def single_class_mispredition_freq(res_path):
"""
Get the frequency of misprediction between single genre instances and the predicted genre
:param res_path:
:return:
"""
print("Loading Iter")
wrong_res_iter=WrongResultsIter.load_iter_from_file(res_path)
right_res_iter=RightResultsIter.load_iter_from_file(res_path)
genre_to_wrong_genre_count=coll.Counter()
for c,res_obj in enumerate(it.chain(wrong_res_iter,right_res_iter)):
if c%500==0:
print(c)
actual=res_obj.actual
#single genre
if len(actual)==1 and actual[0] != res_obj.predicted[0]:
genre_to_wrong_genre_count.update([(actual[0],res_obj.predicted[0])])
#plot
plt=plot_word_frequency("Single Genre Mispredition",genre_to_wrong_genre_count)
plt.tight_layout()
save_fig("C:\\\\Users\\\\Kevin\\\\Desktop\\\\GitHub\\\\Research\\\\Webscraper\\\\classification_res\\\\genre_analysis\\\\single_miss.pdf",
plt)
def plot_miss_per_genre(path,outpath,classifiers=None):
"""
Given the path to classification result folder of multiple classifier.
produce a plot of the classifier's misses.
:param path: the input folder where the classifiers' result(s) are
:param classifiers: A set of classifier whose results to graph. Note that if none, all of classifier's
results will be combined.
:return:
"""
#grab the actual misses, counter in default dict in default dict. First layer for classifiers, second layer
#is for correct genres, finally the counter is to count how many times it got miss classified as somethine else
classifier_to_misses_genre=collections.defaultdict(lambda:collections.defaultdict(lambda:collections.Counter()))
for true_miss in (w for w in WrongResultsIter(path,classifiers) if not w.is_swing_sample()):
assert isinstance(true_miss,ClassificationResultInstance)
classifier_to_misses_genre[true_miss.classifier][true_miss.__actual].update([true_miss.predicted])
#now plot each one, output to OUTPUT/classifier
for classifier, actual_to_miss in classifier_to_misses_genre.items():
for actual_genre,miss_freq in actual_to_miss.items():
plt=plot_word_frequency("{}-{} Misclassifications".format(classifier,actual_genre),miss_freq,plot_top=len(miss_freq))
out_path=os.path.join(outpath,classifier)
if not os.path.exists(out_path):
os.mkdir(out_path)
save_fig("{}/{}_miss_true.pdf".format(out_path,actual_genre),plt)
plt.close()
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 plot_total_consensus(consensus_count,consensus_total):
consensus_count=sorted(consensus_count.items(),key=lambda entry:entry)
num_classes=len(consensus_count)
pyplot.close()
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,sum(count),sum(genre_total_dict[genre])))
genre_to_counts=sorted(genre_to_counts,key=lambda t:t[0])
pyplot.hold(True)
pyplot.title("Consensus plot for Genre {}".format(c))
pyplot.bar(range(len(genre_to_counts)),[g[2] for g in genre_to_counts],color='#deb0b0',label="Consensus Total",align='center')
pyplot.bar(range(len(genre_to_counts)),[g[1] for g in genre_to_counts],color='#b0c4de',label="Consensus Counts",align='center')
pyplot.xticks(range(len(genre_to_counts)),[g[0] for g in genre_to_counts],size= 5)
legend=pyplot.legend(loc="upper right")
legend.set_visible(False)
pyplot.hold(False)
path="C:\\Users\\Kevin\\Desktop\\GitHub\\Research\\Webscraper\\classification_res\\consensus_plots\\total_{}.pdf"
graphics.save_fig(path.format(num_classes),pyplot)
pyplot.close()
print("Done")
print("Done")
def get_all_mi_and_plot(reversed=False):
"""
Grab all mutual information data from the database collection MutualInformation and plot them with matlibplot
:return: None!
"""
# graphics.plot_save_all_genre()
mi = MutualInformation()
for mi_obj in mi.iterable():
genre = mi_obj["short_genre"]
bow_mi = mi_obj["bow"]
filtered_bow_mit = {}
for k, v in bow_mi.items():
if not k.isdigit():
filtered_bow_mit[k] = v
plt = graphics.plot_word_frequency(genre, filtered_bow_mit, reversed=reversed)
graphics.save_fig("graphs/{}.pdf".format(("reversed_" if reversed else "") + genre.replace("/", "_")), plt)
print(genre)