In [6]:
%pylab inline
Seaborn is a Python visualization library. It provides a high-level interface for drawing attractive statistical graphics. It is built on top of matplotlib and tightly integrated with the PyData stack, including support for numpy and pandas data structures and statistical routines from scipy and statsmodels.
In [7]:
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="darkgrid")
rs = np.random.RandomState(33)
d = rs.normal(size=(100, 30))
f, ax = plt.subplots(figsize=(9, 9))
cmap = sns.diverging_palette(220, 10, as_cmap=True)
sns.corrplot(d, annot=False, sig_stars=False,
diag_names=False, cmap=cmap, ax=ax)
f.tight_layout()
In [8]:
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="dark")
f, axes = plt.subplots(3, 3, figsize=(9, 9), sharex=True, sharey=True)
rs = np.random.RandomState(50)
for ax, s in zip(axes.flat, np.linspace(0, 3, 10)):
x, y = rs.randn(2, 50)
cmap = sns.cubehelix_palette(start=s, light=1, as_cmap=True)
sns.kdeplot(x, y, cmap=cmap, shade=True, cut=5, ax=ax)
ax.set(xlim=(-3, 3), ylim=(-3, 3))
f.tight_layout()
In [9]:
import seaborn as sns
sns.set()
flights_long = sns.load_dataset("flights")
flights = flights_long.pivot("month", "year", "passengers")
flights = flights.reindex(flights_long.iloc[:12].month)
sns.heatmap(flights, annot=True, fmt="d")
Out[9]:
Bokeh is a Python interactive visualization library that targets modern web browsers for presentation. Its goal is to provide elegant, concise construction of novel graphics in the style of D3.js, but also deliver this capability with high-performance interactivity over very large or streaming datasets. Bokeh can help anyone who would like to quickly and easily create interactive plots, dashboards, and data applications.
In [10]:
from bokeh.plotting import *
output_notebook()
In [11]:
from collections import OrderedDict
import numpy as np
from bokeh.plotting import *
from bokeh.models import HoverTool, ColumnDataSource
from bokeh.sampledata.les_mis import data
nodes = data['nodes']
names = [node['name'] for node in sorted(data['nodes'], key=lambda x: x['group'])]
N = len(nodes)
counts = np.zeros((N, N))
for link in data['links']:
counts[link['source'], link['target']] = link['value']
counts[link['target'], link['source']] = link['value']
colormap = [
"#444444", "#a6cee3", "#1f78b4", "#b2df8a", "#33a02c", "#fb9a99",
"#e31a1c", "#fdbf6f", "#ff7f00", "#cab2d6", "#6a3d9a"
]
xname = []
yname = []
color = []
alpha = []
for i, n1 in enumerate(nodes):
for j, n2 in enumerate(nodes):
xname.append(n1['name'])
yname.append(n2['name'])
a = min(counts[i,j]/4.0, 0.9) + 0.1
alpha.append(a)
if n1['group'] == n2['group']:
color.append(colormap[n1['group']])
else:
color.append('lightgrey')
source = ColumnDataSource(
data=dict(
xname=xname,
yname=yname,
colors=color,
alphas=alpha,
count=counts.flatten(),
)
)
p = figure(title="Les Mis Occurrences",
x_axis_location="above", tools="resize,hover,save",
x_range=list(reversed(names)), y_range=names)
p.plot_width = 800
p.plot_height = 800
p.rect('xname', 'yname', 0.9, 0.9, source=source,
color='colors', alpha='alphas', line_color=None)
p.grid.grid_line_color = None
p.axis.axis_line_color = None
p.axis.major_tick_line_color = None
p.axis.major_label_text_font_size = "5pt"
p.axis.major_label_standoff = 0
p.xaxis.major_label_orientation = np.pi/3
hover = p.select(dict(type=HoverTool))
hover.tooltips = OrderedDict([
('names', '@yname, @xname'),
('count', '@count'),
])
show(p)
In [12]:
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from scipy import optimize
from bokeh import mpl
from bokeh.plotting import show
# Set the palette colors.
sns.set(palette="Set2")
# Build the sin wave
def sine_wave(n_x, obs_err_sd=1.5, tp_err_sd=.3):
x = np.linspace(0, (n_x - 1) / 2, n_x)
y = np.sin(x) + np.random.normal(0, obs_err_sd) + np.random.normal(0, tp_err_sd, n_x)
return y
sines = np.array([sine_wave(31) for _ in range(20)])
# Generate the Seaborn plot with "ci" bars.
ax = sns.tsplot(sines, err_style="ci_bars", interpolate=False)
xmin, xmax = ax.get_xlim()
x = np.linspace(xmin, xmax, sines.shape[1])
out, _ = optimize.leastsq(lambda p: sines.mean(0) - (np.sin(x / p[1]) + p[0]), (0, 2))
a, b = out
xx = np.linspace(xmin, xmax, 100)
plt.plot(xx, np.sin(xx / b) + a, c="#444444")
plt.title("Seaborn tsplot with CI in bokeh.")
show(mpl.to_bokeh(name="sinerror"))
In [13]:
from collections import OrderedDict
from math import log, sqrt
import numpy as np
import pandas as pd
from six.moves import cStringIO as StringIO
from bokeh.plotting import *
antibiotics = """
bacteria, penicillin, streptomycin, neomycin, gram
Mycobacterium tuberculosis, 800, 5, 2, negative
Salmonella schottmuelleri, 10, 0.8, 0.09, negative
Proteus vulgaris, 3, 0.1, 0.1, negative
Klebsiella pneumoniae, 850, 1.2, 1, negative
Brucella abortus, 1, 2, 0.02, negative
Pseudomonas aeruginosa, 850, 2, 0.4, negative
Escherichia coli, 100, 0.4, 0.1, negative
Salmonella (Eberthella) typhosa, 1, 0.4, 0.008, negative
Aerobacter aerogenes, 870, 1, 1.6, negative
Brucella antracis, 0.001, 0.01, 0.007, positive
Streptococcus fecalis, 1, 1, 0.1, positive
Staphylococcus aureus, 0.03, 0.03, 0.001, positive
Staphylococcus albus, 0.007, 0.1, 0.001, positive
Streptococcus hemolyticus, 0.001, 14, 10, positive
Streptococcus viridans, 0.005, 10, 40, positive
Diplococcus pneumoniae, 0.005, 11, 10, positive
"""
drug_color = OrderedDict([
("Penicillin", "#0d3362"),
("Streptomycin", "#c64737"),
("Neomycin", "black" ),
])
gram_color = {
"positive" : "#aeaeb8",
"negative" : "#e69584",
}
df = pd.read_csv(StringIO(antibiotics),
skiprows=1,
skipinitialspace=True,
engine='python')
width = 800
height = 800
inner_radius = 90
outer_radius = 300 - 10
minr = sqrt(log(.001 * 1E4))
maxr = sqrt(log(1000 * 1E4))
a = (outer_radius - inner_radius) / (minr - maxr)
b = inner_radius - a * maxr
def rad(mic):
return a * np.sqrt(np.log(mic * 1E4)) + b
big_angle = 2.0 * np.pi / (len(df) + 1)
small_angle = big_angle / 7
x = np.zeros(len(df))
y = np.zeros(len(df))
p = figure(plot_width=width, plot_height=height, title="",
x_axis_type=None, y_axis_type=None,
x_range=[-420, 420], y_range=[-420, 420],
min_border=0, outline_line_color="black",
background_fill="#f0e1d2", border_fill="#f0e1d2")
p.line(x+1, y+1, alpha=0)
# annular wedges
angles = np.pi/2 - big_angle/2 - df.index.to_series()*big_angle
colors = [gram_color[gram] for gram in df.gram]
p.annular_wedge(
x, y, inner_radius, outer_radius, -big_angle+angles, angles, color=colors,
)
# small wedges
p.annular_wedge(x, y, inner_radius, rad(df.penicillin),
-big_angle+angles+5*small_angle, -big_angle+angles+6*small_angle,
color=drug_color['Penicillin'])
p.annular_wedge(x, y, inner_radius, rad(df.streptomycin),
-big_angle+angles+3*small_angle, -big_angle+angles+4*small_angle,
color=drug_color['Streptomycin'])
p.annular_wedge(x, y, inner_radius, rad(df.neomycin),
-big_angle+angles+1*small_angle, -big_angle+angles+2*small_angle,
color=drug_color['Neomycin'])
# circular axes and lables
labels = np.power(10.0, np.arange(-3, 4))
radii = a * np.sqrt(np.log(labels * 1E4)) + b
p.circle(x, y, radius=radii, fill_color=None, line_color="white")
p.text(x[:-1], radii[:-1], [str(r) for r in labels[:-1]],
text_font_size="8pt", text_align="center", text_baseline="middle")
# radial axes
p.annular_wedge(x, y, inner_radius-10, outer_radius+10,
-big_angle+angles, -big_angle+angles, color="black")
# bacteria labels
xr = radii[0]*np.cos(np.array(-big_angle/2 + angles))
yr = radii[0]*np.sin(np.array(-big_angle/2 + angles))
label_angle=np.array(-big_angle/2+angles)
label_angle[label_angle < -np.pi/2] += np.pi # easier to read labels on the left side
p.text(xr, yr, df.bacteria, angle=label_angle,
text_font_size="9pt", text_align="center", text_baseline="middle")
# OK, these hand drawn legends are pretty clunky, will be improved in future release
p.circle([-40, -40], [-370, -390], color=list(gram_color.values()), radius=5)
p.text([-30, -30], [-370, -390], text=["Gram-" + gr for gr in gram_color.keys()],
text_font_size="7pt", text_align="left", text_baseline="middle")
p.rect([-40, -40, -40], [18, 0, -18], width=30, height=13,
color=list(drug_color.values()))
p.text([-15, -15, -15], [18, 0, -18], text=list(drug_color.keys()),
text_font_size="9pt", text_align="left", text_baseline="middle")
p.xgrid.grid_line_color = None
p.ygrid.grid_line_color = None
show(p)
In [14]:
from collections import OrderedDict
from bokeh.plotting import *
from bokeh.models import HoverTool, ColumnDataSource
from bokeh.sampledata import periodic_table
elements = periodic_table.elements[periodic_table.elements["group"] != "-"]
group_range = [str(x) for x in range(1,19)]
period_range = [str(x) for x in reversed(sorted(set(elements["period"])))]
colormap = {
"alkali metal" : "#a6cee3",
"alkaline earth metal" : "#1f78b4",
"halogen" : "#fdbf6f",
"metal" : "#b2df8a",
"metalloid" : "#33a02c",
"noble gas" : "#bbbb88",
"nonmetal" : "#baa2a6",
"transition metal" : "#e08e79",
}
source = ColumnDataSource(
data=dict(
group=[str(x) for x in elements["group"]],
period=[str(y) for y in elements["period"]],
symx=[str(x)+":0.1" for x in elements["group"]],
numbery=[str(x)+":0.8" for x in elements["period"]],
massy=[str(x)+":0.15" for x in elements["period"]],
namey=[str(x)+":0.3" for x in elements["period"]],
sym=elements["symbol"],
name=elements["name"],
cpk=elements["CPK"],
atomic_number=elements["atomic number"],
electronic=elements["electronic configuration"],
mass=elements["atomic mass"],
type=elements["metal"],
type_color=[colormap[x] for x in elements["metal"]],
)
)
TOOLS = "resize,hover,save"
p = figure(title="Periodic Table", tools=TOOLS,
x_range=group_range, y_range=period_range)
p.plot_width = 1200
p.toolbar_location = "left"
p.rect("group", "period", 0.9, 0.9, source=source,
fill_alpha=0.6, color="type_color")
text_props = {
"source": source,
"angle": 0,
"color": "black",
"text_align": "left",
"text_baseline": "middle"
}
p.text(x=dict(field="symx", units="data"),
y=dict(field="period", units="data"),
text=dict(field="sym", units="data"),
text_font_style="bold", text_font_size="15pt", **text_props)
p.text(x=dict(field="symx", units="data"),
y=dict(field="numbery", units="data"),
text=dict(field="atomic_number", units="data"),
text_font_size="9pt", **text_props)
p.text(x=dict(field="symx", units="data"),
y=dict(field="namey", units="data"),
text=dict(field="name", units="data"),
text_font_size="6pt", **text_props)
p.text(x=dict(field="symx", units="data"),
y=dict(field="massy", units="data"),
text=dict(field="mass", units="data"),
text_font_size="5pt", **text_props)
p.grid.grid_line_color = None
hover = p.select(dict(type=HoverTool))
hover.tooltips = OrderedDict([
("name", "@name"),
("atomic number", "@atomic_number"),
("type", "@type"),
("atomic mass", "@mass"),
("CPK color", "$color[hex, swatch]:cpk"),
("electronic configuration", "@electronic"),
])
show(p)
In [ ]: