def length_dist(self, pat_out="genes_lengths.png"):
'''Gets a list of sequence lengths, creates a dataframe and plots it using ggplot.
Then saves the file in specified path.'''
len_ditribution = [len(i) for i in self.num]
df = pd.DataFrame({"record_length": np.array(len_ditribution)})
pl = ggplot(df, aes(x="record_length")) + geom_density()
pl.save(pat_out)
def _post_density_plot(self, func=None, x_name='', plot_title='', include_doses=None, boot_samps=1000):
from ggplot import aes, ggplot, geom_density, ggtitle
import pandas as pd
if include_doses is None:
include_doses = range(1, self.num_doses + 1)
def my_func(x, samp):
tox_probs = _pi_T(x, mu=samp[:, 0], beta=samp[:, 1])
eff_probs = _pi_E(x, mu=samp[:, 2], beta1=samp[:, 3], beta2=samp[:, 4])
u = self.metric(eff_probs, tox_probs)
return u
if func is None:
func = my_func
x_boot = []
dose_indices = []
samp = self.pds._samp
p = self.pds._probs
p /= p.sum()
for i, x in enumerate(self.scaled_doses()):
dose_index = i+1
if dose_index in include_doses:
x = func(x, samp)
x_boot.extend(np.random.choice(x, size=boot_samps, replace=True, p=p))
dose_indices.extend(np.repeat(dose_index, boot_samps))
df = pd.DataFrame({x_name: x_boot, 'Dose': dose_indices})
return ggplot(aes(x=x_name, fill='Dose'), data=df) + geom_density(alpha=0.6) + ggtitle(plot_title)
def density_plot(by='dpsi_zscore', categorical=True):
if categorical:
data_dict = {
'muts increasing AAA':
np.array([x[by] for x in variants['increase']]),
'muts decreasing AAA':
np.array([x[by] for x in variants['decrease']]),
'muts not changing AAA length':
np.array([x[by] for x in variants['constant']])
}
else:
data_dict = OrderedDict(
(change,
np.array(
[x[by] for x in variants['all']
if x['change'] == change])) for change in aaa_changes if
len([x[by]
for x in variants['all'] if x['change'] == change]) > 1)
plot = (
ggplot(aes(x='value', colour='variable', fill='variable'),
data=prepare_data_frame(data_dict)) +
ggtitle('Impact of variants affecting poly AAA sequences on %s' %
by) + xlab(by) + ylab('Kernel density estimate') +
geom_density(alpha=0.6))
return plot
def density_chart(self, conn, column, table_chosen, title):
data_df = dfile.single_selector(conn=conn,
table=table_chosen,
column=column)
density_plot = ggplot(
aes(x=column),
data=data_df) + geom_density() + theme_gray() + labs(title=title)
now = datetime.datetime.now()
b = now
print(b)
print(b - a)
print(density_plot)
def build_list_of_plots(self, var):
plots = []
for tbl in self.tables:
df_from_original_table_on_variable = pd.DataFrame(
self.get_variable_data_from_original_table(tbl, var))
df_from_intersection_on_variable = pd.DataFrame(
self.get_variable_data_from_intersection_table(var))
df_from_intersection_on_variable.append(
df_from_intersection_on_variable)
g = ggplot(df_from_intersection_on_variable,
aes(x='var', color='table')) + geom_density()
g.make()
def render(data, bin_width, plot_density=False):
if plot_density:
plot = ggplot.ggplot(data, ggplot.aes(x='datetime', color='conversationWithName')) \
+ ggplot.geom_density() \
+ ggplot.scale_x_date(labels='%b %Y') \
+ ggplot.ggtitle('Conversation Densities') \
+ ggplot.ylab('Density') \
+ ggplot.xlab('Date')
else:
plot = ggplot.ggplot(data, ggplot.aes(x='datetime', fill='conversationWithName')) \
+ ggplot.geom_histogram(alpha=0.6, binwidth=bin_width) \
+ ggplot.scale_x_date(labels='%b %Y', breaks='6 months') \
+ ggplot.ggtitle('Message Breakdown') \
+ ggplot.ylab('Number of Messages') \
+ ggplot.xlab('Date')
print(plot)
from ggplot import aes, diamonds, geom_density, ggplot
import matplotlib.pyplot as plt
from bokeh import mpl
from bokeh.plotting import output_file, show
g = ggplot(diamonds, aes(x='price', color='cut')) + geom_density()
g.draw()
plt.title("Density ggplot-based plot in Bokeh.")
output_file("density.html", title="density.py example")
show(mpl.to_bokeh())
print(subjects_words_count.describe())
#%%
import ggplot as gg
df = pd.DataFrame(subjects_words_count, columns = ["count"])
hist = gg.ggplot(df, gg.aes(x = "count"))
hist += gg.xlab("# of words") +\
gg.ylab("Frequency") +\
gg.ggtitle("Frequency of words")
hist += gg.geom_vline(x = df.mean(), color="red")
hist += gg.geom_vline(x = df.median(), color="blue")
hist += gg.geom_density(color="green")
hist += gg.geom_histogram(binwidth=1, color="grey")
hist
#%%
# 1st attemtp to classify subjects per tag
X_raw_train = subjects_train
X_raw_test = subjects_test
Y_train = raw_data_train.target
Y_test = raw_data_test.target
target_names = raw_data_train.target_names
wordfreq = {key: 0 for key in worduniq}
wordscore = {key: 0 for key in worduniq}
wordprobs = {key: 0 for key in worduniq}
for w in wordbag:
wordfreq[w] += 1
for i in range(nrow):
for j in words[i]:
wordscore[j] += outcomes[i]
for i in wordprobs:
wordprobs[i] = float(wordscore[i]) / wordfreq[i]
b1 = pandas.Series([np.mean([wordprobs[w] for w in l]) if len(l) else 0 for l in words])
d1 = pandas.concat((b1, outcomes), axis=1)
d1.columns = ['prob', 'out']
g1 = ggplot(d1, aes(x='prob', color='out')) + geom_density()
cutoff = 0.3
bpreds = b1 > cutoff
print(float(sum(bpreds == outcomes)) / nrow) # 0.922524752475
# classify test data
words = test[textVar].apply(lambda x: prepare_document(x)).tolist()
b2 = [np.mean([wordprobs.get(w) if w in wordprobs else 0 for w in l]) if len(l) else 0 for l in words]
with open('submission.csv', 'wb') as f:
f.write(idVar + ',' + outVar + '\n')
for i in range(len(b2)):
row = test[idVar][i] + ',' + ('1' if b2[i] > cutoff else '0')
print(row)
f.write(row + '\n')
"rain", "ENTRIESn_hourly", "EXITSn_hourly"
]]
turnstile_rain["rain2"] = np.where(turnstile_rain["rain"] == 1, "raining",
"not raining")
turnstile_rain.groupby("rain2").describe()
turnstile_rain = turnstile_weather[[
"rain", "ENTRIESn_hourly", "EXITSn_hourly"
]]
turnstile_rain["ENTRIESn_hourly_log10"] = np.log10(
turnstile_rain["ENTRIESn_hourly"] + 1)
turnstile_rain["rain2"] = np.where(turnstile_rain["rain"] == 1, "raining",
"not raining")
set1 = brewer2mpl.get_map('Set1', 'qualitative', 3).mpl_colors
plot = gg.ggplot(turnstile_rain, gg.aes(x="ENTRIESn_hourly_log10", color="rain2")) + \
gg.geom_density() + \
gg.facet_wrap("rain2", scales="fixed") + \
gg.scale_colour_manual(values=set1) + \
gg.xlab("log10(entries per hour)") + \
gg.ylab("Number of turnstiles") + \
gg.ggtitle("Entries per hour whilst raining and not raining")
plot
np.random.seed(42)
data = pd.Series(np.random.normal(loc=180, scale=40, size=600))
data.hist()
p = turnstile_weather["ENTRIESn_hourly"].hist()
pylab.suptitle("Entries per hour across all stations")
pylab.xlabel("Entries per hour")
pylab.ylabel("Number of occurrences")
def density(self, inp1, inp2, inp3):
return gg.ggplot(self.data, gg.aes(x=inp1, color=inp2, fill=inp2)) +\
gg.geom_density(alpha=0.5, size=5) +\
gg.facet_grid(inp3) +\
gg.ggtitle('Density of Fare by Sex and Survival Status') +\
gg.ylab('Survival Status')
ax.set_title("Total entries/exits per hour by hour across all stations")
ax.legend(["Entries", "Exits"])
ax.set_ylabel("Entries/exits per hour (1e6 is a million)")
ax.set_xlabel("Hour (0 is midnight, 12 is noon, 23 is 11pm)")
ax.set_xlim(0, 23)
turnstile_rain = turnstile_weather[["rain", "ENTRIESn_hourly", "EXITSn_hourly"]]
turnstile_rain["rain2"] = np.where(turnstile_rain["rain"] == 1, "raining", "not raining")
turnstile_rain.groupby("rain2").describe()
turnstile_rain = turnstile_weather[["rain", "ENTRIESn_hourly", "EXITSn_hourly"]]
turnstile_rain["ENTRIESn_hourly_log10"] = np.log10(turnstile_rain["ENTRIESn_hourly"] + 1)
turnstile_rain["rain2"] = np.where(turnstile_rain["rain"] == 1, "raining", "not raining")
set1 = brewer2mpl.get_map('Set1', 'qualitative', 3).mpl_colors
plot = gg.ggplot(turnstile_rain, gg.aes(x="ENTRIESn_hourly_log10", color="rain2")) + \
gg.geom_density() + \
gg.facet_wrap("rain2", scales="fixed") + \
gg.scale_colour_manual(values=set1) + \
gg.xlab("log10(entries per hour)") + \
gg.ylab("Number of turnstiles") + \
gg.ggtitle("Entries per hour whilst raining and not raining")
plot
np.random.seed(42)
data = pd.Series(np.random.normal(loc=180, scale=40, size=600))
data.hist()
p = turnstile_weather["ENTRIESn_hourly"].hist()
pylab.suptitle("Entries per hour across all stations")
pylab.xlabel("Entries per hour")
pylab.ylabel("Number of occurrences")