diff --git a/tutorials/data/test4dataset.csv b/tutorials/data/test4dataset.csv new file mode 100644 index 00000000..fdf87c08 --- /dev/null +++ b/tutorials/data/test4dataset.csv @@ -0,0 +1,7 @@ +,SentenceId,Sentence,Sentiment +0,1,"['a', 'series', 'of', 'escapades', 'demonstrating', 'the', 'adage', 'that', 'what', 'is', 'good', 'for', 'the', 'goose', 'is', 'also', 'good', 'for', 'the', 'gander', ',', 'some', 'of', 'which', 'occasionally', 'amuses', 'but', 'none', 'of', 'which', 'amounts', 'to', 'much', 'of', 'a', 'story', '.']",negative +1,2,"['this', 'quiet', ',', 'introspective', 'and', 'entertaining', 'independent', 'is', 'worth', 'seeking', '.']",positive +2,3,"['even', 'fans', 'of', 'ismail', 'merchant', ""'s"", 'work', ',', 'i', 'suspect', ',', 'would', 'have', 'a', 'hard', 'time', 'sitting', 'through', 'this', 'one', '.']",negative +3,4,"['a', 'positively', 'thrilling', 'combination', 'of', 'ethnography', 'and', 'all', 'the', 'intrigue', ',', 'betrayal', ',', 'deceit', 'and', 'murder', 'of', 'a', 'shakespearean', 'tragedy', 'or', 'a', 'juicy', 'soap', 'opera', '.']",neutral +4,5,"['a', 'comedy-drama', 'of', 'nearly', 'epic', 'proportions', 'rooted', 'in', 'a', 'sincere', 'performance', 'by', 'the', 'title', 'character', 'undergoing', 'midlife', 'crisis', '.']",positive +5,6,"['the', 'importance', 'of', 'being', 'earnest', ',', 'so', 'thick', 'with', 'wit', 'it', 'plays', 'like', 'a', 'reading', 'from', 'bartlett', ""'s"", 'familiar', 'quotations']",neutral diff --git a/tutorials/data/test4dataset.tsv b/tutorials/data/test4dataset.tsv new file mode 100644 index 00000000..ea2f6f37 --- /dev/null +++ b/tutorials/data/test4dataset.tsv @@ -0,0 +1,7 @@ +SentenceId Sentence Sentiment +1 A series of escapades demonstrating the adage that what is good for the goose is also good for the gander , some of which occasionally amuses but none of which amounts to much of a story . negative +2 This quiet , introspective and entertaining independent is worth seeking . positive +3 Even fans of Ismail Merchant 's work , I suspect , would have a hard time sitting through this one . negative +4 A positively thrilling combination of ethnography and all the intrigue , betrayal , deceit and murder of a Shakespearean tragedy or a juicy soap opera . neutral +5 A comedy-drama of nearly epic proportions rooted in a sincere performance by the title character undergoing midlife crisis . positive +6 The Importance of Being Earnest , so thick with wit it plays like a reading from Bartlett 's Familiar Quotations neutral diff --git a/tutorials/fastnlp_tutorial_1.ipynb b/tutorials/fastnlp_tutorial_1.ipynb index 11bd2219..93e7a664 100644 --- a/tutorials/fastnlp_tutorial_1.ipynb +++ b/tutorials/fastnlp_tutorial_1.ipynb @@ -153,7 +153,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "1969418794120 1971237588872\n", + "2438703969992 2438374526920\n", "+-----+------------------------+------------------------+-----+\n", "| idx | sentence | words | num |\n", "+-----+------------------------+------------------------+-----+\n", @@ -198,7 +198,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "1971237588872 1971237588872\n", + "2438374526920 2438374526920\n", "+-----+------------------------+------------------------+-----+\n", "| idx | sentence | words | num |\n", "+-----+------------------------+------------------------+-----+\n", @@ -774,9 +774,9 @@ { "data": { "text/plain": [ - "{'sentence': ,\n", - " 'words': ,\n", - " 'num': }" + "{'sentence': ,\n", + " 'words': ,\n", + " 'num': }" ] }, "execution_count": 15, @@ -923,7 +923,8 @@ "output_type": "stream", "text": [ "5 Counter({'生活': 1, '就像': 1, '海洋': 1})\n", - "6 Counter({'生活': 1, '就像': 1, '海洋': 1, '只有': 1})\n" + "6 Counter({'生活': 1, '就像': 1, '海洋': 1, '只有': 1})\n", + "6 {'': 0, '': 1, '生活': 2, '就像': 3, '海洋': 4, '只有': 5}\n" ] } ], @@ -931,7 +932,8 @@ "vocab.add_word_lst(['生活', '就像', '海洋'])\n", "print(len(vocab), vocab.word_count)\n", "vocab.add_word('只有')\n", - "print(len(vocab), vocab.word_count)" + "print(len(vocab), vocab.word_count)\n", + "print(len(vocab), vocab.word2idx)" ] }, { @@ -959,7 +961,6 @@ " 0\n", " 1\n", "生活 2\n", - "只有 5\n", "彼岸 1 False\n" ] } @@ -968,7 +969,6 @@ "print(vocab.to_word(0), vocab.to_index(''))\n", "print(vocab.to_word(1), vocab.to_index(''))\n", "print(vocab.to_word(2), vocab.to_index('生活'))\n", - "print(vocab.to_word(5), vocab.to_index('只有'))\n", "print('彼岸', vocab.to_index('彼岸'), vocab.has_word('彼岸'))" ] }, @@ -979,7 +979,9 @@ "source": [ "**`vocabulary`允许反复添加相同单词**，**可以通过`word_count`方法看到相应单词被添加的次数**\n", "\n", - "  但其中没有``和``，`vocabulary`的全部变量与函数可以通过`dir(vocabulary)`查询" + "  但其中没有``和``，`vocabulary`的全部变量与函数可以通过`dir(vocabulary)`查询\n", + "\n", + "  注：**使用`add_word_lst`添加单词**，**单词对应序号不会动态调整**，**使用`dataset`添加单词的情况不同**" ] }, { @@ -992,15 +994,19 @@ "name": "stdout", "output_type": "stream", "text": [ - "13 Counter({'生活': 2, '就像': 2, '海洋': 2, '只有': 2, '意志': 1, '坚强的': 1, '人': 1, '才': 1, '能': 1, '到达': 1, '彼岸': 1})\n", - "彼岸 12 True\n" + "生活 2\n", + "彼岸 12 True\n", + "13 Counter({'人': 4, '生活': 2, '就像': 2, '海洋': 2, '只有': 2, '意志': 1, '坚强的': 1, '才': 1, '能': 1, '到达': 1, '彼岸': 1})\n", + "13 {'': 0, '': 1, '生活': 2, '就像': 3, '海洋': 4, '只有': 5, '人': 6, '意志': 7, '坚强的': 8, '才': 9, '能': 10, '到达': 11, '彼岸': 12}\n" ] } ], "source": [ - "vocab.add_word_lst(['生活', '就像', '海洋', '只有', '意志', '坚强的', '人', '才', '能', '到达', '彼岸'])\n", + "vocab.add_word_lst(['生活', '就像', '海洋', '只有', '意志', '坚强的', '人', '人', '人', '人', '才', '能', '到达', '彼岸'])\n", + "print(vocab.to_word(2), vocab.to_index('生活'))\n", + "print('彼岸', vocab.to_index('彼岸'), vocab.has_word('彼岸'))\n", "print(len(vocab), vocab.word_count)\n", - "print('彼岸', vocab.to_index('彼岸'), vocab.has_word('彼岸'))" + "print(len(vocab), vocab.word2idx)" ] }, { @@ -1082,52 +1088,440 @@ "## 3 dataset 和 vocabulary 的组合使用\n", " \n", "### 3.1 从 dataframe 中加载 dataset\n", - "\n" + "\n", + "以下通过 [NLP-beginner](https://github.com/FudanNLP/nlp-beginner) 实践一中 [Rotten Tomatoes 影评数据集](https://www.kaggle.com/c/sentiment-analysis-on-movie-reviews) 的部分训练数据组成`test4dataset.tsv`文件\n", + "\n", + "  介绍如何使用`dataset`、`vocabulary`简单加载并处理数据集，首先使用`pandas`模块，读取原始数据的`dataframe`" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "3dbd985d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SentenceIdSentenceSentiment
01A series of escapades demonstrating the adage ...negative
12This quiet , introspective and entertaining in...positive
23Even fans of Ismail Merchant 's work , I suspe...negative
34A positively thrilling combination of ethnogra...neutral
45A comedy-drama of nearly epic proportions root...positive
56The Importance of Being Earnest , so thick wit...neutral
\n", + "
" + ], + "text/plain": [ + " SentenceId Sentence Sentiment\n", + "0 1 A series of escapades demonstrating the adage ... negative\n", + "1 2 This quiet , introspective and entertaining in... positive\n", + "2 3 Even fans of Ismail Merchant 's work , I suspe... negative\n", + "3 4 A positively thrilling combination of ethnogra... neutral\n", + "4 5 A comedy-drama of nearly epic proportions root... positive\n", + "5 6 The Importance of Being Earnest , so thick wit... neutral" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "\n", + "df = pd.read_csv('./data/test4dataset.tsv', sep='\\t')\n", + "df" ] }, { "cell_type": "markdown", - "id": "89059713", + "id": "919ab350", "metadata": {}, - "source": [] + "source": [ + "接着，通过`dataset`中的`from_pandas`方法填充数据集，并使用`apply_more`方法对文本进行分词操作" + ] }, { "cell_type": "code", - "execution_count": null, - "id": "3dbd985d", + "execution_count": 25, + "id": "4f634586", "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "
\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------+------------------------------+-----------+\n",
+      "| SentenceId | Sentence                     | Sentiment |\n",
+      "+------------+------------------------------+-----------+\n",
+      "| 1          | ['a', 'series', 'of', 'es... | negative  |\n",
+      "| 2          | ['this', 'quiet', ',', 'i... | positive  |\n",
+      "| 3          | ['even', 'fans', 'of', 'i... | negative  |\n",
+      "| 4          | ['a', 'positively', 'thri... | neutral   |\n",
+      "| 5          | ['a', 'comedy-drama', 'of... | positive  |\n",
+      "| 6          | ['the', 'importance', 'of... | neutral   |\n",
+      "+------------+------------------------------+-----------+\n"
+     ]
+    }
+   ],
+   "source": [
+    "from fastNLP.core.dataset import DataSet\n",
+    "\n",
+    "dataset = DataSet()\n",
+    "dataset = dataset.from_pandas(df)\n",
+    "dataset.apply_more(lambda ins:{'SentenceId': ins['SentenceId'], \n",
+    "                               'Sentence': ins['Sentence'].lower().split(), 'Sentiment': ins['Sentiment']})\n",
+    "print(dataset)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c1ae192",
+   "metadata": {},
+   "source": [
+    "  如果需要保存中间结果，也可以使用`dataset`的`to_csv`方法，生成`.csv`或`.tsv`文件"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "4f634586",
+   "execution_count": 26,
+   "id": "46722efc",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "dataset.to_csv('./data/test4dataset.csv')"
+   ]
   },
   {
    "cell_type": "markdown",
    "id": "5ba13989",
    "metadata": {},
    "source": [
-    "### 3.2 从 dataset 中获取 vocabulary"
+    "### 3.2 从 dataset 中获取 vocabulary\n",
+    "\n",
+    "然后，初始化`vocabulary`，使用`vocabulary`中的`from_dataset`方法，从`dataset`的指定字段中\n",
+    "\n",
+    "  获取字段中的所有元素，然后编号；如果指定字段是个列表，则针对字段中所有列表包含的元素编号\n",
+    "\n",
+    "  注：**使用`dataset`添加单词**，**不同于`add_word_list`**，**单词被添加次数越多**，**序号越靠前**，例如案例中的`a`"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "id": "a2de615b",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "
\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Counter({'a': 9, 'of': 9, ',': 7, 'the': 6, '.': 5, 'is': 3, 'and': 3, 'good': 2, 'for': 2, 'which': 2, 'this': 2, \"'s\": 2, 'series': 1, 'escapades': 1, 'demonstrating': 1, 'adage': 1, 'that': 1, 'what': 1, 'goose': 1, 'also': 1, 'gander': 1, 'some': 1, 'occasionally': 1, 'amuses': 1, 'but': 1, 'none': 1, 'amounts': 1, 'to': 1, 'much': 1, 'story': 1, 'quiet': 1, 'introspective': 1, 'entertaining': 1, 'independent': 1, 'worth': 1, 'seeking': 1, 'even': 1, 'fans': 1, 'ismail': 1, 'merchant': 1, 'work': 1, 'i': 1, 'suspect': 1, 'would': 1, 'have': 1, 'hard': 1, 'time': 1, 'sitting': 1, 'through': 1, 'one': 1, 'positively': 1, 'thrilling': 1, 'combination': 1, 'ethnography': 1, 'all': 1, 'intrigue': 1, 'betrayal': 1, 'deceit': 1, 'murder': 1, 'shakespearean': 1, 'tragedy': 1, 'or': 1, 'juicy': 1, 'soap': 1, 'opera': 1, 'comedy-drama': 1, 'nearly': 1, 'epic': 1, 'proportions': 1, 'rooted': 1, 'in': 1, 'sincere': 1, 'performance': 1, 'by': 1, 'title': 1, 'character': 1, 'undergoing': 1, 'midlife': 1, 'crisis': 1, 'importance': 1, 'being': 1, 'earnest': 1, 'so': 1, 'thick': 1, 'with': 1, 'wit': 1, 'it': 1, 'plays': 1, 'like': 1, 'reading': 1, 'from': 1, 'bartlett': 1, 'familiar': 1, 'quotations': 1}) \n",
+      "\n",
+      "{'': 0, '': 1, 'a': 2, 'of': 3, ',': 4, 'the': 5, '.': 6, 'is': 7, 'and': 8, 'good': 9, 'for': 10, 'which': 11, 'this': 12, \"'s\": 13, 'series': 14, 'escapades': 15, 'demonstrating': 16, 'adage': 17, 'that': 18, 'what': 19, 'goose': 20, 'also': 21, 'gander': 22, 'some': 23, 'occasionally': 24, 'amuses': 25, 'but': 26, 'none': 27, 'amounts': 28, 'to': 29, 'much': 30, 'story': 31, 'quiet': 32, 'introspective': 33, 'entertaining': 34, 'independent': 35, 'worth': 36, 'seeking': 37, 'even': 38, 'fans': 39, 'ismail': 40, 'merchant': 41, 'work': 42, 'i': 43, 'suspect': 44, 'would': 45, 'have': 46, 'hard': 47, 'time': 48, 'sitting': 49, 'through': 50, 'one': 51, 'positively': 52, 'thrilling': 53, 'combination': 54, 'ethnography': 55, 'all': 56, 'intrigue': 57, 'betrayal': 58, 'deceit': 59, 'murder': 60, 'shakespearean': 61, 'tragedy': 62, 'or': 63, 'juicy': 64, 'soap': 65, 'opera': 66, 'comedy-drama': 67, 'nearly': 68, 'epic': 69, 'proportions': 70, 'rooted': 71, 'in': 72, 'sincere': 73, 'performance': 74, 'by': 75, 'title': 76, 'character': 77, 'undergoing': 78, 'midlife': 79, 'crisis': 80, 'importance': 81, 'being': 82, 'earnest': 83, 'so': 84, 'thick': 85, 'with': 86, 'wit': 87, 'it': 88, 'plays': 89, 'like': 90, 'reading': 91, 'from': 92, 'bartlett': 93, 'familiar': 94, 'quotations': 95} \n",
+      "\n",
+      "Vocabulary(['a', 'series', 'of', 'escapades', 'demonstrating']...)\n"
+     ]
+    }
+   ],
+   "source": [
+    "from fastNLP.core.vocabulary import Vocabulary\n",
+    "\n",
+    "vocab = Vocabulary()\n",
+    "vocab = vocab.from_dataset(dataset, field_name='Sentence')\n",
+    "print(vocab.word_count, '\\n')\n",
+    "print(vocab.word2idx, '\\n')\n",
+    "print(vocab)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0857ccb",
+   "metadata": {},
+   "source": [
+    "之后，**通过`vocabulary`的`index_dataset`方法**，**调整`dataset`中指定字段的元素**，**使用编号将之代替**\n",
+    "\n",
+    "  使用上述方法，可以将影评数据集中的单词序列转化为词编号序列，为接下来转化为词嵌入序列做准备"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
+   "id": "2f9a04b2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "
\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------+------------------------------+-----------+\n",
+      "| SentenceId | Sentence                     | Sentiment |\n",
+      "+------------+------------------------------+-----------+\n",
+      "| 1          | [2, 14, 3, 15, 16, 5, 17,... | negative  |\n",
+      "| 2          | [12, 32, 4, 33, 8, 34, 35... | positive  |\n",
+      "| 3          | [38, 39, 3, 40, 41, 13, 4... | negative  |\n",
+      "| 4          | [2, 52, 53, 54, 3, 55, 8,... | neutral   |\n",
+      "| 5          | [2, 67, 3, 68, 69, 70, 71... | positive  |\n",
+      "| 6          | [5, 81, 3, 82, 83, 4, 84,... | neutral   |\n",
+      "+------------+------------------------------+-----------+\n"
+     ]
+    }
+   ],
+   "source": [
+    "vocab.index_dataset(dataset, field_name='Sentence')\n",
+    "print(dataset)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b26b707",
+   "metadata": {},
+   "source": [
+    "最后，使用相同方法，再将`dataset`中`Sentiment`字段中的`negative`、`neutral`、`positive`转化为数字编号"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
    "id": "5f5eed18",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'negative': 0, 'positive': 1, 'neutral': 2}\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "
\n",
+       "
\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+------------+------------------------------+-----------+\n",
+      "| SentenceId | Sentence                     | Sentiment |\n",
+      "+------------+------------------------------+-----------+\n",
+      "| 1          | [2, 14, 3, 15, 16, 5, 17,... | 0         |\n",
+      "| 2          | [12, 32, 4, 33, 8, 34, 35... | 1         |\n",
+      "| 3          | [38, 39, 3, 40, 41, 13, 4... | 0         |\n",
+      "| 4          | [2, 52, 53, 54, 3, 55, 8,... | 2         |\n",
+      "| 5          | [2, 67, 3, 68, 69, 70, 71... | 1         |\n",
+      "| 6          | [5, 81, 3, 82, 83, 4, 84,... | 2         |\n",
+      "+------------+------------------------------+-----------+\n"
+     ]
+    }
+   ],
+   "source": [
+    "target_vocab = Vocabulary(padding=None, unknown=None)\n",
+    "\n",
+    "target_vocab.from_dataset(dataset, field_name='Sentiment')\n",
+    "print(target_vocab.word2idx)\n",
+    "target_vocab.index_dataset(dataset, field_name='Sentiment')\n",
+    "print(dataset)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eed7ea64",
+   "metadata": {},
+   "source": [
+    "在最后的最后，通过以下的一张图，来总结本章关于`dataset`和`vocabulary`主要知识点的讲解，以及两者的联系\n",
+    "\n",
+    ""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35b4f0f7",
+   "metadata": {},
    "outputs": [],
    "source": []
   }
diff --git a/tutorials/fastnlp_tutorial_2.ipynb b/tutorials/fastnlp_tutorial_2.ipynb
new file mode 100644
index 00000000..260d5bf4
--- /dev/null
+++ b/tutorials/fastnlp_tutorial_2.ipynb
@@ -0,0 +1,41 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/tutorials/figures/T1-fig-dataset-and-vocabulary.png b/tutorials/figures/T1-fig-dataset-and-vocabulary.png
new file mode 100644
index 00000000..803cf34a
Binary files /dev/null and b/tutorials/figures/T1-fig-dataset-and-vocabulary.png differ