| 1 |
""" |
| 2 |
.. _dataframe_export_example: |
| 3 |
|
| 4 |
Export Mesh Data to a DataFrame |
| 5 |
------------------------------- |
| 6 |
|
| 7 |
Convert a mesh's :attr:`point_data <pyvista.DataSet.point_data>` or |
| 8 |
:attr:`cell_data <pyvista.DataSet.cell_data>` to a :class:`pandas.DataFrame` |
| 9 |
or :class:`pyarrow.Table` for downstream analytics, export, or interactive |
| 10 |
exploration in IDEs like Positron's Data Explorer, JupyterLab, or VS Code's |
| 11 |
data viewer. |
| 12 |
|
| 13 |
This example uses a classic CFD-style workflow: a scalar field and a vector |
| 14 |
field attached to a mesh, then filtered / aggregated / exported using |
| 15 |
pandas idioms. |
| 16 |
|
| 17 |
""" |
| 18 |
|
| 19 |
import numpy as np |
| 20 |
from pyvista import examples |
| 21 |
|
| 22 |
# %% |
| 23 |
# Load a mesh and attach some data |
| 24 |
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 25 |
# Use the hexbeam fixture mesh and attach a pressure scalar plus a |
| 26 |
# velocity vector. |
| 27 |
|
| 28 |
mesh = examples.load_hexbeam() |
| 29 |
rng = np.random.default_rng(seed=0) |
| 30 |
mesh.point_data['pressure'] = rng.normal(loc=100.0, scale=20.0, size=mesh.n_points) |
| 31 |
mesh.point_data['velocity'] = rng.normal(size=(mesh.n_points, 3)) |
| 32 |
|
| 33 |
# %% |
| 34 |
# Convert to a :class:`pandas.DataFrame` |
| 35 |
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 36 |
# ``mesh.to_pandas()`` returns one row per point. Multi-component arrays are |
| 37 |
# expanded to one column per component, named ``{array_name}_{i}``. |
| 38 |
|
| 39 |
df = mesh.to_pandas() |
| 40 |
df.head() |
| 41 |
|
| 42 |
# %% |
| 43 |
# The DataFrame has ``n_points`` rows and one column per (expanded) array. |
| 44 |
|
| 45 |
df.shape |
| 46 |
|
| 47 |
# %% |
| 48 |
# Ad-hoc analytics |
| 49 |
# ~~~~~~~~~~~~~~~~ |
| 50 |
# Since we have a DataFrame, the full pandas API is available: filter, |
| 51 |
# derive new columns, summarize. |
| 52 |
|
| 53 |
velocity = df[['velocity_0', 'velocity_1', 'velocity_2']].to_numpy() |
| 54 |
df['speed'] = np.linalg.norm(velocity, axis=1) |
| 55 |
df[['pressure', 'speed']].describe() |
| 56 |
|
| 57 |
# %% |
| 58 |
# Find the 5 highest-pressure points. |
| 59 |
|
| 60 |
df.nlargest(5, 'pressure')[['pressure', 'speed']] |
| 61 |
|
| 62 |
# %% |
| 63 |
# Cell-level export |
| 64 |
# ~~~~~~~~~~~~~~~~~ |
| 65 |
# Pass ``association='cell'`` to export :attr:`~pyvista.DataSet.cell_data` |
| 66 |
# instead. The result has ``n_cells`` rows. |
| 67 |
|
| 68 |
mesh.cell_data['quality'] = rng.random(mesh.n_cells) |
| 69 |
cell_df = mesh.to_pandas('cell') |
| 70 |
cell_df.head() |
| 71 |
|
| 72 |
# %% |
| 73 |
# Export to disk |
| 74 |
# ~~~~~~~~~~~~~~ |
| 75 |
# A DataFrame gives you one-liner access to every pandas I/O backend: |
| 76 |
# Parquet, CSV, Feather, Excel, SQL, HDF5, and more. Commented out here to |
| 77 |
# keep the gallery build clean. |
| 78 |
|
| 79 |
# df.to_parquet('point_data.parquet') |
| 80 |
# df.to_csv('point_data.csv', index=False) |
| 81 |
|
| 82 |
# %% |
| 83 |
# Zero-copy Arrow interchange |
| 84 |
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 85 |
# ``mesh``, ``mesh.point_data``, ``mesh.cell_data``, and :class:`pyvista.Table` |
| 86 |
# all implement the `Arrow PyCapsule interface |
| 87 |
# <https://arrow.apache.org/docs/format/CDataInterface/PyCapsuleInterface.html>`_, |
| 88 |
# so any Arrow-aware library (polars, DuckDB, ibis, narwhals) can consume them |
| 89 |
# without pyvista depending on those libraries. For example, with pyarrow: |
| 90 |
import pyarrow as pa |
| 91 |
|
| 92 |
arrow_table = pa.table(mesh) |
| 93 |
arrow_table.schema |
| 94 |
|
| 95 |
# %% |
| 96 |
# The ``mesh``, ``mesh.point_data``, and ``mesh.cell_data`` objects can also be |
| 97 |
# opened directly in data-science IDE variable explorers (Positron, Jupyter, |
| 98 |
# VS Code) after calling :meth:`~pyvista.DataSet.to_pandas`. The returned |
| 99 |
# DataFrame renders as an interactive, sortable, filterable table. |