Masalah kolom-kolom data yang bervariasi (selama ini jadi momok)
#alhamdulillah bisa dihandle dengan baik oleh
#mongodb. Sampe hari ini sudah ada 6 jenis data dengan berbagai macam bentuknya bisa masuk ke database. Permasalahan berikutnya adalah mengidentifikasi setiap data ini, step awalnya menurut ane adalah mengidentifikasi kolom/field-field dulu. Data sudah masuk -> inventarisir kolom-kolomnya. Nah, menginventarisir kolom yang buanyak ini, bisa dengan cara seperti dibawah ini.
Command untuk melihat schema collection
#mongodb, menggunakan
#varietyjs. Very
#nice saudara-saudara.
root@newportalkanwil:~# mongo 10.29.254.215/data_mentah -u dataadmin -p GunungMerapi2012 --eval "var collection = 'bulk', persistResults=true, resultsDatabase='data_mentah'" /web/variety.js
MongoDB shell version: 3.0.2
connecting to: 10.29.254.215/data_mentah
Variety: A MongoDB Schema Analyzer
Version 1.5.0, released 14 May 2015
Using collection of "bulk"
Using query of { }
Using limit of 224060
Using maxDepth of 99
Using sort of { "_id" : -1 }
Using outputFormat of "ascii"
Using persistResults of true
Using resultsDatabase of "data_mentah"
Using resultsCollection of "bulkKeys"
Using resultsUser of null
Using resultsPass of null
Using logKeysContinuously of false
Using excludeSubkeys of [ ]
Using arrayEscape of "XX"
Using plugins of [ ]
replacing results collection: bulkKeys
+---------------------------------------------------------------------------------------------------------------------------------------------+
| key | types | occurrences | percents |
| ---------------------------------------------- | --------------------------------------------------- | ----------- | ---------------------- |
| JENIS_DATA | String | 224060 | 100.000000000000000000 |
| _id | ObjectId | 224060 | 100.000000000000000000 |
| cab | String | 201642 | 89.994644291707572847 |
| kpp | String | 201642 | 89.994644291707572847 |
| npwp | String | 201642 | 89.994644291707572847 |
| nama | String | 189952 | 84.777291796840131610 |
| tahun | null (71428),String (117591) | 189019 | 84.360885477104346819 |
| jum_fp | null (78461),Number (108335),String (2) | 186798 | 83.369633133981963624 |
| kd_kwl | String | 186798 | 83.369633133981963624 |
| klu | null (1931),String (184867) | 186798 | 83.369633133981963624 |
| kpp_skrg | String | 186798 | 83.369633133981963624 |
| nama_lawan | null (71428),String (115370) | 186798 | 83.369633133981963624 |
| nm_klu | null (1931),String (184867) | 186798 | 83.369633133981963624 |
| nm_kpp | String | 186798 | 83.369633133981963624 |
| nm_kwl | String | 186798 | 83.369633133981963624 |
| tot_dpp | null (78461),Number (108337) | 186798 | 83.369633133981963624 |
| tot_ppn | null (78461),Number (108337) | 186798 | 83.369633133981963624 |
| tot_ppnbm | null (78464),Number (108334) | 186798 | 83.369633133981963624 |
| NPWP | String | 20292 | 9.056502722485047840 |
| CAB | String | 20285 | 9.053378559314468887 |
| KLU | String (20023),null (245) | 20268 | 9.045791305900205970 |
| KPP | String | 20227 | 9.027492635901097628 |
| kode_kanwil | String | 14844 | 6.625011157725609223 |
| kode_kpp_adm | String | 14680 | 6.551816477729179411 |
| KPP_ADM | String | 11845 | 5.286530393644559567 |
| 1 | null | 10491 | 4.682227974649647351 |
| COUNT(NILAI) | Number | 10491 | 4.682227974649647351 |
| DETAIL | String | 10491 | 4.682227974649647351 |
| JENIS_WP | String | 10491 | 4.682227974649647351 |
| KATEGORI | String | 10491 | 4.682227974649647351 |
| KWL | String | 10491 | 4.682227974649647351 |
| NAMAWP | String | 10491 | 4.682227974649647351 |
| NAMA_ASSIGN_AR | String | 10491 | 4.682227974649647351 |
| NIP_ASSIGN_AR | String | 10491 | 4.682227974649647351 |
| NO_ANALISIS | String | 10491 | 4.682227974649647351 |
| NPWPT | String | 10491 | 4.682227974649647351 |
| OUTSTANDING (AKHIR-USUL) | String (9791),Number (700) | 10491 | 4.682227974649647351 |
| POTENSI_AKHIR | String (9791),Number (700) | 10491 | 4.682227974649647351 |
| POTENSI_USUL | null | 10491 | 4.682227974649647351 |
| SUM(NILAI) | null | 10491 | 4.682227974649647351 |
| THPJ | String | 10491 | 4.682227974649647351 |
| WK | String (10489),null (2) | 10491 | 4.682227974649647351 |
| KODE_KANWIL | String | 9777 | 4.363563331250557731 |
| NAMA_KANWIL | String | 9777 | 4.363563331250557731 |
| NM_KLU | String (9532),null (245) | 9777 | 4.363563331250557731 |
| ALAMAT_LAWAN | null (2186),String (6261) | 8447 | 3.769972328840489162 |
| JMLBPOT | null (2416),Number (6031) | 8447 | 3.769972328840489162 |
| KPP_SKRG | String | 8447 | 3.769972328840489162 |
| NAMA_KPP | String | 8447 | 3.769972328840489162 |
| NAMA_LAWAN | null (1888),String (6559) | 8447 | 3.769972328840489162 |
| NAMA_PEMOTONG | String | 8447 | 3.769972328840489162 |
| TAHUN_PAJAK | null (1888),String (6559) | 8447 | 3.769972328840489162 |
| TOT_DPP | null (2416),Number (6031) | 8447 | 3.769972328840489162 |
| TOT_PPH | null (2416),Number (6031) | 8447 | 3.769972328840489162 |
| est_hrg_kend_faktur | null (4084),Number (3074),String (27) | 7185 | 3.206730340087476705 |
| nama_wp | String | 6215 | 2.773810586450057958 |
| est_hrg_properti_sid | null (4447),Number (850) | 5297 | 2.364098902079800002 |
| dpp | NumberLong (2221),Number (2548),String (4) | 4773 | 2.130232973310720368 |
| nama_pembeli | String | 4773 | 2.130232973310720368 |
| nama_penjual | String | 4773 | 2.130232973310720368 |
| ppn | Number | 4773 | 2.130232973310720368 |
| nilai_aset_njop_pbb | null (4594),String (36),Number (69) | 4699 | 2.097206105507453344 |
| est_hrg_properti_faktur | null (2847),Number (1786) | 4633 | 2.067749709899134203 |
| est_njkb_kend_samsat | null (4504),Number (118),String (11) | 4633 | 2.067749709899134203 |
| jml_kapal_ikan | null (4604),String (27),Number (2) | 4633 | 2.067749709899134203 |
| nilai_obligasi | null | 4633 | 2.067749709899134203 |
| nilai_selisih_piutang_sahamVSmodal_utang_pengh | null | 4633 | 2.067749709899134203 |
| total_nilai_saham_ahu | NumberLong (733),null (3823),String (3),Number (74) | 4633 | 2.067749709899134203 |
| total_saham_ksei | null (3385),Number (1216),String (32) | 4633 | 2.067749709899134203 |
| wp_tltd | String (2738),null (1010) | 3748 | 1.672766223333035818 |
| faktur_pengganti | null (2545),String (7) | 2552 | 1.138980630188342502 |
| masa_pajak | String | 2552 | 1.138980630188342502 |
| no_seri_faktur | String | 2552 | 1.138980630188342502 |
| npwp_penjual | String | 2552 | 1.138980630188342502 |
| pembetulan | String | 2552 | 1.138980630188342502 |
| ppnbm | Number | 2552 | 1.138980630188342502 |
| tahun_pajak | String | 2552 | 1.138980630188342502 |
| tanggal_faktur | String | 2552 | 1.138980630188342502 |
| alamat_wp | String | 2467 | 1.101044363117022140 |
| bulan_pajak | String | 2401 | 1.071587967508702999 |
| cab_pemotong | String | 2401 | 1.071587967508702999 |
| jenis_transaksi | String | 2401 | 1.071587967508702999 |
| jml_lembar_saham_ksei | Number (2363),String (38) | 2401 | 1.071587967508702999 |
| kpp_pemotong | String | 2401 | 1.071587967508702999 |
| nama_pemotong | String | 2401 | 1.071587967508702999 |
| npwp_pemotong | String | 2401 | 1.071587967508702999 |
| thn_2012 | null (2361),Number (39),String (1) | 2401 | 1.071587967508702999 |
| thn_2013 | null (2392),Number (9) | 2401 | 1.071587967508702999 |
| thn_2014 | null (1939),Number (459),String (3) | 2401 | 1.071587967508702999 |
| thn_2015 | Number (1856),null (511),String (34) | 2401 | 1.071587967508702999 |
| alamat | String | 2269 | 1.012675176292064716 |
| est_hrg_properti_FP | Number | 2221 | 0.991252343122377977 |
| jumlah_faktur | Number | 2221 | 0.991252343122377977 |
| identitas_pengirim | String | 2105 | 0.939480496295635126 |
| jenis_data | String | 2105 | 0.939480496295635126 |
| jenis_dokumen | String | 2105 | 0.939480496295635126 |
| keterangan_sumber | String (2094),null (11) | 2105 | 0.939480496295635126 |
| kode_jns_dokumen | String | 2105 | 0.939480496295635126 |
| kode_sumber | String | 2105 | 0.939480496295635126 |
| kota_alamat | String (1652),null (453) | 2105 | 0.939480496295635126 |
| merk | String | 2105 | 0.939480496295635126 |
| nama_kpp_adm | String | 2105 | 0.939480496295635126 |
| nama_pengirim | String | 2105 | 0.939480496295635126 |
| nama_sumber | String | 2105 | 0.939480496295635126 |
| nilai_data | Number | 2105 | 0.939480496295635126 |
| nomor_alket | String | 2105 | 0.939480496295635126 |
| nomor_dokumen | String | 2105 | 0.939480496295635126 |
| tahun_data | String | 2105 | 0.939480496295635126 |
| KATEGORI_GUNGGUNG | null (473),String (857) | 1330 | 0.593591002410068680 |
| KD_KPP_ADM | String | 1330 | 0.593591002410068680 |
| KLU_2_DGT | String (1328),null (2) | 1330 | 0.593591002410068680 |
| NAMA | String | 1330 | 0.593591002410068680 |
| TAHUN | null (473),String (857) | 1330 | 0.593591002410068680 |
| TOT_DPP_GUNGGUNG | null (473),Number (857) | 1330 | 0.593591002410068680 |
| TOT_PENYERAHAN | null (473),Number (857) | 1330 | 0.593591002410068680 |
| 2010 | null (1187),String (85) | 1272 | 0.567705078996697310 |
| 2011 | null (1171),String (101) | 1272 | 0.567705078996697310 |
| 2012 | null (1160),String (112) | 1272 | 0.567705078996697310 |
| 2013 | null (1153),String (119) | 1272 | 0.567705078996697310 |
| 2014 | String (855),null (417) | 1272 | 0.567705078996697310 |
| Cab | String | 1272 | 0.567705078996697310 |
| KPP_adm | String | 1272 | 0.567705078996697310 |
| Kode_Kanwil | String | 1272 | 0.567705078996697310 |
| NAMA PEMEGANG SAHAM | String | 1272 | 0.567705078996697310 |
| NAMA PERUSAHAAN | String | 1272 | 0.567705078996697310 |
| NO AKTA | String | 1272 | 0.567705078996697310 |
| NOTARIS | String | 1272 | 0.567705078996697310 |
| NPWP1 | String | 1272 | 0.567705078996697310 |
| Nilai Saham | String | 1272 | 0.567705078996697310 |
| TANGGAL AKTA | String | 1272 | 0.567705078996697310 |
| URUT | Number | 1272 | 0.567705078996697310 |
| npwp_all | String | 885 | 0.394983486566098385 |
| sts_jeniswp | String | 885 | 0.394983486566098385 |
| 2015 | String (841),null (13) | 854 | 0.381147906810675730 |
| 2016 | String (840),null (14) | 854 | 0.381147906810675730 |
| Selisih | String | 854 | 0.381147906810675730 |
| WP | String | 854 | 0.381147906810675730 |
| alamat_agunan | String | 664 | 0.296349192180665910 |
| bukti_milik | String | 664 | 0.296349192180665910 |
| jenis_agunan | String | 664 | 0.296349192180665910 |
| nama_debitur | String | 664 | 0.296349192180665910 |
| pemilik_agunan | String | 664 | 0.296349192180665910 |
| bahan_bakar | String | 164 | 0.073194679996429535 |
| bbnpk | Number | 164 | 0.073194679996429535 |
| cc | Number | 164 | 0.073194679996429535 |
| est_njkb | Number | 164 | 0.073194679996429535 |
| kabkot | String | 164 | 0.073194679996429535 |
| kode_kpp | String | 164 | 0.073194679996429535 |
| merek | String | 164 | 0.073194679996429535 |
| nama_mfwp | String | 164 | 0.073194679996429535 |
| nik | String | 164 | 0.073194679996429535 |
| nopol | String | 164 | 0.073194679996429535 |
| pkbpk | Number | 164 | 0.073194679996429535 |
| provinsi | String | 164 | 0.073194679996429535 |
| tbt | Number | 164 | 0.073194679996429535 |
| tgl_bayar | String | 164 | 0.073194679996429535 |
| tipe_kendaraan | String | 164 | 0.073194679996429535 |
| alamat_objek_pajak | String | 66 | 0.029456395608319200 |
| kanwil_domisili_sppt | String | 66 | 0.029456395608319200 |
| kpp_domisili_sppt | String | 66 | 0.029456395608319200 |
| luas_bangunan_m2 | Number | 66 | 0.029456395608319200 |
| luas_bumi_m2 | Number | 66 | 0.029456395608319200 |
| luas_sit_tanaman_rp | Number | 66 | 0.029456395608319200 |
| luas_tanaman_m2 | Number | 66 | 0.029456395608319200 |
| nama_kanwil_lokasi | String | 66 | 0.029456395608319200 |
| nama_kpp_lokasi | String | 66 | 0.029456395608319200 |
| njop_bangunan_rp | NumberLong | 66 | 0.029456395608319200 |
| njop_bumi_rp | Number | 66 | 0.029456395608319200 |
| nop_sppt_pbb_2014 | String | 66 | 0.029456395608319200 |
| alamat_pemilik | String | 38 | 0.016959742926001962 |
| gt | Number | 38 | 0.016959742926001962 |
| nama_kapal | String | 38 | 0.016959742926001962 |
| nama_pemilik | String | 38 | 0.016959742926001962 |
| KDKWL | String | 24 | 0.010711416584843345 |
| NAMA_WP | String | 24 | 0.010711416584843345 |
| NMKPP | String | 24 | 0.010711416584843345 |
| NMKWL | String | 24 | 0.010711416584843345 |
| TOT_DPP_NPWP_000 | Number (17),String (7) | 24 | 0.010711416584843345 |
+---------------------------------------------------------------------------------------------------------------------------------------------+