def daily_unique_users(self):
"""
"""
fig = plt.figure(figsize=[20, 6])
ax1 = fig.add_subplot(1, 1, 1)
sgcolors = ['Silver', 'Crimson']
sglabels = ['$Non-Certified$', '$Certified$']
for sg in [0, 1]:
users = self.person[self.person.certified ==
sg].username.dropna().unique()
daily = pd.crosstab(
self.potime[self.potime.username.isin(users)].username,
self.potime.date)
daily = daily[daily > 0].count().sort_index()
daily.index = [np.datetime64(d) for d in daily.index]
daily.plot(ax=ax1,
style="-o",
ms=6,
lw=2,
color=sgcolors[sg],
rot=0,
label=sglabels[sg])
xmin = (self.cinfo['start_date'] -
np.timedelta64(2, 'W')).item().date()
xmax = (self.cinfo['end_date'] + np.timedelta64(4, 'W')).item().date()
ax1.set_xlim(xmin, xmax)
ax1 = xff.timeseries_plot_formatter(ax1, interval=1)
ax1.legend(loc=1, prop={'size': 24}, frameon=False)
ylim1 = ax1.get_ylim()[1]
ax1.vlines([
self.cinfo.start_date.item().date(),
self.cinfo.end_date.item().date()
],
0,
ylim1,
colors='Gray',
lw=1.5,
linestyles='--')
ax1.set_ylim(0, ylim1)
figsavename = self.figpath + 'daily_unique_users_' + self.nickname.replace(
'.', '_')
xff.texify(fig,
ax1,
ylabel='Unique Users',
tic_size=20,
label_size=24,
datefontsize=20,
title=self.nickname,
figsavename=figsavename + '.png')
return None
def enrollment_plots(self,**kwargs):
"""
Plots using the start_date from enrollment_df.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
"""
### For JSON Data Output
jsondata = []
def date2epoch(x):
return int( (datetime.combine(x, datetime.min.time()) - datetime(1970,1,1)).total_seconds()*1000 )
for C in self.enrollment_df.columns:
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
self.enrollment_df[C].plot(ax=ax1,color=xff.colors['institute'],rot=0,lw=3,label=self.nickname)
ax1 = xff.timeseries_plot_formatter(ax1)
ax1.set_yticklabels([r'${0}$'.format("%d" % (y)) for y in ax1.get_yticks()])
#ax1.legend(loc=4,prop={'size':22},frameon=False,scatterpoints=1)
### Generalized Plotting functions
figsavename = self.figpath+C.replace(' ','_')+'_'+self.nickname.replace('.','_')
print figsavename
xff.texify(fig,ax1,
ylabel=C,
#title=self._xdata.course_id+' - All Registrants',
datefontsize=20,
gridb='y',
figsavename=figsavename+'.png')
### Append JSON Data
record = collections.OrderedDict()
record['key'] = C
if C == 'Enroll Count':
record['bar'] = 'true'
record['values'] = [[date2epoch(d),int(v)] for d,v in self.enrollment_df[C].iteritems()]
jsondata.append(record)
print "JSON dump currently commented out."
# str_jsondata = 'var data = '+json.dumps(jsondata)
# with open(self.figpath+'enrollment.json', 'w') as outfile:
# outfile.write(str_jsondata)
return None#self.enrollment_df
def daily_activity(self):
"""
Creates daily timeseries of discussion activity (only posts/comments/votes from forum data).
Parameters (generated during class initialization)
----------
None
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
fig = plt.figure(figsize=[20,6])
ax1 = fig.add_subplot(1,1,1)
### List of Certified Participants
certs = self.pc_plus[self.pc_plus.certified==1].user_id.unique()
certs = [str(u) for u in certs]
### Non-Certified
post_act = self.forum[ (self.forum.created_at.notnull()) & (self.forum.author_id.isin(certs)==False) ].created_at.apply(lambda x: x.date()).value_counts().sort_index()
post_act.plot(ax=ax1,style="-o",ms=6,lw=2,color=xff.colors['neutral'],label='$Non-Certified$')
#(post_act.cumsum()/10).plot(ax=ax1,style="-",ms=3,color='Orange')
### Certified
post_act = self.forum[ (self.forum.created_at.notnull()) & (self.forum.author_id.isin(certs)) ].created_at.apply(lambda x: x.date()).value_counts().sort_index()
post_act.plot(ax=ax1,style="-o",ms=6,lw=2,color=xff.colors['institute'],label='$Certified$')
xmin = (self.cinfo['start_date'] - np.timedelta64(2,'W')).item().date()
xmax = (self.cinfo['end_date'] + np.timedelta64(4,'W')).item().date()
ax1.set_xlim(xmin,xmax)
ylim1 = ax1.get_ylim()[1]
ax1.vlines([self.cinfo.start_date.item().date(),self.cinfo.end_date.item().date()], 0, ylim1, colors='Gray', lw=1.5, linestyles='--')
ax1.set_ylim(0,ylim1)
ax1 = xff.timeseries_plot_formatter(ax1,interval=1)
ax1.legend(loc=1,prop={'size':24},frameon=False)
figsavename = self.figpath+'discussion_activity_'+self.nickname.replace('.','_')
xff.texify(fig,ax1,ylabel='Forum Text Submissions',
tic_size=20,label_size=24,
datefontsize=20,
title=self.nickname,
figsavename=figsavename+'.png')
return None
def daily_unique_users(self):
"""
"""
fig = plt.figure(figsize=[20,6])
ax1 = fig.add_subplot(1,1,1)
sgcolors = ['Silver','Crimson']
sglabels = ['$Non-Certified$','$Certified$']
for sg in [0,1]:
users = self.person[self.person.certified==sg].username.dropna().unique()
daily = pd.crosstab(self.potime[self.potime.username.isin(users)].username,self.potime.date)
daily = daily[daily>0].count().sort_index()
daily.index = [np.datetime64(d) for d in daily.index]
daily.plot(ax=ax1,style="-o",ms=6,lw=2,color=sgcolors[sg],rot=0,label=sglabels[sg])
xmin = (self.cinfo['start_date'] - np.timedelta64(2,'W')).item().date()
xmax = (self.cinfo['end_date'] + np.timedelta64(4,'W')).item().date()
ax1.set_xlim(xmin,xmax)
ax1 = xff.timeseries_plot_formatter(ax1, interval=1)
ax1.legend(loc=1,prop={'size':24},frameon=False)
ylim1 = ax1.get_ylim()[1]
ax1.vlines([self.cinfo.start_date.item().date(),self.cinfo.end_date.item().date()], 0, ylim1, colors='Gray', lw=1.5, linestyles='--')
ax1.set_ylim(0,ylim1)
figsavename = self.figpath+'daily_unique_users_'+self.nickname.replace('.','_')
xff.texify(fig,ax1,ylabel='Unique Users',
tic_size=20,label_size=24,
datefontsize=20,
title=self.nickname,
figsavename=figsavename+'.png')
return None
def last_day_plots_dual(self,**kwargs):
"""
Combining enroll count and cumulative enrollment.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
"""
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
fsize = 24
self.lastact_df['Last Activity Count'].plot(ax=ax1,lw=3,color='Silver',label='left axis')
ax1 = xff.timeseries_plot_formatter(ax1)
ax1.set_yticklabels([r'${0}$'.format("%d" % (y)) for y in ax1.get_yticks()])
ax1.set_ylabel('$Last Activity Count$'.replace(' ','\ '),
fontdict={'fontsize': fsize,'style': 'oblique'})
ax1.grid(which='both', b=False, axis='x')
ax2 = ax1.twinx()
self.lastact_df['Last Activity Survival'].plot(ax=ax2,lw=3,color='Crimson',label='right axis')
ax2 = xff.timeseries_plot_formatter(ax2)
ax2.set_yticklabels([r'${0}$'.format("%d" % (y)) for y in ax2.get_yticks()])
ax2.set_ylabel('$Last Activity Survival$'.replace(' ','\ '),
fontdict={'fontsize': fsize,'style': 'oblique'})
ax2.grid(which='both', b=False, axis='x')
ylim2 = ax2.get_ylim()[1]
ax2.vlines([self.cinfo['start_date'],self.cinfo['end_date']], 0, ylim2, colors='Gray', lw=1.5, linestyles='--')
ax2.set_ylim(0,ylim2)
#Tic Labels
datefontsize = 20
tic_size = fsize
for ax in [ax1,ax2]:
for tics in ax.get_xticklabels() + ax.get_yticklabels():
if datefontsize != None and tics in ax.get_xticklabels():
tics.set_fontsize(datefontsize)
else:
tics.set_fontsize(tic_size)
tics.set_fontname('serif')
tics.set_style('oblique')
figsavename = self.figpath+'last_day_dual_'+self.nickname.replace('.','_')+'.png'
print figsavename
if figsavename != None:
dpiset = 300
#fig.savefig('OUTPUT_Figures/%s/%s_%s.png' %(mens2_cid,figsavename,nickname), bbox_inches='tight', dpi=dpiset)
fig.savefig('%s' % (figsavename), bbox_inches='tight', dpi=dpiset)
return None#self.enrollment_df
def daily_activity(self):
"""
Creates daily timeseries of discussion activity (only posts/comments/votes from forum data).
Parameters (generated during class initialization)
----------
None
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
fig = plt.figure(figsize=[20, 6])
ax1 = fig.add_subplot(1, 1, 1)
### List of Certified Participants
certs = self.pc_plus[self.pc_plus.certified == 1].user_id.unique()
certs = [str(u) for u in certs]
### Non-Certified
post_act = self.forum[(self.forum.created_at.notnull()) & (
self.forum.author_id.isin(certs) == False)].created_at.apply(
lambda x: x.date()).value_counts().sort_index()
post_act.plot(ax=ax1,
style="-o",
ms=6,
lw=2,
color=xff.colors['neutral'],
label='$Non-Certified$')
#(post_act.cumsum()/10).plot(ax=ax1,style="-",ms=3,color='Orange')
### Certified
post_act = self.forum[(self.forum.created_at.notnull()) & (
self.forum.author_id.isin(certs))].created_at.apply(
lambda x: x.date()).value_counts().sort_index()
post_act.plot(ax=ax1,
style="-o",
ms=6,
lw=2,
color=xff.colors['institute'],
label='$Certified$')
xmin = (self.cinfo['start_date'] -
np.timedelta64(2, 'W')).item().date()
xmax = (self.cinfo['end_date'] + np.timedelta64(4, 'W')).item().date()
ax1.set_xlim(xmin, xmax)
ylim1 = ax1.get_ylim()[1]
ax1.vlines([
self.cinfo.start_date.item().date(),
self.cinfo.end_date.item().date()
],
0,
ylim1,
colors='Gray',
lw=1.5,
linestyles='--')
ax1.set_ylim(0, ylim1)
ax1 = xff.timeseries_plot_formatter(ax1, interval=1)
ax1.legend(loc=1, prop={'size': 24}, frameon=False)
figsavename = self.figpath + 'discussion_activity_' + self.nickname.replace(
'.', '_')
xff.texify(fig,
ax1,
ylabel='Forum Text Submissions',
tic_size=20,
label_size=24,
datefontsize=20,
title=self.nickname,
figsavename=figsavename + '.png')
return None
def last_day_plots_dual(self, **kwargs):
"""
Combining enroll count and cumulative enrollment.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
"""
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
fsize = 24
self.lastact_df['Last Activity Count'].plot(ax=ax1,
lw=3,
color='Silver',
label='left axis')
ax1 = xff.timeseries_plot_formatter(ax1)
ax1.set_yticklabels(
[r'${0}$'.format("%d" % (y)) for y in ax1.get_yticks()])
ax1.set_ylabel('$Last Activity Count$'.replace(' ', '\ '),
fontdict={
'fontsize': fsize,
'style': 'oblique'
})
ax1.grid(which='both', b=False, axis='x')
ax2 = ax1.twinx()
self.lastact_df['Last Activity Survival'].plot(ax=ax2,
lw=3,
color='Crimson',
label='right axis')
ax2 = xff.timeseries_plot_formatter(ax2)
ax2.set_yticklabels(
[r'${0}$'.format("%d" % (y)) for y in ax2.get_yticks()])
ax2.set_ylabel('$Last Activity Survival$'.replace(' ', '\ '),
fontdict={
'fontsize': fsize,
'style': 'oblique'
})
ax2.grid(which='both', b=False, axis='x')
ylim2 = ax2.get_ylim()[1]
ax2.vlines([self.cinfo['start_date'], self.cinfo['end_date']],
0,
ylim2,
colors='Gray',
lw=1.5,
linestyles='--')
ax2.set_ylim(0, ylim2)
#Tic Labels
datefontsize = 20
tic_size = fsize
for ax in [ax1, ax2]:
for tics in ax.get_xticklabels() + ax.get_yticklabels():
if datefontsize != None and tics in ax.get_xticklabels():
tics.set_fontsize(datefontsize)
else:
tics.set_fontsize(tic_size)
tics.set_fontname('serif')
tics.set_style('oblique')
figsavename = self.figpath + 'last_day_dual_' + self.nickname.replace(
'.', '_') + '.png'
print figsavename
if figsavename != None:
dpiset = 300
#fig.savefig('OUTPUT_Figures/%s/%s_%s.png' %(mens2_cid,figsavename,nickname), bbox_inches='tight', dpi=dpiset)
fig.savefig('%s' % (figsavename), bbox_inches='tight', dpi=dpiset)
return None #self.enrollment_df
def last_day_plots(self, **kwargs):
"""
Plots using the last_event date from enrollment_df.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
"""
col = self.lastact_df.columns[0]
tmp = self.lastact_df[col][self.lastact_df[col] > 100]
mindate = tmp.index[0] - timedelta(days=21)
maxdate = tmp.index[-1] + timedelta(days=21)
#print mindate,maxdate
### For JSON Data Output
jsondata = []
def date2epoch(x):
return int((datetime.combine(x, datetime.min.time()) -
datetime(1970, 1, 1)).total_seconds() * 1000)
for C in self.lastact_df.columns:
#print C,self.lastact_df[C].idxmin(),self.lastact_df[C].idxmax()
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
self.lastact_df[C].plot(ax=ax1,
color=xff.colors['institute'],
rot=0,
lw=3,
label=self.nickname)
ax1.set_xlim(mindate, maxdate)
ax1 = xff.timeseries_plot_formatter(ax1)
ax1.set_yticklabels(
[r'${0}$'.format("%d" % (y)) for y in ax1.get_yticks()])
#ax1.legend(loc=4,prop={'size':22},frameon=False,scatterpoints=1)
### Generalized Plotting functions
figsavename = self.figpath + C.replace(
' ', '_') + '_' + self.nickname.replace('.', '_')
print figsavename
xff.texify(
fig,
ax1,
ylabel=C,
#title=self._xdata.course_id+' - All Registrants',
datefontsize=20,
gridb='y',
figsavename=figsavename + '.png')
### Append JSON Data
record = collections.OrderedDict()
record['key'] = C
if C == 'Last Activity Count':
record['bar'] = 'true'
record['values'] = [[date2epoch(d), int(v)]
for d, v in self.lastact_df[C].iteritems()]
jsondata.append(record)
print "JSON dump currently commented out."
# str_jsondata = 'var data = '+json.dumps(jsondata)
# with open(self.figpath+'lastday.json', 'w') as outfile:
# outfile.write(str_jsondata)
return None