def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
for sentence in morphologies:
for m in sentence:
if m['pos'] == '動詞':
print m['surface']
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
for sentence in morphologies:
for m in sentence:
if m['pos'] == '名詞' and m['pos1'] == 'サ変接続':
print m['surface']
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
for sentence in morphologies:
for i in range(len(sentence)):
if sentence[i]['surface'] == 'の' and 0 < i < len(sentence) - 1 and sentence[i-1]['pos'] == '名詞' and sentence[i+1]['pos'] == '名詞':
print sentence[i-1]['surface'] + sentence[i]['surface'] + sentence[i+1]['surface']
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
words = [m['base'] for sentence in morphologies for m in sentence]
count = Counter(words)
for word, freq in count.most_common():
print word, freq
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
words = [m['base'] for sentence in morphologies for m in sentence]
count = Counter(words)
plt.hist([f for w, f in count.items()], bins=100, range=(0, 10000))
plt.title('Histogram of Term Frequency in Bocchan')
plt.xlabel('Term Frequency')
plt.ylabel('Freqency')
plt.show()
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
for sentence in morphologies:
noun_phrase = []
for m in sentence:
if m['pos'] == '名詞':
noun_phrase.append(m['surface'])
else:
if len(noun_phrase) >= 2:
print ''.join(noun_phrase)
noun_phrase = []
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
for sentence in morphologies:
noun_phrase = []
for m in sentence:
if m['pos'] == '名詞':
noun_phrase.append(m['surface'])
else:
if len(noun_phrase) >= 2:
print ''.join(noun_phrase)
noun_phrase = []
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
words = [m['base'] for sentence in morphologies for m in sentence]
count = Counter(words)
top10 = count.most_common(10)
ind = np.arange(10)
width = 0.35
plt.bar(ind, [f for w, f in top10], width)
plt.title('Top 10 of Term Frequency in Bocchan')
plt.xlabel('Terms')
plt.ylabel('Frequency')
plt.xticks(ind + width / 2, [w.decode('utf-8') for w, f in top10])
plt.show()
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
words = [m['base'] for sentence in morphologies for m in sentence]
count = Counter(words)
top = count.most_common()
rank = np.arange(len(top)) + 1
freq = [f for w, f in top]
plt.scatter(rank, freq, s=10)
plt.title('Relationship between Rank and Value of Term Frequency')
plt.xlabel('Rank (Logarithmic)')
plt.ylabel('Term Frequency (Logarithmic)')
plt.xscale('log')
plt.yscale('log')
plt.show()
return None
def solve(self):
'''
insert your code
'''
pc = PickleCache()
morphologies = pc.get('./neko.txt.mecab.pickle')
words = [m['base'] for sentence in morphologies for m in sentence]
count = Counter(words)
top = count.most_common()
rank = np.arange(len(top)) + 1
freq = [f for w, f in top]
plt.scatter(rank, freq, s=10)
plt.title('Relationship between Rank and Value of Term Frequency')
plt.xlabel('Rank (Logarithmic)')
plt.ylabel('Term Frequency (Logarithmic)')
plt.xscale('log')
plt.yscale('log')
plt.show()
return None