def create_2d_density(x, y, colorscale='Earth', ncontours=20,
hist_color=(0, 0, 0.5), point_color=(0, 0, 0.5),
point_size=2, title='2D Density Plot',
height=600, width=600):
"""
Returns figure for a 2D density plot
:param (list|array) x: x-axis data for plot generation
:param (list|array) y: y-axis data for plot generation
:param (str|tuple|list) colorscale: either a plotly scale name, an rgb
or hex color, a color tuple or a list or tuple of colors. An rgb
color is of the form 'rgb(x, y, z)' where x, y, z belong to the
interval [0, 255] and a color tuple is a tuple of the form
(a, b, c) where a, b and c belong to [0, 1]. If colormap is a
list, it must contain the valid color types aforementioned as its
members.
:param (int) ncontours: the number of 2D contours to draw on the plot
:param (str) hist_color: the color of the plotted histograms
:param (str) point_color: the color of the scatter points
:param (str) point_size: the color of the scatter points
:param (str) title: set the title for the plot
:param (float) height: the height of the chart
:param (float) width: the width of the chart
Example 1: Simple 2D Density Plot
```
import plotly.plotly as py
from plotly.figure_factory create_2d_density
import numpy as np
# Make data points
t = np.linspace(-1,1.2,2000)
x = (t**3)+(0.3*np.random.randn(2000))
y = (t**6)+(0.3*np.random.randn(2000))
# Create a figure
fig = create_2D_density(x, y)
# Plot the data
py.iplot(fig, filename='simple-2d-density')
```
Example 2: Using Parameters
```
import plotly.plotly as py
from plotly.figure_factory create_2d_density
import numpy as np
# Make data points
t = np.linspace(-1,1.2,2000)
x = (t**3)+(0.3*np.random.randn(2000))
y = (t**6)+(0.3*np.random.randn(2000))
# Create custom colorscale
colorscale = ['#7A4579', '#D56073', 'rgb(236,158,105)',
(1, 1, 0.2), (0.98,0.98,0.98)]
# Create a figure
fig = create_2D_density(
x, y, colorscale=colorscale,
hist_color='rgb(255, 237, 222)', point_size=3)
# Plot the data
py.iplot(fig, filename='use-parameters')
```
"""
# validate x and y are filled with numbers only
for array in [x, y]:
if not all(isinstance(element, Number) for element in array):
raise exceptions.PlotlyError(
"All elements of your 'x' and 'y' lists must be numbers."
)
# validate x and y are the same length
if len(x) != len(y):
raise exceptions.PlotlyError(
"Both lists 'x' and 'y' must be the same length."
)
colorscale = utils.validate_colors(colorscale, 'rgb')
colorscale = make_linear_colorscale(colorscale)
# validate hist_color and point_color
hist_color = utils.validate_colors(hist_color, 'rgb')
point_color = utils.validate_colors(point_color, 'rgb')
trace1 = graph_objs.Scatter(
x=x, y=y, mode='markers', name='points',
marker=dict(
color=point_color[0],
size=point_size,
opacity=0.4
)
)
trace2 = graph_objs.Histogram2dContour(
x=x, y=y, name='density', ncontours=ncontours,
colorscale=colorscale, reversescale=True, showscale=False
)
trace3 = graph_objs.Histogram(
x=x, name='x density',
marker=dict(color=hist_color[0]), yaxis='y2'
)
trace4 = graph_objs.Histogram(
y=y, name='y density',
marker=dict(color=hist_color[0]), xaxis='x2'
)
data = [trace1, trace2, trace3, trace4]
layout = graph_objs.Layout(
showlegend=False,
autosize=False,
title=title,
height=height,
width=width,
xaxis=dict(
domain=[0, 0.85],
showgrid=False,
zeroline=False
),
yaxis=dict(
domain=[0, 0.85],
showgrid=False,
zeroline=False
),
margin=dict(
t=50
),
hovermode='closest',
bargap=0,
xaxis2=dict(
domain=[0.85, 1],
showgrid=False,
zeroline=False
),
yaxis2=dict(
domain=[0.85, 1],
showgrid=False,
zeroline=False
)
)
fig = graph_objs.Figure(data=data, layout=layout)
return fig
def create_violin(data, data_header=None, group_header=None, colors=None,
use_colorscale=False, group_stats=None, rugplot=True,
sort=False, height=450, width=600,
title='Violin and Rug Plot'):
"""
Returns figure for a violin plot
:param (list|array) data: accepts either a list of numerical values,
a list of dictionaries all with identical keys and at least one
column of numeric values, or a pandas dataframe with at least one
column of numbers.
:param (str) data_header: the header of the data column to be used
from an inputted pandas dataframe. Not applicable if 'data' is
a list of numeric values.
:param (str) group_header: applicable if grouping data by a variable.
'group_header' must be set to the name of the grouping variable.
:param (str|tuple|list|dict) colors: either a plotly scale name,
an rgb or hex color, a color tuple, a list of colors or a
dictionary. An rgb color is of the form 'rgb(x, y, z)' where
x, y and z belong to the interval [0, 255] and a color tuple is a
tuple of the form (a, b, c) where a, b and c belong to [0, 1].
If colors is a list, it must contain valid color types as its
members.
:param (bool) use_colorscale: only applicable if grouping by another
variable. Will implement a colorscale based on the first 2 colors
of param colors. This means colors must be a list with at least 2
colors in it (Plotly colorscales are accepted since they map to a
list of two rgb colors). Default = False
:param (dict) group_stats: a dictioanry where each key is a unique
value from the group_header column in data. Each value must be a
number and will be used to color the violin plots if a colorscale
is being used.
:param (bool) rugplot: determines if a rugplot is draw on violin plot.
Default = True
:param (bool) sort: determines if violins are sorted
alphabetically (True) or by input order (False). Default = False
:param (float) height: the height of the violin plot.
:param (float) width: the width of the violin plot.
:param (str) title: the title of the violin plot.
Example 1: Single Violin Plot
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
from scipy import stats
# create list of random values
data_list = np.random.randn(100)
data_list.tolist()
# create violin fig
fig = create_violin(data_list, colors='#604d9e')
# plot
py.iplot(fig, filename='Violin Plot')
```
Example 2: Multiple Violin Plots with Qualitative Coloring
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
import pandas as pd
from scipy import stats
# create dataframe
np.random.seed(619517)
Nr=250
y = np.random.randn(Nr)
gr = np.random.choice(list("ABCDE"), Nr)
norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)]
for i, letter in enumerate("ABCDE"):
y[gr == letter] *=norm_params[i][1]+ norm_params[i][0]
df = pd.DataFrame(dict(Score=y, Group=gr))
# create violin fig
fig = create_violin(df, data_header='Score', group_header='Group',
sort=True, height=600, width=1000)
# plot
py.iplot(fig, filename='Violin Plot with Coloring')
```
Example 3: Violin Plots with Colorscale
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
import pandas as pd
from scipy import stats
# create dataframe
np.random.seed(619517)
Nr=250
y = np.random.randn(Nr)
gr = np.random.choice(list("ABCDE"), Nr)
norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)]
for i, letter in enumerate("ABCDE"):
y[gr == letter] *=norm_params[i][1]+ norm_params[i][0]
df = pd.DataFrame(dict(Score=y, Group=gr))
# define header params
data_header = 'Score'
group_header = 'Group'
# make groupby object with pandas
group_stats = {}
groupby_data = df.groupby([group_header])
for group in "ABCDE":
data_from_group = groupby_data.get_group(group)[data_header]
# take a stat of the grouped data
stat = np.median(data_from_group)
# add to dictionary
group_stats[group] = stat
# create violin fig
fig = create_violin(df, data_header='Score', group_header='Group',
height=600, width=1000, use_colorscale=True,
group_stats=group_stats)
# plot
py.iplot(fig, filename='Violin Plot with Colorscale')
```
"""
# Validate colors
if isinstance(colors, dict):
valid_colors = utils.validate_colors_dict(colors, 'rgb')
else:
valid_colors = utils.validate_colors(colors, 'rgb')
# validate data and choose plot type
if group_header is None:
if isinstance(data, list):
if len(data) <= 0:
raise exceptions.PlotlyError("If data is a list, it must be "
"nonempty and contain either "
"numbers or dictionaries.")
if not all(isinstance(element, Number) for element in data):
raise exceptions.PlotlyError("If data is a list, it must "
"contain only numbers.")
if pd and isinstance(data, pd.core.frame.DataFrame):
if data_header is None:
raise exceptions.PlotlyError("data_header must be the "
"column name with the "
"desired numeric data for "
"the violin plot.")
data = data[data_header].values.tolist()
# call the plotting functions
plot_data, plot_xrange = violinplot(data, fillcolor=valid_colors[0],
rugplot=rugplot)
layout = graph_objs.Layout(
title=title,
autosize=True,
font=graph_objs.Font(size=11),
height=height,
showlegend=False,
width=width,
xaxis=make_XAxis('', plot_xrange),
yaxis=make_YAxis(''),
hovermode='closest'
)
layout['yaxis'].update(dict(showline=False,
showticklabels=False,
ticks=''))
fig = graph_objs.Figure(data=graph_objs.Data(plot_data),
layout=layout)
return fig
else:
if not isinstance(data, pd.core.frame.DataFrame):
raise exceptions.PlotlyError("Error. You must use a pandas "
"DataFrame if you are using a "
"group header.")
if data_header is None:
raise exceptions.PlotlyError("data_header must be the column "
"name with the desired numeric "
"data for the violin plot.")
if use_colorscale is False:
if isinstance(valid_colors, dict):
# validate colors dict choice below
fig = violin_dict(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort,
height, width, title
)
return fig
else:
fig = violin_no_colorscale(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort,
height, width, title
)
return fig
else:
if isinstance(valid_colors, dict):
raise exceptions.PlotlyError("The colors param cannot be "
"a dictionary if you are "
"using a colorscale.")
if len(valid_colors) < 2:
raise exceptions.PlotlyError("colors must be a list with "
"at least 2 colors. A "
"Plotly scale is allowed.")
if not isinstance(group_stats, dict):
raise exceptions.PlotlyError("Your group_stats param "
"must be a dictionary.")
fig = violin_colorscale(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort, height,
width, title
)
return fig
def create_violin(data, data_header=None, group_header=None, colors=None,
use_colorscale=False, group_stats=None, rugplot=True,
sort=False, height=450, width=600,
title='Violin and Rug Plot'):
"""
Returns figure for a violin plot
:param (list|array) data: accepts either a list of numerical values,
a list of dictionaries all with identical keys and at least one
column of numeric values, or a pandas dataframe with at least one
column of numbers.
:param (str) data_header: the header of the data column to be used
from an inputted pandas dataframe. Not applicable if 'data' is
a list of numeric values.
:param (str) group_header: applicable if grouping data by a variable.
'group_header' must be set to the name of the grouping variable.
:param (str|tuple|list|dict) colors: either a plotly scale name,
an rgb or hex color, a color tuple, a list of colors or a
dictionary. An rgb color is of the form 'rgb(x, y, z)' where
x, y and z belong to the interval [0, 255] and a color tuple is a
tuple of the form (a, b, c) where a, b and c belong to [0, 1].
If colors is a list, it must contain valid color types as its
members.
:param (bool) use_colorscale: only applicable if grouping by another
variable. Will implement a colorscale based on the first 2 colors
of param colors. This means colors must be a list with at least 2
colors in it (Plotly colorscales are accepted since they map to a
list of two rgb colors). Default = False
:param (dict) group_stats: a dictioanry where each key is a unique
value from the group_header column in data. Each value must be a
number and will be used to color the violin plots if a colorscale
is being used.
:param (bool) rugplot: determines if a rugplot is draw on violin plot.
Default = True
:param (bool) sort: determines if violins are sorted
alphabetically (True) or by input order (False). Default = False
:param (float) height: the height of the violin plot.
:param (float) width: the width of the violin plot.
:param (str) title: the title of the violin plot.
Example 1: Single Violin Plot
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
from scipy import stats
# create list of random values
data_list = np.random.randn(100)
data_list.tolist()
# create violin fig
fig = create_violin(data_list, colors='#604d9e')
# plot
py.iplot(fig, filename='Violin Plot')
```
Example 2: Multiple Violin Plots with Qualitative Coloring
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
import pandas as pd
from scipy import stats
# create dataframe
np.random.seed(619517)
Nr=250
y = np.random.randn(Nr)
gr = np.random.choice(list("ABCDE"), Nr)
norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)]
for i, letter in enumerate("ABCDE"):
y[gr == letter] *=norm_params[i][1]+ norm_params[i][0]
df = pd.DataFrame(dict(Score=y, Group=gr))
# create violin fig
fig = create_violin(df, data_header='Score', group_header='Group',
sort=True, height=600, width=1000)
# plot
py.iplot(fig, filename='Violin Plot with Coloring')
```
Example 3: Violin Plots with Colorscale
```
import plotly.plotly as py
from plotly.figure_factory import create_violin
from plotly.graph_objs import graph_objs
import numpy as np
import pandas as pd
from scipy import stats
# create dataframe
np.random.seed(619517)
Nr=250
y = np.random.randn(Nr)
gr = np.random.choice(list("ABCDE"), Nr)
norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)]
for i, letter in enumerate("ABCDE"):
y[gr == letter] *=norm_params[i][1]+ norm_params[i][0]
df = pd.DataFrame(dict(Score=y, Group=gr))
# define header params
data_header = 'Score'
group_header = 'Group'
# make groupby object with pandas
group_stats = {}
groupby_data = df.groupby([group_header])
for group in "ABCDE":
data_from_group = groupby_data.get_group(group)[data_header]
# take a stat of the grouped data
stat = np.median(data_from_group)
# add to dictionary
group_stats[group] = stat
# create violin fig
fig = create_violin(df, data_header='Score', group_header='Group',
height=600, width=1000, use_colorscale=True,
group_stats=group_stats)
# plot
py.iplot(fig, filename='Violin Plot with Colorscale')
```
"""
# Validate colors
if isinstance(colors, dict):
valid_colors = utils.validate_colors_dict(colors, 'rgb')
else:
valid_colors = utils.validate_colors(colors, 'rgb')
# validate data and choose plot type
if group_header is None:
if isinstance(data, list):
if len(data) <= 0:
raise exceptions.PlotlyError("If data is a list, it must be "
"nonempty and contain either "
"numbers or dictionaries.")
if not all(isinstance(element, Number) for element in data):
raise exceptions.PlotlyError("If data is a list, it must "
"contain only numbers.")
if pd and isinstance(data, pd.core.frame.DataFrame):
if data_header is None:
raise exceptions.PlotlyError("data_header must be the "
"column name with the "
"desired numeric data for "
"the violin plot.")
data = data[data_header].values.tolist()
# call the plotting functions
plot_data, plot_xrange = violinplot(data, fillcolor=valid_colors[0],
rugplot=rugplot)
layout = graph_objs.Layout(
title=title,
autosize=False,
font=graph_objs.layout.Font(size=11),
height=height,
showlegend=False,
width=width,
xaxis=make_XAxis('', plot_xrange),
yaxis=make_YAxis(''),
hovermode='closest'
)
layout['yaxis'].update(dict(showline=False,
showticklabels=False,
ticks=''))
fig = graph_objs.Figure(data=plot_data,
layout=layout)
return fig
else:
if not isinstance(data, pd.core.frame.DataFrame):
raise exceptions.PlotlyError("Error. You must use a pandas "
"DataFrame if you are using a "
"group header.")
if data_header is None:
raise exceptions.PlotlyError("data_header must be the column "
"name with the desired numeric "
"data for the violin plot.")
if use_colorscale is False:
if isinstance(valid_colors, dict):
# validate colors dict choice below
fig = violin_dict(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort,
height, width, title
)
return fig
else:
fig = violin_no_colorscale(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort,
height, width, title
)
return fig
else:
if isinstance(valid_colors, dict):
raise exceptions.PlotlyError("The colors param cannot be "
"a dictionary if you are "
"using a colorscale.")
if len(valid_colors) < 2:
raise exceptions.PlotlyError("colors must be a list with "
"at least 2 colors. A "
"Plotly scale is allowed.")
if not isinstance(group_stats, dict):
raise exceptions.PlotlyError("Your group_stats param "
"must be a dictionary.")
fig = violin_colorscale(
data, data_header, group_header, valid_colors,
use_colorscale, group_stats, rugplot, sort, height,
width, title
)
return fig
def create_gantt(df,
colors=None,
index_col=None,
show_colorbar=False,
reverse_colors=False,
title='Gantt Chart',
bar_width=0.2,
showgrid_x=False,
showgrid_y=False,
height=600,
width=900,
tasks=None,
task_names=None,
data=None,
group_tasks=False):
"""
Returns figure for a gantt chart
:param (array|list) df: input data for gantt chart. Must be either a
a dataframe or a list. If dataframe, the columns must include
'Task', 'Start' and 'Finish'. Other columns can be included and
used for indexing. If a list, its elements must be dictionaries
with the same required column headers: 'Task', 'Start' and
'Finish'.
:param (str|list|dict|tuple) colors: either a plotly scale name, an
rgb or hex color, a color tuple or a list of colors. An rgb color
is of the form 'rgb(x, y, z)' where x, y, z belong to the interval
[0, 255] and a color tuple is a tuple of the form (a, b, c) where
a, b and c belong to [0, 1]. If colors is a list, it must
contain the valid color types aforementioned as its members.
If a dictionary, all values of the indexing column must be keys in
colors.
:param (str|float) index_col: the column header (if df is a data
frame) that will function as the indexing column. If df is a list,
index_col must be one of the keys in all the items of df.
:param (bool) show_colorbar: determines if colorbar will be visible.
Only applies if values in the index column are numeric.
:param (bool) reverse_colors: reverses the order of selected colors
:param (str) title: the title of the chart
:param (float) bar_width: the width of the horizontal bars in the plot
:param (bool) showgrid_x: show/hide the x-axis grid
:param (bool) showgrid_y: show/hide the y-axis grid
:param (float) height: the height of the chart
:param (float) width: the width of the chart
Example 1: Simple Gantt Chart
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01', Finish='2009-02-30'),
dict(Task="Job B", Start='2009-03-05', Finish='2009-04-15'),
dict(Task="Job C", Start='2009-02-20', Finish='2009-05-30')]
# Create a figure
fig = create_gantt(df)
# Plot the data
py.iplot(fig, filename='Simple Gantt Chart', world_readable=True)
```
Example 2: Index by Column with Numerical Entries
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Complete=10),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Complete=60),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Complete=95)]
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors='Blues', index_col='Complete',
show_colorbar=True, bar_width=0.5,
showgrid_x=True, showgrid_y=True)
# Plot the data
py.iplot(fig, filename='Numerical Entries', world_readable=True)
```
Example 3: Index by Column with String Entries
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Resource='Apple'),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Resource='Grape'),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Resource='Banana')]
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors=['rgb(200, 50, 25)', (1, 0, 1), '#6c4774'],
index_col='Resource', reverse_colors=True,
show_colorbar=True)
# Plot the data
py.iplot(fig, filename='String Entries', world_readable=True)
```
Example 4: Use a dictionary for colors
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Resource='Apple'),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Resource='Grape'),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Resource='Banana')]
# Make a dictionary of colors
colors = {'Apple': 'rgb(255, 0, 0)',
'Grape': 'rgb(170, 14, 200)',
'Banana': (1, 1, 0.2)}
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors=colors, index_col='Resource',
show_colorbar=True)
# Plot the data
py.iplot(fig, filename='dictioanry colors', world_readable=True)
```
Example 5: Use a pandas dataframe
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
import pandas as pd
# Make data as a dataframe
df = pd.DataFrame([['Run', '2010-01-01', '2011-02-02', 10],
['Fast', '2011-01-01', '2012-06-05', 55],
['Eat', '2012-01-05', '2013-07-05', 94]],
columns=['Task', 'Start', 'Finish', 'Complete'])
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors='Blues', index_col='Complete',
show_colorbar=True, bar_width=0.5,
showgrid_x=True, showgrid_y=True)
# Plot the data
py.iplot(fig, filename='data with dataframe', world_readable=True)
```
"""
# validate gantt input data
chart = validate_gantt(df)
if index_col:
if index_col not in chart[0]:
raise exceptions.PlotlyError(
"In order to use an indexing column and assign colors to "
"the values of the index, you must choose an actual "
"column name in the dataframe or key if a list of "
"dictionaries is being used.")
# validate gantt index column
index_list = []
for dictionary in chart:
index_list.append(dictionary[index_col])
utils.validate_index(index_list)
# Validate colors
if isinstance(colors, dict):
colors = utils.validate_colors_dict(colors, 'rgb')
else:
colors = utils.validate_colors(colors, 'rgb')
if reverse_colors is True:
colors.reverse()
if not index_col:
if isinstance(colors, dict):
raise exceptions.PlotlyError(
"Error. You have set colors to a dictionary but have not "
"picked an index. An index is required if you are "
"assigning colors to particular values in a dictioanry.")
fig = gantt(chart,
colors,
title,
bar_width,
showgrid_x,
showgrid_y,
height,
width,
tasks=None,
task_names=None,
data=None,
group_tasks=group_tasks)
return fig
else:
if not isinstance(colors, dict):
fig = gantt_colorscale(chart,
colors,
title,
index_col,
show_colorbar,
bar_width,
showgrid_x,
showgrid_y,
height,
width,
tasks=None,
task_names=None,
data=None,
group_tasks=group_tasks)
return fig
else:
fig = gantt_dict(chart,
colors,
title,
index_col,
show_colorbar,
bar_width,
showgrid_x,
showgrid_y,
height,
width,
tasks=None,
task_names=None,
data=None,
group_tasks=group_tasks)
return fig
def create_gantt(df, colors=None, index_col=None, show_colorbar=False,
reverse_colors=False, title='Gantt Chart', bar_width=0.2,
showgrid_x=False, showgrid_y=False, height=600, width=900,
tasks=None, task_names=None, data=None, group_tasks=False):
"""
Returns figure for a gantt chart
:param (array|list) df: input data for gantt chart. Must be either a
a dataframe or a list. If dataframe, the columns must include
'Task', 'Start' and 'Finish'. Other columns can be included and
used for indexing. If a list, its elements must be dictionaries
with the same required column headers: 'Task', 'Start' and
'Finish'.
:param (str|list|dict|tuple) colors: either a plotly scale name, an
rgb or hex color, a color tuple or a list of colors. An rgb color
is of the form 'rgb(x, y, z)' where x, y, z belong to the interval
[0, 255] and a color tuple is a tuple of the form (a, b, c) where
a, b and c belong to [0, 1]. If colors is a list, it must
contain the valid color types aforementioned as its members.
If a dictionary, all values of the indexing column must be keys in
colors.
:param (str|float) index_col: the column header (if df is a data
frame) that will function as the indexing column. If df is a list,
index_col must be one of the keys in all the items of df.
:param (bool) show_colorbar: determines if colorbar will be visible.
Only applies if values in the index column are numeric.
:param (bool) reverse_colors: reverses the order of selected colors
:param (str) title: the title of the chart
:param (float) bar_width: the width of the horizontal bars in the plot
:param (bool) showgrid_x: show/hide the x-axis grid
:param (bool) showgrid_y: show/hide the y-axis grid
:param (float) height: the height of the chart
:param (float) width: the width of the chart
Example 1: Simple Gantt Chart
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01', Finish='2009-02-30'),
dict(Task="Job B", Start='2009-03-05', Finish='2009-04-15'),
dict(Task="Job C", Start='2009-02-20', Finish='2009-05-30')]
# Create a figure
fig = create_gantt(df)
# Plot the data
py.iplot(fig, filename='Simple Gantt Chart', world_readable=True)
```
Example 2: Index by Column with Numerical Entries
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Complete=10),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Complete=60),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Complete=95)]
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors='Blues', index_col='Complete',
show_colorbar=True, bar_width=0.5,
showgrid_x=True, showgrid_y=True)
# Plot the data
py.iplot(fig, filename='Numerical Entries', world_readable=True)
```
Example 3: Index by Column with String Entries
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Resource='Apple'),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Resource='Grape'),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Resource='Banana')]
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors=['rgb(200, 50, 25)', (1, 0, 1), '#6c4774'],
index_col='Resource', reverse_colors=True,
show_colorbar=True)
# Plot the data
py.iplot(fig, filename='String Entries', world_readable=True)
```
Example 4: Use a dictionary for colors
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
# Make data for chart
df = [dict(Task="Job A", Start='2009-01-01',
Finish='2009-02-30', Resource='Apple'),
dict(Task="Job B", Start='2009-03-05',
Finish='2009-04-15', Resource='Grape'),
dict(Task="Job C", Start='2009-02-20',
Finish='2009-05-30', Resource='Banana')]
# Make a dictionary of colors
colors = {'Apple': 'rgb(255, 0, 0)',
'Grape': 'rgb(170, 14, 200)',
'Banana': (1, 1, 0.2)}
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors=colors, index_col='Resource',
show_colorbar=True)
# Plot the data
py.iplot(fig, filename='dictioanry colors', world_readable=True)
```
Example 5: Use a pandas dataframe
```
import plotly.plotly as py
from plotly.figure_factory import create_gantt
import pandas as pd
# Make data as a dataframe
df = pd.DataFrame([['Run', '2010-01-01', '2011-02-02', 10],
['Fast', '2011-01-01', '2012-06-05', 55],
['Eat', '2012-01-05', '2013-07-05', 94]],
columns=['Task', 'Start', 'Finish', 'Complete'])
# Create a figure with Plotly colorscale
fig = create_gantt(df, colors='Blues', index_col='Complete',
show_colorbar=True, bar_width=0.5,
showgrid_x=True, showgrid_y=True)
# Plot the data
py.iplot(fig, filename='data with dataframe', world_readable=True)
```
"""
# validate gantt input data
chart = validate_gantt(df)
if index_col:
if index_col not in chart[0]:
raise exceptions.PlotlyError(
"In order to use an indexing column and assign colors to "
"the values of the index, you must choose an actual "
"column name in the dataframe or key if a list of "
"dictionaries is being used.")
# validate gantt index column
index_list = []
for dictionary in chart:
index_list.append(dictionary[index_col])
utils.validate_index(index_list)
# Validate colors
if isinstance(colors, dict):
colors = utils.validate_colors_dict(colors, 'rgb')
else:
colors = utils.validate_colors(colors, 'rgb')
if reverse_colors is True:
colors.reverse()
if not index_col:
if isinstance(colors, dict):
raise exceptions.PlotlyError(
"Error. You have set colors to a dictionary but have not "
"picked an index. An index is required if you are "
"assigning colors to particular values in a dictioanry."
)
fig = gantt(
chart, colors, title, bar_width, showgrid_x, showgrid_y,
height, width, tasks=None, task_names=None, data=None,
group_tasks=group_tasks
)
return fig
else:
if not isinstance(colors, dict):
fig = gantt_colorscale(
chart, colors, title, index_col, show_colorbar, bar_width,
showgrid_x, showgrid_y, height, width,
tasks=None, task_names=None, data=None, group_tasks=group_tasks
)
return fig
else:
fig = gantt_dict(
chart, colors, title, index_col, show_colorbar, bar_width,
showgrid_x, showgrid_y, height, width,
tasks=None, task_names=None, data=None, group_tasks=group_tasks
)
return fig
def create_scatterplotmatrix(df,
index=None,
endpts=None,
diag='scatter',
height=500,
width=500,
size=6,
title='Scatterplot Matrix',
colormap=None,
colormap_type='cat',
dataframe=None,
headers=None,
index_vals=None,
**kwargs):
"""
Returns data for a scatterplot matrix.
:param (array) df: array of the data with column headers
:param (str) index: name of the index column in data array
:param (list|tuple) endpts: takes an increasing sequece of numbers
that defines intervals on the real line. They are used to group
the entries in an index of numbers into their corresponding
interval and therefore can be treated as categorical data
:param (str) diag: sets the chart type for the main diagonal plots.
The options are 'scatter', 'histogram' and 'box'.
:param (int|float) height: sets the height of the chart
:param (int|float) width: sets the width of the chart
:param (float) size: sets the marker size (in px)
:param (str) title: the title label of the scatterplot matrix
:param (str|tuple|list|dict) colormap: either a plotly scale name,
an rgb or hex color, a color tuple, a list of colors or a
dictionary. An rgb color is of the form 'rgb(x, y, z)' where
x, y and z belong to the interval [0, 255] and a color tuple is a
tuple of the form (a, b, c) where a, b and c belong to [0, 1].
If colormap is a list, it must contain valid color types as its
members.
If colormap is a dictionary, all the string entries in
the index column must be a key in colormap. In this case, the
colormap_type is forced to 'cat' or categorical
:param (str) colormap_type: determines how colormap is interpreted.
Valid choices are 'seq' (sequential) and 'cat' (categorical). If
'seq' is selected, only the first two colors in colormap will be
considered (when colormap is a list) and the index values will be
linearly interpolated between those two colors. This option is
forced if all index values are numeric.
If 'cat' is selected, a color from colormap will be assigned to
each category from index, including the intervals if endpts is
being used
:param (dict) **kwargs: a dictionary of scatterplot arguments
The only forbidden parameters are 'size', 'color' and
'colorscale' in 'marker'
Example 1: Vanilla Scatterplot Matrix
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe
df = pd.DataFrame(np.random.randn(10, 2),
columns=['Column 1', 'Column 2'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df)
# Plot
py.iplot(fig, filename='Vanilla Scatterplot Matrix')
```
Example 2: Indexing a Column
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with index
df = pd.DataFrame(np.random.randn(10, 2),
columns=['A', 'B'])
# Add another column of strings to the dataframe
df['Fruit'] = pd.Series(['apple', 'apple', 'grape', 'apple', 'apple',
'grape', 'pear', 'pear', 'apple', 'pear'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df, index='Fruit', size=10)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix with Index')
```
Example 3: Styling the Diagonal Subplots
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with index
df = pd.DataFrame(np.random.randn(10, 4),
columns=['A', 'B', 'C', 'D'])
# Add another column of strings to the dataframe
df['Fruit'] = pd.Series(['apple', 'apple', 'grape', 'apple', 'apple',
'grape', 'pear', 'pear', 'apple', 'pear'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df, diag='box', index='Fruit', height=1000,
width=1000)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Diagonal Styling')
```
Example 4: Use a Theme to Style the Subplots
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['A', 'B', 'C'])
# Create scatterplot matrix using a built-in
# Plotly palette scale and indexing column 'A'
fig = create_scatterplotmatrix(df, diag='histogram', index='A',
colormap='Blues', height=800, width=800)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Colormap Theme')
```
Example 5: Example 4 with Interval Factoring
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['A', 'B', 'C'])
# Create scatterplot matrix using a list of 2 rgb tuples
# and endpoints at -1, 0 and 1
fig = create_scatterplotmatrix(df, diag='histogram', index='A',
colormap=['rgb(140, 255, 50)',
'rgb(170, 60, 115)', '#6c4774',
(0.5, 0.1, 0.8)],
endpts=[-1, 0, 1], height=800, width=800)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Intervals')
```
Example 6: Using the colormap as a Dictionary
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
import random
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['Column A',
'Column B',
'Column C'])
# Add new color column to dataframe
new_column = []
strange_colors = ['turquoise', 'limegreen', 'goldenrod']
for j in range(100):
new_column.append(random.choice(strange_colors))
df['Colors'] = pd.Series(new_column, index=df.index)
# Create scatterplot matrix using a dictionary of hex color values
# which correspond to actual color names in 'Colors' column
fig = create_scatterplotmatrix(
df, diag='box', index='Colors',
colormap= dict(
turquoise = '#00F5FF',
limegreen = '#32CD32',
goldenrod = '#DAA520'
),
colormap_type='cat',
height=800, width=800
)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - colormap dictionary ')
```
"""
# TODO: protected until #282
if dataframe is None:
dataframe = []
if headers is None:
headers = []
if index_vals is None:
index_vals = []
validate_scatterplotmatrix(df, index, diag, colormap_type, **kwargs)
# Validate colormap
if isinstance(colormap, dict):
colormap = utils.validate_colors_dict(colormap, 'rgb')
else:
colormap = utils.validate_colors(colormap, 'rgb')
if not index:
for name in df:
headers.append(name)
for name in headers:
dataframe.append(df[name].values.tolist())
# Check for same data-type in df columns
utils.validate_dataframe(dataframe)
figure = scatterplot(dataframe, headers, diag, size, height, width,
title, **kwargs)
return figure
else:
# Validate index selection
if index not in df:
raise exceptions.PlotlyError("Make sure you set the index "
"input variable to one of the "
"column names of your "
"dataframe.")
index_vals = df[index].values.tolist()
for name in df:
if name != index:
headers.append(name)
for name in headers:
dataframe.append(df[name].values.tolist())
# check for same data-type in each df column
utils.validate_dataframe(dataframe)
utils.validate_index(index_vals)
# check if all colormap keys are in the index
# if colormap is a dictionary
if isinstance(colormap, dict):
for key in colormap:
if not all(index in colormap for index in index_vals):
raise exceptions.PlotlyError("If colormap is a "
"dictionary, all the "
"names in the index "
"must be keys.")
figure = scatterplot_dict(dataframe, headers, diag, size, height,
width, title, index, index_vals, endpts,
colormap, colormap_type, **kwargs)
return figure
else:
figure = scatterplot_theme(dataframe, headers, diag, size, height,
width, title, index, index_vals, endpts,
colormap, colormap_type, **kwargs)
return figure
def create_scatterplotmatrix(df, index=None, endpts=None, diag='scatter',
height=500, width=500, size=6,
title='Scatterplot Matrix', colormap=None,
colormap_type='cat', dataframe=None,
headers=None, index_vals=None, **kwargs):
"""
Returns data for a scatterplot matrix.
:param (array) df: array of the data with column headers
:param (str) index: name of the index column in data array
:param (list|tuple) endpts: takes an increasing sequece of numbers
that defines intervals on the real line. They are used to group
the entries in an index of numbers into their corresponding
interval and therefore can be treated as categorical data
:param (str) diag: sets the chart type for the main diagonal plots.
The options are 'scatter', 'histogram' and 'box'.
:param (int|float) height: sets the height of the chart
:param (int|float) width: sets the width of the chart
:param (float) size: sets the marker size (in px)
:param (str) title: the title label of the scatterplot matrix
:param (str|tuple|list|dict) colormap: either a plotly scale name,
an rgb or hex color, a color tuple, a list of colors or a
dictionary. An rgb color is of the form 'rgb(x, y, z)' where
x, y and z belong to the interval [0, 255] and a color tuple is a
tuple of the form (a, b, c) where a, b and c belong to [0, 1].
If colormap is a list, it must contain valid color types as its
members.
If colormap is a dictionary, all the string entries in
the index column must be a key in colormap. In this case, the
colormap_type is forced to 'cat' or categorical
:param (str) colormap_type: determines how colormap is interpreted.
Valid choices are 'seq' (sequential) and 'cat' (categorical). If
'seq' is selected, only the first two colors in colormap will be
considered (when colormap is a list) and the index values will be
linearly interpolated between those two colors. This option is
forced if all index values are numeric.
If 'cat' is selected, a color from colormap will be assigned to
each category from index, including the intervals if endpts is
being used
:param (dict) **kwargs: a dictionary of scatterplot arguments
The only forbidden parameters are 'size', 'color' and
'colorscale' in 'marker'
Example 1: Vanilla Scatterplot Matrix
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe
df = pd.DataFrame(np.random.randn(10, 2),
columns=['Column 1', 'Column 2'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df)
# Plot
py.iplot(fig, filename='Vanilla Scatterplot Matrix')
```
Example 2: Indexing a Column
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with index
df = pd.DataFrame(np.random.randn(10, 2),
columns=['A', 'B'])
# Add another column of strings to the dataframe
df['Fruit'] = pd.Series(['apple', 'apple', 'grape', 'apple', 'apple',
'grape', 'pear', 'pear', 'apple', 'pear'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df, index='Fruit', size=10)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix with Index')
```
Example 3: Styling the Diagonal Subplots
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with index
df = pd.DataFrame(np.random.randn(10, 4),
columns=['A', 'B', 'C', 'D'])
# Add another column of strings to the dataframe
df['Fruit'] = pd.Series(['apple', 'apple', 'grape', 'apple', 'apple',
'grape', 'pear', 'pear', 'apple', 'pear'])
# Create scatterplot matrix
fig = create_scatterplotmatrix(df, diag='box', index='Fruit', height=1000,
width=1000)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Diagonal Styling')
```
Example 4: Use a Theme to Style the Subplots
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['A', 'B', 'C'])
# Create scatterplot matrix using a built-in
# Plotly palette scale and indexing column 'A'
fig = create_scatterplotmatrix(df, diag='histogram', index='A',
colormap='Blues', height=800, width=800)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Colormap Theme')
```
Example 5: Example 4 with Interval Factoring
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['A', 'B', 'C'])
# Create scatterplot matrix using a list of 2 rgb tuples
# and endpoints at -1, 0 and 1
fig = create_scatterplotmatrix(df, diag='histogram', index='A',
colormap=['rgb(140, 255, 50)',
'rgb(170, 60, 115)', '#6c4774',
(0.5, 0.1, 0.8)],
endpts=[-1, 0, 1], height=800, width=800)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - Intervals')
```
Example 6: Using the colormap as a Dictionary
```
import plotly.plotly as py
from plotly.graph_objs import graph_objs
from plotly.figure_factory import create_scatterplotmatrix
import numpy as np
import pandas as pd
import random
# Create dataframe with random data
df = pd.DataFrame(np.random.randn(100, 3),
columns=['Column A',
'Column B',
'Column C'])
# Add new color column to dataframe
new_column = []
strange_colors = ['turquoise', 'limegreen', 'goldenrod']
for j in range(100):
new_column.append(random.choice(strange_colors))
df['Colors'] = pd.Series(new_column, index=df.index)
# Create scatterplot matrix using a dictionary of hex color values
# which correspond to actual color names in 'Colors' column
fig = create_scatterplotmatrix(
df, diag='box', index='Colors',
colormap= dict(
turquoise = '#00F5FF',
limegreen = '#32CD32',
goldenrod = '#DAA520'
),
colormap_type='cat',
height=800, width=800
)
# Plot
py.iplot(fig, filename = 'Scatterplot Matrix - colormap dictionary ')
```
"""
# TODO: protected until #282
if dataframe is None:
dataframe = []
if headers is None:
headers = []
if index_vals is None:
index_vals = []
validate_scatterplotmatrix(df, index, diag, colormap_type, **kwargs)
# Validate colormap
if isinstance(colormap, dict):
colormap = utils.validate_colors_dict(colormap, 'rgb')
else:
colormap = utils.validate_colors(colormap, 'rgb')
if not index:
for name in df:
headers.append(name)
for name in headers:
dataframe.append(df[name].values.tolist())
# Check for same data-type in df columns
utils.validate_dataframe(dataframe)
figure = scatterplot(dataframe, headers, diag, size, height, width,
title, **kwargs)
return figure
else:
# Validate index selection
if index not in df:
raise exceptions.PlotlyError("Make sure you set the index "
"input variable to one of the "
"column names of your "
"dataframe.")
index_vals = df[index].values.tolist()
for name in df:
if name != index:
headers.append(name)
for name in headers:
dataframe.append(df[name].values.tolist())
# check for same data-type in each df column
utils.validate_dataframe(dataframe)
utils.validate_index(index_vals)
# check if all colormap keys are in the index
# if colormap is a dictionary
if isinstance(colormap, dict):
for key in colormap:
if not all(index in colormap for index in index_vals):
raise exceptions.PlotlyError("If colormap is a "
"dictionary, all the "
"names in the index "
"must be keys.")
figure = scatterplot_dict(
dataframe, headers, diag, size, height, width, title,
index, index_vals, endpts, colormap, colormap_type,
**kwargs
)
return figure
else:
figure = scatterplot_theme(
dataframe, headers, diag, size, height, width, title,
index, index_vals, endpts, colormap, colormap_type,
**kwargs
)
return figure