docs: first version of data management example added.

This commit is contained in:
Fabian Joswig 2022-09-29 09:46:15 +01:00
parent cf7919c936
commit 9a7f5679c9
No known key found for this signature in database

View file

@ -0,0 +1,554 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Data management"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import pyerrors as pe"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data has been written using pyerrors 2.0.0.\n",
"Format version 0.1\n",
"Written by fjosw on 2022-01-06 11:11:19 +0100 on host XPS139305, Linux-5.11.0-44-generic-x86_64-with-glibc2.29\n",
"\n",
"Description: Test data for the correlator example\n"
]
}
],
"source": [
"correlator_data = pe.input.json.load_json(\"./data/correlator_test\")\n",
"my_correlator = pe.Corr(correlator_data)\n",
"my_correlator.gamma_method()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import autograd.numpy as anp\n",
"def func_exp(a, x):\n",
" return a[1] * anp.exp(-a[0] * x)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"rows = []\n",
"for t_start in range(12, 17):\n",
" for t_stop in range(30, 35):\n",
" fr = my_correlator.fit(func_exp, [t_start, t_stop], silent=True)\n",
" fr.gamma_method()\n",
" row = {\"t_start\": t_start,\n",
" \"t_stop\": t_stop,\n",
" \"datapoints\": t_stop - t_start + 1,\n",
" \"chisquare_by_dof\": fr.chisquare_by_dof,\n",
" \"mass\": fr[0]}\n",
" rows.append(row)\n",
"my_df = pd.DataFrame(rows)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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>t_start</th>\n",
" <th>t_stop</th>\n",
" <th>datapoints</th>\n",
" <th>chisquare_by_dof</th>\n",
" <th>mass</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12</td>\n",
" <td>30</td>\n",
" <td>19</td>\n",
" <td>0.057872</td>\n",
" <td>0.2218(12)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>20</td>\n",
" <td>0.063951</td>\n",
" <td>0.2221(11)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>12</td>\n",
" <td>32</td>\n",
" <td>21</td>\n",
" <td>0.064960</td>\n",
" <td>0.2223(11)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>12</td>\n",
" <td>33</td>\n",
" <td>22</td>\n",
" <td>0.066495</td>\n",
" <td>0.2224(10)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>12</td>\n",
" <td>34</td>\n",
" <td>23</td>\n",
" <td>0.066606</td>\n",
" <td>0.2225(10)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>13</td>\n",
" <td>30</td>\n",
" <td>18</td>\n",
" <td>0.051577</td>\n",
" <td>0.2215(12)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>13</td>\n",
" <td>31</td>\n",
" <td>19</td>\n",
" <td>0.060901</td>\n",
" <td>0.2219(11)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>13</td>\n",
" <td>32</td>\n",
" <td>20</td>\n",
" <td>0.063551</td>\n",
" <td>0.2221(12)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>13</td>\n",
" <td>33</td>\n",
" <td>21</td>\n",
" <td>0.066406</td>\n",
" <td>0.2223(12)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>13</td>\n",
" <td>34</td>\n",
" <td>22</td>\n",
" <td>0.067237</td>\n",
" <td>0.2224(12)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>14</td>\n",
" <td>30</td>\n",
" <td>17</td>\n",
" <td>0.052349</td>\n",
" <td>0.2213(13)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>14</td>\n",
" <td>31</td>\n",
" <td>18</td>\n",
" <td>0.063640</td>\n",
" <td>0.2218(13)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>14</td>\n",
" <td>32</td>\n",
" <td>19</td>\n",
" <td>0.066883</td>\n",
" <td>0.2220(14)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>14</td>\n",
" <td>33</td>\n",
" <td>20</td>\n",
" <td>0.070019</td>\n",
" <td>0.2223(15)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>14</td>\n",
" <td>34</td>\n",
" <td>21</td>\n",
" <td>0.070775</td>\n",
" <td>0.2224(15)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>15</td>\n",
" <td>30</td>\n",
" <td>16</td>\n",
" <td>0.056088</td>\n",
" <td>0.2213(16)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>15</td>\n",
" <td>31</td>\n",
" <td>17</td>\n",
" <td>0.067552</td>\n",
" <td>0.2218(17)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>15</td>\n",
" <td>32</td>\n",
" <td>18</td>\n",
" <td>0.070170</td>\n",
" <td>0.2221(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>15</td>\n",
" <td>33</td>\n",
" <td>19</td>\n",
" <td>0.072516</td>\n",
" <td>0.2224(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>15</td>\n",
" <td>34</td>\n",
" <td>20</td>\n",
" <td>0.072509</td>\n",
" <td>0.2225(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>16</td>\n",
" <td>30</td>\n",
" <td>15</td>\n",
" <td>0.059969</td>\n",
" <td>0.2214(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>16</td>\n",
" <td>31</td>\n",
" <td>16</td>\n",
" <td>0.070874</td>\n",
" <td>0.2220(20)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>16</td>\n",
" <td>32</td>\n",
" <td>17</td>\n",
" <td>0.072437</td>\n",
" <td>0.2223(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>16</td>\n",
" <td>33</td>\n",
" <td>18</td>\n",
" <td>0.073684</td>\n",
" <td>0.2225(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>16</td>\n",
" <td>34</td>\n",
" <td>19</td>\n",
" <td>0.072767</td>\n",
" <td>0.2227(20)</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" t_start t_stop datapoints chisquare_by_dof mass\n",
"0 12 30 19 0.057872 0.2218(12)\n",
"1 12 31 20 0.063951 0.2221(11)\n",
"2 12 32 21 0.064960 0.2223(11)\n",
"3 12 33 22 0.066495 0.2224(10)\n",
"4 12 34 23 0.066606 0.2225(10)\n",
"5 13 30 18 0.051577 0.2215(12)\n",
"6 13 31 19 0.060901 0.2219(11)\n",
"7 13 32 20 0.063551 0.2221(12)\n",
"8 13 33 21 0.066406 0.2223(12)\n",
"9 13 34 22 0.067237 0.2224(12)\n",
"10 14 30 17 0.052349 0.2213(13)\n",
"11 14 31 18 0.063640 0.2218(13)\n",
"12 14 32 19 0.066883 0.2220(14)\n",
"13 14 33 20 0.070019 0.2223(15)\n",
"14 14 34 21 0.070775 0.2224(15)\n",
"15 15 30 16 0.056088 0.2213(16)\n",
"16 15 31 17 0.067552 0.2218(17)\n",
"17 15 32 18 0.070170 0.2221(18)\n",
"18 15 33 19 0.072516 0.2224(18)\n",
"19 15 34 20 0.072509 0.2225(18)\n",
"20 16 30 15 0.059969 0.2214(21)\n",
"21 16 31 16 0.070874 0.2220(20)\n",
"22 16 32 17 0.072437 0.2223(21)\n",
"23 16 33 18 0.073684 0.2225(21)\n",
"24 16 34 19 0.072767 0.2227(20)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"my_df"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"pe.input.pandas.to_sql(my_df, \"mass_table\", \"my_db.sqlite\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"new_df = df = pe.input.pandas.read_sql(f\"SELECT t_start, t_stop, mass FROM mass_table WHERE t_start > 13\"\n",
" ,\"my_db.sqlite\"\n",
" ,auto_gamma=True)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"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>t_start</th>\n",
" <th>t_stop</th>\n",
" <th>mass</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>14</td>\n",
" <td>30</td>\n",
" <td>0.2213(13)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>14</td>\n",
" <td>31</td>\n",
" <td>0.2218(13)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14</td>\n",
" <td>32</td>\n",
" <td>0.2220(14)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>14</td>\n",
" <td>33</td>\n",
" <td>0.2223(15)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>14</td>\n",
" <td>34</td>\n",
" <td>0.2224(15)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>15</td>\n",
" <td>30</td>\n",
" <td>0.2213(16)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>15</td>\n",
" <td>31</td>\n",
" <td>0.2218(17)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>15</td>\n",
" <td>32</td>\n",
" <td>0.2221(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>15</td>\n",
" <td>33</td>\n",
" <td>0.2224(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>15</td>\n",
" <td>34</td>\n",
" <td>0.2225(18)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>16</td>\n",
" <td>30</td>\n",
" <td>0.2214(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>16</td>\n",
" <td>31</td>\n",
" <td>0.2220(20)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>16</td>\n",
" <td>32</td>\n",
" <td>0.2223(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>16</td>\n",
" <td>33</td>\n",
" <td>0.2225(21)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>16</td>\n",
" <td>34</td>\n",
" <td>0.2227(20)</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" t_start t_stop mass\n",
"0 14 30 0.2213(13)\n",
"1 14 31 0.2218(13)\n",
"2 14 32 0.2220(14)\n",
"3 14 33 0.2223(15)\n",
"4 14 34 0.2224(15)\n",
"5 15 30 0.2213(16)\n",
"6 15 31 0.2218(17)\n",
"7 15 32 0.2221(18)\n",
"8 15 33 0.2224(18)\n",
"9 15 34 0.2225(18)\n",
"10 16 30 0.2214(21)\n",
"11 16 31 0.2220(20)\n",
"12 16 32 0.2223(21)\n",
"13 16 33 0.2225(21)\n",
"14 16 34 0.2227(20)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"new_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 4
}