def distribution():
mu, sigma = 0, 0.5
measured = np.random.normal(mu, sigma, 1000)
hist, edges = np.histogram(measured, density=True, bins=20)
x = np.linspace(-2, 2, 1000)
pdf = 1 / (sigma * np.sqrt(2 * np.pi)) * np.exp(-(x - mu) ** 2 / (2 * sigma ** 2))
cdf = (1 + scipy.special.erf((x - mu) / np.sqrt(2 * sigma ** 2))) / 2
output_server("distribution_reveal")
hold()
figure(title="Interactive plots",
tools="pan, wheel_zoom, box_zoom, reset, previewsave",
background_fill="#E5E5E5")
quad(top=hist, bottom=np.zeros(len(hist)), left=edges[:-1], right=edges[1:],
fill_color="#333333", line_color="#E5E5E5", line_width=3)
# Use `line` renderers to display the PDF and CDF
line(x, pdf, line_color="#348abd", line_width=8, alpha=0.7, legend="PDF")
line(x, cdf, line_color="#7a68a6", line_width=8, alpha=0.7, legend="CDF")
xgrid().grid_line_color = "white"
xgrid().grid_line_width = 3
ygrid().grid_line_color = "white"
ygrid().grid_line_width = 3
legend().orientation = "top_left"
return curplot(), cursession()
def plotHistogram(data):
data_to_plot = data["Age"]
data_to_plot = data_to_plot[-np.isnan(data_to_plot)]
hist,edges = np.histogram(data_to_plot,bins=20)
pl.output_file('histogram.html')
pl.figure()
pl.hold()
pl.quad(top=hist,bottom=0,left=edges[:-1],right=edges[1:],
fill_color="#036564", line_color="#033649",
title="Age distribution",xlabel="Age",ylabel="Number")
pl.show()
def tweetsGraph():
logger.info("Drawing graphs to %s" % path_to_graphs+"Stats.html")
stat_db_cursor.execute('SELECT * FROM tweets')
tweets = stat_db_cursor.fetchall()
date, volume, cumulative, volumePast24h = zip(*[(datetime.datetime.strptime(t['date'], "%Y-%m-%dT%H"), t['current_hour'], t['cumulative'], t['past_24h']) for t in tweets])
hourly =zip([datetime.datetime(year=d.year, month=d.month, day=d.day) for d in date],volume)
hourly.sort()
days, dailyVolume = zip(*[(d, sum([v[1] for v in vol])) for d,vol in itertools.groupby(hourly, lambda i:i[0])])
bokeh_plt.output_file(path_to_graphs+"Stats.html")
bokeh_plt.hold()
bokeh_plt.quad(days, [d+datetime.timedelta(days=1) for d in days], dailyVolume, [0]*len(dailyVolume), x_axis_type="datetime", color='gray', legend="Daily volume")
bokeh_plt.line(date, volume, x_axis_type="datetime", color='red', legend="Hourly volume")
bokeh_plt.line(date, volumePast24h, x_axis_type="datetime", color='green', legend="Volume in the past 24 hours")
bokeh_plt.curplot().title = "Volume"
bokeh_plt.figure()
bokeh_plt.line(date, cumulative, x_axis_type="datetime")
bokeh_plt.curplot().title = "Cumulative volume"
fig, ax = matplotlib_plt.subplots()
f=DateFormatter("%Y-%m-%d")
ax.xaxis.set_major_formatter(f)
matplotlib_plt.plot(date, volume)
matplotlib_plt.plot(date, volumePast24h)
matplotlib_plt.plot(days, dailyVolume)
matplotlib_plt.xticks(np.concatenate((np.array(date)[range(0,len(date),24*7)],[date[-1]])), rotation=70)
matplotlib_plt.savefig(path_to_graphs+"volume.png", bbox_inches="tight")
stat_db_cursor.execute('SELECT * FROM users')
users = stat_db_cursor.fetchall()
date, nUsers, nUsersWithFriends = zip(*[(datetime.datetime.strptime(u['date'], "%Y-%m-%dT%H:%M:%S.%f"), u['total'], u['with_friends']) for u in users])
bokeh_plt.figure()
bokeh_plt.line(date, nUsers, x_axis_type="datetime", legend="Total")
bokeh_plt.line(date, nUsersWithFriends, x_axis_type="datetime", legend="Friendship collected")
bokeh_plt.legend().orientation = "top_left"
bokeh_plt.curplot().title = "Number of users"
bokeh_plt.save()
matplotlib_plt.figure()
fig, ax = matplotlib_plt.subplots()
f=DateFormatter("%Y-%m-%d")
ax.xaxis.set_major_formatter(f)
matplotlib_plt.plot(date, nUsers)
matplotlib_plt.plot(date, nUsersWithFriends)
matplotlib_plt.xticks(np.concatenate((np.array(date)[range(0,len(date),24*7)],[date[-1]])), rotation=70)
matplotlib_plt.savefig(path_to_graphs+"users.png", bbox_inches="tight")
def distribution():
mu, sigma = 0, 0.5
measured = np.random.normal(mu, sigma, 1000)
hist, edges = np.histogram(measured, density=True, bins=20)
x = np.linspace(-2, 2, 1000)
pdf = 1 / (sigma * np.sqrt(2 * np.pi)) * np.exp(-(x - mu)**2 /
(2 * sigma**2))
cdf = (1 + scipy.special.erf((x - mu) / np.sqrt(2 * sigma**2))) / 2
output_server("distribution_reveal")
hold()
figure(title="Interactive plots",
tools="pan, wheel_zoom, box_zoom, reset, previewsave",
background_fill="#E5E5E5")
quad(top=hist,
bottom=np.zeros(len(hist)),
left=edges[:-1],
right=edges[1:],
fill_color="#333333",
line_color="#E5E5E5",
line_width=3)
# Use `line` renderers to display the PDF and CDF
line(x, pdf, line_color="#348abd", line_width=8, alpha=0.7, legend="PDF")
line(x, cdf, line_color="#7a68a6", line_width=8, alpha=0.7, legend="CDF")
xgrid().grid_line_color = "white"
xgrid().grid_line_width = 3
ygrid().grid_line_color = "white"
ygrid().grid_line_width = 3
legend().orientation = "top_left"
return curplot(), cursession()
def create_histogram(releases):
number_of_bidders_list = []
frequency_list = []
for number_of_bidders, corresponding_releases in get_releases_by_amount_of_bidders(releases).items():
number_of_bidders_list.append(number_of_bidders)
frequency_list.append(len(corresponding_releases))
zeros = [0]*len(frequency_list)
right = [x+1 for x in number_of_bidders_list]
histogram = quad(top=frequency_list, bottom=zeros, left=number_of_bidders_list, right=right)
histogram.title = "Frequency of releases vs. Number of Bidders"
xaxis()[0].axis_label = "Number of Bidders"
yaxis()[0].axis_label = "Frequency of Releases"
show()
def make_plot(xr):
yr = Range1d(start=-10, end=10)
figure(plot_width=800, plot_height=350,
y_range=yr,
x_range=xr,
tools="xpan,xwheel_zoom,hover,box_zoom,reset")
hold()
genes = pd.read_csv('/home/hugoshi/data/lab7/genes.refseq.hg19.bed', sep='\t',
skiprows=[0], header=None)
genes.rename(columns={
0: "chromosome",
1: "start",
2: "end"},
inplace=True
)
genes = genes[genes.chromosome == 'chr5']
g_len = len(genes)
quad(genes.start - 0.5, # left edge
genes.end - 0.5, # right edge
[2.3] * g_len, # top edge
[1.7] * g_len,
['blue'] * g_len) # bottom edge
exons = pd.read_csv('/home/hugoshi/data/lab7/exons.refseq.hg19.bed', sep='\t', skiprows=[0], header=None)
exons.columns = ["chromosome", "start", "end", "meta1", "meta2", "meta3"]
exons = exons[exons.chromosome == 'chr5']
e_len = len(exons)
quad(exons.start - 0.5, # left edge
exons.end - 0.5, # right edge
[1.3] * e_len, # top edge
[0.7] * e_len,
['blue'] * e_len) # bottom edge
df = pd.read_csv('/home/hugoshi/data/lab7/CHP2.20131001.hotspots.bed', sep='\t', skiprows=[0], header=None)
df.columns = ["chromosome", "start", "end", "meta1", "meta2", "meta3"]
df = df[df.chromosome == 'chr5']
singles = df[df.start+1 == df.end]
widers = df[df.start+1 != df.end]
slen = len(singles)
wlen = len(widers)
s_source = ColumnDataSource(
data = dict(
start=singles.start,
end=singles.end,
meta1=singles.meta1,
meta2=singles.meta2,
meta3=singles.meta3))
rect('start', # x center
[1]*slen, # y center
[0.9]*slen,
[1]*slen,
color=['red']*slen,
source=s_source) # height
hover = [t for t in curplot().tools if isinstance(t, HoverTool)][0]
hover.tooltips = OrderedDict([
# add to this
("position", "@start"),
("meta 1", "@meta1"),
("meta 2", "@meta2"),
("meta 3", "@meta3")
])
quad(widers.start - 0.5, # left edge
widers.end - 0.5, # right edge
[0.3] * wlen, # top edge
[-0.3] * wlen) # bottom edge
hold()
return curplot()
def make_plot(xr):
yr = Range1d(start=-10, end=10)
figure(plot_width=800,
plot_height=350,
y_range=yr,
x_range=xr,
tools="xpan,xwheel_zoom,hover,box_zoom,reset")
hold()
genes = pd.read_csv('/home/hugoshi/data/lab7/genes.refseq.hg19.bed',
sep='\t',
skiprows=[0],
header=None)
genes.rename(columns={0: "chromosome", 1: "start", 2: "end"}, inplace=True)
genes = genes[genes.chromosome == 'chr5']
g_len = len(genes)
quad(
genes.start - 0.5, # left edge
genes.end - 0.5, # right edge
[2.3] * g_len, # top edge
[1.7] * g_len,
['blue'] * g_len) # bottom edge
exons = pd.read_csv('/home/hugoshi/data/lab7/exons.refseq.hg19.bed',
sep='\t',
skiprows=[0],
header=None)
exons.columns = ["chromosome", "start", "end", "meta1", "meta2", "meta3"]
exons = exons[exons.chromosome == 'chr5']
e_len = len(exons)
quad(
exons.start - 0.5, # left edge
exons.end - 0.5, # right edge
[1.3] * e_len, # top edge
[0.7] * e_len,
['blue'] * e_len) # bottom edge
df = pd.read_csv('/home/hugoshi/data/lab7/CHP2.20131001.hotspots.bed',
sep='\t',
skiprows=[0],
header=None)
df.columns = ["chromosome", "start", "end", "meta1", "meta2", "meta3"]
df = df[df.chromosome == 'chr5']
singles = df[df.start + 1 == df.end]
widers = df[df.start + 1 != df.end]
slen = len(singles)
wlen = len(widers)
s_source = ColumnDataSource(data=dict(start=singles.start,
end=singles.end,
meta1=singles.meta1,
meta2=singles.meta2,
meta3=singles.meta3))
rect(
'start', # x center
[1] * slen, # y center
[0.9] * slen,
[1] * slen,
color=['red'] * slen,
source=s_source) # height
hover = [t for t in curplot().tools if isinstance(t, HoverTool)][0]
hover.tooltips = OrderedDict([
# add to this
("position", "@start"),
("meta 1", "@meta1"),
("meta 2", "@meta2"),
("meta 3", "@meta3")
])
quad(
widers.start - 0.5, # left edge
widers.end - 0.5, # right edge
[0.3] * wlen, # top edge
[-0.3] * wlen) # bottom edge
hold()
return curplot()
color=data["Survived"].map(colormap),alpha=0.8,
xlabel="Fare")
pl.show()
if __name__=="__main__":
data = loadData("train.csv")
data,label = buildDataset(data,False)
data_to_plot = data["Age"]
data_to_plot = data_to_plot[-np.isnan(data_to_plot)]
hist,edges = np.histogram(data_to_plot,bins=20)
pl.output_file('histogram.html')
pl.figure()
pl.hold()
pl.quad(top=hist,bottom=0,left=edges[:-1],right=edges[1:],
fill_color="#036564", line_color="#033649",
title="Age distribution",xlabel="Age",ylabel="Number")
pl.line(np.average([edges[1:],edges[:-1]],axis=0),hist,
line_width=5,color="red",alpha=0.8)
pl.show()