Skip to content

Instantly share code, notes, and snippets.

@jlaw9

jlaw9/matminer-example.ipynb

Created October 4, 2022 22:31
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save jlaw9/723021269238c87057382f093d6c3fe6 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save jlaw9/723021269238c87057382f093d6c3fe6 to your computer and use it in GitHub Desktop.
Download ZIP
Matminer example
Display the source blob
Display the rendered blob
Raw
matminer-example.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "a63c7c38-b694-4528-a7cd-baed73fd7c70",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from pymatgen.core import Structure\n",
"from matminer.featurizers.site import CrystalNNFingerprint\n",
"from matminer.featurizers.structure import SiteStatsFingerprint"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d1a28c55-3a50-45c6-ab65-1515b5eb9681",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1181\n"
]
},
{
"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>material_id</th>\n",
" <th>formula</th>\n",
" <th>nsites</th>\n",
" <th>space_group</th>\n",
" <th>volume</th>\n",
" <th>structure</th>\n",
" <th>elastic_anisotropy</th>\n",
" <th>G_Reuss</th>\n",
" <th>G_VRH</th>\n",
" <th>G_Voigt</th>\n",
" <th>K_Reuss</th>\n",
" <th>K_VRH</th>\n",
" <th>K_Voigt</th>\n",
" <th>poisson_ratio</th>\n",
" <th>compliance_tensor</th>\n",
" <th>elastic_tensor</th>\n",
" <th>elastic_tensor_original</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>mp-10003</td>\n",
" <td>Nb4CoSi</td>\n",
" <td>12</td>\n",
" <td>124</td>\n",
" <td>194.419802</td>\n",
" <td>[[0.94814328 2.07280467 2.5112 ] Nb, [5.273...</td>\n",
" <td>0.030688</td>\n",
" <td>96.844535</td>\n",
" <td>97.141604</td>\n",
" <td>97.438674</td>\n",
" <td>194.267623</td>\n",
" <td>194.268884</td>\n",
" <td>194.270146</td>\n",
" <td>0.285701</td>\n",
" <td>[[0.004385293093993, -0.0016070693558990002, -...</td>\n",
" <td>[[311.33514638650246, 144.45092552856926, 126....</td>\n",
" <td>[[311.33514638650246, 144.45092552856926, 126....</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>mp-10010</td>\n",
" <td>Al(CoSi)2</td>\n",
" <td>5</td>\n",
" <td>164</td>\n",
" <td>61.987320</td>\n",
" <td>[[0. 0. 0.] Al, [1.96639263 1.13529553 0.75278...</td>\n",
" <td>0.266910</td>\n",
" <td>93.939650</td>\n",
" <td>96.252006</td>\n",
" <td>98.564362</td>\n",
" <td>173.647763</td>\n",
" <td>175.449907</td>\n",
" <td>177.252050</td>\n",
" <td>0.268105</td>\n",
" <td>[[0.0037715428949660003, -0.000844229828709, -...</td>\n",
" <td>[[306.93357350984974, 88.02634955100905, 105.6...</td>\n",
" <td>[[306.93357350984974, 88.02634955100905, 105.6...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" material_id formula nsites space_group volume \\\n",
"0 mp-10003 Nb4CoSi 12 124 194.419802 \n",
"1 mp-10010 Al(CoSi)2 5 164 61.987320 \n",
"\n",
" structure elastic_anisotropy \\\n",
"0 [[0.94814328 2.07280467 2.5112 ] Nb, [5.273... 0.030688 \n",
"1 [[0. 0. 0.] Al, [1.96639263 1.13529553 0.75278... 0.266910 \n",
"\n",
" G_Reuss G_VRH G_Voigt K_Reuss K_VRH K_Voigt \\\n",
"0 96.844535 97.141604 97.438674 194.267623 194.268884 194.270146 \n",
"1 93.939650 96.252006 98.564362 173.647763 175.449907 177.252050 \n",
"\n",
" poisson_ratio compliance_tensor \\\n",
"0 0.285701 [[0.004385293093993, -0.0016070693558990002, -... \n",
"1 0.268105 [[0.0037715428949660003, -0.000844229828709, -... \n",
"\n",
" elastic_tensor \\\n",
"0 [[311.33514638650246, 144.45092552856926, 126.... \n",
"1 [[306.93357350984974, 88.02634955100905, 105.6... \n",
"\n",
" elastic_tensor_original \n",
"0 [[311.33514638650246, 144.45092552856926, 126.... \n",
"1 [[306.93357350984974, 88.02634955100905, 105.6... "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from matminer.datasets.convenience_loaders import load_elastic_tensor\n",
"\n",
"df = load_elastic_tensor() # loads dataset in a pandas DataFrame object\n",
"print(len(df))\n",
"df.head(2)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "86b5151c-5458-4718-b242-5a6d00f9f3a9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Structure Summary\n",
"Lattice\n",
" abc : 6.22178 6.22178 5.0224\n",
" angles : 90.0 90.0 90.0\n",
" volume : 194.41984808065214\n",
" A : 6.22178 0.0 0.0\n",
" B : 0.0 6.22178 0.0\n",
" C : 0.0 0.0 5.0224\n",
"PeriodicSite: Nb (0.9481, 2.0728, 2.5112) [0.1524, 0.3332, 0.5000]\n",
"PeriodicSite: Nb (5.2736, 4.1490, 2.5112) [0.8476, 0.6668, 0.5000]\n",
"PeriodicSite: Nb (4.1490, 0.9481, 2.5112) [0.6668, 0.1524, 0.5000]\n",
"PeriodicSite: Nb (2.0728, 5.2736, 2.5112) [0.3332, 0.8476, 0.5000]\n",
"PeriodicSite: Nb (5.2736, 2.0728, 0.0000) [0.8476, 0.3332, 0.0000]\n",
"PeriodicSite: Nb (4.1490, 5.2736, 0.0000) [0.6668, 0.8476, 0.0000]\n",
"PeriodicSite: Nb (2.0728, 0.9481, 0.0000) [0.3332, 0.1524, 0.0000]\n",
"PeriodicSite: Nb (0.9481, 4.1490, 0.0000) [0.1524, 0.6668, 0.0000]\n",
"PeriodicSite: Co (0.0000, 0.0000, 3.7668) [0.0000, 0.0000, 0.7500]\n",
"PeriodicSite: Co (0.0000, 0.0000, 1.2556) [0.0000, 0.0000, 0.2500]\n",
"PeriodicSite: Si (3.1109, 3.1109, 3.7668) [0.5000, 0.5000, 0.7500]\n",
"PeriodicSite: Si (3.1109, 3.1109, 1.2556) [0.5000, 0.5000, 0.2500]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# first use an example structure\n",
"structure = df.structure.values[0]\n",
"structure"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "f3381626-949b-4c05-829c-07c9147d0846",
"metadata": {},
"outputs": [],
"source": [
"ssf = SiteStatsFingerprint(\n",
" CrystalNNFingerprint.from_preset('ops', distance_cutoffs=None, x_diff_weight=0),\n",
" stats=('mean', 'std_dev')\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ec9e7455-cf0f-4f4e-9ba6-998b8251ee84",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"122\n"
]
}
],
"source": [
"features = ssf.featurize(structure)\n",
"print(len(features))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7ba672ba-8990-4161-850a-3069b354d2f2",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "217aecf8f26e4df6916c027733554d5e",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"SiteStatsFingerprint: 0%| | 0/10 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"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>material_id</th>\n",
" <th>formula</th>\n",
" <th>nsites</th>\n",
" <th>space_group</th>\n",
" <th>volume</th>\n",
" <th>structure</th>\n",
" <th>elastic_anisotropy</th>\n",
" <th>G_Reuss</th>\n",
" <th>G_VRH</th>\n",
" <th>G_Voigt</th>\n",
" <th>...</th>\n",
" <th>mean wt CN_20</th>\n",
" <th>std_dev wt CN_20</th>\n",
" <th>mean wt CN_21</th>\n",
" <th>std_dev wt CN_21</th>\n",
" <th>mean wt CN_22</th>\n",
" <th>std_dev wt CN_22</th>\n",
" <th>mean wt CN_23</th>\n",
" <th>std_dev wt CN_23</th>\n",
" <th>mean wt CN_24</th>\n",
" <th>std_dev wt CN_24</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>mp-10003</td>\n",
" <td>Nb4CoSi</td>\n",
" <td>12</td>\n",
" <td>124</td>\n",
" <td>194.419802</td>\n",
" <td>[[0.94814328 2.07280467 2.5112 ] Nb, [5.273...</td>\n",
" <td>0.030688</td>\n",
" <td>96.844535</td>\n",
" <td>97.141604</td>\n",
" <td>97.438674</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>mp-10010</td>\n",
" <td>Al(CoSi)2</td>\n",
" <td>5</td>\n",
" <td>164</td>\n",
" <td>61.987320</td>\n",
" <td>[[0. 0. 0.] Al, [1.96639263 1.13529553 0.75278...</td>\n",
" <td>0.266910</td>\n",
" <td>93.939650</td>\n",
" <td>96.252006</td>\n",
" <td>98.564362</td>\n",
" <td>...</td>\n",
" <td>0.000255</td>\n",
" <td>0.000509</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>mp-10015</td>\n",
" <td>SiOs</td>\n",
" <td>2</td>\n",
" <td>221</td>\n",
" <td>25.952539</td>\n",
" <td>[[1.480346 1.480346 1.480346] Si, [0. 0. 0.] Os]</td>\n",
" <td>0.756489</td>\n",
" <td>120.962289</td>\n",
" <td>130.112955</td>\n",
" <td>139.263621</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>mp-10021</td>\n",
" <td>Ga</td>\n",
" <td>4</td>\n",
" <td>63</td>\n",
" <td>76.721433</td>\n",
" <td>[[0. 1.09045794 0.84078375] Ga, [0. ...</td>\n",
" <td>2.376805</td>\n",
" <td>12.205989</td>\n",
" <td>15.101901</td>\n",
" <td>17.997812</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>mp-10025</td>\n",
" <td>SiRu2</td>\n",
" <td>12</td>\n",
" <td>62</td>\n",
" <td>160.300999</td>\n",
" <td>[[1.0094265 4.24771709 2.9955487 ] Si, [3.028...</td>\n",
" <td>0.196930</td>\n",
" <td>100.110773</td>\n",
" <td>101.947798</td>\n",
" <td>103.784823</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>mp-10037</td>\n",
" <td>AlCo3C</td>\n",
" <td>5</td>\n",
" <td>221</td>\n",
" <td>51.574959</td>\n",
" <td>[[0. 0. 0.] Al, [0. 1.861157 1.861157] C...</td>\n",
" <td>0.420936</td>\n",
" <td>111.795761</td>\n",
" <td>116.501644</td>\n",
" <td>121.207527</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>mp-10063</td>\n",
" <td>CdSnSb2</td>\n",
" <td>16</td>\n",
" <td>122</td>\n",
" <td>580.176940</td>\n",
" <td>[[0. 3.322252 9.855906] Cd, [0. 0....</td>\n",
" <td>0.629264</td>\n",
" <td>16.692188</td>\n",
" <td>17.742410</td>\n",
" <td>18.792631</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>mp-101</td>\n",
" <td>Ir</td>\n",
" <td>4</td>\n",
" <td>225</td>\n",
" <td>58.258386</td>\n",
" <td>[[0. 0. 0.] Ir, [0. 1.938308 1.938308] I...</td>\n",
" <td>0.174540</td>\n",
" <td>212.791803</td>\n",
" <td>216.505869</td>\n",
" <td>220.219935</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>mp-10125</td>\n",
" <td>SbIr</td>\n",
" <td>4</td>\n",
" <td>194</td>\n",
" <td>80.054967</td>\n",
" <td>[[2.03154403 1.17291049 4.19959275] Sb, [-2.03...</td>\n",
" <td>0.591712</td>\n",
" <td>55.983343</td>\n",
" <td>59.245410</td>\n",
" <td>62.507476</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>mp-10154</td>\n",
" <td>MnSbIr</td>\n",
" <td>12</td>\n",
" <td>216</td>\n",
" <td>228.873769</td>\n",
" <td>[[3.0584545 0. 0. ] Mn, [3.058454...</td>\n",
" <td>0.109313</td>\n",
" <td>39.747198</td>\n",
" <td>40.181671</td>\n",
" <td>40.616145</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10 rows × 139 columns</p>\n",
"</div>"
],
"text/plain": [
" material_id formula nsites space_group volume \\\n",
"0 mp-10003 Nb4CoSi 12 124 194.419802 \n",
"1 mp-10010 Al(CoSi)2 5 164 61.987320 \n",
"2 mp-10015 SiOs 2 221 25.952539 \n",
"3 mp-10021 Ga 4 63 76.721433 \n",
"4 mp-10025 SiRu2 12 62 160.300999 \n",
"5 mp-10037 AlCo3C 5 221 51.574959 \n",
"6 mp-10063 CdSnSb2 16 122 580.176940 \n",
"7 mp-101 Ir 4 225 58.258386 \n",
"8 mp-10125 SbIr 4 194 80.054967 \n",
"9 mp-10154 MnSbIr 12 216 228.873769 \n",
"\n",
" structure elastic_anisotropy \\\n",
"0 [[0.94814328 2.07280467 2.5112 ] Nb, [5.273... 0.030688 \n",
"1 [[0. 0. 0.] Al, [1.96639263 1.13529553 0.75278... 0.266910 \n",
"2 [[1.480346 1.480346 1.480346] Si, [0. 0. 0.] Os] 0.756489 \n",
"3 [[0. 1.09045794 0.84078375] Ga, [0. ... 2.376805 \n",
"4 [[1.0094265 4.24771709 2.9955487 ] Si, [3.028... 0.196930 \n",
"5 [[0. 0. 0.] Al, [0. 1.861157 1.861157] C... 0.420936 \n",
"6 [[0. 3.322252 9.855906] Cd, [0. 0.... 0.629264 \n",
"7 [[0. 0. 0.] Ir, [0. 1.938308 1.938308] I... 0.174540 \n",
"8 [[2.03154403 1.17291049 4.19959275] Sb, [-2.03... 0.591712 \n",
"9 [[3.0584545 0. 0. ] Mn, [3.058454... 0.109313 \n",
"\n",
" G_Reuss G_VRH G_Voigt ... mean wt CN_20 std_dev wt CN_20 \\\n",
"0 96.844535 97.141604 97.438674 ... 0.000000 0.000000 \n",
"1 93.939650 96.252006 98.564362 ... 0.000255 0.000509 \n",
"2 120.962289 130.112955 139.263621 ... 0.000000 0.000000 \n",
"3 12.205989 15.101901 17.997812 ... 0.000000 0.000000 \n",
"4 100.110773 101.947798 103.784823 ... 0.000000 0.000000 \n",
"5 111.795761 116.501644 121.207527 ... 0.000000 0.000000 \n",
"6 16.692188 17.742410 18.792631 ... 0.000000 0.000000 \n",
"7 212.791803 216.505869 220.219935 ... 0.000000 0.000000 \n",
"8 55.983343 59.245410 62.507476 ... 0.000000 0.000000 \n",
"9 39.747198 40.181671 40.616145 ... 0.000000 0.000000 \n",
"\n",
" mean wt CN_21 std_dev wt CN_21 mean wt CN_22 std_dev wt CN_22 \\\n",
"0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"5 0.0 0.0 0.0 0.0 \n",
"6 0.0 0.0 0.0 0.0 \n",
"7 0.0 0.0 0.0 0.0 \n",
"8 0.0 0.0 0.0 0.0 \n",
"9 0.0 0.0 0.0 0.0 \n",
"\n",
" mean wt CN_23 std_dev wt CN_23 mean wt CN_24 std_dev wt CN_24 \n",
"0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"5 0.0 0.0 0.0 0.0 \n",
"6 0.0 0.0 0.0 0.0 \n",
"7 0.0 0.0 0.0 0.0 \n",
"8 0.0 0.0 0.0 0.0 \n",
"9 0.0 0.0 0.0 0.0 \n",
"\n",
"[10 rows x 139 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# example of computing the features for structures in a dataframe\n",
"# add CrystalNNFingerprint to the dataframe \n",
"df_head = ssf.featurize_dataframe(df.head(10), \"structure\")\n",
"# df[['material_id', 'formula']].head(2)\n",
"df_head"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "3beecafa-5a9b-4bf5-bc7a-c71769d8ac77",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"139"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(df_head.columns)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "1bd0fdec-c41b-45d2-a46b-3d9e4ad81d88",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.metrics.pairwise import paired_cosine_distances\n",
"paired_cosine_distances(df_head.iloc[:, -122:].values, df_head.iloc[:, -122:].values)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "5da6e26e-c8b5-4a4d-87df-21f9d1cba9ac",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"mp-10003 mp-10037 0.962867\n",
"mp-10010 mp-10063 0.997863\n",
"mp-10015 mp-101 1.000000\n",
"mp-10021 mp-10125 0.635249\n",
"mp-10025 mp-10154 0.564862\n",
"dtype: float64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# compute the cosine distance between all pairs of structures\n",
"all_distances = {}\n",
"for i in range(5, len(df_head)):\n",
" idxs_to_compare = list(range(i, len(df_head))) + list(range(i))\n",
" distances = paired_cosine_distances(df_head.iloc[:, -122:].values, df_head.iloc[idxs_to_compare, -122:].values)\n",
" labels = zip(df_head.material_id.values, df_head.iloc[idxs_to_compare].material_id.values)\n",
" labels = [tuple(sorted(pair)) for pair in labels]\n",
" all_distances.update({labels[j]: distances[j] for j in range(len(labels))})\n",
"\n",
"all_distances = pd.Series(all_distances)\n",
"all_distances.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "f8c4016d-5eb7-43a8-8bd1-9035d04ddea0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<AxesSubplot:>"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"all_distances.hist(bins=20)"
]
}
],
"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": "3.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment