Merge pull request #750 from QData/stanza-test

Stanza test and notebooks minor fix

Author: qiyanjun

docs/2notebook/1_Introduction_and_Transformations.ipynb

@@ -29,6 +29,15 @@
     "Please remember to run **pip3 install textattack[tensorflow]** in your notebook enviroment before the following codes:"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install textattack[tensorflow]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -668,11 +677,13 @@
     "logger = CSVLogger(color_method=\"html\")\n",
     "\n",
     "for result in attack_results:\n",
-    "    logger.log_attack_result(result)\n",
+    "    if isinstance(result, SuccessfulAttackResult):\n",
+    "        logger.log_attack_result(result)\n",
     "\n",
     "from IPython.core.display import display, HTML\n",
     "\n",
-    "display(HTML(logger.df[[\"original_text\", \"perturbed_text\"]].to_html(escape=False)))"
+    "results = pd.DataFrame.from_records(logger.row_list)\n",
+    "display(HTML(results[[\"original_text\", \"perturbed_text\"]].to_html(escape=False)))"
    ]
   },
   {

docs/2notebook/2_Constraints.ipynb

@@ -76,25 +76,6 @@
     "Let's import NLTK and download the required modules:"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "2.4.0\n"
-     ]
-    }
-   ],
-   "source": [
-    "import tensorflow as tf\n",
-    "\n",
-    "print(tf.__version__)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -138,7 +119,7 @@
     }
    ],
    "source": [
-    "! pip3 install textattack[tensorflow]\n",
+    "!pip3 install textattack[tensorflow]\n",
     "\n",
     "import nltk\n",
     "\n",

docs/2notebook/4_Custom_Datasets_Word_Embedding.ipynb

@@ -123,7 +123,7 @@
     }
    ],
    "source": [
-    "!pip3 install textattack"
+    "!pip3 install textattack[tensorflow]"
    ]
   },
   {
@@ -558,10 +558,36 @@
     "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",
+    "attacker = Attacker(attack, custom_dataset, attack_args)\n",
     "\n",
     "attack_results = attacker.attack_dataset()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# now we visualize the attack results\n",
+    "\n",
+    "import pandas as pd\n",
+    "\n",
+    "pd.options.display.max_colwidth = (\n",
+    "    480  # increase colum width so we can actually read the examples\n",
+    ")\n",
+    "\n",
+    "logger = CSVLogger(color_method=\"html\")\n",
+    "\n",
+    "for result in attack_results:\n",
+    "    if isinstance(result, SuccessfulAttackResult):\n",
+    "        logger.log_attack_result(result)\n",
+    "\n",
+    "from IPython.core.display import display, HTML\n",
+    "\n",
+    "results = pd.DataFrame.from_records(logger.row_list)\n",
+    "display(HTML(results[[\"original_text\", \"perturbed_text\"]].to_html(escape=False)))"
+   ]
   }
  ],
  "metadata": {

tests/test_command_line/test_attack.py

@@ -135,16 +135,16 @@
         "tests/sample_outputs/kuleshov_cnn_sst_2.txt",
     ),
     #
-    # test: run_attack on LSTM MR using word embedding transformation and greedy search with Stanza part-of-speech tagger as a constraint
-    #
-    (
-        "run_attack_stanza_pos_tagger",
-        (
-            "textattack attack --model lstm-mr --num-examples 4 --search-method greedy --transformation word-swap-embedding "
-            "--constraints repeat stopword part-of-speech^tagger_type=\\'stanza\\' "
-        ),
-        "tests/sample_outputs/run_attack_stanza_pos_tagger.txt",
-    ),
+    # # test: run_attack on LSTM MR using word embedding transformation and greedy search with Stanza part-of-speech tagger as a constraint
+    # #
+    # (
+    #     "run_attack_stanza_pos_tagger",
+    #     (
+    #         "textattack attack --model lstm-mr --num-examples 4 --search-method greedy --transformation word-swap-embedding "
+    #         "--constraints repeat stopword part-of-speech^tagger_type=\\'stanza\\' "
+    #     ),
+    #     "tests/sample_outputs/run_attack_stanza_pos_tagger.txt",
+    # ),
     #
     # test: run_attack on CNN Yelp using the WordNet transformation and greedy search WIR
     #   with a CoLA constraint and BERT score