def plot_Gmeta(array1, array2, array3, title, ylabel, density):
barWidth = .3
colors = ['tan', 'yellowgreen', 'midnightblue']
labels = ['Corpus', 'k-core', 'k-truss']
names = get_names()
bars = [array1, array2, array3]
fig, ax = plt.subplots()
# Set position of bar on X axis
r = list()
r.append(np.arange(len(bars[0])) + barWidth / 2)
r.append([x + barWidth for x in r[0]])
r.append([x + barWidth for x in r[1]])
# Make the plot
for i in range(3):
plt.bar(r[i],
bars[i],
color=colors[i],
width=barWidth,
edgecolor='white',
label=labels[i])
text_x_offset = .1
text_y_offset = 1.5
for i in range(3):
for j in range(3):
x_pos = r[i][j] - barWidth / 3 + text_x_offset
if density == False:
y_pos = bars[i][j] + np.exp(text_y_offset)
label = f'{bars[i][j]:.0f}'
else:
y_pos = bars[i][j] + np.log(1.0001)
label = f'{bars[i][j]:.3f}'
plt.text(x_pos,
y_pos,
label,
horizontalalignment='center',
rotation=0,
color='black',
fontsize=10)
# Add ticks on the middle of the group bars
plt.ylabel(ylabel, fontweight='normal')
plt.xticks([r + barWidth for r in range(len(array1))], names)
ax.set_yscale('log')
plt.title(title)
# Create legend show graphic & save to file
plt.legend(loc='best', fontsize='small')
plt.savefig(clean_filename(title, 'png', plot_directory))
plt.show()
def ROC_plot(fpr, tpr, roc_auc, n_classes, ix, gmean, algo, method, save=True):
'''Plots ROC curves
gmean = average
'''
color_dict = get_color_dict()
names = get_names()
handles = get_handles()
lw = 1
figsize = 6
title = f'ROC {method}+{algo}'
# Make plot
plt.figure(figsize=(figsize, figsize))
colors = cycle([
color_dict[handles[0]], color_dict[handles[1]], color_dict[handles[2]]
])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i],
tpr[i],
color=color,
linewidth=lw,
label=f'ROC {names[i]} (auc = {roc_auc[i]:0.2f})')
if i == 0:
plt.scatter(fpr[i][ix[i]],
tpr[i][ix[i]],
marker='o',
color='black',
label=f'Best (gmeans={gmean:.3f})')
else:
plt.scatter(fpr[i][ix[i]],
tpr[i][ix[i]],
marker='o',
color='black')
plt.plot([0, 1], [0, 1], 'k--', linewidth=lw, label='No Skill') # diagonal
plt.xlim([0, 1])
plt.ylim([0, 1])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title(title)
plt.legend(loc="lower right")
if save:
plt.savefig(clean_filename(title, 'png', plot_directory))
plt.show()
def plot_confusion_matrix(y_pred,
y_test,
score,
handles,
algo,
method,
normalize,
save=True):
"""
Plot a confusion matrix
Expected True values x-axis & predicted y-axis
obtained from : confusion_matrix(y_pred, y_test, labels = labels)
note: this order is the opposite of that suggested in scikit-learn
"""
figsize_x = 6.5
figsize_y = 6
cm = confusion_matrix(y_pred, y_test, labels=handles)
print(cm)
print(f'[confusion_matrix_wrapper] {algo} score = {score}\n')
labels = get_names()
#print(f'[plot_confusion_matrix] labels = {labels}')
accuracy = np.trace(cm) / float(np.sum(cm))
print(f'[plot_confusion_matrix] Accuracy={accuracy}')
print(f'[plot_confusion_matrix] confusion matrix:\n{cm}')
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
cm = np.round(cm, 2)
fig = plt.figure(figsize=(figsize_x, figsize_y))
ax = fig.add_subplot(111)
ax.matshow(cm)
#if method == 'GOW': method = 'Graph of Words'
title = f'{method}+{algo}'
plt.title(title, y=1.1)
plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Wistia)
ax.set_xticklabels([''] + labels)
ax.set_yticklabels([''] + labels)
plt.ylabel('Predicted')
plt.xlabel(f'True\naccuracy={accuracy:0.3f}')
for i in range(3):
for j in range(3):
plt.text(j, i, str(cm[i][j]))
if save:
plt.savefig(clean_filename(title, 'png', plot_directory))
plt.show()
def build_base_barplot(handles, array, x_pos, title, xlabel, ylabel, color_dict):
'''Builds base plots for 3 handles'''
width = .75
names = get_names()
fig, ax = plt.subplots()
barlist=ax.bar(x_pos, array, width)
for i, handle in enumerate(handles):
barlist[i].set_color(color_dict[handle])
ax.set_xticks(x_pos)
ax.set_xticklabels(names)
ax.set_xlabel(xlabel)
ax.set_ylabel(ylabel)
title = title
ax.set_title(title)
return fig, ax
def tweeting_period_plot(handles, start, end, color_dict):
'''Plot tweeting period from start and end dates'''
fontsize = 14
names = get_names()
ndays = get_ndays(start, end)
fig, ax = plt.subplots(figsize=(18,4.875))
y_pos = np.arange(len(handles))
barlist=ax.barh(y_pos, ndays, .75)
for i, handle in enumerate(handles):
barlist[i].set_color(color_dict[handle])
# Annotate bars
end_x = .89
start_x = [.05, .275, .55]
y_val = [.815, .485, .15]
for i, handle in enumerate(handles):
ax.annotate('<-- ' + start[i],
xy=(start_x[i], y_val[i]),
xycoords = 'axes fraction',
fontsize = fontsize)
ax.annotate(end[i] + ' -->',
xy=(end_x, y_val[i]),
xycoords = 'axes fraction',
fontsize = fontsize)
plt.gca().invert_xaxis() # right to left
ax.set_yticks(y_pos)
ax.set_yticklabels(names)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('# of days')
title = 'Tweeting time period'
ax.set_title(title, fontsize = 18)
plt.savefig(clean_filename(title , 'png', plot_directory))
plt.show()
def build_set(tweets):
'''builds set of (unique) words from corpus of tweets'''
unique_words = set()
for tweet in tweets:
for word in tweet.split():
unique_words.add(word)
return unique_words
if __name__ == '__main__':
t0 = time.time()
name_dict = get_name_dict()
color_dict = get_color_dict()
handles = get_handles()
names = get_names()
start_dates = ['05/01/2018', '03/07/2018', '02/02/2019']
end_dates = ['25/01/2020', '26/01/2020', '25/01/2020']
eda_plots.tweeting_period_plot(handles, start_dates, end_dates, color_dict)
nraw = list() # number of raw tweets for each handle
ntweets = list() # number of processed tweets for each handle
word_counts = list() # list of word counts
char_counts = list() # list of character counts
unique_words = list() # list of # of unique words for each handle
unique_all = set() # set of unique words overall
wc_arrays = list() # list of arrays of word_counts for sig. test
for handle in handles: # Loop over handles
print(name_dict[handle])