'value': response_dict.get('descendants', 0),
'label': response_dict['title'],
'xlink': 'http://news.ycombinator.com/item?id=' + str(submission_id),
}
graph_list.append(submission_dict)
names.append(response_dict['title'])
graph_list = sorted(graph_list, key=itemgetter('value'), reverse=True)
my_config = pygal.Config()
my_config.x_label_rotation = 45
my_config.show_legend = False
my_config.title_font_size = 24
my_config.label_font_size = 14
my_config.major_label_font_size = 18
my_config.truncate_label = 15
my_config.show_y_guides = False
my_config.width = 1000
chart = pygal.Bar(my_config, x_label_rotation=45, show_legend=False)
chart.title = 'Most active disscusions on Hacker News'
chart.x_labels = names
chart.add('', graph_list)
chart.render_to_file('Desktop/Coding_Projects/Working_With_APIs/hn_visual.svg')
print('A popularity graph for the language has been made')
#Here we use requests again, this time calling Hacker News
#The first call returns the 500 most popular articles on the website
#we then loop through 30 of the most popular of those, creating a nice index of-
#- popular articles
def success(data, test=False):
""" Main generate function get data and weapon id = 0 (Overall) """
# Graph generate goes here!
# Export file name as Targets_Frequency_SuccessRate
targets = {
1: "Business",
2: "Government (General)",
3: "Police",
4: "Military",
5: "Abortion Related",
6: "Airports & Aircraft",
7: "Government (Diplomatic)",
8: "Educational Institution",
9: "Food or Water Supply",
10: "Journalists & Media",
11: "Maritime",
12: "NGO",
13: "Other",
14: "Private Citizen & Property",
15: "Religious",
16: "Telecommunication",
17: "Terrorists/Non-State Militias",
18: "Tourists",
19: "Transportation",
20: "Unknown",
21: "Utilities",
22: "Violent Political Parties"
}
result_x = [targets[x] for x in sorted(targets)]
result_y = []
for x in sorted(targets):
if len(data[data['targtype1'] == x]) == 0:
freq = 0
else:
freq = len(
data[(data['targtype1'] == x) & (data['success'] == 1)]) / len(
data[data['targtype1'] == x])
result_y.append(freq)
chart = pygal.Bar(show_minor_x_labels=False,
truncate_legend=40,
truncate_label=20,
x_label_rotation=90,
y_labels_major_every=3,
show_minor_y_labels=False,
value_formatter=lambda x: "%d%%" % x)
chart.x_labels = []
chart.title = 'Overall success rate by targets from 1970 to 2016 except 1993'
for x in range(22):
if result_y[x] == 0:
continue
chart.add(
result_x[x] + " (" + str("%.3f" % (result_y[x] * 100)) + "%)",
round(result_y[x] * 100, 3))
chart.render_to_file('Charts/Targets_Frequency_SuccessRate.svg')
# End of modules and return back to main
if test:
return
print("\nGraph generated!")
targets_main.main(data)
#print("Repositories returned:",len(repo_dicts))
#可视化
my_style = LS('#333366', base_style=LCS)
my_config = pygal.Config()
my_config.x_label_rotation = 45
my_config.show_legend = False
my_config.title_font_size = 24
my_config.label_font_size = 14
my_config.major_label_font_size = 18
my_config.truncate_label = 15
my_config.show_y_guides = False
my_config.width = 1000
chart = pygal.Bar(style=my_style, config=my_config) #x_label必须斜着
chart.title = 'Most-starred Python Projects on Github'
chart.x_labels = names
chart.add('', plot_dicts)
chart.render_to_file('python_repos.svg')
#研究第一个仓库
repo_dict = repo_dicts[0]
print("\nKeys:", len(repo_dict))
for key in sorted(repo_dict.keys()):
print(key)
print("\nSelected information about each repository:")
for repo_dict in repo_dicts:
print('Name:', repo_dict['name'])
100 * together / individually
))
absolute_graph = pygal.Line(x_label_rotation = 20)
absolute_graph.title = 'Projects with features by date'
absolute_graph.x_labels = [format_time(bucket['start']) for bucket in time_buckets]
absolute_graph.add('Totals', [bucket['count'] for bucket in time_buckets])
for feature in features.items():
absolute_graph.add(
feature[1]['description'],
[bucket['feature_count'][feature[0]] for bucket in time_buckets]
)
absolute_graph.render_to_file('features_absolute.svg')
percent_graph = pygal.Line(x_label_rotation = 20)
percent_graph.title = 'Projects with features by date (in %)'
percent_graph.x_labels = [format_time(bucket['start']) for bucket in time_buckets]
for feature in features.items():
percent_graph.add(
feature[1]['description'],
[(int(100 * (bucket['feature_count'][feature[0]] / bucket['count'])) if bucket['count'] > 0 else None) for bucket in time_buckets]
)
percent_graph.render_to_file('features_percent.svg')
feature_histogram = pygal.Bar()
feature_histogram.title = 'Histogram of features per project'
feature_histogram.x_labels = map(str, range(6))
feature_histogram.add('Feature count', feature_counts)
feature_histogram.render_to_file('feature_histogram.svg')
def earthEngine(poi, outputLocation):
ee.Initialize()
#Change projection to WGS1984
wgs = arcpy.SpatialReference(4326)
arcpy.Project_management(
poi, os.path.join(arcpy.env.scratchFolder, "POI_layer_wgs.shp"), wgs)
poi_reproj = os.path.join(arcpy.env.scratchFolder, "POI_layer_wgs.shp")
#Create GEE object for point of interest
desc = arcpy.Describe(poi_reproj)
xmin = desc.extent.XMin
ymin = desc.extent.YMin
poiObject = ee.Geometry.Point([xmin, ymin])
#The CHIRPS data only spans from 50 degrees S to 50 degrees N,
#so exit earthEngine function if POI is placed outside of range
if ymin > 49.999 or ymin < -49.999:
arcpy.AddMessage(
"Point was placed outside geographic range of CHIRPS rainfall data (50 degrees South-50 degrees North). Pick a point between 50 deg S and 50 deg N to return rainfall information."
)
return None
#CHIRPS image collection
chirps = ee.ImageCollection('UCSB-CHG/CHIRPS/DAILY')
#Set the time period over which images will be captured.
#Only rainfall from the past year will be reported.
now = datetime.datetime.now()
endYr = now.year
endMo = now.month
endDy = now.day
stYr = endYr - 1
stMo = endMo
stDy = endDy
#Create variables that will be used to iterate through each day of the year
years = range(stYr, endYr + 1)
endMoRange = endMo + 13
months = range(endMo, endMoRange)
#Set date in EE format
startdate = ee.Date.fromYMD(stYr, stMo, 1)
enddate = ee.Date.fromYMD(endYr, endMo, 1)
#Filter CHIRPS by day
Pchirps = chirps.filterDate(
startdate, enddate).sort('system:time_start').select('precipitation')
#Method to calculate monthly precipitation sum
def calcMonthlySum(imageCollection):
mylist = ee.List([])
for m in months:
if m <= 12:
mo = m
yr = years[0]
w = imageCollection.filter(
ee.Filter.calendarRange(yr, yr, 'year')).filter(
ee.Filter.calendarRange(mo, mo, 'month')).sum()
mylist = mylist.add(
w.set('system:time_start',
str(mo) + '/' + str(yr)))
else:
mo = m - 12
yr = years[1]
w = imageCollection.filter(
ee.Filter.calendarRange(yr, yr, 'year')).filter(
ee.Filter.calendarRange(mo, mo, 'month')).sum()
mylist = mylist.add(
w.set('system:time_start',
str(mo) + '/' + str(yr)))
return ee.ImageCollection.fromImages(mylist)
#Call function to calculate monthly rainfall
monthlyChirps = ee.ImageCollection(calcMonthlySum(Pchirps))
#Limit output to the point of interest
monthlyChirps2 = monthlyChirps.getRegion(poiObject, 24000,
"epsg:4326").getInfo()
#Create pandas dataframe to plot
df = pd.DataFrame(monthlyChirps2, columns=monthlyChirps2[0])
df2 = df[1:]
df2[['id']] = df2[['id']].apply(pd.to_numeric)
collapseDF = df2.groupby('id').agg({
'precipitation': np.sum,
'time': 'first'
})
#Plot the Precipitation Series from the dataframe
precipSeries = collapseDF["precipitation"]
blue = pygal.style.Style(colors=('blue', ))
bar_chart = pygal.Bar(title=u"Monthly Precipitation",
x_title="Date",
y_title="Millimeters",
style=blue)
bar_chart.add("Precipitation", precipSeries)
timeSeries = collapseDF["time"]
timeList = timeSeries.tolist()
bar_chart.x_labels = timeList
bar_chart.render_to_file(os.path.join(outputLocation, 'Rainfall.svg'))
def __init__(self, database):
self.chart = pygal.Bar()
self.db = database
#Import modules
custom_style = Style(background='transparent',
plot_background='#ffffff',
foreground='#1b1b1b',
foreground_strong='#1b1b1b',
foreground_subtle='#1b1b1b',
opacity='.4',
opacity_hover='.6',
colors=('#1b1b1b', '#733380', '#22ff33'))
iterations = 1000
rw = RandomWalk(iterations)
rw.fill_walk()
# Visualize data with pygals's bar chart
hist = pygal.Bar(fill=True,
interpolate='cubic',
style=custom_style,
max_scale=100)
hist.title = f'Visualization of {str(iterations)} random movement iterations.'
hist.x_title = 'Iterations'
hist.y_title = 'Distance'
hist.x_labels = [
label if label % 500 == 0 else '' for label in range(iterations + 1)
]
hist.add('X-Distance', rw.x_values)
hist.add('Y-Distance', rw.y_values)
hist.render_to_file('./generating_data/images/svg/bar.svg')
def bitly():
#trabajar desde una base de datos
db = MongoClient(
'mongodb://Scraper%2Fops:R3vim3x5o5%2F%[email protected]:27017/admin'
).XLamudi
db2 = MongoClient(
'mongodb://*****:*****@35.227.93.9:27017/admin'
).commserver
collection = db['bitly']
enlaces = [x for x in collection.find({})]
collection2 = db2['deliveredmsgs']
collection3 = db2['deliveredmails']
sms = [y for y in collection2.find({})]
email = [z for z in collection3.find({})]
tokenbitly = 'e51c52061b3675fd00e523dfa557bd5efd21558e' #token para api
url = 'https://api-ssl.bitly.com/v3/user/popular_links?access_token={}'
r = json.loads(
(requests.get(url.format(tokenbitly)).content).decode('utf-8'))
historial = r['data']['popular_links']
links_populares = []
for i in historial:
for k in enlaces:
if i['link'] == k['link_corto']:
links_populares.append({
'enlace':
i['link'],
'clicks':
i['clicks'],
'enlace_real':
k['link_largo'],
'tipo':
k['campaña'],
"camp_id":
k["camp_id"],
"enviados":
k["enviados"],
"Fecha":
str(k["fecha_creacion"].year) + '/' +
str(k["fecha_creacion"].month) + '/' +
str(k["fecha_creacion"].day)
})
total_campsms = [x for x in collection2.distinct('camp_id')]
total_campema = [x for x in collection3.distinct('camp_id')]
total_campanasms = []
for i in links_populares:
for j in [x for x in collection2.distinct('camp_id')]:
if j == i['camp_id'] and i['tipo'] == 'sms':
total_campanasms.append({
'enlace':
i['enlace'],
'camp_id':
j,
'entregados':
collection2.find({
"camp_id": j
}).count()
})
for i in links_populares:
for j in total_campanasms:
if i['enlace'] == j['enlace']:
i['entregados'] = j['entregados']
total_campanaema = []
for i in links_populares:
for j in [x for x in collection3.distinct('camp_id')]:
if j == i['camp_id'] and i['tipo'] == 'email':
total_campanaema.append({
'enlace':
i['enlace'],
'camp_id':
j,
'entregados':
collection3.find({
"camp_id": j
}).count()
})
for i in links_populares:
for j in total_campanaema:
if i['enlace'] == j['enlace']:
i['entregados'] = j['entregados']
chart = pygal.Bar()
custom_style = Style(colors=('#E80080', '#404040', '#9BC850', '#E80080',
'#404040'))
chart = pygal.Bar(margin=40)
chart = pygal.Bar(width=180)
chart = pygal.Bar(height=280)
chart.title = 'total interacciones por enlace campaña sms-email'
for i in links_populares:
print(i)
chart.add(
str([i["camp_id"]]) + i['tipo'] + ' ' + 'enviados:' +
str(i['enviados']) + ' ' + 'entregados:' + str([i['entregados']]) +
str(int((i['entregados'] * 100) / i['enviados'])) + '%' + ' ' +
'interaccion:' + str(int(
(i['clicks'] * 100) / i['entregados'])) + '%',
[{
'value': i['clicks'],
'label': 'clicks'
}])
chart.render_to_file('static/images/bar_chart.svg')
img_url = 'static/images/bar_chart.svg?cache=' + str(time.time())
return render_template('app.html', image_url=img_url)
#!/usr/bin/env python
import datetime
import gspread
import pygal
import config
gc = gspread.login(config.login, config.password)
wks = gc.open(config.sheet_name).sheet1
names2reps = []
for i in range(config.starting_row, config.ending_row+1):
names2reps.append((wks.cell(i, 1).value, int(wks.cell(i, 2).value)))
title = datetime.datetime.now().strftime('Last update: %d %b @ %H:%M')
bar_chart = pygal.Bar(title=title, style=pygal.style.DarkSolarizedStyle)
for name, reps in names2reps:
bar_chart.add(name, [reps])
bar_chart.render_to_file(config.svg_path)
from die import Die
import pygal
die = Die()
res = []
for i in range(1, 1000):
single_res = die.roll()
res.append(single_res)
print(res)
freqs = []
for v in range(1, die.side + 1):
single_freq = res.count(v)
freqs.append(single_freq)
print(freqs)
histogram = pygal.Bar()
histogram.title = 'results of rolling the die'
histogram.x_labels = ['1', '2', '3', '4', '5', '6']
histogram.x_title = 'result'
histogram.y_title = 'frequncy of results'
histogram.add('Die6', freqs)
histogram.render_to_file('die_visual4.svg')
def statistics():
up_active = len(
patient_detail.query.filter_by(state="Uttar Pradesh",
status="Active").all())
up_recovered = len(
patient_detail.query.filter_by(state="Uttar Pradesh",
status="Recovered").all())
up_deceased = len(
patient_detail.query.filter_by(state="Uttar Pradesh",
status="Deceased").all())
mp_active = len(
patient_detail.query.filter_by(state="Madhya Pradesh",
status="Active").all())
mp_recovered = len(
patient_detail.query.filter_by(state="Madhya Pradesh",
status="Recovered").all())
mp_deceased = len(
patient_detail.query.filter_by(state="Madhya Pradesh",
status="Deceased").all())
maha_active = len(
patient_detail.query.filter_by(state="Maharashtra",
status="Active").all())
maha_recovered = len(
patient_detail.query.filter_by(state="Maharashtra",
status="Recovered").all())
maha_deceased = len(
patient_detail.query.filter_by(state="Maharashtra",
status="Deceased").all())
guj_active = len(
patient_detail.query.filter_by(state="Gujarat", status="Active").all())
guj_recovered = len(
patient_detail.query.filter_by(state="Gujarat",
status="Recovered").all())
guj_deceased = len(
patient_detail.query.filter_by(state="Gujarat",
status="Deceased").all())
del_active = len(
patient_detail.query.filter_by(state="Delhi", status="Active").all())
del_recovered = len(
patient_detail.query.filter_by(state="Delhi",
status="Recovered").all())
del_deceased = len(
patient_detail.query.filter_by(state="Delhi", status="Deceased").all())
line_chart = pygal.Bar()
line_chart.title = 'Covid-19 cases in different states'
line_chart.x_labels = [
'Uttar Pradesh', 'Madhya Pradesh', 'Maharashtra', 'Gujarat', 'Delhi'
]
line_chart.add('Active',
[up_active, mp_active, maha_active, guj_active, del_active])
line_chart.add('Recovered', [
up_recovered, mp_recovered, maha_recovered, guj_recovered,
del_recovered
])
line_chart.add(
'Deceased',
[up_deceased, mp_deceased, maha_deceased, guj_deceased, del_deceased])
chart_data = line_chart.render_data_uri()
stats = patient_detail.query.all()
return render_template('statistics.html',
stats=stats,
chart_data=chart_data)
import pygal
chart = pygal.Bar()
chart.add('First', [{
'value': 2,
'label': 'This is the first',
'xlink': 'http://en.wikipedia.org/wiki/First'
}])
print(chart.render(is_unicode=True))
def cc():
pl = data.getpid()
# pid = 49
# l1,l2,l3 = data.getdata(pid) # '''l1 未解决按指派对象，l2 已解决按结局方案，l3 已解决按解决者'''
titleList = [
'未解决 - 严重程度', '未解决 - 开发人员', '已解决 - 解决方案', '新增 - 严重程度', '新增 - 测试人员'
]
chartList = []
tabelList = []
lineList = []
X = 49
P = pl[0]
if request.method == 'POST':
# print(request.form)
# if request.form['select'] in [p['name'] for p in pl]:
for p in pl:
if request.form['select'] == p['name']:
X = p['id']
P = p
# print(X)
for item in data.getdata(X):
bar_chart = pygal.Bar(legend_at_bottom=True)
for i in item:
bar_chart.add(str(i['la']), i['num'], rounded_bars=4)
tabelList.append(
bar_chart.render_table(style=True, transpose=False))
chartList.append(bar_chart.render_data_uri())
# 曲线展示
for testlist in data.getdataline(X):
line_chart = pygal.Line(legend_at_bottom=True, x_label_rotation=20)
newlist = []
LL = []
for item in testlist:
newlist.append([i for i in item.values()])
severity = list(set([i['lb'] for i in testlist]))
# print(severity)
date = sorted(list(set([i['la'] for i in testlist])))
# print(date)
for s in severity:
for d in date:
t = 0
for item in newlist:
if (item[1] == s) & (item[0] == d):
t = item[2]
break
LL.append(t)
line_chart.x_labels = date
i = 0
j = len(date)
for s in severity:
line_chart.add('%s' % s, LL[i:j])
del LL[i:j]
lineList.append(line_chart.render_data_uri())
else:
# 列表展示
for item in data.getdata(X):
bar_chart = pygal.Bar(legend_at_bottom=True)
for i in item:
bar_chart.add(str(i['la']), i['num'], rounded_bars=4)
tabelList.append(
bar_chart.render_table(style=True, transpose=False))
chartList.append(bar_chart.render_data_uri())
# 曲线展示
for testlist in data.getdataline(X):
line_chart = pygal.Line(legend_at_bottom=True, x_label_rotation=20)
newlist = []
LL = []
for item in testlist:
newlist.append([i for i in item.values()])
severity = list(set([i['lb'] for i in testlist]))
# print(severity)
date = sorted(list(set([i['la'] for i in testlist])))
# print(date)
for s in severity:
for d in date:
t = 0
for item in newlist:
if (item[1] == s) & (item[0] == d):
t = item[2]
break
LL.append(t)
line_chart.x_labels = date
i = 0
j = len(date)
for s in severity:
line_chart.add('%s' % s, LL[i:j])
del LL[i:j]
# tabelList.append(line_chart.render_table(
# style=True, transpose=False))
lineList.append(line_chart.render_data_uri())
# return render_template('test.html', chart=chartList, title=titleList, table=tabelList, line=lineList, pid=pl, x=X, p=P)
return render_template('test.html',
chart=chartList + lineList,
title=titleList,
table=tabelList,
pid=pl,
x=X,
p=P)
def poltpage():
polt = pygal.Bar()
polt.add('A', (1, 3, 3, 7))
polt.add('B', (1, 6, 6, 4))
return render_template("polt.html", chart=polt)
if pop_dict['Country_Code'] == country_code:
# 使用该国GDP总值除以人口数量，得到人均GDP
country_mean_gdps[i][year] = round(
gpd_dict['Value'] /
pop_dict['Population_in_%d' % year])
# 使用list列表依次保存美国、日本、俄罗斯、加拿大的人均GDP值
country_mean_gdp_list = [[], [], [], []]
# 构建时间数据
x_data = range(2001, 2017)
for i in range(len(country_mean_gdp_list)):
for year in x_data:
country_mean_gdp_list[i].append(country_mean_gdps[i][year])
# 定义国家名称列表
countries = ['美国', '日本', '俄罗斯', '加拿大']
# 创建pygal.Bar对象（柱状图）
bar = pygal.Bar()
# 采用循环添加代表条柱的数据
for i in range(len(countries)):
bar.add(countries[i], country_mean_gdp_list[i])
bar.width = 1100
# 设置X轴的刻度值
bar.x_labels = x_data
bar.title = '2001到2016年各国人均GDP对比'
# 设置X、Y轴的标题
bar.x_title = '年份'
bar.y_title = '人均GDP(美元)'
# 设置X轴的刻度值旋转45度
bar.x_label_rotation = 45
# 设置将图例放在底部
bar.legend_at_bottom = True
# 指定将数据图输出到SVG文件中
import pygal
bar_chart = pygal.Bar()
bar_chart.add('Fibonacci', [0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55])
bar_chart.render_to_file('bar_chart.svg')
bar_chart.render()
'label': repo_dict['description'],
'xlink': repo_dict['html_url'],
}
else:
plot_dict = {
'value': repo_dict['stargazers_count'],
'label': 'None',
'xlink': repo_dict['html_url'],
}
plot_dicts.append(plot_dict)
# 可视化
my_style = LS('#333366', base_style=LCS)
my_config = pygal.Config()
my_config.x_label_rotation = 45
my_config.show_legend = False
my_config.title_font_size = 24
my_config.label_font_size = 14
my_config.major_label_font_size = 18
my_config.truncate_label = 15 # 将较长的项目名缩短为15个字符（如果你将鼠标指向屏幕上被截短的项目名，将显示完整的项目名）
my_config.show_y_guides = False # 以隐藏图表中的水平线
my_config.width = 1000 # 自定义宽度，让图表更充分地利用浏览器中的可用空间。
chart = pygal.Bar(my_config, style=my_style) # 隐藏了图例:show_legend=False
chart.title = 'Most-Starred Python Projects on Github'
chart.x_labels = names
# chart.add("", stars)
chart.add("lalalalalaalalal", plot_dicts)
chart.render_to_file("python_repos_java.svg")
print("There are", runway_12000_to_15000, "runways between 12000-15000")
print("There are", runway_15000_to_18000, "runways between 15000-18000")
#starting v6.0
#graph for lengths against times repeating
import pygal
#List of runways from above
runway_0_to_3000 = 20
runway_3000_to_6000 = 120
runway_6000_to_9000 = 358
runway_9000_to_12000 = 435
runway_12000_to_15000 = 124
runway_15000_to_18000 = 4
#adding to graph
runway_chart = pygal.Bar()
runway_chart.x_title = "Repeating Runway lengths"
runway_chart.y_title = "Runway Lengths in ft "
runway_chart.add('0-3000', runway_0_to_3000)
runway_chart.add('3000-6000', runway_3000_to_6000)
runway_chart.add('6000-9000', runway_6000_to_9000)
runway_chart.add('9000-12000', runway_9000_to_12000)
runway_chart.add('12000-15000', runway_12000_to_15000)
runway_chart.add('15000-18000', runway_15000_to_18000)
#updating to graph
runway_chart.render_to_file('Repeating lengths.svg')
exit()
def stats():
if g.user:
conn = sqlite3.connect('voters.db')
c = conn.cursor()
# START DATA ANALYSIS FOR VOTER GENDERS
c.execute("SELECT count(*) as maleCount FROM basic_info WHERE basic_info_value ='Male'")
maleCount = c.fetchone()
c.execute("SELECT count(*) as femaleCount FROM basic_info WHERE basic_info_value ='Female'")
femaleCount = c.fetchone()
totalCount = maleCount + femaleCount
pie_chart = pygal.Pie()
pie_chart.title = 'Catanduanes Voters by Gender %'
pie_chart.add('Male', maleCount)
pie_chart.add('Female', femaleCount)
pie_chart.add('Total Voters', totalCount)
pieGender = pie_chart.render(is_unicode=True)
# END DATA ANALYSIS FOR VOTER GENDERS
# START DATA ANALYSIS FOR VOTER EDUCATION
c.execute("SELECT count(*) as csuCount FROM education WHERE school = 'Catanduanes State University'")
csuCount = c.fetchone()
c.execute("SELECT count(*) as otherCount FROM education WHERE school != 'Catanduanes State University'")
otherCount = c.fetchone()
line_chart = pygal.HorizontalBar()
line_chart.title = 'Catanduanes Voters by Education %'
line_chart.add('Catanduanes State University', csuCount)
line_chart.add('Others', otherCount)
lineEduc = line_chart.render(is_unicode=True)
# END DATA ANALYSIS FOR VOTER EDUCATION
# START DATA ANALYSIS FOR VOTER AGE
c.execute("SELECT basic_info_value FROM basic_info WHERE basic_info_value < date('now') - 18")
ageCount = c.fetchall()
def calculate_age(dtob):
today = date.today()
return today.year - dtob.year - ((today.month, today.day) < (dtob.month, dtob.day))
ageList = {18: 0, 19: 0, 20: 0, 21: 0, 22: 0, 23: 0, 24: 0, 25: 0, 26: 0, 27: 0, 28: 0, 29: 0, 'other': 0}
i = 0
while i < len(ageCount):
birthday = ageCount[i][0]
date_format = '%Y/%m/%d'
try:
tbirthday = datetime.strptime(birthday, date_format)
ageNow = calculate_age(date(tbirthday.year, tbirthday.month, tbirthday.day))
for x in range(18, 29):
if ageNow == x:
ageList[x] += 1
else:
ageList[x] += 0
except:
pass
i += 1
line_chart = pygal.Bar()
line_chart.title = 'Catanduanes Voters by age %'
line_chart.x_labels = map(str, range(18, 36))
line_chart.add('Voters', [ageList[18], ageList[19], ageList[20], ageList[21], ageList[22], ageList[23], ageList[24], ageList[25], ageList[26], ageList[27], ageList[28], ageList[29]])
lineAge = line_chart.render(is_unicode=True)
# END DATA ANALYSIS FOR VOTER AGE
return render_template('stats.html', pieGender=pieGender, lineEduc=lineEduc, lineAge=lineAge, ageNow=ageNow)
return redirect(url_for('login'))
# Feature Importance:
#Build and Train a Random Forest with 100 estimators
forest = RandomForestRegressor(n_estimators=100)
forest = forest.fit(X, y)
#Extract the feature column names and feature importances for the columns
column_list = df_feat.columns.values.tolist()
importances = forest.feature_importances_
#Zip the column names and importances togther and then sort them
col_imp = list(zip(column_list, importances))
sorted_col_imp = sorted(col_imp, key=lambda i: i[1], reverse=True)
#Create a pygal bar chart to plot the feature importances
bc = pygal.Bar(width=500, height=300, explicit_size=True)
bc.title = 'Forex Feature Importances'
for i in range(len(importances)):
bc.add(sorted_col_imp[i][0], sorted_col_imp[i][1])
bc.render_in_browser()
# Train/Test Split:
#Set the percentage for training data
pct_train = .8
#Get the X,Y train/test sets
X_train = X[0:int(len(X) * pct_train)]
y_train = y[0:int(len(y) * pct_train)]
X_test = X[int(len(X) * pct_train):]
y_test = y[int(len(y) * pct_train):]
