def ggplot(data=None, mapping=None):
"""
Create a new ggplot plot
Parameters
----------
data : dictionary or pandas DataFrame, optional
Default dataset to use for the plot. If not specified, must be supplied in each layer added to the plot.
mapping : dictionary, optional
Default list of aesthetic mappings to use for the plot. If not specified, must be supplied in each layer
added to the plot.
Returns
-------
plot specification
Notes
-----
ggplot() initializes a ggplot object. It can be used to declare the input data frame for a graphic and to
specify the set of plot aesthetics intended to be common throughout all subsequent layers unless specifically
overridden.
ggplot() is typically used to construct a plot incrementally, using the + operator to add layers to the
existing ggplot object. This is advantageous in that the code is explicit about which layers are added
and the order in which they are added. For complex graphics with multiple layers, initialization with
ggplot() is recommended.
There are three common ways to invoke ggplot (see examples below):
- ggplot(dat,aes(x,y)) :
This method is recommended if all layers use the same data and the same set of aesthetics, although
this method can also be used to add a layer using data from another data frame.
- ggplot(dat) :
This method specifies the default data frame to use for the plot, but no aesthetics are defined up front.
This is useful when one data frame is used predominantly as layers are added, but the aesthetics may vary
from one layer to another.
- ggplot() :
This method initializes a skeleton ggplot object which is fleshed out as layers are added. This method is
useful when multiple data frames are used to produce different layers, as is often the case in complex
graphics.
ggplot() with no layers defined will produce an error message: "No layers in plot"
Examples
---------
>>> import numpy as np
>>> import pandas as pd
>>> from lets_plot import *
>>> x = np.random.uniform(-1, 1, size=100)
>>> y = np.random.normal(size=100)
>>> dat = pd.DataFrame({'x': x, 'y': 25 * x ** 2 + y})
>>> dat['class'] = ['0' if dat['x'][i] < 0 else '1' for i in range(100)]
>>> # three ways to invoke ggplot, producing the same output:
>>> # (1)
>>> ggplot(dat, aes(x='x', y='y')) + layer()
>>> # (2)
>>> ggplot(dat) + layer()
>>> # (3)
>>> ggplot() + layer('point', 'identity', dat)
"""
if isinstance(data, FeatureSpec):
raise ValueError(
"Object {!r} is not acceptable as 'data' argument in ggplot()".
format(data.kind))
data, mapping, data_meta = as_annotated_data(data, mapping)
return PlotSpec(data, mapping, scales=[], layers=[], **data_meta)
def ggplot(data=None, mapping=None):
"""
Create a new ggplot plot.
Parameters
----------
data : dict or `DataFrame`
Default dataset to use for the plot. If not specified,
must be supplied in each layer added to the plot.
mapping : `FeatureSpec`
Default list of aesthetic mappings to use for the plot.
If not specified, must be supplied in each layer added to the plot.
Returns
-------
`PlotSpec`
Plot specification.
Note
----
`ggplot()` initializes a ggplot object.
It can be used to declare the input data frame for a graphic and
to specify the set of plot aesthetics intended to be common
throughout all subsequent layers unless specifically overridden.
`ggplot()` is typically used to construct a plot incrementally,
using the + operator to add layers to the existing ggplot object.
This is advantageous in that the code is explicit about which layers
are added and the order in which they are added. For complex graphics
with multiple layers, initialization with `ggplot()` is recommended.
There are three common ways to invoke ggplot (see examples below):
- `ggplot(data, aes(x, y))`: This method is recommended if all layers use the same data and the same set of aesthetics, although this method can also be used to add a layer using data from another data frame.
- `ggplot(data)`: This method specifies the default data frame to use for the plot, but no aesthetics are defined up front. This is useful when one data frame is used predominantly as layers are added, but the aesthetics may vary from one layer to another.
- `ggplot()`: This method initializes a skeleton ggplot object which is fleshed out as layers are added. This method is useful when multiple data frames are used to produce different layers, as is often the case in complex graphics.
`ggplot()` with no layers defined will produce an error message:
"No layers in plot".
Examples
--------
.. jupyter-execute::
:linenos:
:emphasize-lines: 11, 13, 15
import numpy as np
from lets_plot import *
LetsPlot.setup_html()
np.random.seed(42)
n = 100
x = np.random.uniform(-1, 1, size=n)
y = np.random.normal(size=n)
data = {'x': x, 'y': 25 * x ** 2 + y}
# three ways to invoke ggplot, producing the same output:
# (1)
ggplot(data, aes(x='x', y='y')) + geom_point()
# (2)
ggplot(data) + geom_point(aes(x='x', y='y'))
# (3)
ggplot() + geom_point(aes(x='x', y='y'), data=data)
"""
if isinstance(data, FeatureSpec):
raise ValueError(
"Object {!r} is not acceptable as 'data' argument in ggplot()".
format(data.kind))
if is_geocoder(data):
data = data.get_geocodes()
data, mapping, data_meta = as_annotated_data(data, mapping)
return PlotSpec(data, mapping, scales=[], layers=[], **data_meta)
def get_data_meta(data):
_, _, data_meta = as_annotated_data(data, None)
return data_meta['data_meta']