def plot_trend_season(dates, ndf_domain, x, x_trend, season, my_domain):
# ---------------------- Prepare Data Frame ----------------------- #
df_domain = pd.DataFrame(ndf_domain, columns=['Date', 'Volume'])
df_domain['Date'] = dates
x_lbl = ['Observed Volume' for i in xrange(len(x))]
xt_lbl = ['Overall Trend' for i in xrange(len(x_trend))]
xs_lbl = ['Repeat Sending Trend' for i in xrange(len(season))]
col3 = pd.DataFrame(x_lbl+xt_lbl+xs_lbl)
df_plot = pd.concat( (df_domain, col3), axis=1)
df_plot.columns = ['Date', 'Volume', 'Data']
# ---------------------- Plot Decomposition ----------------------- #
p = ggplot.ggplot(aes(x='Date', y='Volume', color='Data'), data=df_plot) + \
ggplot.geom_line(color='blue', size=2) + \
ggplot.scale_x_date(labels = date_format("%Y-%m-%d"), breaks="1 week") + \
ggplot.xlab("Week (Marked on Mondays)") + \
ggplot.ylab("Message Vol") + \
ggplot.ggtitle("%s Message Volume by Week" % my_domain) + \
ggplot.facet_grid('Data', scales='free_y') + \
ggplot.theme_seaborn()
return p
def plot_bin_dists(df, bin_def="distance_bin <= 500"):
plt.rcParams['figure.figsize'] = np.array([16, 12]) * 0.65
p = gp.ggplot(gp.aes(x='R2'), data=df.query(bin_def))
p = p + gp.geom_histogram(
fill='coral') + gp.facet_wrap("distance_bin") + gp.theme_seaborn(
context='talk') + gp.ggtitle(bin_def)
return p
def _ggplot(df, out_file):
"""Plot faceted items with ggplot wrapper on top of matplotlib.
XXX Not yet functional
"""
import ggplot as gg
df["variant.type"] = [vtype_labels[x] for x in df["variant.type"]]
df["category"] = [cat_labels[x] for x in df["category"]]
df["caller"] = [caller_labels.get(x, None) for x in df["caller"]]
p = (gg.ggplot(df, gg.aes(x="caller", y="value.floor")) + gg.geom_bar() +
gg.facet_wrap("variant.type", "category") + gg.theme_seaborn())
gg.ggsave(p, out_file)
def _ggplot(df, out_file):
"""Plot faceted items with ggplot wrapper on top of matplotlib.
XXX Not yet functional
"""
import ggplot as gg
df["variant.type"] = [vtype_labels[x] for x in df["variant.type"]]
df["category"] = [cat_labels[x] for x in df["category"]]
df["caller"] = [caller_labels.get(x, None) for x in df["caller"]]
p = (gg.ggplot(df, gg.aes(x="caller", y="value.floor")) + gg.geom_bar()
+ gg.facet_wrap("variant.type", "category")
+ gg.theme_seaborn())
gg.ggsave(p, out_file)
def googletrend_command(delta_t, threshold=0.0, inverse=False):
"""the command to run google trend algorithm.
:param delta_t: the upper bound for original delta_t parameter
:param threshold: upper bound for the threshold of differentiating two classes
:param inverse: whether to inverse the classifier
"""
## handle filepath and title based on parameter inverse
filename = "googletrend"
titlename = "ROC of google trend classifier"
if inverse:
filename += "_inverse"
titlename += " (inverse version)"
filepath = "./plots/%s.jpg" % filename
## generate data first
data = googletrend.preprocess()
## store classifier evaluation metrics into dict
output = {}
output['tpr'] = []
output['fpr'] = []
output['plot'] = []
for thre in np.arange(0, threshold + 0.1, 0.1):
print "==> threshold: %f, inverse: %s" % (thre, inverse)
for i in xrange(1, int(delta_t)):
googletrend.algorithm(data, i, thre, inverse)
tp_rate, fp_rate = googletrend.evaluate(data)
# print "delta_t: %d, TPR: %f, FPR: %f" % (i, tp_rate, fp_rate)
output['tpr'].append(tp_rate)
output['fpr'].append(fp_rate)
output['plot'].append('thre_' + str(thre))
## plot ROC graph
## add a y=x baseline for comparison
output['tpr'].extend([0.0, 1.0])
output['fpr'].extend([0.0, 1.0])
output['plot'].extend(['baseline', 'baseline'])
df = pd.DataFrame(output)
graph = gg.ggplot(df, gg.aes('fpr', 'tpr', color='plot')) + \
gg.theme_seaborn() + \
gg.ggtitle(titlename) + \
gg.xlab("FPR") + \
gg.ylab("TPR") + \
gg.xlim(0.0, 1.0) + \
gg.ylim(0.0, 1.0) + \
gg.geom_point() + \
gg.geom_line()
gg.ggsave(plot=graph, filename=filepath, width=6, height=6, dpi=100)
def _plot_scat_w_line(self, gp_aes):
return gp_aes + gp.geom_point(color='coral') + gp.stat_smooth(span=.2, color='blue',
se=False) + gp.theme_seaborn(
context='talk')
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
