Skip to content

Commit 300c87b

Browse files
refining options documentation not in the dataset
1 parent fe77c9f commit 300c87b

File tree

2 files changed

+586
-4
lines changed

2 files changed

+586
-4
lines changed

.ipynb_checkpoints/feature_frequency-checkpoint.ipynb

Lines changed: 293 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -512,9 +512,16 @@
512512
},
513513
{
514514
"cell_type": "code",
515-
"execution_count": 15,
515+
"execution_count": 22,
516516
"metadata": {},
517517
"outputs": [
518+
{
519+
"name": "stdout",
520+
"output_type": "stream",
521+
"text": [
522+
"(31, 4)\n"
523+
]
524+
},
518525
{
519526
"data": {
520527
"text/html": [
@@ -799,15 +806,299 @@
799806
"145 XEN_STUB 0 0 0"
800807
]
801808
},
802-
"execution_count": 15,
809+
"execution_count": 22,
803810
"metadata": {},
804811
"output_type": "execute_result"
805812
}
806813
],
807814
"source": [
815+
"# all options \"not\" in our dataset (because value is unique: no diversity!)\n",
816+
"print(options_distr.query(\"val_0 == 0 and val_1 == 0 and val_2 == 0\").shape)\n",
808817
"options_distr.query(\"val_0 == 0 and val_1 == 0 and val_2 == 0\")"
809818
]
810819
},
820+
{
821+
"cell_type": "code",
822+
"execution_count": 31,
823+
"metadata": {},
824+
"outputs": [
825+
{
826+
"data": {
827+
"text/html": [
828+
"<div>\n",
829+
"<style scoped>\n",
830+
" .dataframe tbody tr th:only-of-type {\n",
831+
" vertical-align: middle;\n",
832+
" }\n",
833+
"\n",
834+
" .dataframe tbody tr th {\n",
835+
" vertical-align: top;\n",
836+
" }\n",
837+
"\n",
838+
" .dataframe thead th {\n",
839+
" text-align: right;\n",
840+
" }\n",
841+
"</style>\n",
842+
"<table border=\"1\" class=\"dataframe\">\n",
843+
" <thead>\n",
844+
" <tr style=\"text-align: right;\">\n",
845+
" <th></th>\n",
846+
" <th>option</th>\n",
847+
" <th>val_0</th>\n",
848+
" <th>val_1</th>\n",
849+
" <th>val_2</th>\n",
850+
" </tr>\n",
851+
" </thead>\n",
852+
" <tbody>\n",
853+
" <tr>\n",
854+
" <th>9</th>\n",
855+
" <td>ATM_FORE200E_DEBUG</td>\n",
856+
" <td>0</td>\n",
857+
" <td>0</td>\n",
858+
" <td>0</td>\n",
859+
" </tr>\n",
860+
" <tr>\n",
861+
" <th>10</th>\n",
862+
" <td>B43LEGACY_DMA_MODE</td>\n",
863+
" <td>0</td>\n",
864+
" <td>0</td>\n",
865+
" <td>0</td>\n",
866+
" </tr>\n",
867+
" <tr>\n",
868+
" <th>11</th>\n",
869+
" <td>B43LEGACY_PIO_MODE</td>\n",
870+
" <td>0</td>\n",
871+
" <td>0</td>\n",
872+
" <td>0</td>\n",
873+
" </tr>\n",
874+
" <tr>\n",
875+
" <th>25</th>\n",
876+
" <td>CC_STACKPROTECTOR_REGULAR</td>\n",
877+
" <td>0</td>\n",
878+
" <td>0</td>\n",
879+
" <td>0</td>\n",
880+
" </tr>\n",
881+
" <tr>\n",
882+
" <th>26</th>\n",
883+
" <td>CC_STACKPROTECTOR_STRONG</td>\n",
884+
" <td>0</td>\n",
885+
" <td>0</td>\n",
886+
" <td>0</td>\n",
887+
" </tr>\n",
888+
" <tr>\n",
889+
" <th>32</th>\n",
890+
" <td>CPU_SUP_CYRIX_32</td>\n",
891+
" <td>0</td>\n",
892+
" <td>0</td>\n",
893+
" <td>0</td>\n",
894+
" </tr>\n",
895+
" <tr>\n",
896+
" <th>34</th>\n",
897+
" <td>CPU_SUP_TRANSMETA_32</td>\n",
898+
" <td>0</td>\n",
899+
" <td>0</td>\n",
900+
" <td>0</td>\n",
901+
" </tr>\n",
902+
" <tr>\n",
903+
" <th>35</th>\n",
904+
" <td>CPU_SUP_UMC_32</td>\n",
905+
" <td>0</td>\n",
906+
" <td>0</td>\n",
907+
" <td>0</td>\n",
908+
" </tr>\n",
909+
" <tr>\n",
910+
" <th>46</th>\n",
911+
" <td>EISA_NAMES</td>\n",
912+
" <td>0</td>\n",
913+
" <td>0</td>\n",
914+
" <td>0</td>\n",
915+
" </tr>\n",
916+
" <tr>\n",
917+
" <th>56</th>\n",
918+
" <td>HWSPINLOCK_SIRF</td>\n",
919+
" <td>0</td>\n",
920+
" <td>0</td>\n",
921+
" <td>0</td>\n",
922+
" </tr>\n",
923+
" <tr>\n",
924+
" <th>58</th>\n",
925+
" <td>INITRAMFS_COMPRESSION_BZIP2</td>\n",
926+
" <td>0</td>\n",
927+
" <td>0</td>\n",
928+
" <td>0</td>\n",
929+
" </tr>\n",
930+
" <tr>\n",
931+
" <th>59</th>\n",
932+
" <td>INITRAMFS_COMPRESSION_GZIP</td>\n",
933+
" <td>0</td>\n",
934+
" <td>0</td>\n",
935+
" <td>0</td>\n",
936+
" </tr>\n",
937+
" <tr>\n",
938+
" <th>60</th>\n",
939+
" <td>INITRAMFS_COMPRESSION_LZ4</td>\n",
940+
" <td>0</td>\n",
941+
" <td>0</td>\n",
942+
" <td>0</td>\n",
943+
" </tr>\n",
944+
" <tr>\n",
945+
" <th>61</th>\n",
946+
" <td>INITRAMFS_COMPRESSION_LZMA</td>\n",
947+
" <td>0</td>\n",
948+
" <td>0</td>\n",
949+
" <td>0</td>\n",
950+
" </tr>\n",
951+
" <tr>\n",
952+
" <th>62</th>\n",
953+
" <td>INITRAMFS_COMPRESSION_LZO</td>\n",
954+
" <td>0</td>\n",
955+
" <td>0</td>\n",
956+
" <td>0</td>\n",
957+
" </tr>\n",
958+
" <tr>\n",
959+
" <th>63</th>\n",
960+
" <td>INITRAMFS_COMPRESSION_NONE</td>\n",
961+
" <td>0</td>\n",
962+
" <td>0</td>\n",
963+
" <td>0</td>\n",
964+
" </tr>\n",
965+
" <tr>\n",
966+
" <th>64</th>\n",
967+
" <td>INITRAMFS_COMPRESSION_XZ</td>\n",
968+
" <td>0</td>\n",
969+
" <td>0</td>\n",
970+
" <td>0</td>\n",
971+
" </tr>\n",
972+
" <tr>\n",
973+
" <th>77</th>\n",
974+
" <td>KASAN_INLINE</td>\n",
975+
" <td>0</td>\n",
976+
" <td>0</td>\n",
977+
" <td>0</td>\n",
978+
" </tr>\n",
979+
" <tr>\n",
980+
" <th>85</th>\n",
981+
" <td>LGUEST_GUEST</td>\n",
982+
" <td>0</td>\n",
983+
" <td>0</td>\n",
984+
" <td>0</td>\n",
985+
" </tr>\n",
986+
" <tr>\n",
987+
" <th>89</th>\n",
988+
" <td>MATH_EMULATION</td>\n",
989+
" <td>0</td>\n",
990+
" <td>0</td>\n",
991+
" <td>0</td>\n",
992+
" </tr>\n",
993+
" <tr>\n",
994+
" <th>99</th>\n",
995+
" <td>NOMMU_INITIAL_TRIM_EXCESS</td>\n",
996+
" <td>0</td>\n",
997+
" <td>0</td>\n",
998+
" <td>0</td>\n",
999+
" </tr>\n",
1000+
" <tr>\n",
1001+
" <th>101</th>\n",
1002+
" <td>OMAP_REMOTEPROC</td>\n",
1003+
" <td>0</td>\n",
1004+
" <td>0</td>\n",
1005+
" <td>0</td>\n",
1006+
" </tr>\n",
1007+
" <tr>\n",
1008+
" <th>110</th>\n",
1009+
" <td>PREEMPT_TRACER</td>\n",
1010+
" <td>0</td>\n",
1011+
" <td>0</td>\n",
1012+
" <td>0</td>\n",
1013+
" </tr>\n",
1014+
" <tr>\n",
1015+
" <th>121</th>\n",
1016+
" <td>SH_CPU_FREQ</td>\n",
1017+
" <td>0</td>\n",
1018+
" <td>0</td>\n",
1019+
" <td>0</td>\n",
1020+
" </tr>\n",
1021+
" <tr>\n",
1022+
" <th>145</th>\n",
1023+
" <td>XEN_STUB</td>\n",
1024+
" <td>0</td>\n",
1025+
" <td>0</td>\n",
1026+
" <td>0</td>\n",
1027+
" </tr>\n",
1028+
" </tbody>\n",
1029+
"</table>\n",
1030+
"</div>"
1031+
],
1032+
"text/plain": [
1033+
" option val_0 val_1 val_2\n",
1034+
"9 ATM_FORE200E_DEBUG 0 0 0\n",
1035+
"10 B43LEGACY_DMA_MODE 0 0 0\n",
1036+
"11 B43LEGACY_PIO_MODE 0 0 0\n",
1037+
"25 CC_STACKPROTECTOR_REGULAR 0 0 0\n",
1038+
"26 CC_STACKPROTECTOR_STRONG 0 0 0\n",
1039+
"32 CPU_SUP_CYRIX_32 0 0 0\n",
1040+
"34 CPU_SUP_TRANSMETA_32 0 0 0\n",
1041+
"35 CPU_SUP_UMC_32 0 0 0\n",
1042+
"46 EISA_NAMES 0 0 0\n",
1043+
"56 HWSPINLOCK_SIRF 0 0 0\n",
1044+
"58 INITRAMFS_COMPRESSION_BZIP2 0 0 0\n",
1045+
"59 INITRAMFS_COMPRESSION_GZIP 0 0 0\n",
1046+
"60 INITRAMFS_COMPRESSION_LZ4 0 0 0\n",
1047+
"61 INITRAMFS_COMPRESSION_LZMA 0 0 0\n",
1048+
"62 INITRAMFS_COMPRESSION_LZO 0 0 0\n",
1049+
"63 INITRAMFS_COMPRESSION_NONE 0 0 0\n",
1050+
"64 INITRAMFS_COMPRESSION_XZ 0 0 0\n",
1051+
"77 KASAN_INLINE 0 0 0\n",
1052+
"85 LGUEST_GUEST 0 0 0\n",
1053+
"89 MATH_EMULATION 0 0 0\n",
1054+
"99 NOMMU_INITIAL_TRIM_EXCESS 0 0 0\n",
1055+
"101 OMAP_REMOTEPROC 0 0 0\n",
1056+
"110 PREEMPT_TRACER 0 0 0\n",
1057+
"121 SH_CPU_FREQ 0 0 0\n",
1058+
"145 XEN_STUB 0 0 0"
1059+
]
1060+
},
1061+
"execution_count": 31,
1062+
"metadata": {},
1063+
"output_type": "execute_result"
1064+
}
1065+
],
1066+
"source": [
1067+
"options_distr_p = options_distr.query(\"val_0 == 0 and val_1 == 0 and val_2 == 0\")\n",
1068+
"\n",
1069+
"\n",
1070+
"csizes = ['LZ4', 'GZIP', 'LZO', 'XZ', 'LZMA', 'BZIP2'] \n",
1071+
"# we remove (1) compressed sizes options (we have in the dataset)\n",
1072+
"# https://wiki.gentoo.org/wiki/Custom_Initramfs\n",
1073+
"# (2) we mayb also remove INITRAMFS_COMPRESSION_ that have no effect on size we measure, but I'm not sure here\n",
1074+
"options_distr_p.query(' and '.join([\"option != 'KERNEL_\" + compr + \"'\" for compr in csizes]))\n",
1075+
"\n",
1076+
"# .query(' and '.join([\"option != 'INITRAMFS_COMPRESSION_\" + compr + \"'\" for compr in csizes])).query(\"option != 'INITRAMFS_COMPRESSION_NONE'\")"
1077+
]
1078+
},
1079+
{
1080+
"cell_type": "code",
1081+
"execution_count": 37,
1082+
"metadata": {},
1083+
"outputs": [
1084+
{
1085+
"data": {
1086+
"text/plain": [
1087+
"0 46302\n",
1088+
"1 46169\n",
1089+
"Name: BLK_DEV_INITRD, dtype: int64"
1090+
]
1091+
},
1092+
"execution_count": 37,
1093+
"metadata": {},
1094+
"output_type": "execute_result"
1095+
}
1096+
],
1097+
"source": [
1098+
"df['BLK_DEV_INITRD'].value_counts() \n",
1099+
"#, df['INITRAMFS_SOURCE']"
1100+
]
1101+
},
8111102
{
8121103
"cell_type": "code",
8131104
"execution_count": null,

0 commit comments

Comments
 (0)