Update spaCy pipeline

README.md

@@ -13,13 +13,13 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9723641431
+      value: 0.9709657059
     - name: NER Recall
       type: recall
-      value: 0.9716871664
+      value: 0.9711700337
     - name: NER F Score
       type: f_score
-      value: 0.9720255369
+      value: 0.971067859
 ---
 | Feature | Description |
 | --- | --- |
@@ -49,8 +49,8 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 97.20 |
-| `ENTS_P` | 97.24 |
-| `ENTS_R` | 97.17 |
-| `TOK2VEC_LOSS` | 61026.64 |
-| `NER_LOSS` | 140932.96 |
+| `ENTS_F` | 97.11 |
+| `ENTS_P` | 97.10 |
+| `ENTS_R` | 97.12 |
+| `TOK2VEC_LOSS` | 94293.73 |
+| `NER_LOSS` | 130969.24 |

en_pipeline-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68122a6417fc04c976c920a9291d2df00a393881dad3a9e7bc5e2085ea824c
-size 606870367
+oid sha256:5702dca4c94bfb35ed6876bc597aa82dcaf73ba37c332aa7cd539a7ca358bad0
+size 606888018

meta.json

@@ -49,34 +49,34 @@
 
   ],
   "performance":{
-    "ents_f":0.9720255369,
-    "ents_p":0.9723641431,
-    "ents_r":0.9716871664,
+    "ents_f":0.971067859,
+    "ents_p":0.9709657059,
+    "ents_r":0.9711700337,
     "ents_per_type":{
       "ORIGIN":{
-        "p":0.9847715736,
-        "r":0.9810366625,
-        "f":0.98290057
+        "p":0.9741784038,
+        "r":0.9707602339,
+        "f":0.9724663152
       },
       "DESTINATION":{
-        "p":0.9762419006,
-        "r":0.9762419006,
-        "f":0.9762419006
+        "p":0.969488189,
+        "r":0.9723593287,
+        "f":0.9709216363
       },
       "COMMODITY":{
-        "p":0.9379652605,
-        "r":0.9356435644,
-        "f":0.936802974
+        "p":0.9516483516,
+        "r":0.9252136752,
+        "f":0.9382448537
       },
       "QUANTITY":{
-        "p":0.9809322034,
-        "r":0.9809322034,
-        "f":0.9809322034
+        "p":0.9730250482,
+        "r":0.9844054581,
+        "f":0.9786821705
       },
       "GROSSWEIGHT":{
-        "p":0.9896373057,
-        "r":0.9922077922,
-        "f":0.990920882
+        "p":0.9931034483,
+        "r":0.9953917051,
+        "f":0.9942462601
       },
       "SHIPMENTDATE":{
         "p":1.0,
@@ -84,19 +84,19 @@
         "f":1.0
       },
       "DIMENSIONS":{
-        "p":0.9554030875,
-        "r":0.9586919105,
-        "f":0.9570446735
+        "p":0.9693430657,
+        "r":0.9693430657,
+        "f":0.9693430657
       },
       "VOLUMEWEIGHT":{
-        "p":0.9851485149,
-        "r":0.995,
-        "f":0.9900497512
+        "p":0.9872881356,
+        "r":0.9957264957,
+        "f":0.9914893617
       },
       "WEIGHT":{
-        "p":0.98125,
-        "r":0.9602446483,
-        "f":0.970633694
+        "p":0.9665653495,
+        "r":0.9724770642,
+        "f":0.9695121951
       },
       "HSNCODE":{
         "p":1.0,
@@ -109,9 +109,9 @@
         "f":1.0
       },
       "MODE":{
-        "p":0.9255319149,
-        "r":0.90625,
-        "f":0.9157894737
+        "p":0.9361702128,
+        "r":0.9166666667,
+        "f":0.9263157895
       },
       "TEMPERATURE":{
         "p":1.0,
@@ -129,8 +129,8 @@
         "f":1.0
       }
     },
-    "tok2vec_loss":610.266410009,
-    "ner_loss":1409.3295778695
+    "tok2vec_loss":942.9372959798,
+    "ner_loss":1309.692444711
   },
   "requirements":[
 

ner/moves

@@ -1 +1 @@
-��moves��{"0":{},"1":{"DIMENSIONS":4318,"DESTINATION":4054,"ORIGIN":3507,"COMMODITY":1871,"QUANTITY":1818,"GROSSWEIGHT":1722,"WEIGHT":1240,"VOLUMEWEIGHT":900,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"2":{"DIMENSIONS":4318,"DESTINATION":4054,"ORIGIN":3507,"COMMODITY":1871,"QUANTITY":1818,"GROSSWEIGHT":1722,"WEIGHT":1240,"VOLUMEWEIGHT":900,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"3":{"DIMENSIONS":4318,"DESTINATION":4054,"ORIGIN":3507,"COMMODITY":1871,"QUANTITY":1818,"GROSSWEIGHT":1722,"WEIGHT":1240,"VOLUMEWEIGHT":900,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"4":{"DIMENSIONS":4318,"DESTINATION":4054,"ORIGIN":3507,"COMMODITY":1871,"QUANTITY":1818,"GROSSWEIGHT":1722,"WEIGHT":1240,"VOLUMEWEIGHT":900,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18,"":1},"5":{"":1}}�cfg��neg_key�
+��moves��{"0":{},"1":{"DIMENSIONS":4931,"DESTINATION":4278,"ORIGIN":3594,"COMMODITY":2172,"QUANTITY":1985,"GROSSWEIGHT":1901,"WEIGHT":1240,"VOLUMEWEIGHT":1070,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"2":{"DIMENSIONS":4931,"DESTINATION":4278,"ORIGIN":3594,"COMMODITY":2172,"QUANTITY":1985,"GROSSWEIGHT":1901,"WEIGHT":1240,"VOLUMEWEIGHT":1070,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"3":{"DIMENSIONS":4931,"DESTINATION":4278,"ORIGIN":3594,"COMMODITY":2172,"QUANTITY":1985,"GROSSWEIGHT":1901,"WEIGHT":1240,"VOLUMEWEIGHT":1070,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18},"4":{"DIMENSIONS":4931,"DESTINATION":4278,"ORIGIN":3594,"COMMODITY":2172,"QUANTITY":1985,"GROSSWEIGHT":1901,"WEIGHT":1240,"VOLUMEWEIGHT":1070,"MODE":206,"TEMPERATURE":173,"HSNCODE":171,"INCOTERMS":122,"INVOICE":59,"SHIPMENTDATE":29,"AWB":18,"":1},"5":{"":1}}�cfg��neg_key�

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb216668d436b3068bd4ba72974c12c5ab0c5064c40b5d5689ca11d6ed738fa
+oid sha256:3123e0eadfda47f7561667dee743d681acb6ef26c4c60938d07c9ffe363d8deb
 size 34434008

vocab/strings.json

@@ -731,6 +731,7 @@
   "(>_<)",
   "(AM",
   "(A\\",
+  "(HS",
   "(I",
   "(II",
   "(ML",
@@ -753,6 +754,7 @@
   "(es",
   "(f\\",
   "(hp",
+  "(hs",
   "(i",
   "(mm",
   "(more",
@@ -792,6 +794,10 @@
   ")//",
   ")/2",
   ")/\u00af",
+  ")14",
+  ")16",
+  ")17",
+  ")18",
   ")20",
   ")25",
   ")27",
@@ -1790,6 +1796,7 @@
   "-A.",
   "-AII",
   "-ALL",
+  "-AMD",
   "-AND",
   "-ARE",
   "-ATPase",
@@ -1898,6 +1905,8 @@
   "-B",
   "-B.",
   "-BETTY",
+  "-BLR",
+  "-BOM",
   "-BOTH",
   "-BP",
   "-BUT",
@@ -1984,6 +1993,7 @@
   "-C'mon",
   "-C.",
   "-C.J.",
+  "-CCU",
   "-COME",
   "-Call",
   "-Calm",
@@ -2075,6 +2085,7 @@
   "-Cute",
   "-D",
   "-D.",
+  "-DEL",
   "-DO",
   "-DOCTOR",
   "-Dad",
@@ -2303,6 +2314,7 @@
   "-HEY",
   "-HI",
   "-HOW",
+  "-HYD",
   "-Ha",
   "-Had",
   "-Hail",
@@ -3380,6 +3392,7 @@
   "-am",
   "-amanda",
   "-amazing",
+  "-amd",
   "-amen",
   "-america",
   "-american",
@@ -3482,9 +3495,11 @@
   "-blood",
   "-bloody",
   "-blow",
+  "-blr",
   "-blue",
   "-bob",
   "-bobby",
+  "-bom",
   "-bon",
   "-bonjour",
   "-boo",
@@ -3546,6 +3561,7 @@
   "-catch",
   "-catherine",
   "-cause",
+  "-ccu",
   "-central",
   "-certainly",
   "-champagne",
@@ -3662,6 +3678,7 @@
   "-death",
   "-deep",
   "-definitely",
+  "-del",
   "-delicious",
   "-dennis",
   "-dependent",
@@ -3970,6 +3987,7 @@
   "-human",
   "-hurry",
   "-hush",
+  "-hyd",
   "-i",
   "-i'd",
   "-i'ii",
@@ -8326,6 +8344,7 @@
   "1)-(5000",
   "1)-dimensional",
   "1)/2",
+  "1)9",
   "1):-",
   "1)A",
   "1)Department",
@@ -10401,8 +10420,10 @@
   "1018",
   "1019",
   "101A",
+  "101Kg//",
   "101a",
   "101domain",
+  "101kg//",
   "101s",
   "101st",
   "102",
@@ -11619,6 +11640,7 @@
   "11E",
   "11F",
   "11H00",
+  "11Kg",
   "11PM",
   "11S",
   "11TH",
@@ -11646,6 +11668,7 @@
   "11h00",
   "11i",
   "11k",
+  "11kg",
   "11lbs",
   "11million",
   "11n",
@@ -12472,6 +12495,8 @@
   "13",
   "13'x11'x11",
   "13(1",
+  "13(1)16",
+  "13(1)9",
   "13(2",
   "13(3",
   "13(6",
@@ -14145,6 +14170,7 @@
   "16",
   "16%-owned",
   "16(1",
+  "16(1)17",
   "16(2",
   "16(3",
   "16(4",
@@ -15154,6 +15180,7 @@
   "17th\u201319th",
   "17u",
   "17w",
+  "17x13x15",
   "17\u00bd",
   "17\u03b1",
   "17\u03b2",
@@ -16785,6 +16812,7 @@
   "18v",
   "18w",
   "18x",
+  "18x12x13",
   "18x18",
   "18x24",
   "18yo",
@@ -19999,6 +20027,7 @@
   "19th\u201320th",
   "19w",
   "19x",
+  "19x14x12",
   "19xx",
   "19yo",
   "19\u0412",
@@ -23245,6 +23274,7 @@
   "20x",
   "20x10",
   "20x10x30",
+  "20x15x14",
   "20x20",
   "20x20px",
   "20x30",
@@ -28573,6 +28603,7 @@
   "3401",
   "340111",
   "3402",
+  "34029059",
   "3403",
   "3404",
   "3405",
@@ -30213,6 +30244,7 @@
   "4'x8",
   "4(+",
   "4(1",
+  "4(1)18",
   "4(2",
   "4(3",
   "4(4",
@@ -31037,10 +31069,12 @@
   "41:10",
   "41A",
   "41C",
+  "41Kg",
   "41Kgs",
   "41X",
   "41a",
   "41c",
+  "41kg",
   "41kgs",
   "41st",
   "41x",
@@ -31647,6 +31681,8 @@
   "4554",
   "4555",
   "4558",
+  "455Kg//",
+  "455kg//",
   "455th",
   "456",
   "456,000",
@@ -31657,6 +31693,8 @@
   "4567",
   "4568",
   "4569",
+  "456Kg//",
+  "456kg//",
   "456th",
   "457",
   "457(b",
@@ -32869,6 +32907,7 @@
   "5.4bn",
   "5.4l",
   "5.5",
+  "5.5(1)18",
   "5.5.1",
   "5.5/10",
   "5.50",
@@ -34727,6 +34766,7 @@
   "6.4L",
   "6.4l",
   "6.5",
+  "6.5(1)16",
   "6.5.1",
   "6.5/10",
   "6.50",
@@ -35422,6 +35462,8 @@
   "6440",
   "6441",
   "6444",
+  "644Kg//",
+  "644kg//",
   "644th",
   "645",
   "645,000",
@@ -35836,6 +35878,19 @@
   "691",
   "691.09",
   "6910",
+  "6916900",
+  "6916901",
+  "6916902",
+  "6916903",
+  "6916905",
+  "6916906",
+  "6916907",
+  "6916908",
+  "6916909",
+  "6916910",
+  "6916911",
+  "6916912",
+  "6916913",
   "692",
   "6920",
   "6922",
@@ -38519,6 +38574,8 @@
   "87725",
   "8777",
   "8778",
+  "877Kg//",
+  "877kg//",
   "878",
   "8787",
   "8787902546",
@@ -38957,6 +39014,7 @@
   "9'x9'x9",
   "9(1",
   "9(2",
+  "9(2)14",
   "9(3",
   "9(4",
   "9(a",
@@ -39084,6 +39142,8 @@
   "9.58",
   "9.59",
   "9.5:1",
+  "9.5Kg",
+  "9.5kg",
   "9.6",
   "9.60",
   "9.61",
@@ -39869,6 +39929,18 @@
   "9875708805",
   "9876539000",
   "9876543210",
+  "9876543211",
+  "9876543212",
+  "9876543213",
+  "9876543215",
+  "9876543216",
+  "9876543217",
+  "9876543218",
+  "9876543219",
+  "9876543220",
+  "9876543221",
+  "9876543222",
+  "9876543223",
   "9877",
   "988",
   "98807",
@@ -87782,6 +87854,7 @@
   "CIPE",
   "CIPFA",
   "CIPHER",
+  "CIPL",
   "CIPM",
   "CIPN",
   "CIPO",
@@ -112794,6 +112867,7 @@
   "DMCs",
   "DMD",
   "DME",
+  "DME//",
   "DME//85Kg//",
   "DMEM",
   "DMF",
@@ -134271,6 +134345,7 @@
   "EquipNet",
   "Equipe",
   "Equipment",
+  "Equipment(HS",
   "EquipmentMine",
   "EquipmentTrader.com",
   "Equipments",
@@ -139241,6 +139316,7 @@
   "FR3",
   "FR4",
   "FRA",
+  "FRA//",
   "FRAC",
   "FRACP",
   "FRACTION",
@@ -207883,6 +207959,7 @@
   "LAWYER",
   "LAWYERS",
   "LAX",
+  "LAX//",
   "LAY",
   "LAYER",
   "LAYERS",
@@ -208327,6 +208404,7 @@
   "LHON",
   "LHP",
   "LHR",
+  "LHR//",
   "LHRH",
   "LHS",
   "LHSAA",
@@ -258239,6 +258317,7 @@
   "ORCL",
   "ORCS",
   "ORD",
+  "ORD//",
   "ORDER",
   "ORDERED",
   "ORDERING",
@@ -286763,6 +286842,7 @@
   "R.V.",
   "R.W.",
   "R.W.D.",
+  "R//",
   "R/3",
   "R0",
   "R00",
@@ -302397,6 +302477,7 @@
   "SCIENCE",
   "SCIENCES",
   "SCIENTIFIC",
+  "SCIENTIFIC//",
   "SCIENTIST",
   "SCIENTISTS",
   "SCIF",
@@ -303502,6 +303583,7 @@
   "SIMs",
   "SIM\u00d3N",
   "SIN",
+  "SIN//",
   "SINA",
   "SINATRA",
   "SINBAD",
@@ -364147,6 +364229,7 @@
   "W.s",
   "W/",
   "W/(m\u00b7K",
+  "W//",
   "W0",
   "W1",
   "W10",
@@ -364437,6 +364520,7 @@
   "WAVING",
   "WAVY",
   "WAW",
+  "WAW//",
   "WAX",
   "WAY",
   "WAY--",
@@ -446879,6 +446963,7 @@
   "ciphertext",
   "ciphertexts",
   "ciphertrace",
+  "cipl",
   "cipla",
   "cipm",
   "cipn",
@@ -462774,6 +462859,7 @@
   "d(X",
   "d(d",
   "d(d)(x",
+  "d(d)dd",
   "d(s",
   "d(x",
   "d)",
@@ -462880,6 +462966,7 @@
   "d.c.l.",
   "d.c.s.",
   "d.d",
+  "d.d(d)dd",
   "d.d-",
   "d.d-xxxx",
   "d.d.",
@@ -466095,6 +466182,7 @@
   "dd'xxxx",
   "dd(XX)X",
   "dd(d",
+  "dd(d)d",
   "dd(d)dd",
   "dd(dd",
   "dd(x",
@@ -475720,6 +475808,7 @@
   "dmcs",
   "dmd",
   "dme",
+  "dme//",
   "dme//85kg//",
   "dmedical",
   "dmem",
@@ -490122,6 +490211,7 @@
   "equiped",
   "equipement",
   "equipment",
+  "equipment(hs",
   "equipment-",
   "equipment;Ball",
   "equipment;ball",
@@ -504793,6 +504883,7 @@
   "fr3",
   "fr4",
   "fra",
+  "fra//",
   "fraas",
   "fraassen",
   "frabill",
@@ -576147,6 +576238,7 @@
   "lawyerly",
   "lawyers",
   "lax",
+  "lax//",
   "laxa",
   "laxalt",
   "laxative",
@@ -579268,6 +579360,7 @@
   "lhotse",
   "lhp",
   "lhr",
+  "lhr//",
   "lhrh",
   "lhs",
   "lhsaa",
@@ -632512,6 +632605,7 @@
   "orcutt",
   "orczy",
   "ord",
+  "ord//",
   "orda",
   "ordabasy",
   "ordain",
@@ -687774,6 +687868,7 @@
   "scientiarum",
   "scientic",
   "scientific",
+  "scientific//",
   "scientifically",
   "scientificamerican.com",
   "scientifico",
@@ -698177,6 +698272,7 @@
   "sim\u00f3n",
   "sim\u00f5es",
   "sin",
+  "sin//",
   "sina",
   "sina.com",
   "sinablog",
@@ -751657,6 +751753,7 @@
   "w.|",
   "w/",
   "w/(m\u00b7k",
+  "w//",
   "w/2",
   "w/3",
   "w/4",
@@ -754088,6 +754185,7 @@
   "wavves",
   "wavy",
   "waw",
+  "waw//",
   "wawa",
   "wawanesa",
   "wawarsing",