update

bias_detector/bias_detector.py

@@ -141,10 +141,10 @@ class Detector:
                     for item in prediction:
                         result[item['word']] = {item['entity_group']: item['score']}
                 elif self.classifier == 'Sentence' and self.model_type == 'All':
-                    result = {self.MD_SL_label_mapping.get(item['label'].split('__')[-1], 'unknown'): item['score'] for item in
+                    result = {item['label'].split('__')[-1]: item['score'] for item in
                               prediction}
                 else:
-                    result = {self.SD_SL_label_mapping.get(item['label'].split('__')[-1], 'unknown'): item['score'] for item in
+                    result = {item['label'].split('__')[-1]: item['score'] for item in
                               prediction}
                 results.append({text: result})
 

test.ipynb

@@ -0,0 +1,256 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2023-07-03T11:40:02.257868Z",
+     "start_time": "2023-07-03T11:39:50.130235Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting transformers\r\n",
+      "  Using cached transformers-4.30.2-py3-none-any.whl (7.2 MB)\r\n",
+      "Collecting torch\r\n",
+      "  Using cached torch-2.0.1-cp39-none-macosx_11_0_arm64.whl (55.8 MB)\r\n",
+      "Requirement already satisfied: pyyaml>=5.1 in ./venv/lib/python3.9/site-packages (from transformers) (6.0)\r\n",
+      "Requirement already satisfied: requests in ./venv/lib/python3.9/site-packages (from transformers) (2.31.0)\r\n",
+      "Collecting huggingface-hub<1.0,>=0.14.1\r\n",
+      "  Using cached huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\r\n",
+      "Collecting regex!=2019.12.17\r\n",
+      "  Using cached regex-2023.6.3-cp39-cp39-macosx_11_0_arm64.whl (288 kB)\r\n",
+      "Collecting safetensors>=0.3.1\r\n",
+      "  Using cached safetensors-0.3.1-cp39-cp39-macosx_12_0_arm64.whl (401 kB)\r\n",
+      "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\r\n",
+      "  Using cached tokenizers-0.13.3-cp39-cp39-macosx_12_0_arm64.whl (3.9 MB)\r\n",
+      "Requirement already satisfied: numpy>=1.17 in ./venv/lib/python3.9/site-packages (from transformers) (1.25.0)\r\n",
+      "Requirement already satisfied: packaging>=20.0 in ./venv/lib/python3.9/site-packages (from transformers) (23.1)\r\n",
+      "Collecting filelock\r\n",
+      "  Using cached filelock-3.12.2-py3-none-any.whl (10 kB)\r\n",
+      "Collecting tqdm>=4.27\r\n",
+      "  Using cached tqdm-4.65.0-py3-none-any.whl (77 kB)\r\n",
+      "Collecting networkx\r\n",
+      "  Using cached networkx-3.1-py3-none-any.whl (2.1 MB)\r\n",
+      "Requirement already satisfied: jinja2 in ./venv/lib/python3.9/site-packages (from torch) (3.1.2)\r\n",
+      "Collecting sympy\r\n",
+      "  Using cached sympy-1.12-py3-none-any.whl (5.7 MB)\r\n",
+      "Requirement already satisfied: typing-extensions in ./venv/lib/python3.9/site-packages (from torch) (4.7.0)\r\n",
+      "Collecting fsspec\r\n",
+      "  Using cached fsspec-2023.6.0-py3-none-any.whl (163 kB)\r\n",
+      "Requirement already satisfied: MarkupSafe>=2.0 in ./venv/lib/python3.9/site-packages (from jinja2->torch) (2.1.3)\r\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in ./venv/lib/python3.9/site-packages (from requests->transformers) (2.0.3)\r\n",
+      "Requirement already satisfied: idna<4,>=2.5 in ./venv/lib/python3.9/site-packages (from requests->transformers) (3.4)\r\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in ./venv/lib/python3.9/site-packages (from requests->transformers) (2023.5.7)\r\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in ./venv/lib/python3.9/site-packages (from requests->transformers) (3.1.0)\r\n",
+      "Collecting mpmath>=0.19\r\n",
+      "  Using cached mpmath-1.3.0-py3-none-any.whl (536 kB)\r\n",
+      "Installing collected packages: tokenizers, safetensors, mpmath, tqdm, sympy, regex, networkx, fsspec, filelock, torch, huggingface-hub, transformers\r\n",
+      "Successfully installed filelock-3.12.2 fsspec-2023.6.0 huggingface-hub-0.15.1 mpmath-1.3.0 networkx-3.1 regex-2023.6.3 safetensors-0.3.1 sympy-1.12 tokenizers-0.13.3 torch-2.0.1 tqdm-4.65.0 transformers-4.30.2\r\n",
+      "\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip available: \u001B[0m\u001B[31;49m22.3.1\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m23.1.2\u001B[0m\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\r\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install transformers torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zekunwu/Desktop/Multidimensional_Multilevel_Bias_Detection/venv/lib/python3.9/site-packages/urllib3/__init__.py:34: NotOpenSSLWarning: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-07-03T11:40:15.740384Z",
+     "start_time": "2023-07-03T11:40:13.337662Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "Downloading (…)lve/main/config.json:   0%|          | 0.00/1.22k [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "fe49340d8bde452783356e63521406f8"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "Downloading pytorch_model.bin:   0%|          | 0.00/268M [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "5bde37e9ea7847aabe552d785ad92259"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "Downloading (…)okenizer_config.json:   0%|          | 0.00/320 [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "d37b8a75cfbe4d45a432e4f60f467f9e"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "Downloading (…)solve/main/vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "849bb76de24745edb6dc2525abddb654"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/712k [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "7715e71cc3ee417880da6791d3fb5c59"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "Downloading (…)cial_tokens_map.json:   0%|          | 0.00/125 [00:00<?, ?B/s]",
+      "application/vnd.jupyter.widget-view+json": {
+       "version_major": 2,
+       "version_minor": 0,
+       "model_id": "4ee0092408bc48cd8cbe84b7e173ff2b"
+      }
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Xformers is not installed correctly. If you want to use memory_efficient_attention to accelerate training use the following command to install Xformers\n",
+      "pip install xformers.\n"
+     ]
+    }
+   ],
+   "source": [
+    "testpipe = pipeline(\"text-classification\",\"wu981526092/Sentence-Level-Multidimensional-Bias-Detector\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-07-03T11:40:46.412969Z",
+     "start_time": "2023-07-03T11:40:18.473347Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "outputs": [],
+   "source": [
+    "result = testpipe.predict([\"this is a test sentence\"])"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-07-03T11:40:50.912734Z",
+     "start_time": "2023-07-03T11:40:50.881524Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[{'label': 'unrelated', 'score': 0.990786075592041}]"
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-07-03T11:40:54.505395Z",
+     "start_time": "2023-07-03T11:40:54.498101Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}