def drawing_pie(start_date, end_date):
sentiment_dictionary = get_sentiment_dates(start_date, end_date)
sentiment_array = util.total_sentiment_array(sentiment_dictionary)
positive_count = sentiment_array[0]
negative_count = sentiment_array[1]
neutral_count = sentiment_array[2]
sentiment = ''
if positive_count > negative_count or positive_count > neutral_count:
sentiment = 'Sentiment is Positive'
elif negative_count > positive_count or negative_count > neutral_count:
sentiment = 'Sentiment is Negative'
elif neutral_count > positive_count or neutral_count > negative_count:
sentiment = 'Sentiment is Neutral'
elif positive_count == neutral_count and positive_count > negative_count:
sentiment = 'Sentiment is Positive'
elif negative_count == neutral_count and negative_count > positive_count:
sentiment = 'Sentiment is Negative'
labels = ['Positive', 'Negative', 'Neutral']
colors = ['blue', 'green', 'red']
explode = (0, 0, 0)
plt.pie(sentiment_array, explode=explode, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal')
plt.title(sentiment)
plt.show()
return
def plotGenomicregions(GPcount, name):
"""
:param GPcount: is a list of tuples [(region, size),....()]
:return:
"""
""" Now we produce some pie charts """
gr = ['tss', 'intergenic', 'intron', 'exon', 'upstream']
size = [0, 0, 0, 0, 0]
for a, b in GPcount:
if a == 'tss':
size[0] = b
if a == 'intergenic':
size[1] = b
if a == 'intron':
size[2] = b
if a == 'exon':
size[3] = b
if a == 'upstream':
size[4] = b
colors = ['yellowgreen', 'gold', 'lightskyblue', 'lightcoral', 'cyan']
explode = (0.1, 0, 0, 0, 0) # only "explode" the 2nd slice
plt.pie(size, explode=explode, labels=gr, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
# Set aspect ratio to be equal so that pie is drawn as a circle.
#plt.legend(['tss', 'intergenic', 'intron', 'exon', 'upstream'], loc='upper left')
plt.axis('equal')
plt.savefig('/ps/imt/e/20141009_AG_Bauer_peeyush_re_analysis/further_analysis/plots/' + name + '.svg')
plt.clf()
def display_PER(self):
number_of_pkts = len(self.pcap_file)
retransmission_pkts = 0
for pkt in self.pcap_file:
if (pkt[Dot11].FCfield & 0x8) != 0:
retransmission_pkts += 1
ans = (retransmission_pkts / number_of_pkts)*100
ans = float("%.2f" % ans)
labels = ['Standard packets', 'Retransmitted packets']
sizes = [100.0 - ans,ans]
colors = ['g', 'firebrick']
# Make a pie graph
plt.clf()
plt.figure(num=1, figsize=(8, 6))
plt.axes(aspect=1)
plt.suptitle('Retransmitted packet', fontsize=14, fontweight='bold')
plt.rcParams.update({'font.size': 13})
plt.pie(sizes, labels=labels, autopct='%.2f%%', startangle=60, colors=colors, pctdistance=0.7, labeldistance=1.2)
plt.show()
def comparison_pie_plot(path, data, txt):
"""
Plots a pie chart comparison of the # of times each AD found
the highest best/average final solution for all simulations
"""
# The slices will be ordered and plotted counter-clockwise.
unzipped_data = list(zip(*data))
num_sims = len(unzipped_data)
sizes = [0] * len(data)
for simulation_data in unzipped_data:
m = max(simulation_data)
max_indexes = [i for i, j in enumerate(simulation_data) if j == m]
for i in max_indexes:
sizes[i] += 1
# percentages
for i in range(len(sizes)):
sizes[i] = round((sizes[i] / num_sims) * 100)
# "explode" all slices
explode = [0.1] * len(data)
plt.figure()
plt.title("Comparison of the # of times each AD found the highest " + txt + " final solution for all simulations")
plt.pie(sizes, explode=tuple(explode), labels=AD_labels, colors=AD_color, autopct='%1.1f%%', shadow=True)
plt.axis('equal') # Set aspect ratio to be equal so that pie is drawn as a circle.
plt.savefig(path + "/pie_" + txt + ".png", bbox_inches='tight')
plt.close()
return
def plot_percent_mentions(tweets, gop = False, save_to = None):
'''
Plots the percent mentions of each candidate (filtered for party)
Used for Task 3.
'''
percents = tweets.get_percent_mentions(gop)
candidates = []
mentions = []
for c, ment in percents:
if c == "other":
other_v = ment
else:
candidates.append(CANDIDATE_NAMES[c[:-1]])
mentions.append(ment)
candidates.append("other")
mentions.append(other_v)
fig = plt.figure(figsize = (FIGWIDTH, FIGHEIGHT))
plt.pie(mentions, labels = candidates, autopct='%1.1f%%')
if gop:
plt.title("Percent of Mentions per GOP candidate")
else:
plt.title("Percent of Mentions per candidate")
plt.show()
if save_to:
fig.savefig(save_to)
def printdata(projects, graph):
print "************************************************************************"
print
print
labels = []
sizes = []
explode = []
timeSheetHours = 0
for project in projects:
timeSheetHours = timeSheetHours + projects[project].totalhours
labels.append(project)
sizes.append(projects[project].totalhours)
explode.append(0.025)
print(Fore.RED + "%s (%s)" % (project, str(projects[project].totalhours)) + Fore.RESET)
for activity in projects[project].activities:
print(Fore.CYAN + " - %s (%s)" % (activity, str(projects[project].activities[activity].totalhours)) + Fore.RESET)
print
print(Fore.RED + "Total number of hours on these timesheets: " + str(timeSheetHours) + Fore.RESET)
print
print "************************************************************************"
if graph:
colors = ('b', 'g', 'r', 'c', 'm', 'y')
plt.pie(sizes, explode=explode, labeldistance=1.2, pctdistance=1.1, labels=labels, colors=colors, autopct='%1.1f%%')
plt.axis('equal')
plt.show()
def display_channel_efficiency(self):
size = 0
start_time = self.pcap_file[0].time
end_time = self.pcap_file[len(self.pcap_file) - 1].time
duration = (end_time - start_time)/1000
for i in range(len(self.pcap_file) - 1):
size += len(self.pcap_file[i])
ans = (((size * 8) / duration) / BW_STANDARD_WIFI) * 100
ans = float("%.2f" % ans)
labels = ['utilized', 'unutilized']
sizes = [ans, 100.0 - ans]
colors = ['g', 'r']
# Make a pie graph
plt.clf()
plt.figure(num=1, figsize=(8, 6))
plt.axes(aspect=1)
plt.suptitle('Channel efficiency', fontsize=14, fontweight='bold')
plt.title("Bits/s: " + str(float("%.2f" % ((size*8)/duration))),fontsize = 12)
plt.rcParams.update({'font.size': 17})
plt.pie(sizes, labels=labels, autopct='%.2f%%', startangle=60, colors=colors, pctdistance=0.7, labeldistance=1.2)
plt.show()
def main():
## Open the file with read only permit
f = open(filepath + alertfilename)
## Read the first line
line = f.readline()
## If the file is not empty keep reading line one at a time
## till the file is empty
while line:
if "User IP:" in line:
ipquery(line[9:-1])
line = f.readline()
f.close()
## Count the unique IP
ip_data = Counter(ips)
## Count the unique countries
country_data = Counter(countries)
## Find the index of the largest entry to explode on chart
indx = country_data.values().index(max(country_data.values()))
explode = [0] * len(country_data.values())
explode[indx] = 0.1
## Draw the chart
a = np.random.random(20)
cs = cm.Set1(np.arange(20)/20.)
plt.pie(country_data.values(), explode=explode, labels=country_data.keys(), colors=cs, autopct='%1.1f%%', startangle=90)
plt.axis('equal')
plt.show()
def analyzeData(db):
# Total calls, incoming, outgoing (and percents). Times to/from liz and percentage.
cursor = db.cursor()
numCalls = cursor.execute('''SELECT Count(*) FROM calls''').fetchone()[0]
print numCalls, "calls from May to July 2014."
numIncoming = cursor.execute('''SELECT Count(*) FROM calls WHERE incoming=1''').fetchone()[0]
print numIncoming, "incoming calls. (" + str((numIncoming*100.0)/numCalls) + "%)"
numOutgoing = cursor.execute('''SELECT Count(*) FROM calls WHERE incoming=0''').fetchone()[0]
print numOutgoing, "outgoing calls. (" + str((numOutgoing*100.0)/numCalls) + "%)"
# Display the info in a pie chart
labels = 'Incoming Calls', 'Outgoing Calls'
values = [numIncoming, numOutgoing]
colors = ['orange', 'seagreen']
plt.pie(values, labels=labels, colors=colors, autopct='%1.1f%%')
plt.axis('equal')
plt.show()
numLiz = cursor.execute('''SELECT Count(*) FROM calls WHERE phone_number='630-380-4152';
''').fetchone()[0]
percentLiz = (numLiz*100.0)/numCalls
print numLiz, "calls to/from Liz. (" + str(percentLiz) + "%)"
# Display the info in a pie chart
labels = 'Liz', 'Others'
sizes = [int(percentLiz), 100 - int(percentLiz)]
colors = ['turquoise', 'gold']
plt.pie(sizes, colors=colors, labels=labels, autopct='%1.1f%%')
plt.axis('equal')
plt.show()
return
def GraficaPastel():
import matplotlib.pyplot as plt
import numpy as np
datos=int(input("Cuantos datos ingresaras: "))
impr=[0]*datos
vol=[0]*datos
expl=[0]*datos
for x in range(0,datos):
impr[x]=(input("Nombre: "))
vol[x]=(int(input("Numero: ")))
mayor=0
for x in range(0,datos):
if vol[x] > mayor:
mayor = vol[x]
for x in range(0,datos):
if vol[x] == mayor:
expl[x] = 0.05
plt.pie(vol, explode=expl, labels=impr, autopct='%1.1f%%', shadow=True)
plt.title("Pastel", bbox={"facecolor":"0.8", "pad":5})
plt.legend()
plt.show()
def plotPieChart(self, title=None, cmap_name='Pastel2'):
if sys.hexversion >= 0x02700000:
self.fig.set_tight_layout(True)
# Generate plot data
labels, ydata = self._getPlotData()
totalobjects = float(np.sum(ydata))
fracs = [ynum / totalobjects for ynum in ydata]
explode = np.zeros(len(fracs)) # non zero makes the slices come out of the pie
# plot pie chart
cmap = plt.cm.get_cmap(cmap_name)
colors = cmap(np.linspace(0., 0.9, len(fracs)))
plt.pie(fracs, explode=explode, labels=labels, autopct='%1.1f%%', shadow=False, startangle=90,
colors=colors)
# generate plot / axis labels
for axis in self.ax.get_xticklabels():
axis.set_fontsize(self.xticksize)
if self.unit is None: # NOTE this is hacked in so it only works with DataPerParameterClass
self.unit = self._getParLabelAndUnit(self._planetProperty)[1] # use the default unit defined in this class
self._yaxis_unit = self.unit
if title is None:
title = 'Planet {0} Bins'.format(self._gen_label(self._planetProperty, self.unit)) # NOTE not always planet
plt.title(title)
plt.xlim(-1.5, 1.5)
def plot_educationLevel(df):
"""
Function takes dataframe as input,
plot a pie of
Argument
========
DataFrame
"""
degree=degreeDict(df)
bach=degree['Bachelor']
master=degree['Master']
others=degree['High School or others non-degree']
labels = 'At least \n a Bachelor degree', 'At least\n A Master \n degree','Others:\nHigh school \nDiploma or \nSome experiences '
fracs = [bach, master, others]
plt.figure(figsize=(12,8))
explode = (0.05, 0.05, 0.05)
colors = ['yellowgreen', 'gold', 'lightskyblue', 'lightcoral']
plt.pie(fracs,explode=explode, colors=colors, autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal')
plt.legend(labels,loc="lower right")
plt.title('Minimum Degree Requirement', fontsize=20)
plt.show()
def create_pie_chart(data, title, filename, cutoff=0.01, verbose=False):
"""Create a pie chart from the given data
Params:
data- a collections.Counter where the keys should be the labels to
the graph
"""
total = float(sum(data.values()))
frac_labels = []
other_count = 0
# compute the fraction for each label
for cnt in data.keys():
fraction = float(data[cnt]) / total
if verbose:
print "{}: {}".format(cnt, fraction)
# if this slice is too small, just add it to other small
# totals and display them together
if fraction < cutoff:
other_count += data[cnt]
continue
frac_labels.append((fraction, cnt))
if other_count > 0:
frac_labels.append((float(other_count) / total, "Other"))
frac_labels.sort(key=lambda entry: entry[1])
fractions, labels = zip(*frac_labels)
plt.figure()
plt.pie(fractions, labels=labels, autopct='%1.1f%%',
colors=('b', 'g', 'r', 'c', 'm', 'y', 'k', 'w'))
plt.title(title)
plt.savefig(filename, fmt='pdf')
def plot_visit_duration_dist(page_info, course, style='pie',
include_subpages=True):
dict_to_plot = visit_duration_dist(page_info, course, include_subpages)
y = []
my_labels = []
for num, key in enumerate(sorted(dict_to_plot.keys())):
# disregard entries below 1%
if float(dict_to_plot[key]) / sum(dict_to_plot.values()) < 0.01:
continue
y.append(dict_to_plot[key])
if 'pie' == style:
my_labels.append(key.replace(
'_', '') + ' [' + str(int(y[num] / 60 / 60)) + 'h ' + str(
int(100 * round(float(dict_to_plot[key]) / sum(
dict_to_plot.values()), 2))) + '%]')
elif 'bar' == style:
my_labels.append(key.replace(
'December_', 'Dec').replace(
'April_', 'Apr').replace(
'20', '') + '\n' + str(
int(100 * round(float(dict_to_plot[key]) / sum(
dict_to_plot.values()), 2))) + '%')
y = np.asarray(y)
if 'pie' == style:
plt.pie(y, labels=my_labels, startangle=90)
elif 'bar' == style:
plt.bar(range(len(y)), y / 60 / 60, align='center',
color=create_RGB_list(len(y)))
plt.gca().set_xticks(range(len(y)))
plt.gca().set_xticklabels(my_labels)
plt.ylabel('Total pageview time in hours')
plt.title(course + ' - Total pageview time per exam')
def plot_NA_ratio_features(dataset, feature_names, missing_value_string='nan'):
y, x = dataset.shape
ind = np.zeros((x, 1)).reshape(1, x)
for j in range(y):
for i in range(x):
# print str(dataset[j, i])
if missing_value_string == str(dataset[j, i]):
ind[0, i] += 1
ind = (ind/y*100)
labels = 'NA', ''
colors = ['yellowgreen', 'lightcoral']
explode = (0, 0)
plt.rcParams.update({'font.size': 8})
plt.suptitle("NA ration", fontsize=16)
for i in range(x):
ax = plt.subplot(5, 5, i+1)
ax.set_title(feature_names[i])
sizes = [ind[0, i], 100-ind[0, i]]
plt.pie(sizes, explode=explode, labels=labels, colors=colors, autopct='%1.1f%%')
# autopct permits to add the value of the part in chart
plt.axis('equal')
plt.show()
def displayIncomeByGender():
from FileValidation import Validation
a = Validation()
data_list = a.theFile
list_size = len(data_list)
incomes = []
female_income = 0
male_income = 0
for element in range(0, list_size):
if data_list[element][1] == "F":
female_income += int(data_list[element][5])
elif data_list[element][1] == "M":
male_income += int(data_list[element][5])
incomes.append(female_income)
incomes.append(male_income)
plt.title("Male and Female Income Ratio")
labels = 'Female Income', 'Male Income'
sizes = incomes
colors = ['pink', 'blue']
plt.pie(sizes, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal')
plt.show()
def make_chart_pie_chart():
plt.pie([0.95, 0.05], labels=["Uses pie charts", "Knows better"])
# make sure pie is a circle and not an oval
plt.axis("equal")
plt.show()
def createSingleObjectPieChart(objectOrientationDict,outputPath,objectType):
userInput=''
orientationList = objectOrientationDict[objectType]
labels = 'Left - ' + str(orientationList[0]), 'Right - ' + str(orientationList[1]), 'Frontal - ' + str(orientationList[2]), 'Rear - ' + str(orientationList[3]), 'Unspecified - ' + str(orientationList[4])
sizes = objectOrientationDict[objectType]
colors = ['yellowgreen', 'gold', 'lightskyblue', 'orange','red']
plt.subplots_adjust(top=0.85)
plt.title('The Distribution of ' + str(sum(orientationList)) + ' '+ objectType[0].upper() + objectType[1:] + ' Object by Orientation.',fontsize=16, fontweight='bold')
plt.pie(sizes, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=45)
# Set aspect ratio to be equal so that pie is drawn as a circle.
plt.axis('equal')
while userInput is not 'y' or 'n':
userInput = raw_input("Would you like to save the figure? (y/n) ")
userInput = userInput.lower()
if userInput == 'y':
path = os.path.abspath(outputPath)
filename = 'graphObjectOrientation_Piechart.png'
fullpath = os.path.join(path, filename)
plt.savefig(fullpath)
break
elif userInput == 'n':
break
else:
print "Please answer y or n. " '\n'
plt.show()
def displayAgeGroupIncome():
from FileValidation import Validation
a = Validation()
data_list = a.theFile
list_size = len(data_list)
incomes = []
under_30_income = 0
between30_50_income = 0
above50_income = 0
for element in range(0, list_size):
if int(data_list[element][2]) > 0\
and int(data_list[element][2]) <= 30:
under_30_income += int(data_list[element][5])
elif int(data_list[element][2]) > 30\
and int(data_list[element][2]) <= 50:
between30_50_income += int(data_list[element][5])
elif int(data_list[element][2]) > 50:
above50_income += int(data_list[element][5])
incomes.append(under_30_income)
incomes.append(between30_50_income)
incomes.append(above50_income)
plt.title("Age Group and Income Ratio")
labels = 'Age under 30', 'Age between 31-50', 'Age above 50'
sizes = incomes
colors = ['Blue', 'Green', 'Orange']
plt.pie(sizes, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal')
plt.show()
def generate_piechart(TPdata, key, dictionary):
"""generates a pie chart about a key in the dataset using translation dictionary"""
counts = defaultdict(int) # empty dictionary
for TP in TPdata:
counts[TP[key]] += 1
logging.debug("extracted counts: [%s]", str(counts) )
fig1 = plt.figure(figsize=(8,8)) ## makes sure that there is no squeezing of the round pie
plt.axis('equal')
values = [value for key, value in counts.items()]
labels = counts.keys()
if dictionary:
labels = translate_labels(labels, dictionary)
labels = add_sum_to_labels(values, labels)
plt.pie(values, explode=None, \
labels=labels, colors=None, autopct=None, pctdistance=0, \
shadow=False, labeldistance=1.1, hold=None)
plt.show()
def pie_chart_secondary(self, field, period=None, dst_fname=None, dpi=200):
""" 显示顶层分类下的子类别的时间饼图，人这个图里可以看到一段时间内, 某个主类别下面的任务的时间分配情况
:param field: 顶层类别名称
:param period: 统计周期，tuple 类型数据，其中 interval[0] 表示开始的日期，interval[1] 表示结束日期
:param dst_fname: 目标文件名，如果为空，则直接在输出的文件名后加上 ‘_pie_chart.png’ 后缀
:param dpi: 图片质量
"""
if not self.cached:
self._process_data()
if field not in self.data_raw['List Name'].unique():
print('error: field %s is not an top level category.')
return
# select data from interval
if not period:
period = (self.start_day, self.end_day)
data = self.data_raw.loc[period[0]: period[1]]
tag_list = data.groupby(['List Name', 'Tag']).sum()
plt.clf()
_labels = lambda values: [v.decode('utf-8') for v in values]
title = u'精力分配: %s [%s - %s]' % (field.decode('utf-8'), period[0], period[1])
plt.title(title)
plt.axis('equal')
plt.pie(tag_list.loc[field]['Duration'].values,
labels=_labels(tag_list.loc[field].index.values),
autopct='%1.0f%%')
if not dst_fname:
dst_fname = self.datafile + '_pie_chart_sec.png'
plt.savefig(dst_fname, dpi=dpi)
def plot_pie(df, name):
""" plot a pie chart showing composition of different restaurants, return 1 if succeed """
# Get restaurant count group by description in descending order
ranking = df.groupby('DESCRIPTION').count().sort('CAMIS', ascending=False)
n = ranking.sum()[0] - ranking.ix['Other'][0]
# Get top 10 descriptions and their corresponding counts
other = n - ranking[:10].sum()[0]
labels = list(ranking.index[:10])
try:
labels.remove('Other')
except ValueError:
pass
sizes = []
for label in labels:
sizes.append(ranking.ix[label][0])
labels = [x.decode('utf8').encode('ascii', 'replace') for x in labels]
labels.append('Other')
sizes.append(other)
cm = plt.get_cmap('gist_rainbow')
colors = [cm(x) for x in np.arange(0, 1, 1./len(labels))]
plt.figure()
plt.pie(sizes, labels=labels, colors = colors, autopct='%1.1f%%', shadow=True, startangle=90)
plt.title('Percentage of Different Restaurants ({})'.format(name))
plt.axis('equal')
plt.savefig('rest_pie_{}.png'.format(name))
return 1
def pie_graph(conn, query, output, title='', lower=0, log=False):
labels = []
sizes = []
res = query_db(conn, query)
# Sort so the graph doesn't look like complete shit.
res = sorted(res, key=lambda tup: tup[1])
for row in res:
if row[1] > lower:
labels.append(row[0])
if log:
sizes.append(math.log(row[1]))
else:
sizes.append(row[1])
# Normalize.
norm = [float(i)/sum(sizes) for i in sizes]
plt.pie(norm,
labels=labels,
shadow=True,
startangle=90,
)
plt.figtext(.1,.03,'{}\n{} UTC'.format(site,generation_time))
plt.axis('equal')
plt.legend()
plt.title(title)
plt.savefig(output)
plt.close()
def plotResults(red_wins, black_wins, tie):
# Adjusting the plot results to not show 0%`s
def make_autopct(values):
def my_autopct(pct):
if pct == 0:
return ""
else:
return '{p:.1f}% '.format(p=pct)
return my_autopct
# Setting up plot variables
labels = ['Red Wins', 'Black Wins', 'Ties']
sizes = [red_wins, black_wins, tie]
colors = ['yellowgreen', 'gold', 'lightskyblue']
explode = (0.1, 0, 0)
plt.pie(sizes, colors=colors, explode=explode, labels=labels, autopct=make_autopct(sizes), shadow=True,
startangle=70)
plt.axis('equal')
plt.tight_layout()
plt.show()
print "number of red wins ", red_wins
print "number of black wins ", black_wins
print "number of ties ", tie
def plot_single_piechart(self, cluster_no, labels, pdf):
cluster_label_dict = {}
for label in labels:
if label not in cluster_label_dict:
cluster_label_dict[label] = 1
else:
cluster_label_dict[label] += 1
distinct_labels = []
label_counts = []
colors = []
cmap = self.get_cmap(30)
i = 0
for label,value in cluster_label_dict.iteritems():
colors.append(cmap(i))
distinct_labels.append(label)
label_counts.append(value)
i = i+1
matplotlib.rcParams['font.size'] = 5
plt.figure(figsize=(8,8))
plt.pie(label_counts, explode=None, labels=distinct_labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
# Set aspect ratio to be equal so that pie is drawn as a circle.
plt.axis('equal')
plt.suptitle("Cluster no " + str(cluster_no) + "\nNumber of docs in cluster: " + str(len(labels)),fontsize=10)
pdf.savefig()
plt.close()
def makePieChart(bigList):
streetNameList = []
bikeSpaceList = []
x = 0
##bigList = readBikeData.GatherData('rows.json')
for i in range(len(bigList)):
streetName = bigList[i][10].lower()
bikeSpaceInt = int(bigList[i][12])
if streetName in streetNameList:
ndx = streetNameList.index(streetName)
bikeSpaceList[ndx] += bikeSpaceInt
else:
streetNameList.append(streetName)
bikeSpaceList.append(bikeSpaceInt)
bikeSpaceSum = sum(bikeSpaceList)
##I omited any area that was less then 1% of the total bike space to get a cleaner pie chart
while x < len(bikeSpaceList):
if(bikeSpaceList[x] < (bikeSpaceSum * .01) and x >= 0):
del bikeSpaceList[x]
del streetNameList[x]
x-=1
else:
x+=1
plt.axis("equal")
plt.pie(bikeSpaceList, labels = streetNameList, autopct = "%1.1f%%", shadow = False)
plt.title("Bike Space to Street Name Distribution")
plt.show()
def drawing_pie(start_date, end_date):
p_count=0
n_count=0
neu_count=0
sentiment = get_sentiment_dates(start_date,end_date)
for semt in sentiment[0].values():
p_count+=semt
for semt in sentiment[1].values():
n_count+=semt
for semt in sentiment[2].values():
neu_count+=semt
print p_count
print n_count
print neu_count
labels = 'Positive','Negative','Neutral'
sizes = [p_count,n_count,neu_count]
colors = ['green', 'red', 'yellow']
explode = (0, 0.1, 0) # only "explode" the 2nd slice
plt.pie(sizes, explode=explode, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal')
plt.title('Sentiment is Positive')
plt.show()
return
def pieplot(data, total, min, stitle): #Create a pie plot... mmm, pie
import matplotlib.pyplot as plt
labels=[]
sizes=[]
other=0
if total is None: #Calc total if not given
total=0
for cat in data:
total+=cat[0]
for cat in data: #Convert values to a percentage of total, separate smaller categories
cat[0]=cat[0]/total*100
if cat[0]>min:
labels.append(cat[1])
sizes.append(cat[0])
else:
other+=cat[0]
if other>0.1: #Include the rest if it's significant
sizes.append(other)
labels.append("Other")
# The slices will be ordered and plotted counter-clockwise.
colors = ['yellowgreen', 'gold', 'lightskyblue', 'lightcoral']
#explode = (0, 0.1, 0, 0) # only "explode" the 2nd slice # But I don't wanna explode...
plt.pie(sizes, labels=labels, #colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
plt.axis('equal') # Set aspect ratio to be equal so that pie is drawn as a circle.
plt.title(stitle)
plt.show()
def pieplot(self, variable):
""" Plot pie plot for gender or usertype in certain period """
variable_type = self.data[variable].unique()
variable_size = []
if variable == 'gender':
for i in np.sort(variable_type):
variable_size.append(round((sum(self.data[variable] == i) / self.data.shape[0] * 100), 2)) # calculate distirbution
# Gender (Zero=unknown; 1=male; 2=female)
labels = 'Unknown', 'Male', 'Female'
sizes = variable_size
colors = ['lightyellow','lightskyblue', 'lightcoral']
explode = (0, 0.1, 0.1) # "explode" the distribution of male and female
plt.pie(sizes, explode=explode, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
# Set aspect ratio to be equal so that pie is drawn as a circle.
plt.axis('equal')
plt.title('Gender Distribution in {}-{}'.format(self.year, self.month), fontsize = 12,y = 1,x=0.12,bbox={'facecolor':'0.8', 'pad':5})
plt.show()
elif variable == 'usertype':
# usertype (Zero=Customer, 1=Subscriber)
for i in range(2): # change to 0, 1
variable_size.append(round((sum(self.data[variable] == i) / self.data.shape[0] * 100), 2)) # calculate distribution
labels = 'Subscriber', 'Customer'
sizes = variable_size
colors = ['lightcoral','lightskyblue']
explode = (0, 0.1) # only "explode" the subscriber
plt.pie(sizes, explode=explode, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=90)
# Set aspect ratio to be equal so that pie is drawn as a circle.
plt.axis('equal')
plt.title('User Type Distribution in {}-{}'.format(self.year, self.month), fontsize = 12,y = 1,x=0.12,bbox={'facecolor':'0.8', 'pad':5})
plt.show()
def plotTime():
#Time levels
pp = PdfPages('time.pdf')
lev1 = 0
lev2 = 0
lev3 = 0
lev4 = 0
lev5 = 0
lev6 = 0
for time in userTime.keys():
if len(time) > 0:
intTime = int(time)
if intTime < 10:
lev1 += 1 * userTime[time]
elif intTime >=10 and intTime < 20:
lev2 += 1 * userTime[time]
elif intTime >= 20 and intTime < 30:
lev3 += 1 * userTime[time]
elif intTime >=30 and intTime < 40:
lev4 += 1 * userTime[time]
elif intTime >=40 and intTime < 50:
lev5 += 1 * userTime[time]
else:
lev6 += 1 * userTime[time]
labels = '10-', '10-20', '20-30', '30-40', '40-50', '50+'
sizes = [lev1, lev2, lev3, lev4, lev5, lev6]
colors = ['yellowgreen', 'gold', 'lightskyblue', 'blue', 'lightcoral', 'red']
plt.figure()
plt.clf()
plt.pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', shadow=True)
plt.axis('equal')
pp.savefig()
pp.close()
def main(with_plots):
# read data and skip spaces
data = pd.read_csv('data/weather_data.csv', skipinitialspace=True)
# transform our data to a dataframe
df = pd.DataFrame(data)
# Fill NaN with DEC in Month column
df['MONTH'].fillna('DEC', inplace=True)
# filled nans of HIGH and LOW columns
cubic_interpolate(df, 'HIGH')
cubic_interpolate(df, 'LOW')
print('> The median of average temperature is: ' +
str(df['TEMP'].median()))
print('> The std of average temperature is: ' + str(df['TEMP'].std()))
# Find the counts of each direction
df['DIR'].value_counts()
direction = df['DIR'].value_counts().index
counts = df['DIR'].value_counts().values
# make a pie with the counts percentages of all the days of the year
plt.title('Percentage of wind direction throughout the year')
plt.pie(counts, labels=direction, shadow=False, autopct='%1.0f%%')
plt.axis('equal')
if with_plots:
plt.savefig('plots/pie_wind_direction.png')
plt.show()
# Group by high Temp and max and get the time of the 4 highest temperatures
highest_temps = df.groupby('HIGH').max()['TIME'].tail(4)
print('> The 4 of the highest temperature are: ')
print(highest_temps)
print('> Most times the wind was: ' + str(df['DIR'].value_counts()[:1]))
print('> Max wind speed caused: ' +
str(df.groupby('WINDHIGH').max()['W_SPEED'].tail(1)))
# Create a plot with average rain per month
month_sum_df = df.groupby('MONTH').sum().reset_index()
month_sum_df.plot(kind='bar', x='MONTH', y='RAIN', legend=None)
plt.title('Average Rain per month')
plt.tight_layout()
if with_plots:
plt.savefig('plots/avg_rain_monthly.png')
plt.show()
# Predict the temperature for 25 December of the next year
# keep avg temperatures only from December
y = df['TEMP'][df['MONTH'] == 'DEC']
# december days from 1 to 31
x = np.arange(1, len(y) + 0.1, 1)
I = np.ones((len(x), ))
A = np.c_[x, I]
np.linalg.lstsq(A, y, rcond=-1)
# So for 25 december of the next year
xp = 25
yp = -0.18048387 * xp + 14.08129032
print('> The avg temperature predicted is: ' + str(yp) + ' celcius')
# Create plots for seasonal temperatures
# Return temperatures based on season
def season_temp(col, season):
return df[col][df['MONTH'].apply(lambda x: x in season)].values
fig, axs = plt.subplots(2, 2)
axs[0, 0].plot(season_temp('HIGH', winter_months), 'r-', label='High')
axs[0, 0].plot(season_temp('TEMP', winter_months), 'g-', label='Average')
axs[0, 0].plot(season_temp('LOW', winter_months), 'b-', label='Low')
axs[0, 0].set_title('Winter')
axs[0, 1].plot(season_temp('HIGH', spring_months), 'r-', label='High')
axs[0, 1].plot(season_temp('TEMP', spring_months), 'g-', label='Average')
axs[0, 1].plot(season_temp('LOW', spring_months), 'b-', label='Low')
axs[0, 1].legend(loc='upper left', bbox_to_anchor=(1, 0.5))
axs[0, 1].set_title('Spring')
axs[1, 0].plot(season_temp('HIGH', summer_months), 'r-',
season_temp('TEMP', summer_months), 'g-',
season_temp('LOW', summer_months), 'b-')
axs[1, 0].set_title('Summer')
axs[1, 1].plot(season_temp('HIGH', fall_months), 'r-',
season_temp('TEMP', fall_months), 'g-',
season_temp('LOW', fall_months), 'b-')
axs[1, 1].set_title('Fall')
for ax in axs.flat:
ax.set(xlabel='Days', ylabel='Temperatures')
# Hide x labels and tick labels for top plots and y ticks for right plots.
for ax in axs.flat:
ax.label_outer()
plt.suptitle('Seasonal Temperatures')
if with_plots:
fig.savefig('plots/temp_per_season.png', bbox_inches='tight')
plt.show()
# Get rain status
print('> Rain status: ')
rain_status(df['RAIN'].sum())
#给y轴添加标签
plt.ylabel('Amplitude')
#添加图形标题
plt.title('Sin and Cos Waves')
plt.show()
if __name__ == '__main__':
#饼图阴影、分裂等属性设置
# labels参数设置每一块的标签；
# labeldistance参数设置标签距离圆心的距离（比例值）
# autopct参数设置比例值小数保留位(%.3f%%)；
# pctdistance参数设置比例值文字距离圆心的距离
# explode参数设置每一块顶点距圆心的长度（比例值,列表）；
# colors参数设置每一块的颜色（列表）；
# shadow参数为布尔值，设置是否绘制阴影
# startangle参数设置饼图起始角度
x = [11, 22, 33, 44]
plt.pie(x, labels=['a', 'b', 'c', 'd'])
plt.show()
print(
f"The answer to the 1st question is {data.hospital.value_counts().idxmax()}"
)
data.groupby('hospital').agg({'hospital': 'count'}).plot(kind='bar')
plt.hist(data['hospital'], histtype='bar')
plt.show()
# What is the most common diagnosis among the sports patients?
print(
f"The answer to the 2nd question is {data[data.hospital=='sports'].diagnosis.value_counts().idxmax()}"
)
# print(f"The answer to the 2nd question is {data.diagnosis.value_counts().max()/1000}")
data.groupby('diagnosis').agg({
'diagnosis': 'count'
}).plot(kind='pie', y='diagnosis')
plt.pie(data.diagnosis.value_counts())
plt.show()
# print(f"The answer to the 2nd question is {round(data[(data.hospital == 'general') & (data.diagnosis == 'stomach')].shape[0]/data[(data.hospital == 'general')].shape[0], 3)}")
# print(f"The answer to the 3rd question is {round(data[(data.hospital == 'sports') & (data.diagnosis == 'dislocation')].shape[0]/data[(data.hospital == 'sports')].shape[0], 3)}")
# data[(data.hospital == 'general') | (data.hospital == 'sports')].groupby('hospital').agg({'age': 'median'}).diff
# print("The answer to the 4th question is 19.0")
# Build a violin plot of growth distribution by hospitals.
plt.violinplot([
data[data.hospital == 'general']['height'],
data[data.hospital == 'prenatal']['height'],
data[data.hospital == 'sports']['height']
])
plt.show()
# Save Figure and print
plt.savefig("C:/Users/May 2018/Pictures/Saved Pictures/Pyberscatterplot.png")
plt.show()
# ## Total Fares by City Type
# In[168]:
# Calculate Total Fares by Type
total_fare_type = merged_data2.groupby(['type']).sum()[["fare"]]
# Build Pie Chart
labels = ["Rural","Suburban","Urban"]
plt.title("% of Total Fares by City Type", fontweight='bold')
colors = ["gold","skyblue","lightcoral"]
explode = (0, 0, 0.1)
plt.pie(total_fare_type, labels=labels, colors=colors, autopct="%1.1f%%", explode=explode, shadow=True, startangle=140)
#Save Figure and display
plt.savefig("C:/Users/May 2018/Pictures/Saved Pictures/Pyberpie1.png")
plt.show()
# ## Total Rides by City Type
# In[170]:
# Calculate Ride Percents
total_ride_type = merged_data2.groupby(['type']).count()[["fare"]]
# Build Pie Chart
labels = ["Rural","Suburban","Urban"]
plt.title("% of Total Rides by City Type", fontweight='bold')
colors = ["gold","skyblue","lightcoral"]
import pandas as pd
from matplotlib import pyplot as plt
fruit = ['Apple', 'Mango', 'Guava', 'Orange', 'PineApple']
quantity = [10, 5, 15, 20, 8]
plt.pie(quantity,
labels=fruit,
autopct='%0.1f',
colors=['yellow', 'blue', 'green', 'red', 'orange'])
plt.show()
plt.pie(quantity,
labels=fruit,
radius=2,
autopct='%0.1f%%',
colors=['yellow', 'blue', 'green', 'red', 'orange'])
plt.pie([50], radius=1, colors=['w'])
plt.show()
plt.ylabel("Sales")
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5b.pdf')
plt.show()
plt.boxplot(df['Age'])
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5c.pdf')
plt.show()
plt.boxplot(df['Sales'])
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5d.pdf')
plt.show()
plt.boxplot(df['Income'])
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5e.pdf')
plt.show()
plt.pie(df['Age'], labels = {"A", "B", "C","D", "E", "F","G", "H", "I", "J"},
autopct ='% 1.1f %%', shadow = True)
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5f.pdf')
plt.show()
plt.pie(df['Income'], labels = {"A", "B", "C","D", "E", "F","G", "H", "I", "J"},
autopct ='% 1.1f %%', shadow = True)
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5g.pdf')
plt.show()
plt.pie(df['Sales'], labels = {"A", "B", "C","D", "E", "F","G", "H", "I", "J"},
autopct ='% 1.1f %%', shadow = True)
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5h.pdf')
plt.show()
plt.scatter(df['Income'], df['Age'])
plt.savefig('/home/cloudera/Desktop/diwakar/figures/asgn1_5i.pdf')
plt.show()
import matplotlib.pyplot as plt
# Data to plot
labels = 'sweet', ' candy ', ' silk ', 'strawberries ', 'marshmallows', 'cheese', 'vanilla', 'tart'
sizes = [13, 12, 5, 3, 3, 3, 2, 1]
colors = [
'gold', 'yellowgreen', 'lightcoral', 'lightskyblue', 'red', 'purple',
'magenta', 'blue'
]
explode = (0.1, 0, 0, 0, 0, 0, 0, 0) # explode 1st slice
# Plot
plt.pie(sizes,
explode=explode,
labels=labels,
colors=colors,
autopct='%1.1f%%',
shadow=False,
startangle=140)
plt.axis('equal')
plt.show()
props.append(100 - sum(props))
print "-EVENTS FOUNDS-------------------------------------------------"
print "Number of events found: ", len(eventsindexes)
print "Number of events still to classify: ", totalmovements - len(
eventsindexes)
print "Total number of movements: ", totalmovements
print "-EVENTS TO GROUP-------------------------------------------------"
for i in (bm.index - eventsindexes)[:10]:
print bm['Label'][i]
plt.figure()
plt.plot(bm['Amount'][:])
plt.savefig('myAccounting.png')
plt.figure()
#labels = 'Frogs', 'Hogs', 'Dogs', 'Logs'
#sizes = [15, 30, 45, 10]
#colors = ['yellowgreen', 'gold', 'lightskyblue', 'lightcoral']
#explode = (0, 0.1, 0, 0) # only "explode" the 2nd slice (i.e. 'Hogs')
groups.append('Misc')
labels = groups
sizes = props
print labels
print sizes
plt.pie(sizes, labels=labels, autopct='%1.1f%%', shadow=True)
# Set aspect ratio to be equal so that pie is drawn as a circle.
plt.axis('equal')
plt.savefig('myAccountingByGroups.png')
import matplotlib
matplotlib.use("TkAgg")
from matplotlib import pyplot
# 1. Prepare database
labels = ["Web", "iOS", "Android", "React Native"]
values = [40, 20, 35, 15]
colors = ["red", "orange", "yellow", "beige"]
explode = [0, 0.2, 0, 0]
# 2. Plot
pyplot.pie(values, labels=labels, colors=colors, explode=explode, shadow=True)
pyplot.axis("equal")
# 3. Show
pyplot.show()
customers = db['customers']
# 4. Create document
# quote = {
# "title": "Quote",
# "author": "Đ.T.H.Nhung",
# "content": """Only I can change my life.
# No one can do it for me
# -Carol Burnett-"""
# }
# 5. Insert document into collection
# posts.insert_one(quote)
count_ads = customers.count({"ref": "ads"})
count_wom = customers.count({"ref": "wom"})
count_events = customers.count({"ref": "events"})
print(count_ads, count_wom, count_events)
# use matplotlib to draw a pie chart
# 1. Prepare data
labels = ["Advertisements", "Events", "World of mouth"]
values = [count_ads, count_events, count_wom]
colors = ["green", "red", "yellow"]
# 2. plot
pyplot.pie(values, labels=labels, colors=colors)
pyplot.axis("equal")
# 3. Show
pyplot.show()
positive = format(positive, '.2f')
#print(positive)
negative = format(negative, '.2f')
neutral = format(neutral, '.2f')
#print(neutral)
print("How people are reacting on " + searchTerm + " by analyzing " +
str(noOfSearchTerms) + " Tweets.")
if polarity == 0:
print("Neutral")
elif polarity > 0.00:
print("Positive")
elif polarity < 0.00:
print("Negative")
labels = [
'Positive [' + str(positive) + '%]', 'Neutral [' + str(neutral) + '%]',
'Negative [' + str(negative) + '%]'
]
sizes = [positive, neutral, negative]
colors = ['yellowgreen', 'gold', 'red']
patches, text = plt.pie(sizes, colors=colors, startangle=90)
plt.legend(patches, labels, loc="best")
plt.title("How people are reacting on " + searchTerm + " by analyzing " +
str(noOfSearchTerms) + " Tweets.")
plt.axis('equal')
plt.tight_layout()
plt.show()
def home():
form = SearchForm()
if form.validate_on_submit():
flash('Query {}'.format(form.query.data))
runtime = boto3.client('sagemaker-runtime',
aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key,
region_name='us-east-1')
# get tweets
if (form.submitUsername.data):
search_type = 'user'
search_t = '@'
tweets = get_users_tweets(form.query.data)
else:
search_type = 'hashtag'
search_t = '#'
tweets = get_hashtag_tweets(form.query.data)
#if rate limit was exceeded print message
if tweets == RATE_ERROR:
return render_template(
'index.html',
form=form,
error='Rate limit reached. Please wait before trying again')
#if search error occured print message
elif tweets == SEARCH_ERROR:
return render_template(
'index.html',
form=form,
error=
'An error occured while searching. Please check that your syntax is correct or that the username searched exists and is not private.'
)
#if no tweets exist
elif not tweets:
return render_template(
'index.html',
form=form,
error='There are no avalible tweets for that user or hashtag')
else:
processedTweets = []
#send each tweet to preprocess function
for x in tweets['tweet']:
processedTweets.append(preprocess(x))
processedTweet = {"tweet": processedTweets}
#call sentiment alg with processedTweet
response = runtime.invoke_endpoint(
EndpointName='twitter-svc-tuner-200324-1449-015-0d842270',
Body=json.dumps(processedTweet),
ContentType='application/json')
results = json.loads(response['Body'].read())
#aggregates the results into a result object with score, posIndex, and negIndex
result = aggregateData(results)
#creates database entry
now = datetime.now()
post = {
"query": form.query.data,
"type": search_type,
"score": result['score'],
"mostPositive": tweets['tweet'][result['posIndex']],
"mostNegative": tweets['tweet'][result['negIndex']],
"timeLog": now
}
#comment this line out if you dont want to log the results in the database
collection.insert_one(post)
#donut chart creation
# create data
names = 'Positive', 'Negative',
size = [result['positive'], result['negative']]
# Create a circle for the center of the plot
# change color to = color of background to give illusion of transparency
my_circle = plt.Circle((0, 0),
0.7,
color='white',
linewidth=1,
ls='-',
ec='white')
# Give color names and set wedge properites
plt.pie(size,
labels=names,
labeldistance=1.1,
colors=['skyblue', '#0084b4'],
wedgeprops={
'linewidth': 4,
'edgecolor': 'white'
})
p = plt.gcf()
p.gca().add_artist(my_circle)
# needed to send chart as png to html page
img = BytesIO()
plt.savefig(img, format='png', transparent=True)
plt.close()
img.seek(0)
donut_url = base64.b64encode(img.getvalue()).decode('utf8')
new_score = (result['score'] + 1) * 100 / 2
new_score = round(new_score, 1)
# Use flash messages to display validation errors and stuff
return render_template(
'index.html',
form=form,
data=form.query.data,
search_type=search_t,
score=new_score,
posTweet=tweets['tweet'][result['posIndex']],
negTweet=tweets['tweet'][result['negIndex']],
donut_url='data:image/png;base64,' + donut_url)
return render_template('index.html', form=form)
def plot_pruning_pie_chart(self, threshold, to_file="MicroResNet_pie.png"):
"""
Plots the # of kernels pruned by each kernel pruning criterion
Pie chart areas:
- "a": min_eig
- "b": weight
- "c": det
- "d": spectral_radius
- "e": spectral_norm
- "f": det_corr
"""
pie_chart_vals = {}
for layer in self.values:
for neuron in self.values[layer]:
for kernel in self.values[layer][neuron]:
val_dict = self.values[layer][neuron][kernel]
n = val_dict["kernel_dim"]
# Check decisions of the different criterias
min_eig_flag = self.is_pruned(val_dict, threshold,
"min_eig")
weight_flag = self.is_pruned(val_dict, threshold, "weight")
det_flag = self.is_pruned(val_dict, pow(threshold, n),
"det")
spectral_radius_flag = self.is_pruned(
val_dict, threshold, "spectral_radius")
spectral_norm_flag = self.is_pruned(
val_dict, threshold, "spectral_norm")
det_corr_flag = self.is_pruned(val_dict,
pow(threshold, 2 * n),
"det_corr")
# Process Venn diagram data
key = ""
if min_eig_flag:
key += "a"
if weight_flag:
key += "b"
if det_flag:
key += "c"
if spectral_radius_flag:
key += "d"
if spectral_norm_flag:
key += "e"
if det_corr_flag:
key += "f"
pie_chart_vals[key] = pie_chart_vals[
key] + 1 if key in pie_chart_vals else 1
# Prepare the chart data
groups = sorted(list(pie_chart_vals.keys()))
sizes = [pie_chart_vals[g] for g in groups]
total = sum(sizes)
sizes = [(x / float(total)) * 100 for x in sizes]
groups = ["{%s}" % (",".join(list(g))) for g in groups]
fig = plt.figure(figsize=(11, 11))
# Plot the pie chart
patches, texts, _ = plt.pie(sizes, labels=groups, autopct="%1.1f%%")
plt.legend(patches, groups, loc="best")
plt.axis('equal')
plt.tight_layout()
# Save the diagram
plt.savefig(to_file, bbox_inches="tight")
plt.close(fig)
plt.rcParams["font.size"] = 12
plt.rcParams["figure.figsize"] = (12, 8)
# 데이터 계산
value1 = np.array(car_vs_people)
value2 = np.array(car_vs_car)
value3 = np.array(car_only)
# 데이터 범위
ratio = [value1.sum(), value2.sum(), value3.sum()]
# 라벨
labels = ['차 대 사람', '차 대 차', '차량단독']
# 색상
colors = ['#ff6600', '#ff00ff', '#00ffff']
# 확대 비율
explode = [0.0, 0.0, 0.0]
# 파이그래프 표현
plt.pie(ratio, labels=labels, colors=colors, explode=explode,
autopct='%0.2f%%', shadow=False, startangle=90)
# 그래프 제목
plt.title('2005년 ~ 2017년 유형별 교통 사고 현황')
# 범주 표시
plt.legend()
# 그래프 보이기
plt.show()
# 그래프 종료
plt.close()
def main():
if request.method == 'GET':
return render_template('index.html')
query = request.form['query']
number = request.form['num']
results = api.search(lang="en",
q=query + " -rt",
count=number,
result_type="recent")
print("--- Gathered Tweets \n")
## open a csv file to store the Tweets and their sentiment
file_name = 'Sentiment_Analysis_of_{}_Tweets_About_{}.csv'.format(
number, query)
with open(file_name, 'w', newline='') as csvfile:
csv_writer = csv.DictWriter(f=csvfile,
fieldnames=["Tweet", "Sentiment"])
csv_writer.writeheader()
print(
"--- Opened a CSV file to store the results of your sentiment analysis... \n"
)
## tidy up the Tweets and send each to the AYLIEN Text API
for c, result in enumerate(results, start=1):
tweet = result.text
tidy_tweet = tweet.strip().encode('ascii', 'ignore')
if len(tweet) == 0:
print('Empty Tweet')
continue
response = client.Sentiment({'text': tidy_tweet})
csv_writer.writerow({
'Tweet': response['text'],
'Sentiment': response['polarity']
})
print("Analyzed Tweet {}".format(c))
## count the data in the Sentiment column of the CSV file
with open(file_name, 'r') as data:
counter = Counter()
for row in csv.DictReader(data):
counter[row['Sentiment']] += 1
positive = counter['positive']
negative = counter['negative']
neutral = counter['neutral']
## declare the variables for the pie chart, using the Counter variables for "sizes"
colors = ['green', 'red', 'grey']
sizes = [positive, negative, neutral]
labels = 'Positive', 'Negative', 'Neutral'
## use matplotlib to plot the chart
plt.pie(x=sizes, shadow=True, colors=colors, labels=labels, startangle=90)
return render_template('pie_chart.html',
title=query,
num=number,
max=17000,
set=zip(sizes, labels, colors))
"""
from poster.encode import multipart_encode, MultipartParam
from poster.streaminghttp import register_openers
import urllib2
url="https://api.webempath.net/v2/analyzeWav"
register_openers()
items = []
items.append(MultipartParam('apikey', "o2lvbxnxWBVkLBFrpfb6Tzwp2RRUxsy_bIMzFbsybVo"))
items.append(MultipartParam.from_file('wav', "./sample.wav"))
datagen, headers = multipart_encode(items)
request = urllib2.Request(url, datagen, headers)
response = urllib2.urlopen(request)
if response.getcode() == 200:
print(response.read())
else:
print("HTTP status %d" % (response.getcode()))
"""
import numpy as np
import matplotlib.pyplot as plt
x = np.array([100, 200, 300, 400, 500])
plt.pie(x)
plt.show()
#Generating the Barchart
objects = ('positive', 'negative', 'neutral')
y_pos = np.arange(len(objects))
performance = [posper, negper, neuper]
plt.bar(y_pos, performance, align='center', alpha=0.5)
plt.xticks(y_pos, objects)
plt.ylabel('percentage of tweets %')
plt.title('sentiment polarities')
plt.show()
#Generating the Pichart
positive = [0]
negative = [0]
neutral = [0]
slices = [posper, negper, neuper]
activities = ['positive', 'negative', 'neutral']
cols = ['c', 'm', 'r', 'k']
plt.pie(slices, labels=activities, colors=cols)
plt.xlabel('x')
plt.ylabel('y')
plt.title('sentiment polarities')
plt.legend()
plt.show()
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv("Setor CSV 01.csv") #Pega o dataset
obj = ("A", "B", "C", "D", "F") #Rótulos
valores = [
len(df.loc[df["Grade"] == "A"]), #Localiza as notas A
len(df.loc[df["Grade"] == "B"]), #Localiza as notas B
len(df.loc[df["Grade"] == "C"]), #Localiza as notas C
len(df.loc[df["Grade"] == "D"]), #Localiza as notas D
len(df.loc[df["Grade"] == "F"])
] #Localiza as notas F
colors = ["blue", "red", "grey", "yellow", "orange"] #Cores
explode = (0.2, 0, 0, 0, 0) #Valor de afastamento de cada segmento
plt.pie(valores,
labels=obj,
explode=explode,
colors=colors,
autopct="%1.1f%%",
shadow=True,
startangle=12)
#explode é para separar um segmento da tabela
#autopct é para mostrar a porcentagem que o segmento vale na tabela
#shadow define a sombra
#startangle define o angulo inicial
plt.legend(obj) #Insere as legendas
plt.axis("equal") #Deixa a tabela redonda
import matplotlib.pyplot as plt
import pandas as pd
raw_data = {
'names': ['Nick', 'Panda', 'S', 'Ari', 'Valos'],
'jan_ir': [143, 122, 101, 106, 365],
'feb_ir': [122, 132, 144, 98, 62],
'march_ir': [65, 88, 12, 32, 65]
}
df = pd.DataFrame(raw_data, columns=['names', 'jan_ir', 'feb_ir', 'march_ir'])
df['total_ir'] = df['jan_ir'] + df['feb_ir'] + df['march_ir']
print(df)
color = [(1, .4, .4), (1, .6, 1), (.5, .3, 1), (.3, 1, .5), (.7, .7, .2)]
plt.pie(df['total_ir'], labels=df['names'], colors=color, autopct='%1.1f%%')
plt.axis('equal')
plt.show()
print('数据分析师工资描述：\n{}'.format(df['月工资'].describe()))
# 绘制频率直方图并保存
plt.hist(df['月工资'], bins=12)
plt.xlabel('工资 (千元)')
plt.ylabel('频数')
plt.title("工资直方图")
plt.savefig('histogram.jpg')
plt.show()
# 绘制饼图并保存
count = df['区域'].value_counts()
# 将龙华区和龙华新区的数据汇总
count['龙华新区'] += count['龙华区']
del count['龙华区']
plt.pie(count, labels=count.keys(), labeldistance=1.4, autopct='%2.1f%%')
plt.axis('equal') # 使饼图为正圆形
plt.legend(loc='upper left', bbox_to_anchor=(-0.1, 1))
plt.savefig('pie_chart.jpg')
plt.show()
# 绘制词云,将职位福利中的字符串汇总
text = ''
for line in df['职位福利']:
text += line
# 使用jieba模块将字符串分割为单词列表
cut_text = ' '.join(jieba.cut(text))
#color_mask = imread('cloud.jpg') #设置背景图
wc = WordCloud(background_color="white",
activities = ["sleep", "eat", "play", "sport", "work"]
hours = [7, 2, 5, 3, 8]
#define color in pie chart
'''
Colors can be added to graph by one of the following ways:
Hex value (#_ _ _ _ _ _)
rgb value ( r , g , b ) or ( r , g , b , a ) where r, g, b, a are in range 0–1
grey shades (0–1 range)
as in active color cycle ( “c0”, “c1”)[capital C followed by digit]
'''
#colors = ['b','r']
colors = ['#ff9999', '#66b3ff', '#99ff99', '#ffcc99', '#00cc99']
#only explode the "work" portion
explode = (0, 0, 0, 0, 0.1)
#autopct = percentage 1 decimal only
plt.pie(hours,
labels=activities,
explode=explode,
shadow=True,
startangle=90,
colors=colors,
autopct='%.1f%%')
plt.title('My Activities')
#draw center circle
centre_circle = plt.Circle((0, 0), 0.70, fc='white')
fig = plt.gcf()
fig.gca().add_artist(centre_circle)
#show plot
plt.show()
import matplotlib.pyplot as plt
labels = "name1", "name2", "name3", "name4"
#各部分占比
sizes = [20, 30, 40, 10]
#name2突出
explode = (0, 0.1, 0, 0)
plt.pie(sizes,
explode=explode,
labels=labels,
autopct="%1.1f%%",
shadow=False,
startangle=90)
#正圆
plt.axis("equal")
plt.show()
#Plotting bar graph of 'gender_count'
plt.bar(gender_count.index, gender_count)
plt.show()
#Code starts here
# --------------
#Code starts here
#Storing the value count of 'Alignment'
alignment = data['Alignment'].value_counts()
#Setting the figure size
plt.figure(figsize=(6, 6))
#Plotting pie chart for 'alignment'
plt.pie(alignment,
labels=alignment.index,
explode=(0.05, 0.05, 0.05),
autopct='%1.1f %%')
#Setting the pie chart title
plt.title('Character alignment')
#Code ends here
# --------------
#Code starts here
#Subsetting the data with columns ['Strength', 'Combat']
sc_df = data[['Strength', 'Combat']].copy()
#Finding covariance between 'Strength' and 'Combat'
sc_covariance = sc_df.cov().iloc[0, 1]
#%%
#饼图
#sns.set(style='whitegrid')
# data['volume_CATE2'] = data['volume_CATE'].apply(lambda x: x if x<10 else -1)
count = data.groupby(by='volume_CATE').size()
fig = plt.figure(figsize=(6, 6))
plt.pie(x=list(count),
labels=[
'0~5', '5~10', '10~15', '15~20', '20~25', '25~30', '30~35',
'35~40', '40~45', '45~50'
],
explode=[0, 0, 0, 0, 0, 0, 0, 0, 0, 0.2],
colors=sns.color_palette('Blues', n_colors=11),
labeldistance=1.2,
autopct='%.2f%%',
pctdistance=0.8,
radius=2,
textprops={
'fontsize': 20,
'weight': 'bold'
},
shadow=True)
plt.savefig('饼图.png', dpi=200, bbox_inches='tight')
#%%
#直方图1
fig = plt.figure(figsize=(10, 6))
sns.distplot(data['aveSpeed'])
plt.tick_params(labelsize=18)
plt.xlabel('平均速度', fontsize=20)
import pandas as pd
from apyori import apriori
import matplotlib.pyplot as plt
from apyori import apriori
dataset = pd.read_csv('BreadBasket_DMS.csv')
list1 = dataset.index[dataset['Item'] == 'NONE'].tolist()
dataset.drop(list1, axis=0, inplace=True)
x = dataset['Item'].value_counts()
print("Top 15 selling items are : ")
counts = x[:15].values.tolist()
names = x[:15].index.tolist()
plt.pie(counts, labels=names, autopct="%2.2f%%", radius=3)
item = dataset.groupby('Transaction')['Item'].unique()
item_list = [x.tolist() for x in item]
rules = apriori(item_list, min_support=0.0025, min_confidence=0.2, min_lift=3)
results = list(rules)
for item in results:
# first index of the inner list
# Contains base item and add item
pair = item[0]
items = [x for x in pair]
print("Rule: " + items[0] + " -> " + items[1])
Pie chart, where the slices will be ordered and plotted counter-clockwise:
"""
labels = 'CSE', 'ECE', 'IT', 'EE'
sizes = [15, 30, 25, 10]
colors = ['gold', 'yellowgreen', 'lightcoral', 'lightskyblue']
explode = (0.5, 0, 0, 0) # explode 1st slice
#plt.pie(sizes, labels=labels, autopct='%.0f%%')
# or
plt.pie(sizes,
explode=explode,
labels=labels,
colors=colors,
autopct='%1.2f%%',
shadow=True,
startangle=180)
plt.axis('equal') # Equal aspect ratio ensures that pie is drawn as a circle.
plt.show()
"""
Plotting a bar chart
"""
import matplotlib.pyplot as plt
objects = ('Python', 'C++', 'Java', 'Perl', 'Scala', 'Lisp')
performance = [10, 8, 6, 4, 2, 1]
mouse_sex = combined_df.groupby(['Sex']).count()
plot = mouse_sex.plot.pie(y='Mouse ID', figsize=(5, 5))
# In[8]:
# Generate a pie plot showing the distribution of female versus male mice using pyplot
mouse_sex = combined_df.groupby(['Sex']).count()
sizes = mouse_sex['Mouse ID']
labels = ['Male', 'Female']
colors = ["red", "blue"]
explode = (0, 0)
plt.pie(sizes,
explode=explode,
labels=labels,
colors=colors,
autopct="%1.1f%%",
shadow=True,
startangle=140)
# ## Quartiles, outliers and boxplots
# In[45]:
# Calculate the final tumor volume of each mouse across four of the most promising treatment regimens. Calculate the IQR and quantitatively determine if there are any potential outliers.
#find top treatments regimens
top_check = combined_df.groupby(['Drug Regimen']).mean()
top_four = top_check.nsmallest(4, ['Tumor Volume (mm3)'])
top_four
score_not_exit = []
for score in range(11):
if score not in list(table[satisfaction_var]):
score_not_exit.append(score)
for score in range(11):
if score in score_not_exit:
percentage_list.append("%.2f" % round(0, 2))
else:
percentage_list.append(
"%.2f" % round(count_list[score] / total_respond * 100, 2))
labels = '0~4', '5~7', '8~10'
sizes = [
sum(list(map(float, percentage_list[0:4]))),
sum(list(map(float, percentage_list[5:7]))),
sum(list(map(float, percentage_list[8:10])))
]
colors = ['yellowgreen', 'lightskyblue', 'lightcoral']
explode_list = [0, 0, 0.1]
# explode_list[sizes.index(max(sizes))] = 0.1
explode = tuple(explode_list)
'''Plot'''
plt.pie(sizes,
labels=labels,
colors=colors,
autopct='%1.1f%%',
shadow=True,
startangle=140)
plt.title('Score Distribution of %s' % app.upper())
data['text'].value_counts()
data.columns
total_sentiment_counts=data['airline_sentiment'].value_counts()
total_sentiment_counts
data.shape
labels = 'negative', 'neutral', 'positive'
colors = ['gold', 'yellowgreen', 'lightcoral']
explode = (0, 0, 0) # explode 1st slice
# Plot
plt.pie(total_sentiment_counts, explode=explode, labels=labels, colors=colors,
autopct='%1.1f%%', shadow=True, startangle=140)
plt.axis('equal')
plt.tight_layout()
plt.show()
#https://www.kaggle.com/rashmitarouy01/us-airlines-twitter-sentiment-analysis
air_senti=pd.crosstab(data.airline, data.airline_sentiment)
air_senti
total_negativereasons_counts=data['negativereason'].value_counts()
data.negativereason.value_counts().plot(kind='pie', autopct='%1.0f%%')
air_nega=pd.crosstab(data.negativereason, data.airline_sentiment)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Oct 11 16:30:39 2018
@author: taylormade
"""
import matplotlib.pyplot as plt
labels = 'basketball', 'soccer', 'golf', 'baseball'
sizes = [15, 30, 45, 10]
colors = ['yellowgreen', 'gold', 'lightskyblue', 'lightcoral']
explode = (0.1, 0, 0, 0)
plt.pie(sizes,
explode=explode,
labels=labels,
colors=colors,
shadow=False,
startangle=90)
plt.axis('equal')
plt.show()