def plot_data(self, pdf_file, image_filename):
place_types = []
reference_counts = []
for data_row in Utils.get_data_vectors(self._datafile, ' '):
place_types.append(data_row[0])
reference_counts.append(int(data_row[1]))
figure(1, figsize = (6, 6))
ax = axes([0.1, 0.1, 0.8, 0.8])
# The slices will be ordered and plotted counter-clockwise.
labels = place_types
total_references = sum(reference_counts)
# Eliminate the NA data
index = place_types.index('NotAvailable')
place_types.pop(index)
NA_count = reference_counts.pop(index)
NA_percentage = 100 * NA_count / float(total_references)
total_references -= NA_count
fracs = [count / float(total_references) for count in reference_counts]
explode = (0, 0, 0, 0, 0)
mpl.rcParams['font.size'] = 9.0
pie(fracs, explode = explode, labels = labels, autopct = '%1.1f%%', shadow = False, startangle = 0)
# The default startangle is 0, which would start
# the Frogs slice on the x-axis. With startangle=90,
# everything is rotated counter-clockwise by 90 degrees,
# so the plotting starts on the positive y-axis.
title('Place Type Distribution: ' + str(NA_percentage) +
'% tweets dont have a place type, showing the remaining tweets',
bbox = {'facecolor':'0.8', 'pad':5})
savefig(pdf_file, format = 'pdf')
savefig(image_filename)
clf()
def plot_data(self, pdf_file, image_filename):
categories = []
tweet_count = []
for data_row in Utils.get_data_vectors(self._datafile, ' '):
categories.append(data_row[0])
tweet_count.append(int(data_row[1]))
figure(1, figsize = (6, 6))
ax = axes([0.1, 0.1, 0.8, 0.8])
# The slices will be ordered and plotted counter-clockwise.
labels = categories
total_references = sum(tweet_count)
fracs = [count / float(total_references) for count in tweet_count]
explode = (0, 0)
mpl.rcParams['font.size'] = 12.0
pie(fracs, explode = explode, labels = labels, autopct = '%1.1f%%', shadow = False, startangle = 0)
# The default startangle is 0, which would start
# the Frogs slice on the x-axis. With startangle=90,
# everything is rotated counter-clockwise by 90 degrees,
# so the plotting starts on the positive y-axis.
title('Tweet Distribution for ' + str(total_references) + ' tweets.', bbox = {'facecolor':'0.8', 'pad':5})
savefig(pdf_file, format = 'pdf')
savefig(image_filename)
clf()
def plot_data(self, pdf_file, image_filename):
data_points = []
total = 0
for data_row in Utils.get_data_vectors(self._datafile, ' '):
bin = int(float(data_row[0]))
data = int(float(data_row[1]))
total += data
data_points.append((bin, data))
bins = []
data = []
for data_point in sorted(data_points, key = itemgetter(0)):
bins.append(data_point[0])
percentage = 100 * data_point[1] / float(total)
data.append(percentage)
P.bar(bins, data, width = 1, color = 'r')
mpl.rcParams['font.size'] = 10.0
P.xlabel('Geotagged tweet percentage')
P.ylabel('Users percentage')
P.savefig(pdf_file, format = 'pdf')
P.savefig(image_filename)
P.clf()
def plot_data(self, pdf_file, image_filename):
data_points = []
total_user_count = 0
total_tweet_count = 0
for data_row in Utils.get_data_vectors(self._datafile, ' '):
num_tweets = int(data_row[0])
user_count = int(data_row[1])
total_user_count += user_count
total_tweet_count += num_tweets
data_points.append((num_tweets, user_count))
bins = []
user_count = []
for data_point in sorted(data_points, key = itemgetter(0)):
bins.append(log(data_point[0])) # / float(total_tweet_count))
user_count.append(log(data_point[1])) # / float(total_user_count))
_, axes = P.subplots()
axes.plot(user_count, bins, 'ro')
axes.set_ylabel('log(GeoTweet Count)')
axes.set_xlabel('log(User Count)')
P.savefig(pdf_file, format = 'pdf')
P.savefig(image_filename)
P.clf()
def plot_data(self, pdf_file, image_filename):
data_dict = {}
for data_row in Utils.get_data_vectors(self._datafile, '|'):
data_dict[data_row[0]] = int(data_row[1])
fig = figure(1, figsize = (6, 6))
ax = axes([0.2, 0.2, 0.6, 0.6])
# The slices will be ordered and plotted counter-clockwise.
data_dict = sorted(data_dict.iteritems(), key = itemgetter(1), reverse = True)
total_tweet_count_original = sum(float(data[1]) for data in data_dict)
data_dict = data_dict[0:5] + data_dict[10:12] + data_dict[6:9] + data_dict[13:15]
total_tweet_count = sum(float(data[1]) for data in data_dict)
application_names = list(data[0] for data in data_dict)
tweet_percentage = 100 * (total_tweet_count / float(total_tweet_count_original))
fracs = [float(data[1]) / total_tweet_count for data in data_dict]
mpl.rcParams['font.size'] = 6.0
pie(fracs, labels = application_names, autopct = '%1.1f%%', shadow = False, startangle = 0)
title('Tweet sources Distribution: Showing top 15 tweet sources which generate ' +
str(tweet_percentage) +
'% of the total tweets', bbox = {'facecolor':'0.8', 'pad':5})
savefig(pdf_file, format = 'pdf')
savefig(image_filename)
clf()
