def plot_cal_bars(data):
#group data by calendar and week, use units of hours
weekShow = ((data['Duration'] / np.timedelta64(1, 'h')).groupby(
data.Calendar).resample('W').sum().unstack(level=0)).round(1)
#xlabels
weekShow = weekShow.fillna(value=0)
weekNames = weekShow.set_index(
weekShow.index.strftime("%b %d")).index.tolist()
#mini bar names
calNames = weekShow.columns.tolist()
#generate some D3 code
chart = nvd3.multiBarChart(width=1600, height=400, x_axis_format=None)
xdata = weekNames
#add hover tooltips
extra_serie = {"tooltip": {"y_start": "You spent ", "y_end": " hours"}}
for cal_name in weekShow:
chart.add_serie(name=cal_name,
y=weekShow[cal_name].tolist(),
x=xdata,
extra=extra_serie)
chart.buildhtml()
#make safe for HTML
plot = Markup(chart.htmlcontent)
return plot
def hello():
output = open('static/index.html', 'w')
input_data = list(csv.reader(open('dateCrimeOutput.txt', 'rb'), delimiter='\t'))
chart = multiBarChart(name='multiBarChart', height=800, width=1800, margin_bottom=300, margin_top=40, margin_left=60, margin_right=60)
crimes = []
for row in input_data:
crimes.append([row[0], int(row[1]), int(row[2])])
crimes = sorted(crimes, key=lambda crimes: crimes[1], reverse=True)
current_year = None
i = 0
for crime in crimes:
if crime[1] == current_year:
globals()['xdata%s' % i].append(crime[0])
globals()['ydata%s' % i].append(crime[2])
else:
current_year = crime[1]
i = i+1
globals()['year%s' % i] = str(crime[1])
globals()['ydata%s' % i] = []
globals()['xdata%s' % i] = []
globals()['ydata%s' % i].append(crime[2])
globals()['xdata%s' % i].append(crime[0])
i = 1
while True:
try:
kwargs1 = {'key': globals()['year%s' % i]}
chart.add_serie(name=globals()['year%s' % i], y=globals()['ydata%s' % i], x=globals()['xdata%s' % i], **kwargs1)
i = i + 1
except:
break
chart.buildhtml()
output.write(chart.htmlcontent)
return chart.htmlcontent
def get_result(self, request, graph_type, state_Abrv):
# define variables
usResult = request['usResult']
stateResult = request['stateResult']
type = graph_type
# Display pie chart
if (type == "pieChart"):
value = int(usResult) - int(stateResult)
chart = pieChart(name=type,
color_category='category20c',
height=450,
width=450)
xdata = ["United States", state_Abrv]
ydata = [int(value), int(stateResult)]
extra_serie = {"tooltip": {"y_start": "", "y_end": " cal"}}
chart.add_serie(y=ydata, x=xdata, extra=extra_serie)
# else display bar chart
else:
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = ["United States", state_Abrv]
ydata = [usResult, stateResult]
chart.add_serie(name="", y=ydata, x=xdata)
chart.show_legend = False
# convert charts into html content (and JavaScript)
chart.buildcontent()
result = chart.htmlcontent
return result
def test_MultiBarChart(self):
"""Test Multi Bar Chart"""
type = "MultiBarChart"
chart = multiBarChart(name=type, height=400)
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
chart.add_serie(y=ydata, x=xdata)
chart.buildhtml()
def test_MultiBarChart(self):
"""Test Multi Bar Chart"""
type = "MultiBarChart"
chart = multiBarChart(name=type, height=400)
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
chart.add_serie(y=ydata, x=xdata)
chart.buildhtml()
def get_barchart(formatted):
""" Create a bar chart and return html content """
chart = multiBarChart(width=1200, height=500, x_axis_format=None)
xdata = formatted[formatted.keys()[0]].values.tolist()
ydata1 = formatted[formatted.keys()[1]].values.tolist()
chart.add_serie(name=formatted.keys()[0], y=ydata1, x=xdata)
chart.buildhtml()
with open("test.html", 'w') as fil:
fil.write(chart.htmlcontent)
return chart.htmlcontent
def build_conclude_graph():
"""This function build the chart template and set the histogram graph with data
then show about the main cause of situation in 2006-2013 """
chart = multiBarChart(width = 2040, height = 500, x_axis_format = None)
for collum_year in range(1, 9):
xdata, ydata = [], []
for i in manage_data():
cause = ((i[0])[0:6])
if cause == ' Cause' or cause == ' Other':
xdata.append(i[0])
ydata.append(int(i[collum_year]))
else:
pass
chart.add_serie(name = 'THE SITUATION OF TRAFFIC ACCIDENT IN (case)' + str(2005 + collum_year), y = ydata, x = xdata)
return chart
def chart(name, hs):
"""13.71888 100.52578"""
chart = multiBarChart(width=250, height=150, x_axis_format=None)
xdata = ['จำนวนทั้งหมด', 'ไม่สวมหมวก', 'ดื่มสุรา']
ydata1 = list_hs[hs][0]
ydata2 = list_hs[hs][1]
chart.add_serie(name="ชาย", y=ydata1, x=xdata)
chart.add_serie(name="หญิง", y=ydata2, x=xdata)
chart.buildhtml()
file_name = name + str(hs) + ".html"
text_file = open(file_name, "w")
text_file.write(chart.htmlcontent)
print(chart.htmlcontent)
text_file.close()
return file_name
def build_each_graph(situation):
"""This function build the chart template and set the histogram graph with data
then show about a cause of the accident that user want to know"""
chart = multiBarChart(width = 2040, height = 500, x_axis_format = None)
for collum_year in range(1, 9):
xdata, ydata = [], []
for i in manage_data():
cause = ((i[0])[0:len(situation[0])])
if cause == situation[0]:
xdata.append(i[0])
ydata.append(int(i[collum_year]))
else:
pass
chart.add_serie(name = 'THE SITUATION OF TRAFFIC ACCIDENT IN (Case)' + str(2005+collum_year), y = ydata, x = xdata)
return chart
def hello():
output = open('static/index.html', 'w')
input_data = list(
csv.reader(open('dateCrimeOutput.txt', 'rb'), delimiter='\t'))
chart = multiBarChart(name='multiBarChart',
height=800,
width=1800,
margin_bottom=300,
margin_top=40,
margin_left=60,
margin_right=60)
crimes = []
for row in input_data:
crimes.append([row[0], int(row[1]), int(row[2])])
crimes = sorted(crimes, key=lambda crimes: crimes[1], reverse=True)
current_year = None
i = 0
for crime in crimes:
if crime[1] == current_year:
globals()['xdata%s' % i].append(crime[0])
globals()['ydata%s' % i].append(crime[2])
else:
current_year = crime[1]
i = i + 1
globals()['year%s' % i] = str(crime[1])
globals()['ydata%s' % i] = []
globals()['xdata%s' % i] = []
globals()['ydata%s' % i].append(crime[2])
globals()['xdata%s' % i].append(crime[0])
i = 1
while True:
try:
kwargs1 = {'key': globals()['year%s' % i]}
chart.add_serie(name=globals()['year%s' % i],
y=globals()['ydata%s' % i],
x=globals()['xdata%s' % i],
**kwargs1)
i = i + 1
except:
break
chart.buildhtml()
output.write(chart.htmlcontent)
return chart.htmlcontent
def stackedMF():
output_file = open('literacy_rate_nvd3.html', 'w')
chart = multiBarChart(width=1000,
height=400,
x_axis_format=None,
color='green')
data = ['Male', 'Female']
Arabic_countries = [95, 90]
Asian_countries = [85, 75]
African_countries = [56, 71]
American_countries = [90, 88]
rest_countries = [95, 93]
chart.add_serie(name="Arab region", y=Arabic_countries, x=data)
chart.add_serie(name="Asian region", y=Asian_countries, x=data)
chart.add_serie(name="African region", y=African_countries, x=data)
chart.add_serie(name="American region", y=American_countries, x=data)
chart.add_serie(name=" Rest of world", y=rest_countries, x=data)
chart.buildhtml()
display(HTML(chart.htmlcontent))
output_file.write(chart.htmlcontent)
output_file.close()
def wealthquintileNAR():
output_file = open('net_attendance_rate_nvd3.html', 'w')
chart = multiBarChart(width=1000,
height=400,
x_axis_format=None,
color='green')
data = ['Poorest', 'Second', 'Middle', 'Fourth', 'Richest']
Arabic_countries = [92, 95, 96, 97, 97.]
Asian_countries = [81, 86, 89, 90, 92]
African_countries = [62, 69, 75, 82, 88]
American_countries = [91, 94, 95, 96, 97]
rest_countries = [89, 91, 92, 92, 94]
chart.add_serie(name="Arab region", y=Arabic_countries, x=data)
chart.add_serie(name="Asian region", y=Asian_countries, x=data)
chart.add_serie(name="African region", y=African_countries, x=data)
chart.add_serie(name="American region", y=American_countries, x=data)
chart.add_serie(name=" Rest of world", y=rest_countries, x=data)
chart.buildhtml()
display(HTML(chart.htmlcontent))
output_file.write(chart.htmlcontent)
output_file.close()
def generate_friends_chart(group):
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = ["Followers per user", "Friends per user", "Retweets per post"]
ydata = [[], []]
for topics in group:
index = group.index(topics)
total_population = []
for topic in topics:
population = retrieve_by_topic(topic, "users")
for p in population:
total_population.append(p)
y = ydata[index]
follow, friend, retw = get_friendship_stats(total_population)
y.append(follow)
y.append(friend)
y.append(retw)
chart.add_serie(name="Gamers", y=ydata[0], x=xdata)
chart.add_serie(name="Non-gamers", y=ydata[1], x=xdata)
str(chart)
return chart.content
import pandas as pd
import nvd3
from nvd3 import multiBarChart
from IPython.display import Image
from IPython.core.display import display, HTML
df = pd.read_csv("/home/varun/q5-4.6-table.csv")
# saving a file into HTML file
output_file = open('allexam3rwre.html', 'w')
chart = multiBarChart(width=1000,
height=400,
x_axis_format=None,
color='green')
xdata = df['Year']
One = df['Total']
Two = df['Women']
Three = df['Women1']
chart.add_serie(name="Public Sector", y=One, x=xdata)
chart.add_serie(name="Public Sector", y=Two, x=xdata)
chart.add_serie(name="Public Sector", y=Three, x=xdata)
chart.buildhtml()
display(HTML(chart.htmlcontent))
output_file.write(chart.htmlcontent)
# close HTML file
output_file.close()
#>>> ax = sns.barplot(x="day", y="total_bill", hue="sex", data=tips)
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(-10, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " Calls"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " Min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
#---------------------------------------
type = "multiBarChart"
chart = multiBarChart(name=type, height=350, jquery_on_ready=True)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " call"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
#---------------------------------------
def certification_prob(self, **kwargs):
'''
Simple grade distribution.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
'''
data = self.person[['start_time', 'certified']].copy()
data.start_time = data.start_time.apply(lambda x: (x - self.cinfo[
'start_date']).days / 7 if pd.notnull(x) else x)
data.certified = data.certified.apply(lambda x: 'Certified'
if x == 1 else 'Non-Certified')
data = pd.crosstab(data.start_time, data.certified).sort_index()
print data.head()
# mindate = tmp.index[0] - timedelta(days=21)
# maxdate = tmp.index[-1] + timedelta(days=21)
NVD3 = kwargs.get('NVD3', False)
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### Data
bins = 50
hmin = 0.0
hmax = 1.0
DATA = self.person[(self.person.grade >= glowbound)]
Y1, X1 = np.histogram(DATA[DATA.certified == 0].grade.values,
bins=bins,
range=(hmin, hmax))
Y2, X2 = np.histogram(DATA[DATA.certified == 1].grade.values,
bins=bins,
range=(hmin, hmax))
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_grade_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Certification Bubble Chart: %s" % self._xdata.course_id
chart = multiBarChart(name=title, height=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(X1)
extra_serie = {
"tooltip": {
"y_start": "",
"y_end": ""
},
"color": xff.colors['neutral']
}
chart.add_serie(name="Count", y=Y1, x=X1, extra=extra_serie)
extra_serie = {
"tooltip": {
"y_start": "",
"y_end": ""
},
"color": xff.colors['institute']
}
chart.add_serie(name="Duration", y=Y2, x=X2, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def Total():
All_city = []
All_Geo_x = []
All_Geo_y = []
for city in range(len(RdataDaily['features'])):
Name_Eng = RdataDaily['features'][city]['attributes']["Name_Eng"]
GEOx = RdataDaily['features'][city]['geometry']['x']
GEOy = RdataDaily['features'][city]['geometry']['y']
if Name_Eng not in All_city:
All_city.append(Name_Eng)
All_Geo_x.append(GEOx)
All_Geo_y.append(GEOy)
# print(len(All_city)) # print the length
All_confirmed = []
All_Deaths = []
All_Tested = []
All_Recovered = []
for city in range(len(All_city)):
Confirmed = 0
Deaths = 0
Tested = 0
Recovered = 0
date2 = []
# Check for the last date
for cases in range(len(RdataDaily['features'])):
date = RdataDaily['features'][cases]['attributes']["Reportdt"]
if date not in date2:
date2.append(date)
date_now = max(date2)
# Check for Confimed Cases
for cases in range(len(RdataDaily['features'])):
check = RdataDaily['features'][cases]['attributes']["Name_Eng"]
date = RdataDaily['features'][cases]['attributes']["Reportdt"]
if All_city[city] == check and date == date_now:
Deaths += RdataDaily['features'][cases]['attributes']["Deaths"]
Recovered += RdataDaily['features'][cases]['attributes'][
"Recovered"]
Confirmed += RdataDaily['features'][cases]['attributes'][
"Confirmed"]
All_confirmed.append(Confirmed)
All_Deaths.append(Deaths)
All_Recovered.append(Recovered)
rec = 0
deaths = 0
conf = 0
Total_file = open('Total.json', 'w+')
All_info2 = []
for cases in range(len(All_city)):
a = {
"city": All_city[cases],
"Deaths": All_Deaths[cases],
"Recovered": All_Recovered[cases],
"Confirmed": All_confirmed[cases]
}
All_info2.append(dict(a))
conf += All_confirmed[cases]
rec += All_Recovered[cases]
deaths += All_Deaths[cases]
print(f"Total Confirmed: {str(conf)}")
print(f"Total Recovered: {str(rec)}")
print(f"Total Deaths: {str(deaths)}")
Total_file.write(json.dumps(All_info2))
Total_file.close()
New_Geo_x = []
New_Geo_y = []
for Infected in range(len(All_info2)):
infction = All_info2[Infected]['Confirmed']
if infction != 0:
New_Geo_x.append(All_Geo_x[Infected])
New_Geo_y.append(All_Geo_y[Infected])
random = []
for i in range(len(New_Geo_x)):
random.append(0.009)
gmap5 = gmplot.GoogleMapPlotter(23.68363, 45.76787, 6)
gmap5.heatmap(New_Geo_y,
New_Geo_x,
radius=20,
gradient=[(0, 0, 255, 0), (0, 255, 0, 0.9), (255, 0, 0, 1)])
gmap5.draw('map.html')
Chart_all = open('Visiual.html', 'w+')
chart = multiBarChart(width=3000, height=1000, x_axis_format=None)
chart.add_serie(name="Recovered 1", y=All_Recovered, x=All_city)
chart.add_serie(name="Infected 2", y=All_confirmed, x=All_city)
chart.buildhtml()
Chart_all.write(chart.htmlcontent)
Chart_all.close()
def grade_distribution(self,**kwargs):
'''
Simple grade distribution.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
'''
NVD3 = kwargs.get('NVD3',False)
if self.person.grade.count() < 50:
print "Not enough grade information. Return without grade distribution."
return None
bins = 50
hmin = 0.0 #self.person['grade'].min()
hmax = 1.0 #self.person['grade'].max()
glowbound = 0.1
### Plot
fig = plt.figure(figsize=(12,7))
ax1 = fig.add_subplot(1,1,1)
self.person[(self.person.grade>=glowbound) & (self.person.certified==0)]['grade'].hist(ax=ax1,bins=bins,range=(hmin,hmax),log=False,cumulative=0,
color=xff.colors['neutral'],edgecolor=xff.colors['neutral'])
self.person[(self.person.grade>=glowbound) & (self.person.certified==1)]['grade'].hist(ax=ax1,bins=bins,range=(hmin,hmax),log=False,cumulative=0,
color=xff.colors['institute'],edgecolor=xff.colors['institute'],alpha=0.8)
xlab = 'Grade'
#ax1.set_xlabel(r'%s' % (xlab),fontdict={'fontsize': 30,'style': 'oblique'})
#ax1.set_ylabel(r'Count (log scale)',fontdict={'fontsize': 30,'style': 'oblique'})
ax1.set_xlim(0,hmax)
ax1.set_ylim(1,)
ax1.legend(['$Non-Certified$','$Certified$'],loc=1,prop={'size':24},frameon=False)
ax1.set_xticklabels([r'$%.1f$' % x for x in ax1.get_xticks()],fontsize=30)
ax1.set_yticklabels([r'$%d$' % y for y in ax1.get_yticks()],fontsize=30)
### Generalized Plotting functions
figsavename = self.figpath+'grade_distribution_'+self.nickname.replace('.','_')
xff.texify(fig,ax1,
xlabel='Grade (> %.2f)' % (glowbound),
ylabel='Count',
gridb='y',
figsavename=figsavename+'.png')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### Data
bins = 50
hmin = 0.0
hmax = 1.0
DATA = self.person[(self.person.grade>=glowbound)]
Y1,X1 = np.histogram(DATA[DATA.certified==0].grade.values,bins=bins,range=(hmin,hmax))
Y2,X2 = np.histogram(DATA[DATA.certified==1].grade.values,bins=bins,range=(hmin,hmax))
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_grade_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Grade Distribution: %s" % self._xdata.course_id
chart = multiBarChart(name=title, height=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(X1)
extra_serie = {"tooltip": {"y_start": "", "y_end": ""},
"color":xff.colors['neutral']
}
chart.add_serie(name="Count", y=Y1, x=X1, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": ""},
"color":xff.colors['institute']
}
chart.add_serie(name="Duration", y=Y2, x=X2, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def level_of_education(self, **kwargs):
'''
Plot Level of Education Attained; typically taken from the edX enrollment questionairre.
'''
"""
Creates distribution of highest level of education attained.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3', False)
### Level of Education (LoE)
### Data
eddict = {
'el': "Less\ than$\n$ Secondary",
'jhs': "Less\ than$\n$ Secondary",
'none': "Less\ than$\n$ Secondary",
'hs': "Secondary",
'a': "Secondary",
'b': "Bachelor\'s",
'm': "Master\'s",
'p_se': "Doctorate",
'p_oth': "Doctorate",
'p': "Doctorate",
'other': None,
'NA': None,
'nan': None,
}
edlist = [
"Less\ than$\n$ Secondary", "Secondary", "Bachelor\'s",
"Master\'s", "Doctorate"
]
trim_data = self.person[(self.person.registered == 1)
& (self.person.user_id > 156633)]
edlevels = trim_data.LoE.apply(lambda x: eddict[str(x)] if x in eddict.
keys() else None).value_counts()[edlist]
if trim_data[trim_data.certified ==
1].username.count() > self.mincerts:
certs = trim_data[trim_data.certified == 1].LoE.apply(
lambda x: eddict[str(x)]
if x in eddict.keys() else None).value_counts()[edlist]
else:
certs = pd.Series(index=edlevels.index)
edlevels = pd.concat([edlevels, certs],
join='inner',
axis=1,
keys=['$Non-Certified$', '$Certified$'])
edlevels = 100. * edlevels / edlevels.sum()
edlevels = edlevels.apply(lambda x: np.round(x, 1))
#print edlevels
#Plot
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
edlevels.plot(ax=ax1,
kind='bar',
color=[xff.colors['neutral'], xff.colors['institute']],
rot=40)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in edlist])
ax1.set_yticklabels(
[r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],
fontsize=30)
ax1.legend(loc=2, prop={'size': 22}, frameon=False)
### Generalized Plotting functions
figsavename = self.figpath + 'loe_distribution_' + self.nickname.replace(
'.', '_')
print figsavename
xff.texify(fig,
ax1,
xlabel=None,
ylabel=None,
figsavename=figsavename + '.png')
### Output JSON Records
#cc.name = 'value'
#cc = cc.reset_index().rename(columns={'index':'label'})
#cc.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_edlevel_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Education Level Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype,
height=350,
x_axis_format="",
y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(edlevels)
X = [
x.replace('\ ', ' ').replace('$\n$', ' ')
for x in edlevels.index
] #list(range(nb_element))
Y1 = edlevels.ix[:, '$Non-Certified$'].values
Y2 = edlevels.ix[:, '$Certified$'].values
### Series 1
extra_serie1 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['neutral'],
"format": ".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['institute'],
"format": ".1f"
}
chart.add_serie(name="Certificate Earners",
y=Y2,
x=X,
extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def country_of_origin(self,**kwargs):
"""
Creates figures for the top "ccnum" of enrolled countries.
Parameters (generated during class initialization)
----------
ccnum = number of requested countries to be plotted. Max 25 for plotting issues.
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3',False)
ccnum = kwargs.get('ccnum',10)
cc = self.person.final_cc.value_counts().order(ascending=False)
if self.person[self.person.certified==1].username.count() > self.mincerts:
certs = self.person[self.person.certified==1].final_cc.value_counts()
else:
certs = pd.Series(index=cc.index)
cc = pd.concat([cc,certs],join='inner',axis=1,keys=['$Non-Certified$','$Certified$'])
cc = cc.sort('$Non-Certified$',ascending=False)[0:ccnum]
perc = 100.*cc/cc.sum()
perc = perc.apply(lambda x: np.round(x,1))
#print perc
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
perc.plot(ax=ax1,kind='bar',color=[xff.colors['neutral'],xff.colors['institute']],rot=40,)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in perc.index])
ax1.set_yticklabels([r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],fontsize=30)
ax1.legend(loc=1,prop={'size':28},frameon=False)
### Generalized Plotting functions
figsavename = self.figpath+'country_geoloc_distribution_'+self.nickname.replace('.','_')
print figsavename
xff.texify(fig,ax1,xlabel='Country Code',ylabel=None,figsavename=figsavename+'.png')
### Output JSON Records
#cc.name = 'value'
#cc = cc.reset_index().rename(columns={'index':'label'})
#cc.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_country_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Education Level Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype, height=350, x_axis_format="", y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(perc)
X = perc.index #list(range(nb_element))
Y1 = perc.ix[:,'$Non-Certified$'].values
Y2 = perc.ix[:,'$Certified$'].values
### Series 1
extra_serie1 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['neutral'],
"format":".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['institute'],
"format":".1f"
}
chart.add_serie(name="Certificate Earners", y=Y2, x=X, extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def level_of_education(self,**kwargs):
'''
Plot Level of Education Attained; typically taken from the edX enrollment questionairre.
'''
"""
Creates distribution of highest level of education attained.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3',False)
### Level of Education (LoE)
### Data
eddict = {'el': "Less\ than$\n$ Secondary",'jhs': "Less\ than$\n$ Secondary",'none':"Less\ than$\n$ Secondary",
'hs':"Secondary",'a':"Secondary",
'b':"Bachelor\'s",
'm': "Master\'s",
'p_se': "Doctorate",'p_oth': "Doctorate",'p': "Doctorate",
'other': None,'NA':None,'nan':None,
}
edlist = ["Less\ than$\n$ Secondary","Secondary","Bachelor\'s","Master\'s","Doctorate"]
trim_data = self.person[(self.person.registered==1) & (self.person.user_id>156633)]
edlevels = trim_data.LoE.apply(lambda x: eddict[str(x)] if x in eddict.keys() else None).value_counts()[edlist]
if trim_data[trim_data.certified==1].username.count() > self.mincerts:
certs = trim_data[trim_data.certified==1].LoE.apply(lambda x: eddict[str(x)] if x in eddict.keys() else None).value_counts()[edlist]
else:
certs = pd.Series(index=edlevels.index)
edlevels = pd.concat([edlevels,certs],join='inner',axis=1,keys=['$Non-Certified$','$Certified$'])
edlevels = 100.*edlevels/edlevels.sum()
edlevels = edlevels.apply(lambda x: np.round(x,1))
#print edlevels
#Plot
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
edlevels.plot(ax=ax1,kind='bar',color=[xff.colors['neutral'],xff.colors['institute']],rot=40)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in edlist])
ax1.set_yticklabels([r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],fontsize=30)
ax1.legend(loc=2,prop={'size':22},frameon=False)
### Generalized Plotting functions
figsavename = self.figpath+'loe_distribution_'+self.nickname.replace('.','_')
print figsavename
xff.texify(fig,ax1,xlabel=None,ylabel=None,figsavename=figsavename+'.png')
### Output JSON Records
#cc.name = 'value'
#cc = cc.reset_index().rename(columns={'index':'label'})
#cc.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_edlevel_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Education Level Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype, height=350, x_axis_format="", y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(edlevels)
X = [ x.replace('\ ',' ').replace('$\n$',' ') for x in edlevels.index ] #list(range(nb_element))
Y1 = edlevels.ix[:,'$Non-Certified$'].values
Y2 = edlevels.ix[:,'$Certified$'].values
### Series 1
extra_serie1 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['neutral'],
"format":".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['institute'],
"format":".1f"
}
chart.add_serie(name="Certificate Earners", y=Y2, x=X, extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def age(self,**kwargs):
"""
Creates gender distribution figures.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3',False)
### Removes those users not having the option to fill in edX registration data.
trim_data = self.person[(self.person.registered==1) & (self.person.user_id>156633)]
# Add age column from year_of_birth
trim_data['age'] = trim_data['YoB'].apply(lambda x: datetime.datetime.now().year - x if isinstance(x,int) else None)
age = trim_data.age.dropna()
h,e = np.histogram(age.values,bins=9,range=(0,90))
age = pd.Series(data=h,index=['0-9','10-19','20-29','30-39','40-49','50-59','60-69','70-79','80-89'])
certs = trim_data[trim_data.certified==1]
if certs.username.count() > self.mincerts:
certs = certs.age.dropna()
h,e = np.histogram(certs.values,bins=9,range=(0,90))
certs = pd.Series(data=h,index=['0-9','10-19','20-29','30-39','40-49','50-59','60-69','70-79','80-89'])
else:
certs = pd.Series(index=age.index)
age = pd.concat([age,certs],join='inner',axis=1,keys=['$Non-Certified$','$Certified$'])
age = 100.*age/age.sum()
age = age.apply(lambda x: np.round(x,1))
#print age
#----------------------------------------------------------------
### Static Matplotlib PNG
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
age.plot(ax=ax1,kind='bar',color=[xff.colors['neutral'],xff.colors['institute']],rot=40,)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in age.index])
ax1.set_yticklabels([r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],fontsize=30)
ax1.legend(loc=1,prop={'size':28},frameon=False)
### Generalized Plotting functions
figsavename = self.figpath+'age_distribution_'+self.nickname.replace('.','_')
print figsavename
xff.texify(fig,ax1,xlabel='Age',ylabel=None,figsavename=figsavename+'.png')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_age_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Age Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype, height=350, x_axis_format="", y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(age)
X = age.index #list(range(nb_element))
Y1 = age['$Non-Certified$'].values
Y2 = age['$Certified$'].values
### Series 1
extra_serie1 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['neutral'],
"format":".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['institute'],
"format":".1f"
}
chart.add_serie(name="Certificate Earners", y=Y2, x=X, extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def gender(self,**kwargs):
"""
Creates gender distribution figures.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3',False)
### Removes those users not having the option to fill in edX registration data.
trim_data = self.person[(self.person.registered==1) & (self.person.user_id>156633)]
### Data
gdict = {'f': "$Female$",'m': "$Male$",'o':"$Other$"}
glist = ['$Female$','$Male$']
### Munge and Plot
gender = trim_data.gender.dropna().apply(lambda x: gdict[x]).value_counts()
#print gender
certs = trim_data[trim_data.certified==1]
if certs.username.count() > self.mincerts:
certs = certs.gender.dropna().apply(lambda x: gdict[x]).value_counts()
else:
certs = pd.Series(index=gender.index)
gender = pd.concat([gender,certs],join='inner',axis=1,keys=['$Non-Certified$','$Certified$'])
gender = 100.*gender/gender.sum()
gender = gender.apply(lambda x: np.round(x,1))
fig = plt.figure(figsize=(12,6))
ax1 = fig.add_subplot(1,1,1)
gender.ix[glist,:].plot(ax=ax1,kind='bar',color=[xff.colors['neutral'],xff.colors['institute']],rot=0)
### Plot Details
ax1.set_xticklabels([r'%s' % x for x in glist])
ax1.set_yticklabels([r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],fontsize=30)
ax1.legend(loc=2,prop={'size':28},frameon=False)
### Generalized Plotting functions
figsavename = self.figpath+'gender_distribution_'+self.nickname.replace('.','_')
print figsavename
xff.texify(fig,ax1,xlabel=None,ylabel='Count',figsavename=figsavename+'.png')
# ### Output JSON Records
# gender.name = 'value'
# gender = gender.reset_index().rename(columns={'index':'label'})
# gender.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
'http://nvd3.org/examples/pie.html'
X = [ x.replace('$','') for x in gender.index ]
Y1 = gender.ix[glist,'$Non-Certified$'].values
Y2 = gender.ix[glist,'$Certified$'].values
#----------------------------------------------------------------
### BAR Chart
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_gender_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Gender Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype, height=350, x_axis_format="", y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(gender.ix[glist,:])
### Series 1
extra_serie1 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['neutral'],
"format":".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {"tooltip": {"y_start": "", "y_end": "%"},
"color":xff.colors['institute'],
"format":".1f"
}
chart.add_serie(name="Certificate Earners", y=Y2, x=X, extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
#----------------------------------------------------------------
### Pie Chart
from nvd3 import pieChart
### Output File
figsavename = self.figpath+'interactive_gender_piechart_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Gender Pie Chart: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = pieChart(name=charttype, color_category='category20c', height=400, width=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
extra_serie = {"tooltip": {"y_start": "", "y_end": " certified"}}
chart.add_serie(y=Y1, x=X, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
d66.columns = ['Developing']
d66
#cell 81
res6 = pd.concat([d6, d66], axis=1, join_axes=[d6.index])
res6
#cell 82
frames = [res,res1,res2,res3,res4,res5,res6]
#cell 83
final_frames = pd.concat(frames)
final_frames
#cell 84
chart = multiBarChart(width=1100, height=500, x_axis_format=None)
causes = list(final_frames.index)
Developed = list(final_frames.Developed)
Developing = list(final_frames.Developing)
chart.add_serie(name="Developed", y=Developed, x=causes)
chart.add_serie(name="Developing", y=Developing, x=causes)
chart.buildhtml()
display(HTML(chart.htmlcontent))
#cell 85
#get_ipython().magic('matplotlib nbagg')
#final_frames.plot(kind='barh', title='Variations of the diseases for under 5yrs of age', rot=0, color=(['g','y']),
# stacked=True, figsize=(12, 6), edgecolor='b', linewidth=1, fontsize='13', )
#plt.ylabel('<------ Cause of death ------>', fontsize=14, color='b')
#plt.xlabel('<------ Percentage aggregated values ------>', fontsize=14, color='b')
import pandas as pd
import nvd3
from nvd3 import multiBarChart
from IPython.display import Image
from IPython.core.display import display, HTML
#
output_file = open('china.html', 'w')
chart = multiBarChart(width=1250, height=400, x_axis_format=None, color='blue')
xdata = ['1990.5', '1995.5', '2000.5', '2005.5', '2010.5', '2015.5']
ylower = [49.6, 44.8, 34.9, 22.5, 14.7, 9]
ymedian = [53.8, 47.5, 36.9, 24, 15.7, 10.7]
yupper = [58.8, 50.4, 39.2, 25.5, 16.7, 12.7]
chart.add_serie(name="Upper", y=yupper, x=xdata)
chart.add_serie(name="Median", y=ymedian, x=xdata)
chart.add_serie(name="Lower", y=ylower, x=xdata)
chart.set_containerheader(
"<h2>Child Mortality rate for China from 1990.5 to 2015.5<h2>")
chart.buildhtml()
display(HTML(chart.htmlcontent))
output_file.write(chart.htmlcontent)
output_file.close()
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(-10, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " Calls"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " Min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
#---------------------------------------
type = "multiBarChart"
chart = multiBarChart(name=type, height=350, jquery_on_ready=True)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " call"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
#---------------------------------------
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(-10, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " Calls"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " Min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
type = "multiBarChart"
chart = multiBarChart(name=type, height=350)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " call"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
def country_of_origin(self, **kwargs):
"""
Creates figures for the top "ccnum" of enrolled countries.
Parameters (generated during class initialization)
----------
ccnum = number of requested countries to be plotted. Max 25 for plotting issues.
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3', False)
ccnum = kwargs.get('ccnum', 10)
cc = self.person.final_cc.value_counts().order(ascending=False)
if self.person[self.person.certified ==
1].username.count() > self.mincerts:
certs = self.person[self.person.certified ==
1].final_cc.value_counts()
else:
certs = pd.Series(index=cc.index)
cc = pd.concat([cc, certs],
join='inner',
axis=1,
keys=['$Non-Certified$', '$Certified$'])
cc = cc.sort('$Non-Certified$', ascending=False)[0:ccnum]
perc = 100. * cc / cc.sum()
perc = perc.apply(lambda x: np.round(x, 1))
#print perc
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
perc.plot(
ax=ax1,
kind='bar',
color=[xff.colors['neutral'], xff.colors['institute']],
rot=40,
)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in perc.index])
ax1.set_yticklabels(
[r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],
fontsize=30)
ax1.legend(loc=1, prop={'size': 28}, frameon=False)
### Generalized Plotting functions
figsavename = self.figpath + 'country_geoloc_distribution_' + self.nickname.replace(
'.', '_')
print figsavename
xff.texify(fig,
ax1,
xlabel='Country Code',
ylabel=None,
figsavename=figsavename + '.png')
### Output JSON Records
#cc.name = 'value'
#cc = cc.reset_index().rename(columns={'index':'label'})
#cc.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_country_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Education Level Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype,
height=350,
x_axis_format="",
y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(perc)
X = perc.index #list(range(nb_element))
Y1 = perc.ix[:, '$Non-Certified$'].values
Y2 = perc.ix[:, '$Certified$'].values
### Series 1
extra_serie1 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['neutral'],
"format": ".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['institute'],
"format": ".1f"
}
chart.add_serie(name="Certificate Earners",
y=Y2,
x=X,
extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(-10, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " Calls"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " Min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
type = "multiBarChart"
chart = multiBarChart(name=type, height=350)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " call"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
data.append(information_per_simbol(freq))
#print '%s : %f' % ( letter, counter[letter]/float(sum_all_letters) )
return data
# https://plus.maths.org/MI/56c09cb543ec31341504b1627e490cb7/images/img-0008.png
# formula.
def information_per_simbol(data):
return -data * math.log(data, 2)
# Open File to write the D3 Graph
output_file = open('view.html', 'w')
type = 'Calculo: informacao por simbolo'
chart = multiBarChart(color_category='category20c',
width=900,
height=600,
x_axis_format=None)
chart.set_containerheader(
"\n\n<h2>" + type +
"\n\n<img src='https://plus.maths.org/MI/56c09cb543ec31341504b1627e490cb7/images/img-0008.png' /> <br> Baseado na frequencia de ocorrencia cada Letra</h2>\n\n"
)
# Isso cria o html do grafico
#esses sao os dados - letters in lowecase ascii
xdata = ascii_lowercase
# source http://docente.ifrn.edu.br/paulomartins/livros-classicos-de-literatura/dom-casmurro-de-machado-de-assis.-pdf/at_download/file
# to txt
pt_br = count_letters_in_file('machado_pt-br.txt')
# source https://raw.githubusercontent.com/bbejeck/hadoop-algorithms/master/src/shakespeare.txt
en_us = count_letters_in_file('shakespeare_en-us.txt')
ydata_pt_br = array_of_distribution_letters(pt_br)
type = "pieChart"
chart = pieChart(name=type, height=400, width=400)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
xdata = [
"Orange", "Banana", "Pear", "Kiwi", "Apple", "Strawberry", "Pineapple"
]
ydata = [3, 4, 0, 1, 5, 7, 3]
chart.add_serie(y=ydata, x=xdata)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
type = "multiBarChart"
chart = multiBarChart(name=type, height=350)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = range(nb_element)
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = map(lambda x: x * 2, ydata)
ydata3 = map(lambda x: x * 3, ydata)
ydata4 = map(lambda x: x * 4, ydata)
chart.add_serie(y=ydata, x=xdata)
chart.add_serie(y=ydata2, x=xdata)
#chart.add_serie(y=ydata3, x=xdata)
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
def certification_prob(self,**kwargs):
'''
Simple grade distribution.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
'''
data = self.person[['start_time','certified']].copy()
data.start_time = data.start_time.apply(lambda x: (x-self.cinfo['start_date']).days/7 if pd.notnull(x) else x)
data.certified = data.certified.apply(lambda x: 'Certified' if x == 1 else 'Non-Certified')
data = pd.crosstab(data.start_time,data.certified).sort_index()
print data.head()
# mindate = tmp.index[0] - timedelta(days=21)
# maxdate = tmp.index[-1] + timedelta(days=21)
NVD3 = kwargs.get('NVD3',False)
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### Data
bins = 50
hmin = 0.0
hmax = 1.0
DATA = self.person[(self.person.grade>=glowbound)]
Y1,X1 = np.histogram(DATA[DATA.certified==0].grade.values,bins=bins,range=(hmin,hmax))
Y2,X2 = np.histogram(DATA[DATA.certified==1].grade.values,bins=bins,range=(hmin,hmax))
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath+'interactive_grade_distribution_'+self.nickname+'.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Certification Bubble Chart: %s" % self._xdata.course_id
chart = multiBarChart(name=title, height=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(X1)
extra_serie = {"tooltip": {"y_start": "", "y_end": ""},
"color":xff.colors['neutral']
}
chart.add_serie(name="Count", y=Y1, x=X1, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": ""},
"color":xff.colors['institute']
}
chart.add_serie(name="Duration", y=Y2, x=X2, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
headhtml = """<!DOCTYPE html>
<html lang="th">
<head>
<meta charset="utf-8" />
<link href="https://cdnjs.cloudflare.com/ajax/libs/nvd3/1.7.0/nv.d3.min.css" rel="stylesheet" />
<script src="https://cdnjs.cloudflare.com/ajax/libs/d3/3.5.5/d3.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/nvd3/1.7.0/nv.d3.min.js"></script>
<title>2014 Annual Survey of State Government Tax Collections</title>
</head>
<body>
<center><h1>2014 Annual Survey of State Government Tax Collections</h1></center>
"""
pattern = {"tooltip": {"y_start": "", "y_end": " Million USD"}}
chart = multiBarChart(width=1024, height=768, x_axis_format=None)
chart1 = pieChart(name="chart1", color_category="category20c", height=800, width=768)
chart1.add_serie(y=total_taxes, x=states, extra={"tooltip": {"y_start": "", "y_end": " %"}})
chart1.buildcontent()
chart.add_serie(name="chart", y=total_taxes, x=states)
chart.buildcontent()
file.write(headhtml)
file.write("<center><h2>All Tax Collections By States</h2></center>")
file.write("<center>")
file.write(chart1.htmlcontent)
file.write("</center>")
file.write("<center><h2>State Government Tax CollectionsTax Collections By Category</h2></center>")
def grade_distribution(self, **kwargs):
'''
Simple grade distribution.
Parameters
----------
None
Output
------
Figures and respective formats.
Returns
-------
None
'''
NVD3 = kwargs.get('NVD3', False)
if self.person.grade.count() < 50:
print "Not enough grade information. Return without grade distribution."
return None
bins = 50
hmin = 0.0 #self.person['grade'].min()
hmax = 1.0 #self.person['grade'].max()
glowbound = 0.1
### Plot
fig = plt.figure(figsize=(12, 7))
ax1 = fig.add_subplot(1, 1, 1)
self.person[(self.person.grade >= glowbound)
& (self.person.certified == 0)]['grade'].hist(
ax=ax1,
bins=bins,
range=(hmin, hmax),
log=False,
cumulative=0,
color=xff.colors['neutral'],
edgecolor=xff.colors['neutral'])
self.person[(self.person.grade >= glowbound)
& (self.person.certified == 1)]['grade'].hist(
ax=ax1,
bins=bins,
range=(hmin, hmax),
log=False,
cumulative=0,
color=xff.colors['institute'],
edgecolor=xff.colors['institute'],
alpha=0.8)
xlab = 'Grade'
#ax1.set_xlabel(r'%s' % (xlab),fontdict={'fontsize': 30,'style': 'oblique'})
#ax1.set_ylabel(r'Count (log scale)',fontdict={'fontsize': 30,'style': 'oblique'})
ax1.set_xlim(0, hmax)
ax1.set_ylim(1, )
ax1.legend(['$Non-Certified$', '$Certified$'],
loc=1,
prop={'size': 24},
frameon=False)
ax1.set_xticklabels([r'$%.1f$' % x for x in ax1.get_xticks()],
fontsize=30)
ax1.set_yticklabels([r'$%d$' % y for y in ax1.get_yticks()],
fontsize=30)
### Generalized Plotting functions
figsavename = self.figpath + 'grade_distribution_' + self.nickname.replace(
'.', '_')
xff.texify(fig,
ax1,
xlabel='Grade (> %.2f)' % (glowbound),
ylabel='Count',
gridb='y',
figsavename=figsavename + '.png')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### Data
bins = 50
hmin = 0.0
hmax = 1.0
DATA = self.person[(self.person.grade >= glowbound)]
Y1, X1 = np.histogram(DATA[DATA.certified == 0].grade.values,
bins=bins,
range=(hmin, hmax))
Y2, X2 = np.histogram(DATA[DATA.certified == 1].grade.values,
bins=bins,
range=(hmin, hmax))
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_grade_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Grade Distribution: %s" % self._xdata.course_id
chart = multiBarChart(name=title, height=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(X1)
extra_serie = {
"tooltip": {
"y_start": "",
"y_end": ""
},
"color": xff.colors['neutral']
}
chart.add_serie(name="Count", y=Y1, x=X1, extra=extra_serie)
extra_serie = {
"tooltip": {
"y_start": "",
"y_end": ""
},
"color": xff.colors['institute']
}
chart.add_serie(name="Duration", y=Y2, x=X2, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
def plot_cal_bars(data):
weekShow = ((data['Duration'] / np.timedelta64(1, 'h')).groupby(
data.Calendar).resample('W').sum().unstack(level=0)).round(1)
#xlabels
weekNames = weekShow.set_index(
weekShow.index.strftime("%b %d")).index.tolist()
#mini bar names
calNames = weekShow.columns.tolist()
from nvd3 import multiBarChart
from markupsafe import Markup
chart = multiBarChart(width=1600, height=400, x_axis_format=None)
xdata = weekNames
extra_serie = {"tooltip": {"y_start": "You spent ", "y_end": " hours"}}
for cal_name in weekShow:
chart.add_serie(name=cal_name,
y=weekShow[cal_name].tolist(),
x=xdata,
extra=extra_serie)
chart.buildhtml()
plot = Markup(chart.htmlcontent)
return plot
# months = [g for n, g in weekShow.groupby(pd.TimeGrouper('3M'))]
# # pdb.set_trace()
# from matplotlib.backends.backend_pdf import PdfPages
# #pp = PdfPages('calData.pdf')
# F = []
# pdb.set_trace()
# for dmonth in months:
# f = Figure()
# dmonth.set_index(dmonth.index.strftime("%b %d")).plot(kind = "bar")
# monthStart = dmonth.index[0].strftime("%B %Y")
# monthEnd = dmonth.index[len(dmonth)-1].strftime("%B %Y")
# plt.title('{} - {}'.format(monthStart,monthEnd))
# plt.ylabel('Time (hours)')
# plt.gcf().subplots_adjust(bottom = 0.15)
# plt.close()
# F.append(f)
# return f
# pp.savefig()
# pp.close()
# for event in events:
# start = event['start'].get('dateTime', event['start'].get('date'))
# dt = datetime.fromtimestamp(rfc.tf_from_timestamp(start),Local)
# if event['summary'].lower() == 'Arrived At work'.lower():
# timeList.append([dt, []])
# i = i + 1
# if event['summary'].lower() == 'Left Work'.lower():
# if not timeList[len(timeList)-1][1]: #means there exists a arrival time for this session
# timeList[len(timeList)-1][1] = dt
# else:
# timeList.append([[],dt])
# cond.append(event['summary'])
# print(start, event['summary'])
# workTime = []
# totTime = timedelta(0)
# i = 1
# for session in timeList:
# if session[0] and session[1]:
# dur = session[1] - session[0]
# else:
# print(session[0])
# print(session[1])
# # print('start time = {0}, end time = {1}'.format(session[0].strftime("%A, %d. %B %Y %I:%M%p"),session[1].strftime("%A, %d. %B %Y %I:%M%p"))
# dur = timedelta(0)
# workTime.append(dur)
# print('Session {0}: time = {1} hrs'.format(i, dur.total_seconds()/3600))
# totTime = workTime[len(workTime) - 1] + totTime
# i = i + 1
# print('Total work this week: {0} hrs'.format(totTime))
# if event['summary'] == 'Arrived At Work':
# arrivalTimes.append(start)
# if event['summary'] == 'Left Work':
# departTimes.append(start)
# if __name__ == '__main__':
# main()
from nvd3 import pieChart
from nvd3 import multiBarChart
import time
import datetime
output_file = open('Visual.html', 'w') # Write html output file
#----------------------- Stacked Bar Chart of First MultiBarChart - Keywords in Job Title
# Title of Chart
type = "Hottest Key Words in Job Title"
# Use Multibar Chart to display in our HTML - Height, Width, Stacked, Formating X axis into date
chart = multiBarChart(name=type,
height=400,
width=1100,
stacked=True,
x_is_date=True,
x_axis_format="%d-%b-%Y")
# Header insert in our HTML
chart.set_containerheader("\n\n<h3>" + type + "</h3>\n\n")
# Date - X axis
xdata = [
1416027600001, 1416227600001, 1416427600001, 1416627600001, 1416727600001
]
# Data - Y axis - Values
ydata1 = [
0.19763513513513514, 0.1625, 0.1704225352112676, 0.20998719590268886,
0.16584158415841585
]
# Transfer to [0, 100] percentage
ydata1 = [ydata1[i] * 100 for i in range(5)]
# 6. Install nvd3#.1.12-beta: bower install nvd3#1.1.12-beta
#------------------------------------------------------------------------------------
from nvd3 import pieChart
from nvd3 import multiBarChart
import time
import datetime
output_file = open('Visual.html', 'w') # Write html output file
#----------------------- Stacked Bar Chart of First MultiBarChart - Keywords in Job Title
# Title of Chart
type = "Hottest Key Words in Job Title"
# Use Multibar Chart to display in our HTML - Height, Width, Stacked, Formating X axis into date
chart = multiBarChart(name=type, height=400, width=1100, stacked= True, x_is_date=True, x_axis_format="%d-%b-%Y")
# Header insert in our HTML
chart.set_containerheader("\n\n<h3>" + type + "</h3>\n\n")
# Date - X axis
xdata= [1416027600001, 1416227600001, 1416427600001, 1416627600001, 1416727600001]
# Data - Y axis - Values
ydata1 = [0.19763513513513514, 0.1625, 0.1704225352112676, 0.20998719590268886, 0.16584158415841585]
# Transfer to [0, 100] percentage
ydata1 = [ydata1[i]*100 for i in range(5)]
ydata2 = [0.13429054054054054, 0.1375, 0.1323943661971831, 0.18053777208706787, 0.15594059405940594]
ydata2 = [ydata2[i]*100 for i in range(5)]
ydata3 = [0.11570945945945946, 0.1125, 0.11408450704225352, 0.10627400768245839, 0.1419141914191419]
ydata3 = [ydata3[i]*100 for i in range(5)]
ydata4 = [0.10557432432432433, 0.10000001, 0.09859154929577464, 0.09603072983354674, 0.12458745874587458]
ydata4 = [ ydata4[i]*100 for i in range(5) ]
ydata5 = [0.10050675675675676, 0.0875, 0.08873239436619719, 0.07810499359795134, 0.09735973597359736]
for d3.js without taking away the power that d3.js gives you.
Project location : https://github.com/areski/python-nvd3
"""
from nvd3 import multiBarChart
import random
import time
import datetime
#Open File for test
output_file = open('test_multiBarChart_date.html', 'w')
type = "multiBarChart"
chart = multiBarChart(name=type, height=350, x_is_date=True)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 100
start_time = int(time.mktime(datetime.datetime(2013, 6, 1).timetuple()) * 1000)
xdata = range(nb_element)
xdata = map(lambda x: start_time + x * 100000000, xdata)
ydata = [i + random.randint(1, 10) for i in range(nb_element)]
ydata2 = map(lambda x: x * 2, ydata)
tooltip_date = "%d %b %Y %H:%M:%S %p"
extra_serie = {"tooltip": {"y_start": "There are ", "y_end": " calls"},
"date_format": tooltip_date}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
def gender(self, **kwargs):
"""
Creates gender distribution figures.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3', False)
### Removes those users not having the option to fill in edX registration data.
trim_data = self.person[(self.person.registered == 1)
& (self.person.user_id > 156633)]
### Data
gdict = {'f': "$Female$", 'm': "$Male$", 'o': "$Other$"}
glist = ['$Female$', '$Male$']
### Munge and Plot
gender = trim_data.gender.dropna().apply(
lambda x: gdict[x]).value_counts()
#print gender
certs = trim_data[trim_data.certified == 1]
if certs.username.count() > self.mincerts:
certs = certs.gender.dropna().apply(
lambda x: gdict[x]).value_counts()
else:
certs = pd.Series(index=gender.index)
gender = pd.concat([gender, certs],
join='inner',
axis=1,
keys=['$Non-Certified$', '$Certified$'])
gender = 100. * gender / gender.sum()
gender = gender.apply(lambda x: np.round(x, 1))
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
gender.ix[glist, :].plot(
ax=ax1,
kind='bar',
color=[xff.colors['neutral'], xff.colors['institute']],
rot=0)
### Plot Details
ax1.set_xticklabels([r'%s' % x for x in glist])
ax1.set_yticklabels(
[r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],
fontsize=30)
ax1.legend(loc=2, prop={'size': 28}, frameon=False)
### Generalized Plotting functions
figsavename = self.figpath + 'gender_distribution_' + self.nickname.replace(
'.', '_')
print figsavename
xff.texify(fig,
ax1,
xlabel=None,
ylabel='Count',
figsavename=figsavename + '.png')
# ### Output JSON Records
# gender.name = 'value'
# gender = gender.reset_index().rename(columns={'index':'label'})
# gender.dropna().to_json(figsavename+'.json',orient='records')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
'http://nvd3.org/examples/pie.html'
X = [x.replace('$', '') for x in gender.index]
Y1 = gender.ix[glist, '$Non-Certified$'].values
Y2 = gender.ix[glist, '$Certified$'].values
#----------------------------------------------------------------
### BAR Chart
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_gender_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Gender Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype,
height=350,
x_axis_format="",
y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(gender.ix[glist, :])
### Series 1
extra_serie1 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['neutral'],
"format": ".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['institute'],
"format": ".1f"
}
chart.add_serie(name="Certificate Earners",
y=Y2,
x=X,
extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
#----------------------------------------------------------------
### Pie Chart
from nvd3 import pieChart
### Output File
figsavename = self.figpath + 'interactive_gender_piechart_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Gender Pie Chart: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = pieChart(name=charttype,
color_category='category20c',
height=400,
width=400)
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
extra_serie = {"tooltip": {"y_start": "", "y_end": " certified"}}
chart.add_serie(y=Y1, x=X, extra=extra_serie)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(-10, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " Calls"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " Min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
# ---------------------------------------
type = "multiBarChart"
chart = multiBarChart(height=400, width=800, jquery_on_ready=True)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 10
xdata = list(range(nb_element))
ydata = [random.randint(1, 10) for i in range(nb_element)]
ydata2 = [x * 2 for x in ydata]
extra_serie = {"tooltip": {"y_start": "", "y_end": " call"}}
chart.add_serie(name="Count", y=ydata, x=xdata, extra=extra_serie)
extra_serie = {"tooltip": {"y_start": "", "y_end": " min"}}
chart.add_serie(name="Duration", y=ydata2, x=xdata, extra=extra_serie)
chart.buildcontent()
output_file.write(chart.htmlcontent)
# ---------------------------------------
def age(self, **kwargs):
"""
Creates gender distribution figures.
Parameters (generated during class initialization)
----------
NVD3 = False. If true, nvd3 interactive figure output.
Output
------
Saves figures to specified directories.
Returns
-------
None
"""
NVD3 = kwargs.get('NVD3', False)
### Removes those users not having the option to fill in edX registration data.
trim_data = self.person[(self.person.registered == 1)
& (self.person.user_id > 156633)]
# Add age column from year_of_birth
trim_data['age'] = trim_data['YoB'].apply(
lambda x: datetime.datetime.now().year - x
if isinstance(x, int) else None)
age = trim_data.age.dropna()
h, e = np.histogram(age.values, bins=9, range=(0, 90))
age = pd.Series(data=h,
index=[
'0-9', '10-19', '20-29', '30-39', '40-49', '50-59',
'60-69', '70-79', '80-89'
])
certs = trim_data[trim_data.certified == 1]
if certs.username.count() > self.mincerts:
certs = certs.age.dropna()
h, e = np.histogram(certs.values, bins=9, range=(0, 90))
certs = pd.Series(data=h,
index=[
'0-9', '10-19', '20-29', '30-39', '40-49',
'50-59', '60-69', '70-79', '80-89'
])
else:
certs = pd.Series(index=age.index)
age = pd.concat([age, certs],
join='inner',
axis=1,
keys=['$Non-Certified$', '$Certified$'])
age = 100. * age / age.sum()
age = age.apply(lambda x: np.round(x, 1))
#print age
#----------------------------------------------------------------
### Static Matplotlib PNG
fig = plt.figure(figsize=(12, 6))
ax1 = fig.add_subplot(1, 1, 1)
age.plot(
ax=ax1,
kind='bar',
color=[xff.colors['neutral'], xff.colors['institute']],
rot=40,
)
### Plot Details
ax1.set_xticklabels([r'$%s$' % x for x in age.index])
ax1.set_yticklabels(
[r'${0}\%$'.format("%.0f" % (y)) for y in ax1.get_yticks()],
fontsize=30)
ax1.legend(loc=1, prop={'size': 28}, frameon=False)
### Generalized Plotting functions
figsavename = self.figpath + 'age_distribution_' + self.nickname.replace(
'.', '_')
print figsavename
xff.texify(fig,
ax1,
xlabel='Age',
ylabel=None,
figsavename=figsavename + '.png')
#----------------------------------------------------------------
### NVD3 Interactive http://nvd3.org/
if NVD3:
### FIGURE
from nvd3 import multiBarChart
### Output File
figsavename = self.figpath + 'interactive_age_distribution_' + self.nickname + '.html'
output_file = open(figsavename, 'w')
print figsavename
title = "Age Distribution: %s" % self._xd.course_id
charttype = 'multiBarChart'
chart = multiBarChart(name=charttype,
height=350,
x_axis_format="",
y_axis_format=".1f")
chart.set_containerheader("\n\n<h2>" + title + "</h2>\n\n")
nb_element = len(age)
X = age.index #list(range(nb_element))
Y1 = age['$Non-Certified$'].values
Y2 = age['$Certified$'].values
### Series 1
extra_serie1 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['neutral'],
"format": ".1f"
}
chart.add_serie(name="Participants", y=Y1, x=X, extra=extra_serie1)
### Series 2
extra_serie2 = {
"tooltip": {
"y_start": "",
"y_end": "%"
},
"color": xff.colors['institute'],
"format": ".1f"
}
chart.add_serie(name="Certificate Earners",
y=Y2,
x=X,
extra=extra_serie2)
### Final Output
chart.buildhtml()
output_file.write(chart.htmlcontent)
#---------------------------------------
#close Html file
output_file.close()
return None
for d3.js without taking away the power that d3.js gives you.
Project location : https://github.com/areski/python-nvd3
"""
from nvd3 import multiBarChart
import random
import time
import datetime
# Open File for test
output_file = open('test_multiBarChart_date.html', 'w')
type = "multiBarChart"
chart = multiBarChart(name=type, height=350, x_is_date=True)
chart.set_containerheader("\n\n<h2>" + type + "</h2>\n\n")
nb_element = 100
start_time = int(time.mktime(datetime.datetime(2013, 6, 1).timetuple()) * 1000)
xdata = range(nb_element)
xdata = map(lambda x: start_time + x * 100000000, xdata)
ydata = [i + random.randint(1, 10) for i in range(nb_element)]
ydata2 = map(lambda x: x * 2, ydata)
tooltip_date = "%d %b %Y %H:%M:%S %p"
extra_serie = {
"tooltip": {
"y_start": "There are ",
"y_end": " calls"
},
def graph_ecotype():
key = 'organsim'
key2 = "multigraph"
requete="SELECT "\
" distinct(organism.organism_name), "\
" ecotype.ecotype_name, "\
" sample_source.project_id "\
" FROM "\
" chips.sample_source, "\
" chips.organism, "\
" chips.ecotype "\
"WHERE "\
" sample_source.ecotype_id = ecotype.ecotype_id AND "\
" organism.organism_id = sample_source.organism_id "\
"order by ecotype_name,organism.organism_name; "
r, data = getdata(requete)
dat = pd.DataFrame(data)
dat2 = pd.crosstab(dat[0], dat[1])
#test du plus lon
dat2 = pd.crosstab(dat[0], dat[1])
dat2 = pd.DataFrame(np.transpose(dat2))
#r,data=getdata(requete)
#if len(data)>0:
# for i in range(0,len(data)):
# xdata.append(data[i][0])
# ydata1.append(int(data[i][1]))
split = dict(np.transpose(dat2).sum())
list1 = []
list2 = []
for element in split.keys():
if split[element] > 1:
list1.append(element)
else:
list2.append(element)
from nvd3 import multiBarChart
chart1 = multiBarChart(name=key2,
width=800,
height=800,
x_axis_format=None)
#text_white="chart.stacked(true);"
#chart1.add_chart_extras(text_white)
chart2 = multiBarChart(width=800, height=800, x_axis_format=None)
xdata = list(dat2.index) #['one', 'two', 'three', 'four']
#ydata1 = [6, 12, 9, 16]
serie_lab = list(dat2.columns)
for ele in range(0, len(serie_lab)):
if ele != 1:
chart1.add_serie(name=serie_lab[ele],
y=list(dat2.loc[list1, serie_lab[ele]]),
x=list1)
#chart2.add_serie(name=serie_lab[ele], y=list(dat2.loc[list2,serie_lab[ele]]), x=list1)
chart1.buildhtml()
text = chart1.htmlcontent
argument1 = "var chart = nv.models.multiBarChart();\n\n"
argument2 = "var chart" + key + " = nv.models.multiBarChart();\n\n \n\n"
text = text.replace(argument1, argument2)
text = text.replace("chart.", "chart" + key + ".")
argument7 = """});\n var datum ="""
argument8 = """});\n chart""" + key + """.legendPosition("right");\n var datum ="""
text = text.replace(argument7, argument8)
text = text.replace(".call(chart);", ".call(chart" + key + ");")
text = text.replace(
"</script>",
"$('#multigraph1 .nv-controlsWrap .nv-series:eq(0)').addClass('nv-disabled');\n </script>"
)
argument3 = "nv.addGraph(function() {\n"
argument4 = "function rungraph(){ \n nv.addGraph(function() {\n"
text = text.replace(argument3, argument4)
argument5 = "</script>"
argument6 = "};\n rungraph(); \n alert(); </script>"
text = text.replace(argument5, argument6)
return text
import os
import csv
from nvd3 import multiBarChart
output = open('static/index.html', 'w')
input_data = list(csv.reader(open('dateCrimeOutput.txt', 'rb'),
delimiter='\t'))
chart = multiBarChart(name='multiBarChart',
height=800,
width=1800,
margin_bottom=300,
margin_top=40,
margin_left=60,
margin_right=60)
crimes = []
for row in input_data:
crimes.append([row[0], int(row[1]), int(row[2])])
crimes = sorted(crimes, key=lambda crimes: crimes[1], reverse=True)
current_year = None
i = 0
for crime in crimes:
if crime[1] == current_year:
globals()['xdata%s' % i].append(crime[0])
globals()['ydata%s' % i].append(crime[2])
else:
current_year = crime[1]
i = i + 1
globals()['year%s' % i] = str(crime[1])
globals()['ydata%s' % i] = []
globals()['xdata%s' % i] = []
globals()['ydata%s' % i].append(crime[2])
def main():
mo = ['JANUARY','FEBRUARY','MARCH','APRIL','MAY','JUNE',\
'JULY','AUGUST','SEPTEMBER','OCTOBER','NOVEMBER','DECEMBER']
######year 2014#####
list_inj = []
list_fata = []
list_city = []
lis = year_2014_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2014_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2014.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
##end year 2014##
#####year 2013#####
list_inj = []
list_fata = []
lis = year_2013_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2013_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2013.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
##end year 2013##
#####year 2012#####
list_inj = []
list_fata = []
lis = year_2012_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2012_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2012.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
######year 2011#####
list_inj = []
list_fata = []
lis = year_2011_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2011_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2011.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
###end year 2011###
#####year 2010#####
list_inj = []
list_fata = []
lis = year_2010_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2010_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2010.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
#######year 2009########
list_inj = []
list_fata = []
lis = year_2009_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2009_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2009.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
####year 2008#####
list_inj = []
list_fata = []
lis = year_2008_01()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_02()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_03()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_04()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_05()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_06()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_07()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_08()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_09()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_10()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_11()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
lis = year_2008_12()
fata = lis[0]
inj = lis[1]
list_inj.append(inj)
list_fata.append(fata)
chart = multiBarChart(width=500, height=400, x_axis_format=None)
xdata = mo
ydata1 = list_inj
ydata2 = list_fata
chart.add_serie(name="INJURED", y=ydata1, x=xdata)
chart.add_serie(name="FATALITIES", y=ydata2, x=xdata)
chart.buildhtml()
text_file = open("year_2008.html", "w")
text_file.write(chart.htmlcontent)
text_file.close()
########################################################
########################################################
########################################################
####plot map####
######year 2014#
list_la = []
list_long = []
new_la = []
new_long = []
lis = la_2014()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2013()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2012()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2011()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2010()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2009()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
lis = la_2008()
la = lis[1]
long = lis[2]
list_la.append(la)
list_long.append(long)
for i in list_la:
num = float(i)
new_la.append(num)
for j in list_long:
num2 = float(j)
new_long.append(num2)
mymap = pygmaps.maps(new_la[0], new_long[0], 14)
path = [(new_la[0], new_long[0]),
(new_la[1], new_long[1]),
(new_la[2], new_long[2]),
(new_la[3], new_long[3]),
(new_la[4], new_long[4]),
(new_la[5], new_long[5]),
(new_la[6], new_long[6]),]
for point in path:
mymap.addpoint(point[0], point[1])
mymap.draw('./map_all.html')