From 844a525ebeba9ced65803b6a3e7fb650918769c1 Mon Sep 17 00:00:00 2001 From: Fred Reiss Date: Thu, 1 Apr 2021 16:47:34 -0700 Subject: [PATCH] Prep for 0.1b3 release (#184) * Get tests working on Pandas 1.0.x * Re-enable Feather example in intro notebook * Rerun notebooks prior to release * Rerun tutorial notebooks prior to release * Update version number --- notebooks/Analyze_Text.ipynb | 2 +- notebooks/Integrate_NLP_Libraries.ipynb | 116 +++++++++--------- notebooks/Model_Training_with_BERT.ipynb | 14 +-- .../Text_Extensions_for_Pandas_Overview.ipynb | 94 +++++++++++--- notebooks/Understand_Tables.ipynb | 12 +- setup.py | 2 +- .../array/test_token_span.py | 11 +- tutorials/corpus/CoNLL_2.ipynb | 8 +- tutorials/corpus/CoNLL_3.ipynb | 28 ++--- tutorials/corpus/CoNLL_4.ipynb | 86 ++++++------- tutorials/corpus/CoNLL_View_Doc.ipynb | 6 +- 11 files changed, 216 insertions(+), 163 deletions(-) diff --git a/notebooks/Analyze_Text.ipynb b/notebooks/Analyze_Text.ipynb index 0480954e..e5b369b6 100644 --- a/notebooks/Analyze_Text.ipynb +++ b/notebooks/Analyze_Text.ipynb @@ -143,7 +143,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 3, diff --git a/notebooks/Integrate_NLP_Libraries.ipynb b/notebooks/Integrate_NLP_Libraries.ipynb index 4ba9e74d..326edca7 100644 --- a/notebooks/Integrate_NLP_Libraries.ipynb +++ b/notebooks/Integrate_NLP_Libraries.ipynb @@ -174,7 +174,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 4, @@ -3117,7 +3117,7 @@ { "data": { "text/html": [ - "\n", + "\n", "\n", " Galahad\n", " NNP\n", @@ -3299,225 +3299,225 @@ "\n", "\n", "\n", - " \n", + " \n", " \n", - " det\n", + " det\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " dobj\n", + " dobj\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " compound\n", + " compound\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " neg\n", + " neg\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " advmod\n", + " advmod\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " prep\n", + " prep\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " compound\n", + " compound\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " pobj\n", + " pobj\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " cc\n", + " cc\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " nmod\n", + " nmod\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " neg\n", + " neg\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " nmod\n", + " nmod\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " prep\n", + " prep\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " pobj\n", + " pobj\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " punct\n", + " punct\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " prep\n", + " prep\n", " \n", " \n", "\n", "\n", "\n", - " \n", + " \n", " \n", - " prep\n", + " prep\n", " \n", " \n", "\n", diff --git a/notebooks/Model_Training_with_BERT.ipynb b/notebooks/Model_Training_with_BERT.ipynb index 0c0b0df9..f9c49892 100644 --- a/notebooks/Model_Training_with_BERT.ipynb +++ b/notebooks/Model_Training_with_BERT.ipynb @@ -1643,7 +1643,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 13, @@ -1996,7 +1996,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "061593082c6e43f8bbbdab066a447502", + "model_id": "9e44a9af650543e59d81dfd8d5baa4ed", "version_major": 2, "version_minor": 0 }, @@ -2017,7 +2017,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "d2e59e90113648dfb0a929c90ff7d1fb", + "model_id": "acc0673fceae466f94cc16ccfbd67fdd", "version_major": 2, "version_minor": 0 }, @@ -2038,7 +2038,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "716b10c7c7a840048c1a780ff1723d84", + "model_id": "a0f64dff11304556ad22cd8df77954b7", "version_major": 2, "version_minor": 0 }, @@ -3183,8 +3183,8 @@ "output_type": "stream", "text": [ "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 9.1min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 9.1min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 11.9min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 11.9min finished\n" ] }, { @@ -5041,7 +5041,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "0a775ec7ee9f42ccb4367432d97f6958", + "model_id": "fde70dc5306b41f09a4844106b127aa1", "version_major": 2, "version_minor": 0 }, diff --git a/notebooks/Text_Extensions_for_Pandas_Overview.ipynb b/notebooks/Text_Extensions_for_Pandas_Overview.ipynb index 2bbc615a..2f02f02b 100644 --- a/notebooks/Text_Extensions_for_Pandas_Overview.ipynb +++ b/notebooks/Text_Extensions_for_Pandas_Overview.ipynb @@ -1522,7 +1522,7 @@ " [4, 5],\n", " [6, 7],\n", " [8, 9]]),\n", - " )" + " )" ] }, "execution_count": 22, @@ -1903,7 +1903,7 @@ "
\n", " 0\n", " [0, 2): 'In'\n", - " [0, 1, 0, 0]\n", + " [0, 0, 1, 0]\n", "
\n", "
\n", " 1\n", @@ -1918,12 +1918,12 @@ "
\n", " 3\n", " [11, 15): 'King'\n", - " [0, 0, 0, 1]\n", + " [0, 1, 0, 0]\n", "
\n", "
\n", " 4\n", " [16, 22): 'Arthur'\n", - " [0, 1, 0, 0]\n", + " [0, 0, 1, 0]\n", "
\n", " \n", "\n", @@ -1931,11 +1931,11 @@ ], "text/plain": [ " span features\n", - "0 [0, 2): 'In' [0, 1, 0, 0]\n", + "0 [0, 2): 'In' [0, 0, 1, 0]\n", "1 [3, 5): 'AD' [0, 1, 0, 0]\n", "2 [6, 9): '932' [0, 0, 0, 1]\n", - "3 [11, 15): 'King' [0, 0, 0, 1]\n", - "4 [16, 22): 'Arthur' [0, 1, 0, 0]" + "3 [11, 15): 'King' [0, 1, 0, 0]\n", + "4 [16, 22): 'Arthur' [0, 0, 1, 0]" ] }, "execution_count": 32, @@ -1958,22 +1958,88 @@ "# Save DataFrame to a feather file.\n", "# Feather is a lightweight, fast binary columnar format, with basic\n", "# compression and support built into Pandas.\n", - "\n", - "# TODO: Temporarily disabled while we revamp Feather support to handle multi-doc span arrays\n", - "#df.to_feather(\"outputs/tp_overview.feather\")" + "df.to_feather(\"outputs/tp_overview.feather\")" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, - "outputs": [], + "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", + "
spanfeatures
0[0, 2): 'In'[0, 0, 1, 0]
1[3, 5): 'AD'[0, 1, 0, 0]
2[6, 9): '932'[0, 0, 0, 1]
3[11, 15): 'King'[0, 1, 0, 0]
4[16, 22): 'Arthur'[0, 0, 1, 0]
\n", + "
" + ], + "text/plain": [ + " span features\n", + "0 [0, 2): 'In' [0, 0, 1, 0]\n", + "1 [3, 5): 'AD' [0, 1, 0, 0]\n", + "2 [6, 9): '932' [0, 0, 0, 1]\n", + "3 [11, 15): 'King' [0, 1, 0, 0]\n", + "4 [16, 22): 'Arthur' [0, 0, 1, 0]" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Read the file back into a new DataFrame.\n", "\n", - "# TODO: Temporarily disabled while we revamp Feather support to handle multi-doc span arrays\n", - "#df_load = pd.read_feather(\"outputs/tp_overview.feather\")\n", - "#df_load.head()" + "df_load = pd.read_feather(\"outputs/tp_overview.feather\")\n", + "df_load.head()" ] }, { diff --git a/notebooks/Understand_Tables.ipynb b/notebooks/Understand_Tables.ipynb index fb9c58f2..670b6970 100644 --- a/notebooks/Understand_Tables.ipynb +++ b/notebooks/Understand_Tables.ipynb @@ -4422,16 +4422,6 @@ "execution_count": 22, "metadata": {}, "outputs": [ - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 22, - "metadata": {}, - "output_type": "execute_result" - }, { "data": { "image/png": "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\n", @@ -4447,7 +4437,7 @@ ], "source": [ "plt.rcParams.update({'font.size': 16})\n", - "revenue_table.transpose().plot(title=\"Revenue by Geographic Region\",\n", + "_ = revenue_table.transpose().plot(title=\"Revenue by Geographic Region\",\n", " ylabel=\"Revenue (Millions of US$)\",\n", " figsize=(12, 7), ylim=(0, 50000))" ] diff --git a/setup.py b/setup.py index b46b20e5..fc8c63ee 100644 --- a/setup.py +++ b/setup.py @@ -24,7 +24,7 @@ setuptools.setup( name="text_extensions_for_pandas", - version="0.1b2", + version="0.1b3", author="IBM", author_email="frreiss@example.com", description="Natural language processing support for Pandas dataframes.", diff --git a/text_extensions_for_pandas/array/test_token_span.py b/text_extensions_for_pandas/array/test_token_span.py index 926393dc..613ebe0a 100644 --- a/text_extensions_for_pandas/array/test_token_span.py +++ b/text_extensions_for_pandas/array/test_token_span.py @@ -518,7 +518,8 @@ def data_for_grouping(dtype): return pd.array([b, b, na, na, a, a, b, c], dtype=dtype) -# Can't import due to dependencies, taken from pandas.conftest import all_compare_operators +# Can't import due to dependencies, taken +# from pandas.conftest import all_compare_operators @pytest.fixture(params=["__eq__", "__ne__", "__lt__", "__gt__", "__le__", "__ge__"]) def all_compare_operators(request): return request.param @@ -552,14 +553,10 @@ class TestPandasConstructors(base.BaseConstructorsTests): def test_series_constructor_no_data_with_index(self, dtype, na_value): pass + @pytest.mark.skipif(pd.__version__.startswith("1.0"), + reason="Test added in Pandas 1.1.0") def test_construct_empty_dataframe(self, dtype): super().test_construct_empty_dataframe(dtype) - # try: - # with pytest.raises(TypeError, match="Expected SpanArray as tokens"): - # super().test_construct_empty_dataframe(dtype) - # except AttributeError: - # # Test added in Pandas 1.1.0, ignore for earlier versions - # pass class TestPandasGetitem(base.BaseGetitemTests): diff --git a/tutorials/corpus/CoNLL_2.ipynb b/tutorials/corpus/CoNLL_2.ipynb index 5b6edf65..4310eb2c 100644 --- a/tutorials/corpus/CoNLL_2.ipynb +++ b/tutorials/corpus/CoNLL_2.ipynb @@ -3730,7 +3730,7 @@ "\n", "
\n", "
\n", + " style=\"color: var(--jp-layout-color2); border: 1px solid var(--jp-border-color0); float:left; padding:10px;\">\n", " \n", " \n", " \n", @@ -3899,11 +3899,11 @@ "
\n", "
\n", "
\n", + " style=\"float:right; border: 1px solid var(--jp-border-color0); width: 60%;\">\n", "\n", "
\n", - "

\n", - " -DOCSTART-
Belgian police smash major drugs rings, 30 arrested.
BRUSSELS 1996-12-06
Police smashed two drugs smuggling rings and arrested 30 people after a taxidriver in Spain alerted them to a suitcase of heroin left in his cab, Belgian police said on Friday.
Police seized dozens of kilos of heroin with a street value of hundreds of millions of Belgian francs, a public prosecutor's office spokesman in the port city of Antwerp said.
He said a 24-year-old Belgian woman left a suitcase containing 13 kg (29 lb) of heroin in a taxi in Barcelona.
The taxidriver alerted police who arrested a 33-year-old Turkish man when he came to pick up the suitcase at a lost luggage office.
The woman was later arrested in Belgium.
She and the Turkish man smuggled heroin from Turkey to Antwerp from where it was taken to Spain, France and Germany by others, the spokesman said.
He said 14 people were arrested in Belgium and 16 others in other European nations after an investigation lasting nearly a year.
($1=32.14 Belgian Franc)\n", + "

\n", + " -DOCSTART-
Belgian police smash major drugs rings, 30 arrested.
BRUSSELS 1996-12-06
Police smashed two drugs smuggling rings and arrested 30 people after a taxidriver in Spain alerted them to a suitcase of heroin left in his cab, Belgian police said on Friday.
Police seized dozens of kilos of heroin with a street value of hundreds of millions of Belgian francs, a public prosecutor's office spokesman in the port city of Antwerp said.
He said a 24-year-old Belgian woman left a suitcase containing 13 kg (29 lb) of heroin in a taxi in Barcelona.
The taxidriver alerted police who arrested a 33-year-old Turkish man when he came to pick up the suitcase at a lost luggage office.
The woman was later arrested in Belgium.
She and the Turkish man smuggled heroin from Turkey to Antwerp from where it was taken to Spain, France and Germany by others, the spokesman said.
He said 14 people were arrested in Belgium and 16 others in other European nations after an investigation lasting nearly a year.
($1=32.14 Belgian Franc)\n", "

\n", "
\n", "\n", diff --git a/tutorials/corpus/CoNLL_3.ipynb b/tutorials/corpus/CoNLL_3.ipynb index 6df6c02d..84c07c9b 100644 --- a/tutorials/corpus/CoNLL_3.ipynb +++ b/tutorials/corpus/CoNLL_3.ipynb @@ -1805,7 +1805,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "815b01606369445c892dedefbfd4916b", + "model_id": "0a612388df9249dab67efb5a4d358d5c", "version_major": 2, "version_minor": 0 }, @@ -1826,7 +1826,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "daa8e13738e2453c93e334d08b6d251b", + "model_id": "cae2fc8df4a44049be700f26f4f20e88", "version_major": 2, "version_minor": 0 }, @@ -1847,7 +1847,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "f5e610805fac4f44b706c223dc091820", + "model_id": "83c8f7f605eb4a55ab194aad964e947f", "version_major": 2, "version_minor": 0 }, @@ -3027,8 +3027,8 @@ "output_type": "stream", "text": [ "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.7min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.7min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 46.1min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 46.1min finished\n" ] }, { @@ -6006,7 +6006,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "49d7275934fe48f3a27017d92225844a", + "model_id": "af7f756dbfc2467c9cf525caa83b83eb", "version_major": 2, "version_minor": 0 }, @@ -6499,12 +6499,12 @@ { "data": { "text/plain": [ - "{'num_true_positives': 4169,\n", + "{'num_true_positives': 4329,\n", " 'num_entities': 5648,\n", - " 'num_extracted': 4929,\n", - " 'precision': 0.8458105092310814,\n", - " 'recall': 0.7381373937677054,\n", - " 'F1': 0.7883142668053323}" + " 'num_extracted': 5163,\n", + " 'precision': 0.8384660081348053,\n", + " 'recall': 0.7664660056657224,\n", + " 'F1': 0.8008509851077606}" ] }, "execution_count": 38, @@ -6965,7 +6965,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "571d376cdc19420d93df405970d42435", + "model_id": "63868a5aeb4e4847ba9b7df10e6d28b5", "version_major": 2, "version_minor": 0 }, @@ -8598,7 +8598,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "ab550997976f4d9b9ea777894d28fd12", + "model_id": "13b1edab9e1241ccb22166e9c0c8ca40", "version_major": 2, "version_minor": 0 }, @@ -10072,7 +10072,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "bd25f50dd1aa4bed9c9fc148b87603b5", + "model_id": "7110dc85e13145a2a9ab455aaa167948", "version_major": 2, "version_minor": 0 }, diff --git a/tutorials/corpus/CoNLL_4.ipynb b/tutorials/corpus/CoNLL_4.ipynb index 293b49ae..b57fddeb 100644 --- a/tutorials/corpus/CoNLL_4.ipynb +++ b/tutorials/corpus/CoNLL_4.ipynb @@ -162,7 +162,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "9e2771255af24c3fa802e5cf515b8945", + "model_id": "37f2c69bf2c840d99f1ee2a72a303c63", "version_major": 2, "version_minor": 0 }, @@ -183,7 +183,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "9bc9aba493ef4c4892f63f9115fb26d8", + "model_id": "353b9733093a470cacfe9806c1712640", "version_major": 2, "version_minor": 0 }, @@ -197,7 +197,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "9bbe18beaff245efa74fb345d1196b9a", + "model_id": "71f3932d55c9496a836c4e591657c676", "version_major": 2, "version_minor": 0 }, @@ -1258,8 +1258,8 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.3min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.3min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.7min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.7min finished\n" ] } ], @@ -1363,7 +1363,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "1b07971e26824ba5832ad8ee6a1ede8b", + "model_id": "a11e552d71084e2fb7ab4e9bd1679a36", "version_major": 2, "version_minor": 0 }, @@ -1477,7 +1477,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "cb4aabe72b644dcba8f41ce729564299", + "model_id": "72962b08c276470db9fdf0658d87de29", "version_major": 2, "version_minor": 0 }, @@ -2957,14 +2957,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.8min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.8min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 49.5min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 49.5min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "7c0d06308d8042b38eb71631ff02bddb", + "model_id": "0be91ca7db4840af9d88956de9956403", "version_major": 2, "version_minor": 0 }, @@ -2978,7 +2978,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "4327d4744cad46dd9b33b12596e374ac", + "model_id": "c66bbf2ba8954a1dbaa7d2d343fa6221", "version_major": 2, "version_minor": 0 }, @@ -3048,14 +3048,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 39.1min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 39.1min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.2min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.2min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "734b6288f9dc4b9d8c20495837e29915", + "model_id": "f0e27dfbf23a46319e150ba0474ec9ca", "version_major": 2, "version_minor": 0 }, @@ -3069,7 +3069,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "4dfaa624fb5847b9b6f4d6b261beebbd", + "model_id": "a2879d412b944ad39f2f76c061101b1b", "version_major": 2, "version_minor": 0 }, @@ -3139,14 +3139,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.9min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.9min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.6min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.6min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "89697e27c4c54cd38d3a1d210277c357", + "model_id": "104c208aeb3a4631a375a14738aeae24", "version_major": 2, "version_minor": 0 }, @@ -3160,7 +3160,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "0c1f123bd933477dabfaa1fbfaf20d52", + "model_id": "7f8988491a6144d3aed3c22e60048567", "version_major": 2, "version_minor": 0 }, @@ -3230,14 +3230,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 45.2min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 45.2min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 45.7min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 45.7min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "e90dca1c2024493fbbfed0b7e5eb498e", + "model_id": "3b4b80ae9d554a6eacb95f689161e35d", "version_major": 2, "version_minor": 0 }, @@ -3251,7 +3251,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "c990f106c5b54beabf58009cbab55bc4", + "model_id": "239a178f68fd46728b0d7c78cc9b030d", "version_major": 2, "version_minor": 0 }, @@ -3321,14 +3321,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 34.8min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 34.8min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 34.4min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 34.4min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "39b9c08de3a044eaa84bd48fbc0b0803", + "model_id": "44d4586ec0844d0da6a6e6b098248e09", "version_major": 2, "version_minor": 0 }, @@ -3342,7 +3342,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "32bcea8144994c68a21f7dc38edf5417", + "model_id": "84fafaf171604715946f187f93ee2316", "version_major": 2, "version_minor": 0 }, @@ -3412,14 +3412,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.0min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.0min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.4min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.4min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "e8f6b61485ee4c4ebe06076f7486d5fc", + "model_id": "9a01299ad6104771941c6096b8a3487f", "version_major": 2, "version_minor": 0 }, @@ -3433,7 +3433,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "3b7d9213ae7443a0897edf0af8013ba1", + "model_id": "f55dcc6b01d04f3b99cbc22afaa5186e", "version_major": 2, "version_minor": 0 }, @@ -3503,14 +3503,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.2min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.2min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.5min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 42.5min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "4a41b657f1ba4d4bab8c2227285a88c9", + "model_id": "3d2be6188a874dfdb550d1861e8afea8", "version_major": 2, "version_minor": 0 }, @@ -3524,7 +3524,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "5a6fb1961ec94739a4df5ea9e8ef654d", + "model_id": "c193f2b621674c4dab710bd6b7446943", "version_major": 2, "version_minor": 0 }, @@ -3594,14 +3594,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.5min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 47.5min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 50.9min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 50.9min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "86d6a8dda95c44f08e13dfa30acc2e52", + "model_id": "7e31ca3ed3c948c8b954d2332c75783f", "version_major": 2, "version_minor": 0 }, @@ -3615,7 +3615,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "779c4b254c574ce5b947451ee427bcdd", + "model_id": "f68b2d0fa7b64ee2870067640f5331d6", "version_major": 2, "version_minor": 0 }, @@ -3685,14 +3685,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.1min remaining: 0.0s\n", - "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 41.1min finished\n" + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.4min remaining: 0.0s\n", + "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 44.4min finished\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "c3f777face614588a8d9d82e73f73c8e", + "model_id": "f6bbf0a66849456d9190dadf100da73f", "version_major": 2, "version_minor": 0 }, @@ -3706,7 +3706,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "d261c6fdc22c454db9218830a19d3f82", + "model_id": "9b0bda6a0bbf473391b7c01446720e6b", "version_major": 2, "version_minor": 0 }, diff --git a/tutorials/corpus/CoNLL_View_Doc.ipynb b/tutorials/corpus/CoNLL_View_Doc.ipynb index 30e18e38..78fb5776 100644 --- a/tutorials/corpus/CoNLL_View_Doc.ipynb +++ b/tutorials/corpus/CoNLL_View_Doc.ipynb @@ -382,11 +382,11 @@ "text/html": [ "\n", "
\n", + " style=\"float:right; color: var(--jp-layout-color2); border: 1px solid var(--jp-border-color0); width: 100%;\">\n", "\n", "
\n", - "

\n", - " -DOCSTART-
MOTORCYCLING- SAN MARINO GRAND PRIX PRACTICE TIMES.
IMOLA, Italy 1996-08-30
Practice times set on Friday
for Sunday's San Marino 500cc motorcycling Grand Prix:
1. Michael Doohan (Australia) Honda one minute 50.250
2. Jean-Michel Bayle (France) Yamaha 1:50.727
3. Norifumi Abe (Japan) Yamaha 1:50.858
4. Luca Cadalora (Italy) Honda 1:51.006
5. Alex Criville (Spain) Honda 1:51.075
6. Scott Russell (United States) Suzuki 1:51.287
7. Tadayuki Okada (Japan) Honda 1:51.528
8. Carlos Checa (Spain) Honda 1:51.588
9. Alexandre Barros (Brazil) Honda 1:51.784
10. Shinichi Itoh (Japan) Honda 1:51.857\n", + "

\n", + " -DOCSTART-
MOTORCYCLING- SAN MARINO GRAND PRIX PRACTICE TIMES.
IMOLA, Italy 1996-08-30
Practice times set on Friday
for Sunday's San Marino 500cc motorcycling Grand Prix:
1. Michael Doohan (Australia) Honda one minute 50.250
2. Jean-Michel Bayle (France) Yamaha 1:50.727
3. Norifumi Abe (Japan) Yamaha 1:50.858
4. Luca Cadalora (Italy) Honda 1:51.006
5. Alex Criville (Spain) Honda 1:51.075
6. Scott Russell (United States) Suzuki 1:51.287
7. Tadayuki Okada (Japan) Honda 1:51.528
8. Carlos Checa (Spain) Honda 1:51.588
9. Alexandre Barros (Brazil) Honda 1:51.784
10. Shinichi Itoh (Japan) Honda 1:51.857\n", "

\n", "
\n", "\n",