henry/paraphrase_detector
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add jupyter to requirments

Browse Source
This commit is contained in:
Henry Dowd
2025-11-23 14:48:13 +00:00
parent 5a38131e9a
commit fb68bc869a
2 changed files with 90 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

453
notebooks/01_data_exploration.ipynb
View File

@@ -1,19 +1,22 @@
{ {
"cells": [ "cells": [
{ {
"metadata": {},
"cell_type": "markdown", "cell_type": "markdown",
"source": "Import Cell\n", "id": "dd72d1539056a64",
"id": "dd72d1539056a64" "metadata": {},
"source": [
"Import Cell\n"
]
}, },
{ {
"cell_type": "code",
"id": "12579bf734bb1a92",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-11-21T17:01:35.974978Z", "end_time": "2025-11-23T13:53:57.753560Z",
"start_time": "2025-11-21T17:01:34.412508Z" "start_time": "2025-11-23T13:53:56.325948Z"
} }
}, },
"cell_type": "code",
"source": [ "source": [
"import token\n", "import token\n",
"import spacy\n", "import spacy\n",
@@ -28,24 +31,26 @@
" \"A completely different sentence about something else.\"\n", " \"A completely different sentence about something else.\"\n",
"]" "]"
], ],
"id": "12579bf734bb1a92",
"outputs": [], "outputs": [],
"execution_count": 21 "execution_count": 1
}, },
{ {
"metadata": {},
"cell_type": "markdown", "cell_type": "markdown",
"source": "Keep punctuation for direct copy detection but remove for semantic/keyword based methods", "id": "1c26616777253f10",
"id": "1c26616777253f10" "metadata": {},
"source": [
"Keep punctuation for direct copy detection but remove for semantic/keyword based methods"
]
}, },
{ {
"cell_type": "code",
"id": "e003ac06a58cfbb4",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-11-20T19:03:29.658876Z", "end_time": "2025-11-23T13:54:12.922343Z",
"start_time": "2025-11-20T19:03:27.809309Z" "start_time": "2025-11-23T13:54:12.896440Z"
} }
}, },
"cell_type": "code",
"source": [ "source": [
"\n", "\n",
"for sent in test_sentences:\n", "for sent in test_sentences:\n",
@@ -54,7 +59,6 @@
" print(f\"Tokens: {[token.text for token in doc]}\")\n", " print(f\"Tokens: {[token.text for token in doc]}\")\n",
" print(\"---\")\n" " print(\"---\")\n"
], ],
"id": "e003ac06a58cfbb4",
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@@ -72,16 +76,17 @@
] ]
} }
], ],
"execution_count": 17 "execution_count": 2
}, },
{ {
"cell_type": "code",
"id": "5e488a878a5cfccb",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-11-21T23:26:23.172796Z", "end_time": "2025-11-23T13:55:23.734853Z",
"start_time": "2025-11-21T23:26:21.541542Z" "start_time": "2025-11-23T13:55:22.744266Z"
} }
}, },
"cell_type": "code",
"source": [ "source": [
"\n", "\n",
"class TextPreprocessor:\n", "class TextPreprocessor:\n",
@@ -153,7 +158,6 @@
"# print(f\"Preprocessed Sentence: {preprocessor.syntactic_analysis(sent)}\")\n", "# print(f\"Preprocessed Sentence: {preprocessor.syntactic_analysis(sent)}\")\n",
"# print(\"-\" * 50)" "# print(\"-\" * 50)"
], ],
"id": "5e488a878a5cfccb",
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@@ -187,16 +191,17 @@
] ]
} }
], ],
"execution_count": 37 "execution_count": 3
}, },
{ {
"cell_type": "code",
"id": "83fc18c9de2e354",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-11-21T23:39:48.443022Z", "end_time": "2025-11-23T13:55:33.587912Z",
"start_time": "2025-11-21T23:39:48.411766Z" "start_time": "2025-11-23T13:55:33.565711Z"
} }
}, },
"cell_type": "code",
"source": [ "source": [
"\n", "\n",
"def extract_parse_tree(text):\n", "def extract_parse_tree(text):\n",
@@ -215,7 +220,6 @@
" doc = extract_parse_tree(sentence)\n", " doc = extract_parse_tree(sentence)\n",
" print(\"\\n\" + \"=\"*60 + \"\\n\")" " print(\"\\n\" + \"=\"*60 + \"\\n\")"
], ],
"id": "83fc18c9de2e354",
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@@ -269,22 +273,25 @@
] ]
} }
], ],
"execution_count": 39 "execution_count": 4
}, },
{ {
"metadata": {},
"cell_type": "markdown", "cell_type": "markdown",
"source": "***USE NetworkX", "id": "5b5c8742d7c4c4c5",
"id": "5b5c8742d7c4c4c5" "metadata": {},
"source": [
"***USE NetworkX"
]
}, },
{ {
"cell_type": "code",
"id": "e413238c1af12f62",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
"end_time": "2025-11-21T18:20:09.575176Z", "end_time": "2025-11-23T13:56:21.733459Z",
"start_time": "2025-11-21T18:20:09.465504Z" "start_time": "2025-11-23T13:56:21.702279Z"
} }
}, },
"cell_type": "code",
"source": [ "source": [
"\n", "\n",
"\n", "\n",
@@ -295,21 +302,18 @@
"\n", "\n",
"\n", "\n",
"\n", "\n",
"for sentence in test_sentences:\n", "for sentence in processed_syntactic:\n",
" print(f\"Sentence: {sentence}\")\n", " print(f\"Sentence: {sentence}\")\n",
" print(\"---\")\n", " print(\"---\")\n",
" processed_sentence = preprocessor.syntactic_analysis(sentence)\n", " print(f\"Processed Sentence: \" + sentence)\n",
" print(f\"Processed Sentence: \" + processed_sentence)\n",
" visualize_parse_tree(processed_sentence)\n",
" visualize_parse_tree(sentence)" " visualize_parse_tree(sentence)"
], ],
"id": "e413238c1af12f62",
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Sentence: The cat sat on the mat.\n", "Sentence: the cat sit on the mat .\n",
"---\n", "---\n",
"Processed Sentence: the cat sit on the mat .\n" "Processed Sentence: the cat sit on the mat .\n"
] ]
@@ -320,7 +324,7 @@
"<IPython.core.display.HTML object>" "<IPython.core.display.HTML object>"
], ],
"text/html": [ "text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"cbdcc1a7b2c3434da049b33ce22ba9dc-0\" class=\"displacy\" width=\"650\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n", "<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"4ec65c2317524f6dab93c3963fcc5973-0\" class=\"displacy\" width=\"650\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n", "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">the</tspan>\n", " <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">the</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n", " <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n",
@@ -352,126 +356,41 @@
"</text>\n", "</text>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,52.0 145.0,52.0 145.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-4ec65c2317524f6dab93c3963fcc5973-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,52.0 145.0,52.0 145.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n", " <textPath xlink:href=\"#arrow-4ec65c2317524f6dab93c3963fcc5973-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-4ec65c2317524f6dab93c3963fcc5973-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n", " <textPath xlink:href=\"#arrow-4ec65c2317524f6dab93c3963fcc5973-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-4ec65c2317524f6dab93c3963fcc5973-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n", " <textPath xlink:href=\"#arrow-4ec65c2317524f6dab93c3963fcc5973-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M345.0,104.0 L353.0,92.0 337.0,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M345.0,104.0 L353.0,92.0 337.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-3\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-4ec65c2317524f6dab93c3963fcc5973-0-3\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n", " <textPath xlink:href=\"#arrow-4ec65c2317524f6dab93c3963fcc5973-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M470,104.0 L462,92.0 478,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M470,104.0 L462,92.0 478,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-4\" stroke-width=\"2px\" d=\"M370,102.0 C370,2.0 550.0,2.0 550.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-4ec65c2317524f6dab93c3963fcc5973-0-4\" stroke-width=\"2px\" d=\"M370,102.0 C370,2.0 550.0,2.0 550.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-cbdcc1a7b2c3434da049b33ce22ba9dc-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n", " <textPath xlink:href=\"#arrow-4ec65c2317524f6dab93c3963fcc5973-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M550.0,104.0 L558.0,92.0 542.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"</svg>"
]
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"03663f6b8c874937b96eb1c0bf766ed5-0\" class=\"displacy\" width=\"650\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">The</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"150\">cat</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"150\">NOUN</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"250\">sat</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"250\">VERB</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"350\">on</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"350\">ADP</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"450\">the</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"450\">DET</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"550\">mat.</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"550\">NOUN</tspan>\n",
"</text>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-03663f6b8c874937b96eb1c0bf766ed5-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,52.0 145.0,52.0 145.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-03663f6b8c874937b96eb1c0bf766ed5-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-03663f6b8c874937b96eb1c0bf766ed5-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-03663f6b8c874937b96eb1c0bf766ed5-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-03663f6b8c874937b96eb1c0bf766ed5-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-03663f6b8c874937b96eb1c0bf766ed5-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M345.0,104.0 L353.0,92.0 337.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-03663f6b8c874937b96eb1c0bf766ed5-0-3\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-03663f6b8c874937b96eb1c0bf766ed5-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M470,104.0 L462,92.0 478,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-03663f6b8c874937b96eb1c0bf766ed5-0-4\" stroke-width=\"2px\" d=\"M370,102.0 C370,2.0 550.0,2.0 550.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-03663f6b8c874937b96eb1c0bf766ed5-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M550.0,104.0 L558.0,92.0 542.0,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M550.0,104.0 L558.0,92.0 542.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
@@ -488,7 +407,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Sentence: On the mat, the cat was sitting.\n", "Sentence: on the mat , the cat be sit .\n",
"---\n", "---\n",
"Processed Sentence: on the mat , the cat be sit .\n" "Processed Sentence: on the mat , the cat be sit .\n"
] ]
@@ -499,7 +418,7 @@
"<IPython.core.display.HTML object>" "<IPython.core.display.HTML object>"
], ],
"text/html": [ "text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"c413fa0318d04c93b9c3ffea0645caff-0\" class=\"displacy\" width=\"750\" height=\"287.0\" direction=\"ltr\" style=\"max-width: none; height: 287.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n", "<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"239d41ebf05341878765b3474355df7c-0\" class=\"displacy\" width=\"750\" height=\"287.0\" direction=\"ltr\" style=\"max-width: none; height: 287.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n", "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">on</tspan>\n", " <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">on</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">ADP</tspan>\n", " <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">ADP</tspan>\n",
@@ -536,147 +455,49 @@
"</text>\n", "</text>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-0\" stroke-width=\"2px\" d=\"M70,152.0 C70,2.0 650.0,2.0 650.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-0\" stroke-width=\"2px\" d=\"M70,152.0 C70,2.0 650.0,2.0 650.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,154.0 L62,142.0 78,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M70,154.0 L62,142.0 78,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-1\" stroke-width=\"2px\" d=\"M170,152.0 C170,102.0 240.0,102.0 240.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-1\" stroke-width=\"2px\" d=\"M170,152.0 C170,102.0 240.0,102.0 240.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,154.0 L162,142.0 178,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M170,154.0 L162,142.0 178,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-2\" stroke-width=\"2px\" d=\"M70,152.0 C70,52.0 245.0,52.0 245.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-2\" stroke-width=\"2px\" d=\"M70,152.0 C70,52.0 245.0,52.0 245.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M245.0,154.0 L253.0,142.0 237.0,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M245.0,154.0 L253.0,142.0 237.0,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-3\" stroke-width=\"2px\" d=\"M370,152.0 C370,102.0 440.0,102.0 440.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-3\" stroke-width=\"2px\" d=\"M370,152.0 C370,102.0 440.0,102.0 440.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M370,154.0 L362,142.0 378,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M370,154.0 L362,142.0 378,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-4\" stroke-width=\"2px\" d=\"M470,152.0 C470,52.0 645.0,52.0 645.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-4\" stroke-width=\"2px\" d=\"M470,152.0 C470,52.0 645.0,52.0 645.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M470,154.0 L462,142.0 478,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M470,154.0 L462,142.0 478,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-c413fa0318d04c93b9c3ffea0645caff-0-5\" stroke-width=\"2px\" d=\"M570,152.0 C570,102.0 640.0,102.0 640.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-239d41ebf05341878765b3474355df7c-0-5\" stroke-width=\"2px\" d=\"M570,152.0 C570,102.0 640.0,102.0 640.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-c413fa0318d04c93b9c3ffea0645caff-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">aux</textPath>\n", " <textPath xlink:href=\"#arrow-239d41ebf05341878765b3474355df7c-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">aux</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M570,154.0 L562,142.0 578,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"</svg>"
]
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"0a7ff36b205d4165a3261fa3265e8c53-0\" class=\"displacy\" width=\"750\" height=\"287.0\" direction=\"ltr\" style=\"max-width: none; height: 287.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">On</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">ADP</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"150\">the</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"150\">DET</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"250\">mat,</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"250\">NOUN</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"350\">the</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"350\">DET</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"450\">cat</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"450\">NOUN</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"550\">was</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"550\">AUX</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"197.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"650\">sitting.</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"650\">VERB</tspan>\n",
"</text>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-0\" stroke-width=\"2px\" d=\"M70,152.0 C70,2.0 650.0,2.0 650.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,154.0 L62,142.0 78,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-1\" stroke-width=\"2px\" d=\"M170,152.0 C170,102.0 240.0,102.0 240.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,154.0 L162,142.0 178,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-2\" stroke-width=\"2px\" d=\"M70,152.0 C70,52.0 245.0,52.0 245.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M245.0,154.0 L253.0,142.0 237.0,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-3\" stroke-width=\"2px\" d=\"M370,152.0 C370,102.0 440.0,102.0 440.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M370,154.0 L362,142.0 378,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-4\" stroke-width=\"2px\" d=\"M470,152.0 C470,52.0 645.0,52.0 645.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M470,154.0 L462,142.0 478,142.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-0a7ff36b205d4165a3261fa3265e8c53-0-5\" stroke-width=\"2px\" d=\"M570,152.0 C570,102.0 640.0,102.0 640.0,152.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-0a7ff36b205d4165a3261fa3265e8c53-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">aux</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M570,154.0 L562,142.0 578,142.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M570,154.0 L562,142.0 578,142.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
@@ -693,7 +514,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Sentence: A completely different sentence about something else.\n", "Sentence: a completely different sentence about something else .\n",
"---\n", "---\n",
"Processed Sentence: a completely different sentence about something else .\n" "Processed Sentence: a completely different sentence about something else .\n"
] ]
@@ -704,7 +525,7 @@
"<IPython.core.display.HTML object>" "<IPython.core.display.HTML object>"
], ],
"text/html": [ "text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"358275480b4d4b099e836e8136c5b023-0\" class=\"displacy\" width=\"750\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n", "<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"645c3d0343ff46cfb12d7ba372193893-0\" class=\"displacy\" width=\"750\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n", "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">a</tspan>\n", " <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">a</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n", " <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n",
@@ -741,147 +562,49 @@
"</text>\n", "</text>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,2.0 350.0,2.0 350.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,2.0 350.0,2.0 350.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">amod</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">amod</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M270,104.0 L262,92.0 278,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M270,104.0 L262,92.0 278,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-3\" stroke-width=\"2px\" d=\"M370,102.0 C370,52.0 445.0,52.0 445.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-3\" stroke-width=\"2px\" d=\"M370,102.0 C370,52.0 445.0,52.0 445.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M445.0,104.0 L453.0,92.0 437.0,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M445.0,104.0 L453.0,92.0 437.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-4\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-4\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M545.0,104.0 L553.0,92.0 537.0,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M545.0,104.0 L553.0,92.0 537.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
"\n", "\n",
"<g class=\"displacy-arrow\">\n", "<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-358275480b4d4b099e836e8136c5b023-0-5\" stroke-width=\"2px\" d=\"M570,102.0 C570,52.0 645.0,52.0 645.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n", " <path class=\"displacy-arc\" id=\"arrow-645c3d0343ff46cfb12d7ba372193893-0-5\" stroke-width=\"2px\" d=\"M570,102.0 C570,52.0 645.0,52.0 645.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n", " <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-358275480b4d4b099e836e8136c5b023-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n", " <textPath xlink:href=\"#arrow-645c3d0343ff46cfb12d7ba372193893-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M645.0,104.0 L653.0,92.0 637.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"</svg>"
]
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"bc8c620b992c40b5b591d785f5e540a4-0\" class=\"displacy\" width=\"750\" height=\"237.0\" direction=\"ltr\" style=\"max-width: none; height: 237.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">A</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">DET</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"150\">completely</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"150\">ADV</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"250\">different</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"250\">ADJ</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"350\">sentence</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"350\">NOUN</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"450\">about</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"450\">ADP</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"550\">something</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"550\">PRON</tspan>\n",
"</text>\n",
"\n",
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"147.0\">\n",
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"650\">else.</tspan>\n",
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"650\">ADV</tspan>\n",
"</text>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-0\" stroke-width=\"2px\" d=\"M70,102.0 C70,2.0 350.0,2.0 350.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M70,104.0 L62,92.0 78,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-1\" stroke-width=\"2px\" d=\"M170,102.0 C170,52.0 245.0,52.0 245.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M170,104.0 L162,92.0 178,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-2\" stroke-width=\"2px\" d=\"M270,102.0 C270,52.0 345.0,52.0 345.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">amod</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M270,104.0 L262,92.0 278,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-3\" stroke-width=\"2px\" d=\"M370,102.0 C370,52.0 445.0,52.0 445.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">prep</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M445.0,104.0 L453.0,92.0 437.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-4\" stroke-width=\"2px\" d=\"M470,102.0 C470,52.0 545.0,52.0 545.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pobj</textPath>\n",
" </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M545.0,104.0 L553.0,92.0 537.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n",
"\n",
"<g class=\"displacy-arrow\">\n",
" <path class=\"displacy-arc\" id=\"arrow-bc8c620b992c40b5b591d785f5e540a4-0-5\" stroke-width=\"2px\" d=\"M570,102.0 C570,52.0 645.0,52.0 645.0,102.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
" <textPath xlink:href=\"#arrow-bc8c620b992c40b5b591d785f5e540a4-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
" </text>\n", " </text>\n",
" <path class=\"displacy-arrowhead\" d=\"M645.0,104.0 L653.0,92.0 637.0,92.0\" fill=\"currentColor\"/>\n", " <path class=\"displacy-arrowhead\" d=\"M645.0,104.0 L653.0,92.0 637.0,92.0\" fill=\"currentColor\"/>\n",
"</g>\n", "</g>\n",
@@ -895,22 +618,22 @@
} }
} }
], ],
"execution_count": 32 "execution_count": 6
}, },
{ {
"metadata": {},
"cell_type": "code", "cell_type": "code",
"outputs": [],
"execution_count": null, "execution_count": null,
"source": "", "id": "6aff51eb71eb2238",
"id": "6aff51eb71eb2238" "metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"name": "python3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"display_name": "Python 3 (ipykernel)" "name": "python3"
} }
}, },
"nbformat": 4, "nbformat": 4,

3
requirments.txt
View File

@@ -5,4 +5,5 @@ numpy
scikit-learn scikit-learn
spacy spacy
matplotlib matplotlib
seaborn seaborn
jupyter