Merge pull request #748 from QData/fix-pytest-errors

Fix pytest errors - due to goal_func
QData · Sep 11, 2023 · e426102 · e426102
2 parents 094025e + 987c926
commit e426102
Show file tree

Hide file tree

Showing 20 changed files with 3,885 additions and 3,710 deletions.
diff --git a/docs/2notebook/0_End_to_End.ipynb b/docs/2notebook/0_End_to_End.ipynb
diff --git a/docs/2notebook/1_Introduction_and_Transformations.ipynb b/docs/2notebook/1_Introduction_and_Transformations.ipynb
@@ -927,7 +927,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.7.11"
   }
  },
  "nbformat": 4,

diff --git a/docs/2notebook/2_Constraints.ipynb b/docs/2notebook/2_Constraints.ipynb
@@ -76,15 +76,6 @@
     "Let's import NLTK and download the required modules:"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# cd .."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -147,7 +138,7 @@
     }
    ],
    "source": [
-    "!pip3 install .\n",
+    "! pip3 install textattack[tensorflow]\n",
     "\n",
     "import nltk\n",
     "\n",
@@ -826,7 +817,7 @@
     ")\n",
     "attacker = Attacker(attack, dataset, attack_args)\n",
     "\n",
-    "attacker.attack_dataset()"
+    "attack_results = attacker.attack_dataset()"
    ]
   },
   {
@@ -884,7 +875,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -898,7 +889,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.7.11"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {

diff --git a/docs/2notebook/3_Augmentations.ipynb b/docs/2notebook/3_Augmentations.ipynb
@@ -1,29 +1,4 @@
 {
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
-  "colab": {
-   "name": "Augmentation with TextAttack.ipynb",
-   "provenance": []
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.8"
-  }
- },
  "cells": [
   {
    "cell_type": "markdown",
@@ -84,9 +59,11 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "id": "5AXyxiLD4X93"
    },
+   "outputs": [],
    "source": [
     "# import transformations, contraints, and the Augmenter\n",
     "from textattack.transformations import WordSwapRandomCharacterDeletion\n",
@@ -97,38 +74,18 @@
     "from textattack.constraints.pre_transformation import StopwordModification\n",
     "\n",
     "from textattack.augmentation import Augmenter"
-   ],
-   "execution_count": null,
-   "outputs": []
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "wFeXF_OL-vyw",
     "outputId": "c041e77e-accd-4a58-88be-9b140dd0cd56"
    },
-   "source": [
-    "# Set up transformation using CompositeTransformation()\n",
-    "transformation = CompositeTransformation(\n",
-    "    [WordSwapRandomCharacterDeletion(), WordSwapQWERTY()]\n",
-    ")\n",
-    "# Set up constraints\n",
-    "constraints = [RepeatModification(), StopwordModification()]\n",
-    "# Create augmenter with specified parameters\n",
-    "augmenter = Augmenter(\n",
-    "    transformation=transformation,\n",
-    "    constraints=constraints,\n",
-    "    pct_words_to_swap=0.5,\n",
-    "    transformations_per_example=10,\n",
-    ")\n",
-    "s = \"What I cannot create, I do not understand.\"\n",
-    "# Augment!\n",
-    "augmenter.augment(s)"
-   ],
-   "execution_count": null,
    "outputs": [
     {
      "data": {
@@ -149,6 +106,24 @@
      "metadata": {},
      "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "# Set up transformation using CompositeTransformation()\n",
+    "transformation = CompositeTransformation(\n",
+    "    [WordSwapRandomCharacterDeletion(), WordSwapQWERTY()]\n",
+    ")\n",
+    "# Set up constraints\n",
+    "constraints = [RepeatModification(), StopwordModification()]\n",
+    "# Create augmenter with specified parameters\n",
+    "augmenter = Augmenter(\n",
+    "    transformation=transformation,\n",
+    "    constraints=constraints,\n",
+    "    pct_words_to_swap=0.5,\n",
+    "    transformations_per_example=10,\n",
+    ")\n",
+    "s = \"What I cannot create, I do not understand.\"\n",
+    "# Augment!\n",
+    "augmenter.augment(s)"
    ]
   },
   {
@@ -173,24 +148,14 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "WkYiVH6lQedu",
     "outputId": "cd5ffc65-ca80-45cd-b3bb-d023bcad09a4"
    },
-   "source": [
-    "# import the CheckListAugmenter\n",
-    "from textattack.augmentation import CheckListAugmenter\n",
-    "\n",
-    "# Alter default values if desired\n",
-    "augmenter = CheckListAugmenter(pct_words_to_swap=0.2, transformations_per_example=5)\n",
-    "s = \"I'd love to go to Japan but the tickets are 500 dollars\"\n",
-    "# Augment\n",
-    "augmenter.augment(s)"
-   ],
-   "execution_count": null,
    "outputs": [
     {
      "name": "stdout",
@@ -218,6 +183,16 @@
      "metadata": {},
      "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "# import the CheckListAugmenter\n",
+    "from textattack.augmentation import CheckListAugmenter\n",
+    "\n",
+    "# Alter default values if desired\n",
+    "augmenter = CheckListAugmenter(pct_words_to_swap=0.2, transformations_per_example=5)\n",
+    "s = \"I'd love to go to Japan but the tickets are 500 dollars\"\n",
+    "# Augment\n",
+    "augmenter.augment(s)"
    ]
   },
   {
@@ -248,42 +223,25 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 9,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "l2b-4scuXvkA",
     "outputId": "5a372fd2-226a-4970-a2c9-c09bf2af56c2"
    },
-   "source": [
-    "from textattack.augmentation import WordNetAugmenter\n",
-    "\n",
-    "augmenter = WordNetAugmenter(\n",
-    "    pct_words_to_swap=0.4,\n",
-    "    transformations_per_example=5,\n",
-    "    high_yield=True,\n",
-    "    enable_advanced_metrics=True,\n",
-    ")\n",
-    "s = \"I'd love to go to Japan but the tickets are 500 dollars\"\n",
-    "results = augmenter.augment(s)\n",
-    "print(f\"Average Original Perplexity Score: {results[1]['avg_original_perplexity']}\\n\")\n",
-    "print(f\"Average Augment Perplexity Score: {results[1]['avg_attack_perplexity']}\\n\")\n",
-    "print(f\"Average Augment USE Score: {results[2]['avg_attack_use_score']}\\n\")\n",
-    "print(f\"Augmentations:\")\n",
-    "results[0]"
-   ],
-   "execution_count": 9,
    "outputs": [
     {
-     "output_type": "stream",
      "name": "stderr",
+     "output_type": "stream",
      "text": [
       "Token indices sequence length is longer than the specified maximum sequence length for this model (1091 > 1024). Running this sequence through the model will result in indexing errors\n"
      ]
     },
     {
-     "output_type": "stream",
      "name": "stdout",
+     "output_type": "stream",
      "text": [
       "Average Original Perplexity Score: 1.09\n",
       "\n",
@@ -295,7 +253,6 @@
      ]
     },
     {
-     "output_type": "execute_result",
      "data": {
       "text/plain": [
        "[\"I'd bang to operate to Japan but the ticket are 500 buck\",\n",
@@ -373,9 +330,27 @@
        " \"I'd screw to plump to Nihon but the tickets are 500 clam\"]"
       ]
      },
+     "execution_count": 9,
      "metadata": {},
-     "execution_count": 9
+     "output_type": "execute_result"
     }
+   ],
+   "source": [
+    "from textattack.augmentation import WordNetAugmenter\n",
+    "\n",
+    "augmenter = WordNetAugmenter(\n",
+    "    pct_words_to_swap=0.4,\n",
+    "    transformations_per_example=5,\n",
+    "    high_yield=True,\n",
+    "    enable_advanced_metrics=True,\n",
+    ")\n",
+    "s = \"I'd love to go to Japan but the tickets are 500 dollars\"\n",
+    "results = augmenter.augment(s)\n",
+    "print(f\"Average Original Perplexity Score: {results[1]['avg_original_perplexity']}\\n\")\n",
+    "print(f\"Average Augment Perplexity Score: {results[1]['avg_attack_perplexity']}\\n\")\n",
+    "print(f\"Average Augment USE Score: {results[2]['avg_attack_use_score']}\\n\")\n",
+    "print(f\"Augmentations:\")\n",
+    "results[0]"
    ]
   },
   {
@@ -388,5 +363,30 @@
     "We have now went through the basics in running `Augmenter` by either creating a new augmenter from scratch or using a pre-built augmenter. This could be done in as few as 4 lines of code so please give it a try if you haven't already! 🐙"
    ]
   }
- ]
-}
+ ],
+ "metadata": {
+  "colab": {
+   "name": "Augmentation with TextAttack.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/docs/2notebook/4_Custom_Datasets_Word_Embedding.ipynb b/docs/2notebook/4_Custom_Datasets_Word_Embedding.ipynb
@@ -537,10 +537,31 @@
     "\n",
     "attack = Attack(goal_function, constraints, transformation, search_method)\n",
     "\n",
+    "# here is a legacy code piece showing how the attack runs in  details \n",
     "for example, label in custom_dataset:\n",
     "    result = attack.attack(example, label)\n",
     "    print(result.__str__(color_method=\"ansi\"))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# here is currently recommendated API-centric way to use customized attack\n",
+    "\n",
+    "from textattack.loggers import CSVLogger  # tracks a dataframe for us.\n",
+    "from textattack.attack_results import SuccessfulAttackResult\n",
+    "from textattack import Attacker, AttackArgs\n",
+    "\n",
+    "attack_args = AttackArgs(\n",
+    "    num_successful_examples=5, log_to_csv=\"results.csv\", csv_coloring_style=\"html\"\n",
+    ")\n",
+    "attacker = Attacker(attack, dataset, attack_args)\n",
+    "\n",
+    "attack_results = attacker.attack_dataset()"
+   ]
   }
  ],
  "metadata": {
@@ -549,7 +570,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -563,7 +584,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.7.11"
   }
  },
  "nbformat": 4,