def test_simple(self):
x = blaze.array([1+1j, 0+2j, 1+2j, blaze.inf, blaze.nan])
y_r = blaze.array([blaze.sqrt(2.), 2, blaze.sqrt(5),
blaze.inf, blaze.nan])
y = blaze.abs(x)
for i in range(len(x)):
assert_almost_equal(y[i], y_r[i])
def plot(self, output_file="termite.html"):
t = blz.Data(self.input_file)
df = pd.read_csv(self.input_file)
MAX = blz.compute(t.weight.max())
MIN = blz.compute(t.weight.min())
# Create a size variable to define the size of the the circle for the plot.
t = blz.transform(t, size=blz.sqrt((t.weight - MIN)/(MAX - MIN))*50)
WORDS = t['word'].distinct()
WORDS = into(list, WORDS)
topics = t['topic'].distinct()
topics = into(list, topics)
# Convert topics to strings
TOPICS = [str(i) for i in topics]
source = into(pd.DataFrame, t)
plt.output_file(output_file)
data_source = ColumnDataSource(source)
p = plt.figure(x_range=TOPICS, y_range=WORDS,
plot_width=1000, plot_height=1700,
title=self.title)
p.circle(x="topic", y="word", size="size", fill_alpha=0.6, source=data_source)
#p.xaxis().major_label_orientation = np.pi/3
logging.info("generating termite plot for file %s" % self.input_file)
plt.show(p)
def plot(self, output_file="termite.html"):
import blaze as blz
from odo import into
import pandas as pd
import bokeh.plotting as plt
from bokeh.models.sources import ColumnDataSource
t = blz.Data(self.input_file)
MAX = blz.compute(t.weight.max())
MIN = blz.compute(t.weight.min())
# Create a size variable to define the size of the the circle for the plot.
t = blz.transform(t, size=blz.sqrt((t.weight - MIN)/(MAX - MIN))*50)
WORDS = t['word'].distinct()
WORDS = into(list, WORDS)
topics = t['topic'].distinct()
topics = into(list, topics)
# Convert topics to strings
TOPICS = [str(i) for i in topics]
source = into(pd.DataFrame, t)
plt.output_file(output_file)
data_source = ColumnDataSource(source)
p = plt.figure(x_range=TOPICS, y_range=WORDS,
plot_width=1000, plot_height=1700,
title=self.title)
p.circle(x="topic", y="word", size="size", fill_alpha=0.6, source=data_source)
plt.show(p)
def plot(self):
t = blz.Data(self.input_file)
df = pd.read_csv(self.input_file)
MAX = blz.compute(t.weight.max())
MIN = blz.compute(t.weight.min())
# Create a size variable to define the size of the the circle for the plot.
t = blz.transform(t, size=blz.sqrt((t.weight - MIN)/(MAX - MIN))*50)
WORDS = t['word'].distinct()
WORDS = into(list, WORDS)
topics = t['topic'].distinct()
topics = into(list, topics)
# Convert topics to strings
TOPICS = [str(i) for i in topics]
source = into(pd.DataFrame, t)
data_source = ColumnDataSource(source)
p = plt.figure(x_range=TOPICS, y_range=WORDS,
plot_width=1000, plot_height=1700, title=None)
p.circle(x="topic", y="word", size="size", fill_alpha=0.6, source=data_source)
#p.xaxis().major_label_orientation = np.pi/3
logging.info("generating termite plot for file %s" % self.input_file)
script, div = components(p, CDN)
return script, div
def termite(modeled_corpus, plot_title="Termite plot", topn=15):
"""A Bokeh Termite Visualization for LDA results analysis.
Parameters
----------
input_file : str or pandas DataFrame
A pandas dataframe from a topik model get_termite_data() containing columns "word", "topic" and "weight".
May also be a string, in which case the string is a filename of a csv file with the above columns.
title : str
The title for your termite plot
Examples
--------
>>> plot = termite(test_model_output, plot_title="My model results", topn=5)
"""
prepared_model_vis_data = _termite_data(modeled_corpus, topn)
t = blz.Data(prepared_model_vis_data)
MAX = blz.compute(t.weight.max())
MIN = blz.compute(t.weight.min())
# Create a size variable to define the size of the the circle for the plot.
t = blz.transform(t, size=blz.sqrt((t.weight - MIN) / (MAX - MIN)) * 50)
WORDS = t['word'].distinct()
WORDS = into(list, WORDS)
topics = t['topic'].distinct()
topics = into(list, topics)
# Convert topics to strings
TOPICS = [str(i) for i in topics]
source = into(pd.DataFrame, t)
data_source = sources.ColumnDataSource(source)
p = plt.figure(x_range=TOPICS,
y_range=WORDS,
plot_width=1000,
plot_height=1700,
title=plot_title)
p.circle(x="topic",
y="word",
size="size",
fill_alpha=0.6,
source=data_source)
return p
def termite(modeled_corpus, plot_title="Termite plot", topn=15):
"""A Bokeh Termite Visualization for LDA results analysis.
Parameters
----------
input_file : str or pandas DataFrame
A pandas dataframe from a topik model get_termite_data() containing columns "word", "topic" and "weight".
May also be a string, in which case the string is a filename of a csv file with the above columns.
title : str
The title for your termite plot
Examples
--------
>>> plot = termite(test_model_output, plot_title="My model results", topn=5)
"""
prepared_model_vis_data = _termite_data(modeled_corpus, topn)
t = blz.Data(prepared_model_vis_data)
MAX = blz.compute(t.weight.max())
MIN = blz.compute(t.weight.min())
# Create a size variable to define the size of the the circle for the plot.
t = blz.transform(t, size=blz.sqrt((t.weight - MIN)/(MAX - MIN))*50)
WORDS = t['word'].distinct()
WORDS = into(list, WORDS)
topics = t['topic'].distinct()
topics = into(list, topics)
# Convert topics to strings
TOPICS = [str(i) for i in topics]
source = into(pd.DataFrame, t)
data_source = sources.ColumnDataSource(source)
p = plt.figure(x_range=TOPICS, y_range=WORDS,
plot_width=1000, plot_height=1700,
title=plot_title)
p.circle(x="topic", y="word", size="size", fill_alpha=0.6, source=data_source)
return p
def distance(lat1, lon1, lat2, lon2, R=3959):
# http://andrew.hedges.name/experiments/haversine/
dlon = radians(lon2 - lon1)
dlat = radians(lat2 - lat1)
a = sin(dlat / 2.0) ** 2 + cos(lat1) * cos(lat2) * sin(dlon / 2.0) ** 2
return R * 2 * atan2(sqrt(a), sqrt(1 - a))
def distance(lat1, lon1, lat2, lon2, R=3959):
# http://andrew.hedges.name/experiments/haversine/
dlon = radians(lon2 - lon1)
dlat = radians(lat2 - lat1)
a = sin(dlat / 2.0) ** 2 + cos(lat1) * cos(lat2) * sin(dlon / 2.0) ** 2
return R * 2 * atan2(sqrt(a), sqrt(1 - a))
def test_cos(self):
a = blaze.array([0, math.pi/6, math.pi/3, 0.5*math.pi,
math.pi, 1.5*math.pi, 2*math.pi])
b = blaze.array([1, 0.5*blaze.sqrt(3), 0.5, 0, -1, 0, 1])
assert_allclose(blaze.cos(a), b, rtol=1e-15, atol=1e-15)
assert_allclose(blaze.cos(-a), b, rtol=1e-15, atol=1e-15)
def test_sin(self):
a = blaze.array([0, math.pi/6, math.pi/3, 0.5*math.pi,
math.pi, 1.5*math.pi, 2*math.pi])
b = blaze.array([0, 0.5, 0.5*blaze.sqrt(3), 1, 0, -1, 0])
assert_allclose(blaze.sin(a), b, rtol=1e-15, atol=1e-15)
assert_allclose(blaze.sin(-a), -b, rtol=1e-15, atol=1e-15)
def test_sqrt(self):
a = blaze.array([0., 9., 64., 1e20, 12345])
b = blaze.array([0., 3., 8., 1e10, math.sqrt(12345)])
result = blaze.sqrt(a)
assert_almost_equal(result, b)
