def plot_consensus_percentile(consensus_count,consensus_total):
"""
Uses the 90th percentile plot.
:param consensus_count:
:param consensus_total:
:return:
"""
consensus_count=sorted(consensus_count.items(),key=lambda entry:entry)
num_classes=len(consensus_count)
pyplot.figure(1)
for c in range(0,num_classes):
ax=pyplot.subplot(num_classes,1,c)
genre_dict=consensus_count[c][1]
genre_total_dict=consensus_total[c]
genre_to_counts=[]
for genre,count in genre_dict.items():
genre_to_counts.append((genre,count,genre_total_dict[genre]))
genre_to_counts=sorted(genre_to_counts,key=lambda t:t[0])
pyplot.title("Consensus plot for Genre {}, total number of instances {}".format(c,sum(it.chain(*(g[2] for g in genre_to_counts)))/6))
#set up xaxis labels
pyplot.xticks(list(range(1,len(genre_to_counts)+1)),[g[0] for g in genre_to_counts])
pyplot.tick_params(axis='both', which='major', labelsize=5)
#now plot y axis
for index,res in enumerate(genre_to_counts):
graphics.add_bar_plot(index+1,res[1])
#pyplot.xticks(range(len(genre_to_counts)),["0"]+[g[0] for g in genre_to_counts],size= 5)
pyplot.legend(loc="upper right")
pyplot.tight_layout()
path="C:\\Users\\Kevin\\Desktop\\GitHub\\Research\\Webscraper\\classification_res\\consensus_plots\\percentile_{}.pdf"
graphics.save_fig(path.format(num_classes),pyplot)
pyplot.close()
print("Done")
def num_genre_per_webpage(matrix_path):
"""
Create a box plot of how many other genres each webpage has for each genre
Also, record the occurence of genres with each other
:param matrix_path:
:return:
"""
label_matrix=unpickle_obj(matrix_path)
genre_to_num_webpages=coll.defaultdict(lambda:[])
for webpage_genre in label_matrix:
normalized_genre=set([normalize_genre_string(g,1) for g in webpage_genre])
for g in normalized_genre:
if g in bad_genre_set:
continue
#if normalized_genre-{g}:
genre_to_num_webpages[g].append(normalized_genre-{g})
#box plot it
genre_to_num_item_iter=genre_to_num_webpages.items()
plt.clf()
plt.figure(1)
plt.xticks([i for i in range(0,len(genre_to_num_item_iter))],[op.itemgetter(0)(i) for i in genre_to_num_item_iter])
plt.yticks(range(0,6))
plt.tick_params(axis="both",which="major",labelsize=5)
for c,(g,counts) in enumerate(genre_to_num_item_iter):
add_bar_plot(c,[ len(gs) for gs in counts])
plt.savefig("C:\\Users\\Kevin\\Desktop\\GitHub\\Research\\Webscraper\\classification_res\\genre_analysis\\genre_dist.pdf")
#print
print(genre_to_num_webpages)
