume</th>\n",
       "      <th>close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>8.813000e+03</td>\n",
       "      <td>8813.0</td>\n",
       "      <td>8813.000000</td>\n",
       "      <td>8813.000000</td>\n",
       "      <td>8813.000000</td>\n",
       "      <td>8.813000e+03</td>\n",
       "      <td>8813.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.346940e+06</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.867305</td>\n",
       "      <td>15.023249</td>\n",
       "      <td>14.692131</td>\n",
       "      <td>9.230663e+07</td>\n",
       "      <td>14.860061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>9.408608e+05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>28.502213</td>\n",
       "      <td>28.753164</td>\n",
       "      <td>28.215895</td>\n",
       "      <td>8.859470e+07</td>\n",
       "      <td>28.486755</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.289120e+05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.168844</td>\n",
       "      <td>0.168844</td>\n",
       "      <td>0.166947</td>\n",
       "      <td>2.504000e+05</td>\n",
       "      <td>0.166947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>4.652440e+05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.909832</td>\n",
       "      <td>0.926958</td>\n",
       "      <td>0.888549</td>\n",
       "      <td>3.725680e+07</td>\n",
       "      <td>0.908528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.191722e+06</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1.410330</td>\n",
       "      <td>1.435624</td>\n",
       "      <td>1.382501</td>\n",
       "      <td>6.468000e+07</td>\n",
       "      <td>1.410330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2.143263e+06</td>\n",
       "      <td>6.0</td>\n",
       "      <td>11.656223</td>\n",
       "      <td>11.867720</td>\n",
       "      <td>11.434086</td>\n",
       "      <td>1.150212e+08</td>\n",
       "      <td>11.697458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.207223e+06</td>\n",
       "      <td>6.0</td>\n",
       "      <td>132.729172</td>\n",
       "      <td>132.808136</td>\n",
       "      <td>130.250366</td>\n",
       "      <td>1.855410e+09</td>\n",
       "      <td>131.380386</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              index  sector         open         high          low  \\\n",
       "count  8.813000e+03  8813.0  8813.000000  8813.000000  8813.000000   \n",
       "mean   1.346940e+06     6.0    14.867305    15.023249    14.692131   \n",
       "std    9.408608e+05     0.0    28.502213    28.753164    28.215895   \n",
       "min    1.289120e+05     6.0     0.168844     0.168844     0.166947   \n",
       "25%    4.652440e+05     6.0     0.909832     0.926958     0.888549   \n",
       "50%    1.191722e+06     6.0     1.410330     1.435624     1.382501   \n",
       "75%    2.143263e+06     6.0    11.656223    11.867720    11.434086   \n",
       "max    3.207223e+06     6.0   132.729172   132.808136   130.250366   \n",
       "\n",
       "             volume        close  \n",
       "count  8.813000e+03  8813.000000  \n",
       "mean   9.230663e+07    14.860061  \n",
       "std    8.859470e+07    28.486755  \n",
       "min    2.504000e+05     0.166947  \n",
       "25%    3.725680e+07     0.908528  \n",
       "50%    6.468000e+07     1.410330  \n",
       "75%    1.150212e+08    11.697458  \n",
       "max    1.855410e+09   131.380386  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "largest gain:\n",
      "(b'2000.04.04', b'LVLT', 8, 1483.125, 1486.875, 1065., 7208100., 1422.1875)\n",
      "CPU times: user 3.13 s, sys: 62.1 ms, total: 3.2 s\n",
      "Wall time: 3.98 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "# find the largest one day gain for any stock\n",
    "# The create_cursor method let's you efficently access all the rows in the table\n",
    "max_gain = 0.0\n",
    "target = None\n",
    "cursor = dset.create_cursor()\n",
    "for row in cursor:\n",
    "    gain = row[\"high\"] - row[\"low\"]\n",
    "    if gain > max_gain:\n",
    "        max_gain = gain\n",
    "        target = np.copy(row)\n",
    "print(\"largest gain:\")\n",
    "print(target)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}