def _palette(self, palette, type="seq", **kwargs):
if isinstance(palette, six.string_types):
return scale_color_brewer(type=type, palette=palette)
elif isinstance(palette, gradient):
return scale_colour_gradient2(low=palette.low, mid=palette.mid, high=palette.high)
elif isinstance(palette, collections.Iterable):
return scale_colour_manual(values=palette)
def production_envelope(self,
dataframe,
grid=None,
width=None,
height=None,
title=None,
points=None,
points_colors=None,
palette=None,
x_axis_label=None,
y_axis_label=None):
palette = self.get_option('palette') if palette is None else palette
width = self.get_option('width') if width is None else width
colors = self._palette(palette, len(dataframe.strain.unique()))
plot = aes(data=dataframe,
ymin="lb",
ymax="ub",
x="value",
color=scale_colour_manual(colors)) + geom_area()
if title:
plot += geom_tile(title)
if x_axis_label:
plot += scale_x_continuous(name=x_axis_label)
if y_axis_label:
plot += scale_y_continuous(name=y_axis_label)
return plot
def _palette(self, palette, type="seq", **kwargs):
if isinstance(palette, six.string_types):
return scale_color_brewer(type=type, palette=palette)
elif isinstance(palette, gradient):
return scale_colour_gradient2(low=palette.low,
mid=palette.mid,
high=palette.high)
elif isinstance(palette, collections.Iterable):
return scale_colour_manual(values=palette)
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")
turnstile_weather["grp"] = turnstile_weather["rain"] + turnstile_weather["fog"]
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")
turnstile_weather["grp"]=turnstile_weather["rain"]+turnstile_weather["fog"]
def main():
global args, ruleset
# Arguments Parser
argparser, subparser = parser_setup()
register_rules(subparser)
args = argparser.parse_args()
rulemod = sys.modules["rpgdice.rulesets.%s" % args.ruleset]
rulemod.prepare(args, srand)
if args.debug:
print "DEBUG: args", args
print
results = list()
pool = multiprocessing.Pool()
try:
for result in pool.map(rulemod.simulate_rolls, rulemod.variables):
results.extend(result)
pool.close()
pool.join()
except KeyboardInterrupt:
sys.exit(130)
if args.debug:
print "DEBUG: results:"
pprint(results)
print
conf = dict()
conf = {"vlab": "Variables", "xlab": "Outcome", "ylab": "Probability %"}
for item in conf:
try:
conf[item] = getattr(rulemod, item)
except:
pass
columns = ("Graph", conf["vlab"], conf["xlab"], "Count", conf["ylab"])
data = pandas.DataFrame.from_records(results, columns=columns)
# Create and save graphs
for gkey in rulemod.graphs:
# Graph Defaults
graph_conf = conf.copy()
graph_conf["file_prefix"] = "%s%02d" % (args.ruleset, gkey)
graph_conf["file_suffix"] = str()
# colors
colors_lower = ["#ff0000", "#cc0000", "#993300", "#666600"]
colors_upper = ["#006666", "#003399", "#0000cc", "#0000ff"]
colors_mid = ["#000000"]
color_count = len(rulemod.variables) - 1
if color_count % 2 == 0:
lower_slice = (color_count / 2) * -1
upper_slice = color_count / 2
else:
lower_slice = ((color_count - 1) / 2) * -1
upper_slice = (color_count + 1) / 2
graph_conf["color_list"] = colors_lower[lower_slice:] + colors_mid + colors_upper[0:upper_slice]
# graph_conf from graph
graph_items = (
"color_list",
"file_prefix",
"file_suffix",
"graph_type",
"limits",
"x_breaks",
"x_labels",
"title",
"vlab",
"xlab",
"ylab",
)
for item in graph_items:
try:
graph_conf[item] = rulemod.graphs[gkey][item]
except:
try:
graph_conf[item] = getattr(rulemod, item)
except:
if item not in graph_conf:
graph_conf[item] = None
if args.debug:
print "DEBUG: graph_conf:"
pprint(graph_conf)
print
# plot_data
plot_data = data.copy()
plot_data = plot_data[plot_data["Graph"] == gkey]
plot_data.rename(
columns={
conf["vlab"]: graph_conf["vlab"],
conf["xlab"]: graph_conf["xlab"],
conf["ylab"]: graph_conf["ylab"],
},
inplace=True,
)
plot_data.index = range(1, len(plot_data) + 1)
if args.debug:
print "DEBUG: plot_data:"
pprint(plot_data)
print
# Create plot
if args.graph:
plot = (
ggplot.ggplot(
ggplot.aes(x=graph_conf["xlab"], y=graph_conf["ylab"], color=graph_conf["vlab"]), data=plot_data
)
+ ggplot.ggtitle(graph_conf["title"])
+ ggplot.theme_gray()
+ ggplot.scale_colour_manual(values=graph_conf["color_list"])
)
plot.rcParams["font.family"] = "monospace"
if graph_conf["x_breaks"] and graph_conf["x_labels"]:
plot += ggplot.scale_x_discrete(breaks=graph_conf["x_breaks"], labels=graph_conf["x_labels"])
if graph_conf["limits"]:
plot += ggplot.ylim(graph_conf["limits"][0], graph_conf["limits"][1])
if graph_conf["graph_type"] == "bars":
plot += ggplot.geom_line(size=20)
text_data = plot_data[plot_data["Count"] > 0]
text_data.index = range(0, len(text_data))
outcomes = dict(text_data[graph_conf["xlab"]])
percents = dict(text_data[graph_conf["ylab"]])
for k in outcomes:
percent = "%4.1f%%" % percents[k]
x = outcomes[k]
y = percents[k] + 4
color = graph_conf["color_list"][k]
plot += ggplot.geom_text(label=[percent], x=[x, x + 1], y=[y, y - 1], color=color)
else:
plot += ggplot.geom_line()
plot += ggplot.geom_point(alpha=0.3, size=50)
if hasattr(rulemod, "update_plot"):
plot = rulemod.update_plot(gkey, graph_conf, plot, plot_data)
if args.dumpsave:
filename = "/dev/null"
else:
filename = "%s%s.png" % (graph_conf["file_prefix"], graph_conf["file_suffix"])
ggplot.ggsave(filename, plot, format="png", dpi=300)
return 0
def plot_vol(dates, x, cp, my_domain):
# -------------------- Prepare for Plotting -------------------------- #
# Prepare DataFrame objects for graphing
#Add a column for the label to show in the legend in the graph
#Need to reshape it, from (124,) to (124,1) for exmple, so that it
#will concatenate. This gives a df with [date, vol_data, 'Volume']
v = ['Volume' for i in xrange(x.shape[0])]
#df_domain = np.concatenate((x, v), axis=1)
ndf_vol = np.transpose(np.array([dates, x, v]))
df_vol = pd.DataFrame(ndf_vol, columns=['Date', 'Volume', 'Data'])
#Create pre-allocated lists for plotting means and cp
xmin_list = [0 for i in xrange(len(cp))] #hold lft pt of vol_mean
xmax_list = [0 for i in xrange(len(cp))] #hold rt pt of vol_mean
yint_list = [0 for i in xrange(len(cp))] #holds vol_means
cp_date_list = [0 for i in xrange(len(cp))] #holds date for cp
cp_value_list = [0 for i in xrange(len(cp))] #holds cp value
ref_idx = 0 #used to keep track of vol_means
#collect list data for plotting
for i in xrange(len(cp)):
cp_idx = cp[i][0] - 1 #-1 b/c 1-indexed (includes cp itself)
xmin_list[i] = dates[ref_idx].toordinal() #convert to match ggplot
xmax_list[i] = dates[cp_idx].toordinal() #convert to match ggplot
yint_list[i] = cp[i][2] #use value from_mean for vol_mean
cp_date_list[i] = dates[cp_idx] #date of cp
#cp_value_list[i] = x[cp_idx] #value of cp
cp_value_list[i] = cp[i][2]
ref_idx = cp_idx + 1 #+1 b/c moving to next point
#Reform lists into a data frame and attach to df_domains. The first two
#lists can be created together since they are both numeric, but if I try
#to create all three together all types will be downgraded to strings.
#np.concatenate avoids this conversion. The transpose is needed to take
#an item from each to form a single row.
cp_lbl = ['Change Point' for i in xrange(len(yint_list))]
#Need to create a dummy entry to put 'Volume Mean' into legend
cp_date_list.append(dates[0])
yint_list.append(x[0])
cp_lbl.append('Volume Mean')
ndf_cp = np.transpose(np.array([cp_date_list, yint_list, cp_lbl]))
yint_list.pop(-1)
cp_date_list.pop(-1)
df_cp = pd.DataFrame(ndf_cp, columns=['Date', 'Volume', 'Data'])
df_plot = pd.concat((df_vol, df_cp), axis=0)
#Need to create a dummy entry to put 'Volume Mean' into legend
#dummy = np.array([dates[0], x[0], 'Volume Mean']).reshape(1,-1)
#df_cp = np.concatenate( (df_cp, dummy), axis=0) #add to bottom df_cp
#df_domain = np.concatenate( (df_domain, df_cp), axis=0 ) #add df_domains
#convert final array into a pd.DataFrame for printing and plotting
#df_domain = pd.DataFrame(df_domain, columns=['Date','Volume','Data'])
#df_domain.to_html(open('out.html','w'))
#os.system('sudo cp out.html /usr/local/www/analytics/rwing')
margin = 0.10 * (np.max(x) - np.min(x))
p = ggplot.ggplot(aes(x='Date', y='Volume', color='Data'), data=df_plot) + \
ggplot.geom_line(color='blue',size=2) + \
ggplot.geom_point(x=xmax_list, y=cp_value_list, color='black', \
shape='D', size=50) + \
ggplot.geom_hline(xmin=xmin_list, \
xmax=xmax_list, \
yintercept=yint_list, color="red", size=3) + \
ggplot.scale_x_date(labels = date_format("%Y-%m-%d"), breaks="1 week") + \
ggplot.scale_colour_manual(values = ["black", "blue", "red"]) + \
ggplot.scale_y_continuous(labels='comma') + \
ggplot.ylim(low=np.min(x)-margin/4.0, high=np.max(x)+margin) + \
ggplot.xlab("Week (Marked on Mondays)") + \
ggplot.ylab("Message Vol") + \
ggplot.ggtitle("%s\nMessage Volume by Week" % my_domain) + \
ggplot.theme_seaborn()
return p