Update spaCy pipeline

README.md

@@ -13,9 +13,9 @@ model-index:
 | **Name** | `da_spacy_sentiment` |
 | **Version** | `0.0.0` |
 | **spaCy** | `>=3.5.1,<3.6.0` |
-| **Default Pipeline** | `textcat` |
-| **Components** | `textcat` |
-| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Default Pipeline** | `tok2vec`, `textcat` |
+| **Components** | `tok2vec`, `textcat` |
+| **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
 | **Sources** | n/a |
 | **License** | n/a |
 | **Author** | [n/a]() |
@@ -36,12 +36,13 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `CATS_SCORE` | 46.44 |
-| `CATS_MICRO_P` | 73.02 |
-| `CATS_MICRO_R` | 73.02 |
-| `CATS_MICRO_F` | 73.02 |
-| `CATS_MACRO_P` | 51.66 |
-| `CATS_MACRO_R` | 44.32 |
-| `CATS_MACRO_F` | 46.44 |
-| `CATS_MACRO_AUC` | 61.67 |
-| `TEXTCAT_LOSS` | 765.85 |
+| `CATS_SCORE` | 85.67 |
+| `CATS_MICRO_P` | 84.44 |
+| `CATS_MICRO_R` | 84.44 |
+| `CATS_MICRO_F` | 84.44 |
+| `CATS_MACRO_P` | 84.80 |
+| `CATS_MACRO_R` | 86.96 |
+| `CATS_MACRO_F` | 85.67 |
+| `CATS_MACRO_AUC` | 92.09 |
+| `TOK2VEC_LOSS` | 5772634.97 |
+| `TEXTCAT_LOSS` | 577.15 |

da_spacy_sentiment-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af39770e26698563f9dd3eef71e89ee1ed1f172a63c89fd8336c227d5df8885a
-size 62187602
+oid sha256:9d513a091f1ee53c04bf0a70a38cfedaea743b22380188ec83ac08cfd1ee3347
+size 62239704

meta.json

@@ -37,34 +37,34 @@
 
   ],
   "performance":{
-    "cats_score":0.421474359,
+    "cats_score":0.8567000249,
     "cats_score_desc":"macro F",
-    "cats_micro_p":0.7312252964,
-    "cats_micro_r":0.7312252964,
-    "cats_micro_f":0.7312252964,
-    "cats_macro_p":0.4364809645,
-    "cats_macro_r":0.4126512651,
-    "cats_macro_f":0.421474359,
-    "cats_macro_auc":0.6258794518,
+    "cats_micro_p":0.8443804035,
+    "cats_micro_r":0.8443804035,
+    "cats_micro_f":0.8443804035,
+    "cats_macro_p":0.848044611,
+    "cats_macro_r":0.8696153576,
+    "cats_macro_f":0.8567000249,
+    "cats_macro_auc":0.9208626102,
     "cats_f_per_type":{
       "neutral":{
-        "p":0.8224299065,
-        "r":0.8712871287,
-        "f":0.8461538462
+        "p":0.8903225806,
+        "r":0.7976878613,
+        "f":0.8414634146
       },
       "negative":{
-        "p":0.2727272727,
-        "r":0.2,
-        "f":0.2307692308
+        "p":0.9210526316,
+        "r":0.985915493,
+        "f":0.9523809524
       },
       "positive":{
-        "p":0.2142857143,
-        "r":0.1666666667,
-        "f":0.1875
+        "p":0.7327586207,
+        "r":0.8252427184,
+        "f":0.7762557078
       }
     },
-    "tok2vec_loss":21328.4948898681,
-    "textcat_loss":8.565279969
+    "tok2vec_loss":57726.349722601,
+    "textcat_loss":5.7714850157
   },
   "requirements":[
 

textcat/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd8a9ba94e6b324126d822c4280cc5a39c3147f86e4e80e1d0ef503d6f7ad8d
+oid sha256:5cfc0361c88c3570f37b7c2ed8470e0df6790a7327c9ec4f89037782340b5b44
 size 3944012

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf42c1667839c262f3d28abdfd979b6504df1c6b089da76fb8a71a7522a0fb40
+oid sha256:6c69a93bb22dbd24fd7932c8c4ba4f1a6a64b9625807348fea3b4cce649ac174
 size 34434008

vocab/strings.json

@@ -157,7 +157,6 @@
   "(det",
   "(e",
   "(jeg",
-  "(jf",
   "(l\u00e6s",
   "(o:",
   "(og",
@@ -7421,7 +7420,6 @@
   "16c",
   "16d",
   "16de",
-  "16etage(75",
   "16i",
   "16kw",
   "16m3",
@@ -24361,7 +24359,6 @@
   "Agerschou",
   "Agersende",
   "Agerskov",
-  "Agerskov)v",
   "Agersnap",
   "Agerspris",
   "Agersted",
@@ -42028,7 +42025,6 @@
   "Brede",
   "Bredebo",
   "Bredebro",
-  "Bredebro)Pyloner",
   "Bredefjord",
   "Bredegaard",
   "Bredegaards",
@@ -45735,7 +45731,6 @@
   "B\u00fcgel",
   "B\u00fchler",
   "B\u00fchlmann",
-  "B\u00fchlmann\u00b4s",
   "B\u00fchrmann",
   "B\u00fclent",
   "B\u00fclo",
@@ -60989,14 +60984,12 @@
   "D\u00fcrrfeld",
   "D\u00fcsseldorf",
   "D\u00fcsseldorfs",
-  "D\u2019Angleterre",
   "E",
   "E%",
   "E&H",
   "E&P",
   "E&S",
   "E&Y",
-  "E&Y\u00b4s",
   "E'S",
   "E's",
   "E+",
@@ -68115,7 +68108,6 @@
   "Ezreal",
   "Ezzence",
   "E|R",
-  "E\u00b4har",
   "E\u00c5R",
   "E\u00d8",
   "E\u00d8F",
@@ -110114,7 +110106,6 @@
   "Klaudia",
   "Klaus",
   "Klaus'",
-  "Klaus(teknisk",
   "Klaus-Peter",
   "Klausdalsbrovej",
   "Klausen",
@@ -124808,7 +124799,6 @@
   "L\u00f8gtved",
   "L\u00f8gum",
   "L\u00f8gumg\u00e5rde",
-  "L\u00f8gumg\u00e5rde)Ved",
   "L\u00f8gumkloster",
   "L\u00f8gumklostervej",
   "L\u00f8hde",
@@ -151423,7 +151413,6 @@
   "Piazzale",
   "Piazzetta",
   "Piazzolla",
-  "Pia\u00b4s",
   "Pibe",
   "Pibeand",
   "Piben",
@@ -161186,7 +161175,6 @@
   "Resterne",
   "Rester\u00f6ds",
   "Restewolf",
-  "Restewolf\u00b4en",
   "Restfugtigheden",
   "Restgruppen",
   "Restg\u00e6ld",
@@ -196690,7 +196678,6 @@
   "T\u00f8ndemageren",
   "T\u00f8nden",
   "T\u00f8nder",
-  "T\u00f8nder)v",
   "T\u00f8nder-sagen",
   "T\u00f8ndergade",
   "T\u00f8nderhus",
@@ -210504,7 +210491,6 @@
   "X&x",
   "X&xxx;X",
   "X&xxx;X.",
-  "X&xxx;X\u00b4x",
   "X&xxxx;Xxxxx",
   "X&xxxx;x",
   "X&xxxx;xx",
@@ -211790,11 +211776,7 @@
   "Xxxxx'xxx",
   "Xxxxx'xxxx",
   "Xxxxx(d",
-  "Xxxxx(xxxx",
-  "Xxxxx)Xxx",
-  "Xxxxx)Xxxxx",
   "Xxxxx)[/xxxx",
-  "Xxxxx)x",
   "Xxxxx)\u200e",
   "Xxxxx*xx",
   "Xxxxx+",
@@ -212030,8 +212012,6 @@
   "Xxxxxdxxxx-",
   "Xxxxx||d||d",
   "Xxxxx\u00adxxxx",
-  "Xxxxx\u00b4x",
-  "Xxxxx\u00b4xx",
   "Xxxxx\u030axxx",
   "Xxxxx\u203aXxxx",
   "Xxxx\u00adxx",
@@ -212048,7 +212028,6 @@
   "Xxx\u00adxxx\u00adx\u00adxx\u00adx\u00adxxx",
   "Xxx\u00adxx\u00adxxx",
   "Xxx\u00adxx\u00adxxxx",
-  "Xxx\u00b4x",
   "Xxx\u2019",
   "Xxx\u203aXxxxx",
   "Xxx\u203aXxxxx\u203aXxxxx",
@@ -212076,7 +212055,6 @@
   "X\u00a5xx",
   "X\u00a5xxx",
   "X\u00a5xxxx",
-  "X\u00b4xxx",
   "X\u00b8xxx",
   "X\u00b8xxxx",
   "X\u00bd",
@@ -212084,7 +212062,6 @@
   "X\u030axxxx",
   "X\u2014XX",
   "X\u2014XXX",
-  "X\u2019Xxxxx",
   "X\u2019xx",
   "X\ufeff",
   "Y",
@@ -212805,7 +212782,6 @@
   "Yvon",
   "Yvonne",
   "Yvonnes",
-  "Y\u00b4s",
   "Y\u00fcksel",
   "Z",
   "Z-",
@@ -219742,7 +219718,6 @@
   "agerschou",
   "agersende",
   "agerskov",
-  "agerskov)v",
   "agersnap",
   "agersnegle",
   "agerspris",
@@ -234063,7 +234038,6 @@
   "a{display",
   "a|s",
   "a\u00adme\u00adri\u00adkan\u00adske",
-  "a\u00b4s",
   "a\u00dfe",
   "a\u00e5",
   "a\u00e7a",
@@ -253445,7 +253419,6 @@
   "brandspr\u00f8jte",
   "brandspr\u00f8jter",
   "brandstation",
-  "brandstation)v",
   "brandstationen",
   "brandstationer",
   "brandstationerne",
@@ -253796,7 +253769,6 @@
   "brede",
   "bredebo",
   "bredebro",
-  "bredebro)pyloner",
   "bredefjord",
   "bredegaard",
   "bredegaards",
@@ -259187,8 +259159,6 @@
   "byggr\u00e6s",
   "byggr\u00f8d",
   "bygherre",
-  "bygherre(Christian",
-  "bygherre(christian",
   "bygherre-",
   "bygherreforeningen",
   "bygherreforeningens",
@@ -261676,7 +261646,6 @@
   "b\u00fcgel",
   "b\u00fchler",
   "b\u00fchlmann",
-  "b\u00fchlmann\u00b4s",
   "b\u00fchrmann",
   "b\u00fclent",
   "b\u00fclo",
@@ -271521,7 +271490,6 @@
   "d.13",
   "d.14",
   "d.15",
-  "d.15/9",
   "d.15/9-14",
   "d.16",
   "d.17",
@@ -271533,12 +271501,10 @@
   "d.21",
   "d.22",
   "d.23",
-  "d.23/9",
   "d.23/9-14",
   "d.24",
   "d.25",
   "d.26",
-  "d.26/11",
   "d.26/11-14",
   "d.26/8",
   "d.27",
@@ -274907,7 +274873,6 @@
   "ddxxx.ddddxx",
   "ddxxx.ddddxx.ddxxx.ddddxx",
   "ddxxxx",
-  "ddxxxx(dd",
   "ddxxxx.xx",
   "ddy",
   "dd\u00b4xx",
@@ -286546,7 +286511,6 @@
   "d\u2013d",
   "d\u2013dd",
   "d\u2014d",
-  "d\u2019angleterre",
   "d\u2019x",
   "d\u2019xx",
   "d\u2019xxx",
@@ -286557,7 +286521,6 @@
   "e",
   "e%",
   "e&y",
-  "e&y\u00b4s",
   "e&h",
   "e&p",
   "e&s",
@@ -299355,7 +299318,6 @@
   "ezy",
   "ezz",
   "ezzence",
-  "e\u00b4har",
   "e\u00e1n",
   "e\u00e5g",
   "e\u00e5r",
@@ -368329,7 +368291,6 @@
   "install",
   "installation",
   "installationen",
-  "installationen(jf",
   "installationens",
   "installationer",
   "installationerne",
@@ -384646,7 +384607,6 @@
   "klaudia",
   "klaus",
   "klaus'",
-  "klaus(teknisk",
   "klaus-peter",
   "klausdalsbrovej",
   "klausen",
@@ -400064,7 +400024,6 @@
   "k\u00e6kt",
   "k\u00e6l",
   "k\u00e6lder",
-  "k\u00e6lder(1",
   "k\u00e6lder-",
   "k\u00e6lderareal",
   "k\u00e6lderarealer",
@@ -418479,7 +418438,6 @@
   "l\u00f8gum",
   "l\u00f8gumgaarde",
   "l\u00f8gumg\u00e5rde",
-  "l\u00f8gumg\u00e5rde)ved",
   "l\u00f8gumkloster",
   "l\u00f8gumklostervej",
   "l\u00f8gv\u00e6kst",
@@ -441355,7 +441313,6 @@
   "n't",
   "n'te",
   "n'y",
-  "n)v",
   "n+",
   "n+1",
   "n,-",
@@ -450446,7 +450403,6 @@
   "nzxt",
   "nzy",
   "nz\u014d",
-  "n\u00b4s",
   "n\u00c3",
   "n\u00c3\u00a5",
   "n\u00c3\u00a5et",
@@ -462851,6 +462807,7 @@
   "p;P",
   "p;Y",
   "p;b",
+  "p;y",
   "p<,1",
   "p<0,001",
   "p<0,01",
@@ -469399,7 +469356,6 @@
   "piazzale",
   "piazzetta",
   "piazzolla",
-  "pia\u00b4s",
   "pib",
   "pibe",
   "pibeand",
@@ -483384,7 +483340,6 @@
   "r'n'b",
   "r's",
   "r(1",
-  "r)v",
   "r*v",
   "r*ven",
   "r+",
@@ -490971,7 +490926,6 @@
   "resterne",
   "rester\u00f6ds",
   "restewolf",
-  "restewolf\u00b4en",
   "restferie",
   "restferiedage",
   "restferien",
@@ -566097,7 +566051,6 @@
   "t\u00f8nden",
   "t\u00f8ndens",
   "t\u00f8nder",
-  "t\u00f8nder)v",
   "t\u00f8nder-sagen",
   "t\u00f8ndergade",
   "t\u00f8nderhus",
@@ -575841,8 +575794,6 @@
   "upton",
   "uptours",
   "uptown",
-  "uptown)Ved",
-  "uptown)ved",
   "upu",
   "upublicerede",
   "upubliceret",
@@ -577437,7 +577388,6 @@
   "v&re",
   "v&s",
   "v's",
-  "v)v",
   "v+",
   "v-",
   "v-1",
@@ -592032,7 +591982,6 @@
   "w.s",
   "w.w.",
   "w/",
-  "w/o",
   "w1",
   "w10",
   "w135",
@@ -595273,7 +595222,6 @@
   "x&xxx",
   "x&xxx;x",
   "x&xxx;x.",
-  "x&xxx;x\u00b4x",
   "x&xxxx",
   "x&xxxx;x",
   "x&xxxx;xx",
@@ -595382,7 +595330,6 @@
   "x.dd",
   "x.dd/d",
   "x.dd/d-dd",
-  "x.dd/dd",
   "x.dd/dd-dd",
   "x.dddd",
   "x.m",
@@ -596261,19 +596208,12 @@
   "xxxx(){xxx",
   "xxxx(){xxxx",
   "xxxx(-xx",
-  "xxxx(Xxxxx",
   "xxxx(d",
   "xxxx(d);xxxx",
   "xxxx(ddddxx",
   "xxxx(dddxx",
-  "xxxx(xx",
-  "xxxx(xxxx",
   "xxxx).&xxxx",
   "xxxx).Xxxxx",
-  "xxxx)Xxx",
-  "xxxx)x",
-  "xxxx)xxx",
-  "xxxx)xxxx",
   "xxxx)\u200e",
   "xxxx***%",
   "xxxx+",
@@ -596573,8 +596513,6 @@
   "xxxx\u00adxx\u00adxx",
   "xxxx\u00adxx\u00adxxx",
   "xxxx\u00adxx\u00adxxx\u00adxx\u00adxxx\u00adxx",
-  "xxxx\u00b4x",
-  "xxxx\u00b4xx",
   "xxxx\u00bexx",
   "xxxx\u0301x",
   "xxxx\u030a",
@@ -596609,7 +596547,6 @@
   "xxx\u00adxx\u00adxxxx",
   "xxx\u00adxx\u00adxxx\u00adxxx",
   "xxx\u00adxx\u00adxx\u00adxx",
-  "xxx\u00b4x",
   "xxx\u0301",
   "xxx\u030a",
   "xxx\u030ax",
@@ -596665,7 +596602,6 @@
   "x~",
   "x\u0080\u0093",
   "x\u00adxx\u00adxx\u00adxxx\u00adxxx",
-  "x\u00b4xxx",
   "x\u00b8xxxx",
   "x\u00bexx",
   "x\u00bexxx",
@@ -596691,7 +596627,6 @@
   "x\u0e34.x.",
   "x\u0e35.x.",
   "x\u2019xx",
-  "x\u2019xxxx",
   "x\u20ac",
   "x\u20ac\u009d",
   "x\ufe35x",
@@ -597998,7 +597933,6 @@
   "yze",
   "yzf",
   "yz\u00f3",
-  "y\u00b4s",
   "y\u00e8s",
   "y\u00f0i",
   "y\u00f6r",
@@ -599135,10 +599069,7 @@
   "\u00b3/s",
   "\u00b3/t",
   "\u00b4",
-  "\u00b4en",
   "\u00b4er",
-  "\u00b4s",
-  "\u00b4x",
   "\u00b5",
   "\u00b5.",
   "\u00b5L",