def createBokehChart(self):
plotwidth = int(self.getPreferredOutputWidth() / 2)
plotheight = int(self.getPreferredOutputHeight() * 0.75)
defaultbin = math.sqrt(len(self.getWorkingPandasDataFrame().index))
binsize = int(self.options.get('binsize', defaultbin))
valueFields = self.getValueFields()
histograms = []
if len(valueFields) != 1:
for i, valueField in enumerate(valueFields):
color = self.options.get("color")
if color is None:
color = Colors.hexRGB(1. * i / 2)
histograms.append(
Histogram(self.getWorkingPandasDataFrame(),
values=valueField,
plot_width=plotwidth,
plot_height=plotheight,
bins=binsize,
color=color,
xgrid=True,
ygrid=True,
ylabel='Frequency'))
return histograms
else:
return Histogram(self.getWorkingPandasDataFrame(),
values=self.getValueFields()[0],
bins=binsize,
color=self.options.get("color"),
xgrid=True,
ygrid=True,
ylabel='Frequency')
def createBokehChart(self):
plotwidth = int(self.getPreferredOutputWidth() / 2)
plotheight = int(self.getPreferredOutputHeight() * 0.75)
binsize = int(self.options.get('binsize', 10))
valueFields = self.getValueFields()
histograms = []
if len(valueFields) != 1:
for i in valueFields:
histograms.append(
Histogram(self.getWorkingPandasDataFrame(),
values=i,
plot_width=plotwidth,
plot_height=plotheight,
bins=binsize,
color=self.options.get("color"),
xgrid=True,
ygrid=True))
return histograms
else:
return Histogram(self.getWorkingPandasDataFrame(),
values=self.getValueFields()[0],
bins=binsize,
color=self.options.get("color"),
xgrid=True,
ygrid=True)
def plot_histogram(same, diff):
df = {"PAINS vs. PAINS": same, "PAINS vs. ChEMBL": diff}
output_file("histogram_pains_self_diff.html")
hist = Histogram(df, bins=20, density=True, legend=True)
hist.x_range = Range1d(0, 1)
#hist.legend.orientation = "top_right"
show(hist)
def exibir(self):
for i in self.dados.keys():
if len(self.dados[i]) > 0: continue
else: return
defaults.width, defaults.height = 400, 300
# prepare some data
# input options
hist_pontuacao = Histogram(self.dados["pontos"],
title="Grades por pontuação",
xlabel="Pontuação",
ylabel="Número de grades",
responsive=True,
bins=30)
hist_tamanho = Histogram(self.dados["tamanhos"],
title="Grades por quantidade de disciplinas",
xlabel="Número de disciplinas",
ylabel="Número de grades",
responsive=True,
bins=8)
hist_pop = Histogram(self.dados["popularidade"],
title="Ocorrências da disciplina x",
xlabel="Disciplina",
ylabel="Ocorrências nas grades",
responsive=True,
bins=46)
output_file("html/histograms.html")
show(hplot(hist_pontuacao, hist_tamanho, hist_pop))
def plot_actions_players_min(actions: dict, output_file_url: str) -> None:
"""
Plots all actions in a line diagrams and outputs them to an html file.
:param actions: a list of all actions and their timestamp.
:param output_file_url: string containing the directory and filename
:return: None
"""
# output to static HTML file
output_file(output_file_url)
tabs = []
for action in actions:
# create a new plot with a title and axis labels
p = Histogram(actions[action],
title=action,
bins=[0, 15, 30, 45, 60, 75, 90, 105])
p.xaxis.axis_label = 'Tijd (min.)'
p.yaxis.axis_label = 'Frequentie'
p.x_range = Range1d(0, 105)
# create a tab
tab = Panel(child=p, title=action)
# add to existing tabs
tabs.append(tab)
tabs = Tabs(tabs=tabs)
# show the results
show(tabs)
def plot_times(dataframe):
dataframe = dataframe.fillna(-1)
p = Histogram(dataframe,'total time',bins=24, color = 'green',
title="Processing Times",height=500,width=1000)
text = """Mean: {mean}
Min: {min}
Max: {max}""".format(mean=round(dataframe[dataframe.status==0]['total time'].mean(skipna=True),3),min = dataframe[dataframe.status==0]['total time'].min(),max=dataframe[dataframe.status==0]['total time'].max())
mytext = glyphs.Text(x=p.x_range.end-(p.x_range.end/3), y=p.y_range.end - (p.y_range.end/3),text=[text],text_font_size='10pt')
p.add_glyph(mytext)
return p
def histogram(self,
dataframe,
bins=None,
width=None,
height=None,
palette=None,
title='Histogram',
values=None,
groups=None,
legend=True):
palette = self.__default_options__.get(
'palette', None) if palette is None else palette
width = self.__default_options__.get('width',
None) if width is None else width
if values:
unique_values = dataframe[groups].unique()
palette = self._palette(palette, len(unique_values))
else:
palette = None
width, height = self._width_height(width, height)
histogram = Histogram(dataframe,
values=values,
color=groups,
bins=bins,
legend=True,
width=width,
height=height,
palette=palette,
title=title)
return histogram
def Histograms():
plot = Histogram(df,
values=value,
color=value,
title=title,
legend='top_right')
# script, div = components(plot)
return plot
def showBacktestingResult(self):
"""显示回测结果"""
d = self.calculateBacktestingResult()
# 输出
self.output('-' * 30)
self.output('First Trade：\t%s' % d['timeList'][0])
self.output('Last Trade：\t%s' % d['timeList'][-1])
self.output('Total Trades：\t%s' % formatNumber(d['totalResult']))
self.output('Total Return：\t%s' % formatNumber(d['capital']))
self.output('Maximum Drawdown: \t%s' %
formatNumber(min(d['drawdownList'])))
self.output('Ave Trade：\t%s' %
formatNumber(d['capital'] / d['totalResult']))
self.output('Ave Slippage：\t%s' %
formatNumber(d['totalSlippage'] / d['totalResult']))
self.output('Ave Commission：\t%s' %
formatNumber(d['totalCommission'] / d['totalResult']))
self.output('Win Ratio\t\t%s%%' % formatNumber(d['winningRate']))
self.output('Ave Win\t%s' % formatNumber(d['averageWinning']))
self.output('Ave Loss\t%s' % formatNumber(d['averageLosing']))
self.output('Profit Factor：\t%s' % formatNumber(d['profitLossRatio']))
# Use Bokeh to plot
from bokeh.charts import Area, Line, Histogram
from bokeh.layouts import column
from bokeh.io import show
plotdata = {
"TradeN": range(len(d['capitalList'])),
"Equity Curve": d['capitalList'],
"Maximum Drawdown": d['drawdownList'],
"Profit/Loss": d['pnlList']
}
f1 = Line(plotdata,
x="TradeN",
y="Equity Curve",
color="blue",
width=1000,
height=300)
f2 = Area(plotdata,
x="TradeN",
y="Maximum Drawdown",
color="tomato",
width=1000,
height=300)
f3 = Histogram(plotdata,
values="Profit/Loss",
bins=30,
color="green",
width=1000,
height=300)
show(column(f1, f2, f3))
def nbd():
#pull 'nbd' from input field and store it:
nbd = request.args.get('nbd')
room_type = "Private room"
#nbd = "East Village"
train = pd.read_sql_query("""
SELECT * FROM listings_price
WHERE neighbourhood_cleansed = %(nbd)s
AND room_type = %(room_type)s;
""",
con, index_col = "id",
params = {"nbd":nbd, "room_type":room_type})
#train
train["ratio"] = (train["preds"] - train["price"])/train["price"]
#keep train for the histogram
sm_train = train[train["ratio"] > 0][train["ratio"] < 1.2]
sm_train = sm_train.sort_values("diff", ascending = False)
sm_train["diff"]
births = []
#showing some tables:
for i in range(0,25):
births.append(dict(price=int(sm_train.iloc[i]['price']),
city=sm_train.iloc[i]['name'],
id = sm_train.index[i],
room_type=int(sm_train.iloc[i]['preds']),
url=sm_train.iloc[i]['listing_url']))
the_result = ''
#births
plot = Histogram(train["price"], bins = 20, plot_width=500, plot_height=300)
script, div = components(plot)
title = "Distribution of daily prices in {0}".format(nbd)
median = train["price"].median()
percentile_05 = np.round(train["price"].quantile(0.05), 1)
percentile_95 = np.round(train["price"].quantile(0.95), 1)
more_info = "The median price per day is ${0}. 95% of the listings are in \
between ${1} and ${2}".format(median, percentile_05, percentile_95)
return render_template('nbd.html', births = births, the_result = the_result, nbd = nbd,
script = script, div = div, title = title, more_info = more_info)
def create_figure(current_feature_name, bins): p = Histogram(iris_df, current_feature_name, title=current_feature_name, color='Species', bins=bins, legend='top_right', width=600, height=400) # Set the x axis label p.xaxis.axis_label = current_feature_name # Set the y axis label p.yaxis.axis_label = 'Count' return p
def create_histogram2(data):
TOOLS = [HoverTool(tooltips=[('Age:', '$x{int}'), ('total', '@y')])]
plot = Histogram(data,
title='Age:',
legend='bottom_right',
ylabel="Number of Tournaments",
tools=TOOLS,
plot_width=400,
plot_height=400)
return plot
def histograms(Y, bins=50, title='', xlabel='', height=3):
df = {xlabel: Y}
df = pd.DataFrame(df)
plot = Histogram(df,
xlabel,
legend=None,
bins=bins,
title=title,
plot_height=int(height * ht),
sizing_mode='scale_width')
return plot
def showHistogram(times):
mydict = {'Time (s)': totalboot(times)}
hist = Histogram(pd.DataFrame(mydict),
values="Time (s)",
title="Total Boot Time (s)",
legend="top_right",
background_fill_alpha=0.6,
bar_width=1)
show(hist)
def plot_distance_distrib(G):
"""
Plots the distribution of distances from the Graph
"""
W = list([G[x][y]['weight'] for (x, y) in G.edges()])
h = Histogram(W,
title="Weight (proximity) distribution",
xlabel='weights',
ylabel="Counts(weights)",
bins=50)
return h
def test_responsive_chart_starts_at_correct_size(output_file_url, selenium):
hist = Histogram(df['mpg'], title="MPG Distribution", responsive=True)
save(hist)
selenium.set_window_size(width=1000, height=600)
selenium.get(output_file_url)
canvas = selenium.find_element_by_tag_name('canvas')
wait_for_canvas_resize(canvas, selenium)
# Canvas width should be just under 1000
assert canvas.size['width'] > 900
assert canvas.size['width'] < 1000
def generate_histogram(table_data, form_data):
"""Generate histogram."""
if form_data['color'] == '':
color = 'blue'
else:
color = form_data['color']
plot = Histogram(table_data,
values=form_data['column'],
color=color,
tools='pan,wheel_zoom,box_zoom,reset,resize,hover,save')
plot.title.text_font_style = "bold"
output_file("output.html")
save(plot)
return build_html()
def get(self, request):
nyse = Listing.objects.filter(exchange='2').count()
nasdaq = Listing.objects.filter(exchange='3').count()
amex = Listing.objects.filter(exchange='1').count()
asx = Listing.objects.filter(exchange='4').count()
exchanges = ["NYSE", "NASDAQ", "AMEX", "ASX"]
values = [nyse, nasdaq, amex, asx ]
# Bar Chart
plot = figure(plot_width=400,
plot_height=400,
x_range=exchanges,
title="Number of Listings")
plot.vbar(x=exchanges,
width=0.5,
bottom=0,
top=values,
color="navy")
script, div = components(plot)
#average_board_size = BoardMember.objects.values_list('id', flat=True)
#average_board_size = BoardMember.objects.all().values('id').query
#average_board_size = list(BoardMember.objects.values_list('id', flat=True))
board_sizes = list(BoardMember.objects.all().values('company').annotate(Count('director')).values_list('director__count', flat=True))
board_statistics = BoardStatistics(board_sizes)
director_ages = list(filter(None, Director.objects.all().values_list('age', flat=True)))
director_statistics = BoardStatistics(director_ages)
plot = Histogram(board_sizes)
histogram_script, histogram_div = components(plot)
return render(request, self.template_name, {
'bokeh_script': script,
'bokeh_div': div,
'bokeh_histogram_div': histogram_div,
'bokeh_histogram_script': histogram_script,
'total_companies': Company.objects.count(),
'total_directors': Director.objects.count(),
'last_update': str(Version.last_update),
'total_listings': Listing.objects.count(),
'board_statistics': board_statistics,
'director_statistics': director_statistics
})
def test_responsive_chart_starts_at_correct_size(output_file_url, selenium):
hist = Histogram(df['mpg'], title="MPG Distribution", responsive=True)
save(hist)
selenium.set_window_size(width=1000, height=600)
selenium.get(output_file_url)
assert has_no_console_errors(selenium)
canvas = selenium.find_element_by_tag_name('canvas')
wait_for_canvas_resize(canvas, selenium)
# Canvas width should be just under 1000 * 0.9
# (default file_html has a body width of 90%)
assert canvas.size['width'] > 850
assert canvas.size['width'] < 900
def simplePlotter(room, datetime, chartpick):
df_day_counts = pd.read_sql_query(
day_count_query.format(date=datetime, room=room), connectDB())
# df_day_survey_counts = pd.read_sql_query(day_count_and_survey_query.format(date=datetime, room=room),
# connectDB())
if chartpick == 'Histogram':
plot = Histogram(df_day_counts['count'], title="Counts", bins=10)
if chartpick == 'Bar':
plot = Bar(df_day_counts['count'], title="Counts")
all_plots = gridplot([[plot]])
return all_plots
def ticker(ticker):
# build line
line = Line(betalyzer.df_betas[ticker], plot_width=1000, plot_height=400)
bokeh_script, bokeh_div = components(line)
# build scatter
scatter = Scatter(betalyzer.df_changes.head(betalyzer.window),
x=betalyzer.market,
y=ticker,
plot_width=550,
plot_height=400)
scatter_script, scatter_div = components(scatter)
# build histogram
df_hist = betalyzer.df_changes[[ticker,
'SPY']].head(500).unstack().reset_index()
df_hist.rename(columns={'level_0': 'ticker', 0: 'change'}, inplace=True)
hist = Histogram(df_hist,
values='change',
color='ticker',
bins=20,
legend='top_right',
plot_width=550,
plot_height=400)
hist_script, hist_div = components(hist)
return render_template(
'ticker.html',
ticker=ticker,
bokeh_script=bokeh_script,
bokeh_div=bokeh_div,
scatter_script=scatter_script,
scatter_div=scatter_div,
hist_script=hist_script,
hist_div=hist_div,
window=betalyzer.window,
dt_ticker=betalyzer.df_tickers.loc[ticker].to_dict())
import numpy as np
import pandas as pd
from bokeh.charts import Histogram, show, output_file
# build some distributions and load them into a dict
mu, sigma = 0, 0.5
normal = np.random.normal(mu, sigma, 1000)
lognormal = np.random.lognormal(mu, sigma, 1000)
distributions = OrderedDict(normal=normal, lognormal=lognormal)
# create a pandas data frame from the dict
df = pd.DataFrame(distributions)
distributions = df.to_dict()
for k, v in distributions.items():
distributions[k] = v.values()
# any of the following commented are valid Histogram inputs
#df = list(distributions.values())
#df = tuple(distributions.values())
#df = tuple([tuple(x) for x in distributions.values()])
#df = np.array(list(distributions.values()))
#df = list(distributions.values())[0]
output_file("histograms.html")
hist = Histogram(df, bins=50, legend=True)
show(hist)
#%matplotlib inline
#pylab.rcParams['figure.figsize'] = (10, 6)
def convert_int(dataframe, colname):
dataframe[colname] = pd.to_numeric(dataframe[colname], errors='coerce')
limit_rows = 1000000
df = pd.read_csv("C:/Users/vasir/Desktop/ADM/train_ver2.CSV", nrows=limit_rows)
convert_int(df, 'age')
print df['age'].dtype
df['age'] = df['age'].fillna(-1)
cols = ['age']
df[cols] = df[cols].applymap(np.int64)
df_frac = df.sample(frac=0.01)
p_age = Histogram(df_frac, values='age', title="Age Distribution")
#show(p_age)
dffrac1 = df_frac.dropna(subset=['sexo'], how='any')
dffrac1.head()
#dffrac1['sexo']=dffrac1['sexo'].astype('category')
p = Bar(dffrac1, 'sexo', title="Sex")
#show(p)
dffrac2 = df_frac.dropna(subset=['renta'], how='any')
bar_renta = Bar(dffrac2,
values='renta',
label='nomprov',
agg='mean',
title="City Vs Renta",
legend=False,
from bokeh.charts import Histogram, output_file, show
from bokeh.sampledata.autompg import autompg as df
p = Histogram(df, values='hp', color='navy', title="HP Distribution")
output_file("histogram_color.html")
show(p)
get_ipython().system(
u'curl --upload-file restaraunts.html https://transfer.sh/restaruants.html'
)
# In[93]:
from bokeh.io import output_notebook
output_notebook()
# In[94]:
from bokeh.charts import Histogram, output_file, show
# In[96]:
p1 = Histogram(samp["SCORE"])
show(p1)
# In[103]:
p2 = Histogram(mRests,
'SCORE',
color='GRADE',
title="Score Grouped by Grade",
bins=15,
legend='top_left')
show(p2)
# In[99]:
def plot_prediction_histogram(images_path,
model_path,
weights_path,
img_shape,
required_class,
class_name_dict={},
batch_size=16,
preprocessing_function=None,
plotting_module="matplotlib"):
""" Function to plot the histogram of predicted probabilities of a given class
images_path --str: full path to the parent directory containing sub-directory(classes) of images
model_path --str: full path to a keras model (.json file) (No default)
weights_path --str: full path to the weights file (.hdf5 file) (No default)
img_shape --tuple: image shape to input to the model (eg : (224,224,3)) (No default)
required_class --str: The name of the required class on which to generate ROC (example "dog")
class_name_dict --dict: Dictionary mapping of classes (default {})
batch_size --int: The batch_size to use for prediction (Default 16)
preprocessing_function --function: The preprocessing function to use before prediction (Default None)
plotting_module --str: The plotting module to use. Either of 'matplotlib' or 'bokeh' (Default matplotlib)
Output:
Plots the histogram of the predicted probabilites of the required class
"""
if len(class_name_dict) == 0:
raise ValueError("Provide the class_name_dict")
# loading model and weights
json_file = open(model_path, 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights
loaded_model.load_weights(weights_path)
print('loaded model from disk')
# generator for data
test_datagen = ImageDataGenerator(
preprocessing_function=preprocessing_function)
test_generator = test_datagen.flow_from_directory(
images_path,
target_size=(img_shape[0], img_shape[1]),
class_mode='categorical',
batch_size=batch_size,
shuffle=False, # to get ordered result
)
# this is an important step else there is a difference in result between predict and predict_generator
test_generator.reset() # reset to start with sample 0
nb_samples = test_generator.samples
class_name_dict = test_generator.class_indices # eg {'dog': 0, 'cat': 1}
# predict
predictions = loaded_model.predict_generator(test_generator,
steps=nb_samples //
batch_size,
max_queue_size=10,
workers=1,
use_multiprocessing=False,
verbose=1)
class_idx = class_name_dict[required_class]
hist_data = predictions[:, class_idx]
if plotting_module == "matplotlib":
plt.hist(hist_data, bins=10)
plt.xlim(0, 1)
plt.title('Histogram of predicted probabilities')
plt.xlabel('Predicted probability of {}'.format(required_class))
plt.ylabel('Frequency')
elif plotting_module == "bokeh":
df = pd.DataFrame(
{"Predicted probability of {}".format(required_class): hist_data})
from bokeh.io import output_notebook
import warnings
warnings.filterwarnings('ignore')
from bokeh.charts import Histogram, show
output_notebook()
p = Histogram(df,
"Predicted probability of {}".format(required_class),
title="Histogram of predicted probabilities")
show(p)
else:
raise ValueError("Only bokeh and matplotlib are supported")
import numpy as np
# we build some distributions and load them into a dict
mu, sigma = 0, 0.5
normal = np.random.normal(mu, sigma, 1000)
lognormal = np.random.lognormal(mu, sigma, 1000)
distributions = dict(normal=normal, lognormal=lognormal)
# then we create a pandas df from the dict
import pandas as pd
df = pd.DataFrame(distributions)
# and finally we drop the df into out Histogram chart
from bokeh.charts import Histogram
hist = Histogram(df, bins=50, filename="histograms.html")
hist.title("Histograms").ylabel("frequency").legend(True).width(400).height(350).show()
def histogram(histDF, values, **kwargs):
from bokeh.charts import Histogram
return Histogram(histDF[values], **kwargs)
def compute_plot_all_Deff(tmin, tmax, particle_chemistry):
"""
Calculates and plots all Deffs in the timepoint range.
This function trims the cleaned MSD pandas dataframe to the user-
selected timepoint range, calculates a Deff from the mean MSD for
each timepoint within the range and for each particle chemistry,
plots a line graph of all Deffs across the timepoint range, and
gives geometric mean Deff values for each chemistry for the time
range specified.
Note: tmin must be less than tmax to get a timepoint range. If,
however, the user requires a Deff calculated from a single
timepoint, he or she can input an equal tmin and tmax, and the
function will consider only the single closest timepoint (on the
later side) to the input.
Inputs:
tmin: a float representing the minimum timepoint the user wishes to
consider in the Deff calculation
tmax: a float representing the maximum timepoint the user wishes to
consider in the Deff calculation (make this the same as tmin if a
single-timepoint Deff is desired)
particle_chemistry: a string matching the column title of the
particle chemistry which is to be emphasized: the Deffs of this
chemistry will be plotted on the histogram, bolded/dashed on the
line plot, and printed in the form of a geometric mean.
Outputs:
A bokeh histogram of Deffs for the inputted chemistry, on the same
figure as the below line plot (this figure defaults to fit nicely
in a 1280x800 screen, but plots can be resized as needed)
A bokeh line plot of Deffs for all particle chemistries across the
timepoint range, with emphasized chemistry bolded/dashed
Deff of inputted chemistry: a geometric mean of the Deffs between
tmin and tmax for the inputted chemistry, printed in the form of
a string within an explanatory sentence
avg_Deffs: a fresh pandas dataframe indexed with the columns
(particle chemistries) of the MSD dataframe, containing single
geometric mean Deff values for each particle chemistry
"""
# Verify time range validity
if tmin < 0 or tmax > round(max(msd.index)):
return "Error: input time range between 0 and your data's tmax"
else:
if tmin == 0:
print 'Divide by 0 error: tmin=0 changed to tmin=0.01'
tmin = 0.01
# Trim out-of-time-range rows
temp1_msd = msd[msd.index >= tmin]
# Trim to a length of 1 if user desires single-timepoint Deff
if tmin == tmax:
temp2_msd = temp1_msd.head(1)
else:
temp2_msd = temp1_msd[temp1_msd.index <= tmax]
# Calculate Deffs for only the timepoints needed and add as
# a new column to a new dataframe
index = temp2_msd.index
Deffs = pd.DataFrame(index=index, columns=columns2)
avg_Deffs = pd.DataFrame(index=columns2)
avg_Deffs_temp = []
h = Histogram([1], bins=50, width=300, height=250)
# maxes will eventually be used for sizing the histogram
maxes = []
# Lay the foundation for the bokeh figure
output_file('Deffs_hist_and_line_plot.html')
p = figure(
tools='resize,pan,box_zoom,wheel_zoom,reset,save', width=950,
height=650, x_axis_label='MSD timepoint', y_axis_label='Deff')
# Cycle through each particle chemistry and fill in Deffs
# and avg_Deffs
for title in columns2:
single_Deff_list = []
for i in range(0, len(temp2_msd)):
index = temp2_msd.index[i]
single_Deff_list.append(temp2_msd[title + ' geo'][index]/(
4*index**ALPHA))
# Add particle-chemistry-specific Deff list to Deffs
# dataframe
Deffs[title] = single_Deff_list
maxes.append(np.max(single_Deff_list))
# Add geometric mean Deff to what will become avg_Deffs
avg_Deffs_temp.append(scipy.stats.gmean(Deffs[title]))
# Create a special bold/dashed line for the inputted
# chemistry only, and generate the printed output
if title == particle_chemistry:
p.line(
Deffs.index, Deffs[title], line_width=5,
line_dash=(15, 10), legend=title, line_color=(
np.random.randint(256), np.random.randint(256),
np.random.randint(256))
)
h = Histogram(Deffs[particle_chemistry], width=300,
height=250)
print particle_chemistry + ' Deff = ' + str(
scipy.stats.gmean(Deffs[title]))
else:
p.line(
Deffs.index, Deffs[title], line_width=1, legend=title,
line_color=(
np.random.randint(256), np.random.randint(256),
np.random.randint(256))
)
avg_Deffs['Deff'] = avg_Deffs_temp
p.legend.label_text_font_size = '6pt'
# The line plot x-axis range is calibrated to include all
# of the desired data and the legend with no overlap
p.x_range = Range1d(tmin, tmax + (tmax - tmin)/5)
# The histogram x-axis is calibrated to remain at a
# constant scale for each given tmin/tmax combination--this
# gives a sense of scale for this particular histogram
# within the possible Deff values for all the chemistries
h.x_range = Range1d(0, np.max(maxes))
f = hplot(h, p)
show(f)
return avg_Deffs
def compute_hist_Deff(particle_chemistry, tmin, tmax):
"""
Calculates and plots Deff in timepoint range for a given chemistry.
This function trims the cleaned MSD pandas dataframe to the user-
selected timepoint range, calculates a Deff from the mean MSD for
each timepoint within the range, plots a histogram of the list of
Deffs, and gives a geometric mean Deff value for the time range
specified. This is all within the specified particle chemistry.
Note: tmin must be less than tmax.
Inputs:
particle_chemistry: a string matching the column title of the
particle chemistry for which a Deff is to be plotted and calculated
tmin: a float representing the minimum timepoint the user wishes to
consider in the Deff calculation
tmax: a float representing the maximum timepoint the user wishes to
consider in the Deff calculation
Outputs:
A bokeh charts histogram of Deff values calculated from the
particle chemistry's MSD of each timepoint within the range
Deff: a single float representing the geometric mean Deff value for
the timepoint range specified
Side effects:
The trimmed MSD dataset is appended (with a new column) to include
the list of Deffs for the given particle chemistry.
"""
# Verify time range validity
if tmin < 0 or tmax > round(max(msd.index)):
return "Error: input time range between 0 and your data's tmax"
else:
if tmin == 0:
print 'Divide by 0 error: tmin=0 changed to tmin=0.01'
tmin = 0.01
# Trim out-of-time-range rows
temp1_msd = msd[msd.index >= tmin]
temp2_msd = temp1_msd[temp1_msd.index <= tmax]
# Calculate Deffs for only the timepoints needed and add as a
# new column
Deff_list = []
for i in range(0, len(temp2_msd)):
index = temp2_msd.index[i]
# Calculate Deff using the conventional relationship
# between MSD and Deff
Deff_list.append(temp2_msd[particle_chemistry + ' geo'][index]/(
4*index**ALPHA))
temp2_msd[particle_chemistry + ' Deff'] = Deff_list
# Plot histogram and print mean Deff value
output_file('Deffs_hist.html')
p = Histogram(
temp2_msd[particle_chemistry + ' Deff'], bins=15, legend=False)
# Set range of x axis to reflect approximate range of all Deff
# values
p.x_range = Range1d(0, 0.015)
show(p)
# There's only one Deff column from this function: calculate
# geometric mean Deff from that column
Deff = scipy.stats.gmean(temp2_msd[particle_chemistry + ' Deff'])
return Deff
def get_memory_hists(self, mode='overview'):
""" Plot memory histogram in a row """
access = self.__get_memory_access_types(mode)
hists = []
data_dfs = []
col_cycle = []
col_index = []
for key, value in access.iteritems():
sql_query = 'SELECT length FROM memory'
sql_query += ' WHERE ' + value
sql_query += ' ORDER by line'
dataframe = pd.read_sql_query(sql_query, self.get_db())
color = tm.get_random_color()
col_sched = []
col_location = []
col_value = []
col_type = []
col_color = []
try:
# Some statistics
mean = np.round_(dataframe["length"].mean(), 2)
median = dataframe["length"].median()
sum_len = dataframe["length"].sum()
col_cycle.append(sum_len)
col_index.append(key)
# Plot histogram
hist_title = key
hist_title += ' / avg ' + str(mean)
hist_title += ' / mid ' + str(median)
plot_hist = Histogram(dataframe["length"].replace(0, np.nan),
'length',
bins=50,
color=color,
xlabel='Latency of instruction in cycle',
ylabel='Count',
title=hist_title)
except ValueError:
continue
# Ignore NaN
if mean == mean and median == median:
# Insert mean
col_sched.append(self.get_name_instruction_scheduler())
col_location.append(key)
col_value.append(mean)
col_type.append('Mean')
col_color.append(color)
# Insert median
col_sched.append(self.get_name_instruction_scheduler())
col_location.append(key)
col_value.append(median)
col_type.append('Median')
col_color.append(color)
data = {'sched': col_sched,
'location': col_location,
'value': col_value,
'type': col_type,
'color': col_color}
data_df = pd.DataFrame(data, index=col_location)
data_dfs.append(data_df)
hists.append(plot_hist)
# Plot break down of cycles
data = {'cycle': col_cycle}
cycle_df = pd.DataFrame(data, index=col_index)
pie_cycle = Donut(cycle_df.replace(0, np.nan),
title='Break down: cycles')
hists.append(pie_cycle)
info = {'hist': hists,
'info': data_dfs}
return info
def simple_chart(request,counter_name):
counter_len = len(Counter.objects.values())
Date = [Counter.objects.values()[i]["pub_date"] for i in range(counter_len)]
name = counter_name
y_values = Counter.objects.values_list("counter_value",flat=True).filter(counter_name=counter_name)
points = zip(Date,y_values)
ddict = OrderedDict({'Date':Date})
#ddict[name] = y_values
TOOLS="pan,wheel_zoom,box_zoom,reset,hover,save"
p = figure(width=1200, height=400, x_axis_type="datetime",tools=TOOLS,title=name+"'s Metrics" )
p.min_border_left = 100
p.min_border_top = 50
p.border_fill = 'whitesmoke'
p.ygrid.band_fill_color = "#E6E6FA"
p.title_text_color = "olive"
p.title_text_font = "times"
p.title_text_font_style = "italic"
p.outline_line_width = 7
p.outline_line_alpha = 0.3
p.outline_line_color = "black"
source = ColumnDataSource(
data=dict(
rates = [slope(points[i][0].microsecond,points[i][1],points[i+1][0].microsecond,points[i+1][1]) for i in range(len(points)-1)]
)
)
hover = p.select(dict(type=HoverTool))
hover.point_policy = "follow_mouse"
hover.tooltips = OrderedDict([
("Counter Name",name),
("Rate of count","@rates c/us"),
])
p.line(Date,y_values,line_width=1,source=source)
p.square(Date, y_values, fill_color=None, line_color="green",size=4)
script1, div1 = components(p, CDN)
hist = Histogram(list(y_values),bins=50,title='Histogram',color="#778899")
hist.border_fill = 'whitesmoke'
hist.background_fill = "beige"
script2, div2 = components(hist, CDN)
area = Area(list(y_values),title="CDF")
area.border_fill ="whitesmoke"
area.background_fill = "#191970"
script3, div3 = components(area,CDN)
context = RequestContext(request,{"the_script1":script1, "the_div1":div1,"the_script2":script2,"the_div2":div2,"the_script3":script3,"the_div3":div3})
return render(request, "counters_app/simple_bokeh.html",context)
from bokeh.charts import Histogram, output_file, show
from bokeh.sampledata.autompg import autompg as df
p = Histogram(df, values='mpg', bins=50, title="MPG Distribution (50 bins)")
output_file("histogram_bins.html")
show(p)
from bokeh.charts import Histogram, output_file, show
from bokeh.layouts import row
from bokeh.sampledata.autompg import autompg as df
hist = Histogram(df, values='mpg', title="Auto MPG Histogram", plot_width=400)
hist2 = Histogram(df, values='mpg', label='cyl', color='cyl', legend='top_right',
title="MPG Histogram by Cylinder Count", plot_width=400)
output_file('hist.html')
show(row(hist, hist2))
from bokeh.charts import Histogram, output_file, show
from bokeh.sampledata.autompg import autompg as df
p = Histogram(df['mpg'], title="MPG Distribution")
output_file("histogram.html", )
show(p)
# ch29.py
# ref:
# http://bokeh.pydata.org/en/latest/docs/user_guide/charts.html#color-groups
# However, the color parameter can also be used to group the data. If
# the value of the color parameter is one of the DataFrame column
# names, the data is first grouped by this column, and a histogram is
# generated for each group. Each histogram is automatically colored
# differently, and a legend displayed:
from bokeh.charts import Histogram, output_file, show
from bokeh.sampledata.autompg import autompg as df
p = Histogram(df, values='hp', color='cyl',
title="HP Distribution (color grouped by CYL)",
legend='top_right')
output_file("/tmp/ch29.html")
show(p)
def get_histogram(t):
t1, t2 = ticker1.value, ticker2.value
data = get_data(t1, t2)
h = Histogram(data[[t]], values=t)
h.toolbar_location = None
return h
