Skip to content

Fix for documentation examples #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
OBrink wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fix for documentation examples #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a43802a
fix table parser example
OBrink May 23, 2023
ed3ceff
add missing import statements in documentation
OBrink May 23, 2023
e62d53c
fix all examples in table parser notebook
OBrink May 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/introduction/finding_records.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@ and then merges data together from every element in the document to produce a si
Consider this simple document as an example::

>>> from chemdataextractor.doc import Document, Heading, Paragraph
>>> from chemdataextractor.model import Compound, MeltingPoint
>>> doc = Document(
Heading('5,10,15,20-Tetra(4-carboxyphenyl)porphyrin (3).'),
Paragraph('m.p. 90°C.'),
Expand Down
85 changes: 58 additions & 27 deletions examples/automatic_parsing_for_tables.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,22 +20,22 @@
"name": "stdout",
"output_type": "stream",
"text": [
"+--------+--------------------------+------------------------------+\n",
"| Data | Row Categories | Column Categories |\n",
"+--------+--------------------------+------------------------------+\n",
"| 1100 | ['Inorganic', 'BiFeO3'] | ['Temperatures', 'Tc/K'] |\n",
"| 643 | ['Inorganic', 'BiFeO3'] | ['Temperatures', 'Tn/K'] |\n",
"| | ['Inorganic', 'BiFeO3'] | ['Magnetic moment', 'B [T]'] |\n",
"| 257 | ['Inorganic', ' LaCrO3'] | ['Temperatures', 'Tc/K'] |\n",
"| 150 | ['Inorganic', ' LaCrO3'] | ['Temperatures', 'Tn/K'] |\n",
"| 0.1 mT | ['Inorganic', ' LaCrO3'] | ['Magnetic moment', 'B [T]'] |\n",
"| | ['Organic', 'LaCrO2'] | ['Temperatures', 'Tc/K'] |\n",
"| 10 | ['Organic', 'LaCrO2'] | ['Temperatures', 'Tn/K'] |\n",
"| 500 | ['Organic', 'LaCrO2'] | ['Magnetic moment', 'B [T]'] |\n",
"| | ['Inorganic', 'Gd'] | ['Temperatures', 'Tc/K'] |\n",
"| 294 | ['Inorganic', 'Gd'] | ['Temperatures', 'Tn/K'] |\n",
"| 659 T | ['Inorganic', 'Gd'] | ['Magnetic moment', 'B [T]'] |\n",
"+--------+--------------------------+------------------------------+\n"
"+---------+--------------------------+------------------------------+\n",
"| Data | Row Categories | Column Categories |\n",
"+---------+--------------------------+------------------------------+\n",
"| 1100 | ['Inorganic', 'BiFeO3'] | ['Temperatures', 'Tc/K'] |\n",
"| 643 | ['Inorganic', 'BiFeO3'] | ['Temperatures', 'Tn/K'] |\n",
"| NoValue | ['Inorganic', 'BiFeO3'] | ['Magnetic moment', 'B [T]'] |\n",
"| 257 | ['Inorganic', ' LaCrO3'] | ['Temperatures', 'Tc/K'] |\n",
"| 150 | ['Inorganic', ' LaCrO3'] | ['Temperatures', 'Tn/K'] |\n",
"| 0.1 mT | ['Inorganic', ' LaCrO3'] | ['Magnetic moment', 'B [T]'] |\n",
"| NoValue | ['Organic', 'LaCrO2'] | ['Temperatures', 'Tc/K'] |\n",
"| 10 | ['Organic', 'LaCrO2'] | ['Temperatures', 'Tn/K'] |\n",
"| 500 | ['Organic', 'LaCrO2'] | ['Magnetic moment', 'B [T]'] |\n",
"| NoValue | ['Inorganic', 'Gd'] | ['Temperatures', 'Tc/K'] |\n",
"| 294 | ['Inorganic', 'Gd'] | ['Temperatures', 'Tn/K'] |\n",
"| 659 T | ['Inorganic', 'Gd'] | ['Magnetic moment', 'B [T]'] |\n",
"+---------+--------------------------+------------------------------+\n"
]
},
{
Expand All @@ -53,7 +53,7 @@
"from chemdataextractor.doc.table import Table\n",
"from chemdataextractor.doc import Caption\n",
"\n",
"path = \"./example_tables/table_example_tkt_2.csv\"\n",
"path = \"./data/table_example.csv\"\n",
"table = Table(caption=Caption(\"\"),table_data=path)\n",
"\n",
"print(table.tde_table)\n",
Expand Down Expand Up @@ -104,15 +104,25 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Initialising AllenNLP model ✔ \n",
"{'Compound': {'names': ['BiFeO3']}}\n",
"{'Compound': {'names': ['LaCrO3']}}\n",
"{'Compound': {'names': ['LaCrO2']}}\n",
"{'Compound': {'names': ['Gd']}}\n",
"{'CurieTemperature': {'raw_value': '1100', 'raw_units': 'K', 'value': [1100.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['BiFeO3']}}}}\n",
"{'CurieTemperature': {'raw_value': '643', 'value': [643.0], 'compound': {'Compound': {'names': ['BiFeO3']}}}}\n",
"{'CurieTemperature': {'raw_value': '257', 'raw_units': 'K', 'value': [257.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO3']}}}}\n",
"{'CurieTemperature': {'raw_value': '150', 'value': [150.0], 'compound': {'Compound': {'names': ['LaCrO3']}}}}\n",
"{'CurieTemperature': {'raw_value': '0.1', 'value': [0.1], 'compound': {'Compound': {'names': ['LaCrO3']}}}}\n",
"{'CurieTemperature': {'raw_value': '10', 'raw_units': 'K', 'value': [10.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO2']}}}}\n",
"{'CurieTemperature': {'raw_value': '294', 'raw_units': 'K', 'value': [294.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['Gd']}}}}\n"
"{'CurieTemperature': {'raw_value': '500', 'raw_units': 'K', 'value': [500.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO2']}}}}\n",
"{'CurieTemperature': {'raw_value': '294', 'raw_units': 'K', 'value': [294.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['Gd']}}}}\n",
"{'CurieTemperature': {'raw_value': '659', 'raw_units': 'K', 'value': [659.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['Gd']}}}}\n"
]
}
],
"source": [
"table.models = [CurieTemperature]\n",
"table = Table(caption=Caption(\"\"),table_data=path, models=[CurieTemperature])\n",
"for record in table.records:\n",
" print(record.serialize())"
]
Expand All @@ -130,16 +140,26 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'Compound': {'names': ['BiFeO3']}}\n",
"{'Compound': {'names': ['LaCrO3']}}\n",
"{'Compound': {'names': ['LaCrO2']}}\n",
"{'Compound': {'names': ['Gd']}}\n",
"{'CurieTemperature': {'raw_value': '1100', 'raw_units': 'K', 'value': [1100.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['BiFeO3']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '643', 'value': [643.0], 'compound': {'Compound': {'names': ['BiFeO3']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '257', 'raw_units': 'K', 'value': [257.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO3']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '10', 'raw_units': 'K', 'value': [10.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO2']}}}}\n"
"{'CurieTemperature': {'raw_value': '150', 'value': [150.0], 'compound': {'Compound': {'names': ['LaCrO3']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '0.1', 'value': [0.1], 'compound': {'Compound': {'names': ['LaCrO3']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '10', 'raw_units': 'K', 'value': [10.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO2']}}}}\n",
"{'CurieTemperature': {'raw_value': '500', 'raw_units': 'K', 'value': [500.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['LaCrO2']}}}}\n",
"{'CurieTemperature': {'raw_value': '294', 'raw_units': 'K', 'value': [294.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['Gd']}}, 'label': 'Inorganic'}}\n",
"{'CurieTemperature': {'raw_value': '659', 'raw_units': 'K', 'value': [659.0], 'units': 'Kelvin^(1.0)', 'specifier': 'Tc', 'compound': {'Compound': {'names': ['Gd']}}, 'label': 'Inorganic'}}\n"
]
}
],
Expand All @@ -150,24 +170,35 @@
" compound = ModelType(Compound, required=True, contextual=True)\n",
" label = StringType(parse_expression=I('inorganic'))\n",
" \n",
"table.models = [CurieTemperature]\n",
"table = Table(caption=Caption(\"\"),table_data=path, models=[CurieTemperature])\n",
"for record in table.records:\n",
" print(record.serialize())"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 7,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'Compound': {'names': ['BiFeO3']}}\n",
"{'Compound': {'names': ['LaCrO3']}}\n",
"{'Compound': {'names': ['LaCrO2']}}\n",
"{'Compound': {'names': ['Gd']}}\n"
]
}
],
"source": [
"class CurieTemperature(TemperatureModel):\n",
" StringType(parse_expression=I('TC'), required=True, contextual=True, updatable=True)\n",
" specifier = StringType(parse_expression=I('TC'), required=True, contextual=True, updatable=True)\n",
" compound = ModelType(Compound, required=True, contextual=True)\n",
" label = StringType(parse_expression=I('something else'), required=True)\n",
" \n",
"table.models = [CurieTemperature]\n",
"table = Table(caption=Caption(\"\"),table_data=path, models=[CurieTemperature])\n",
"for record in table.records:\n",
" print(record.serialize())"
]
Expand All @@ -182,7 +213,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -196,7 +227,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.4"
"version": "3.8.16"
}
},
"nbformat": 4,
Expand Down