def x_2func(traindir,testdir):
'''
train = nb.read('train_nb_eventmodel')
sta = nb.sta_count(train)
category_tokens = get_category_tokens()
token_x = x_2(train,sta,category_tokens)
nb.write(token_x,'token_x')
'''
category = nb.read('category_nb_eventmodel')
tokens_x = nb.read('token_x')
category_convert = nb.convert(category)
tokens_all_x = []
x_category = {}
for i in range(10):
tokens = sorted(tokens_x[i],key=tokens_x[i].get,reverse = True)
x_category[i] = tokens[:100]
'''
x_category[i] = []
for word in tokens:
if tokens_x[i][word] >10.83:
x_category[i].append(word)
else:
break
'''
print len(x_category[i])
tokens_all_x = set(tokens_all_x)|set(x_category[i])
print len(tokens_all_x)
nb.write(x_category,'x_category')
nb.write(tokens_all_x,'tokens_all_x')
def dffunc():
#这里先使用文档频率，需要统计在某一类别下词t在多少个文档中出现
'''
train = nb.read('train_nb_eventmodel')
sta = nb.sta_count(train)
all_tokens = get_all_tokens()
tokens_df = df(train,sta,all_tokens)
nb.write(tokens_df,'tokens_df')
'''
category = nb.read('category_nb_eventmodel')
tokens_df = nb.read('tokens_df')
category_convert = nb.convert(category)
tokens_all_df = []
df_category = {}
for i in range(10):
tokens = sorted(tokens_df,key=tokens_df.get,reverse = True)
df_category[i] = tokens[:200]
tokens_all_df = set(tokens_all_df)|set(df_category[i])
print tokens_all_df
nb.write(df_category,'df_category')
nb.write(tokens_all_df,'tokens_all_df')
def mi_func():
'''
train = nb.read('train_nb_eventmodel')
sta = nb.sta_count(train)
category_tokens = get_category_tokens()
token_mi = mi(train,sta,category_tokens)
nb.write(token_mi,'token_mi')
'''
category = nb.read('category_nb_eventmodel')
token_mi = nb.read('token_mi')
category_convert = nb.convert(category)
tokens_all_mi = []
mi_category = {}
for i in range(10):
tokens = sorted(token_mi[i],key = token_mi[i].get,reverse = True)
mi_category[i] = tokens[:500]
tokens_all_mi = set(tokens_all_mi)|set(mi_category[i])
print len(tokens_all_mi)
nb.write(mi_category,'mi_category')
nb.write(tokens_all_mi,'tokens_all_mi')
'''
def gifunc():
train = nb.read('train_nb_eventmodel')
sta = nb.sta_count(train)
all_tokens = get_all_tokens()
tokens_gi = gi(train,sta,all_tokens)
nb.write(tokens_gi,'tokens_gi')
category = nb.read('category_nb_eventmodel')
tokens_gi = nb.read('tokens_gi')
category_convert = nb.convert(category)
tokens_all_gi = []
gi_category = {}
for i in range(10):
tokens = sorted(tokens_gi,key=tokens_gi.get,reverse=True)
gi_category[i] = tokens[:100]
tokens_all_gi = set(tokens_all_gi)|set(gi_category[i])
print tokens_all_gi
nb.write(gi_category,'gi_category')
nb.write(tokens_all_gi,'tokens_all_gi')
def preprocess():
traindir = './data/training'
testdir = './data/test'
tokens_all_x = nb.read('tokens_all_x')
train_x,train_y,category = nb.func2(traindir)
train_x = np.array(train_x)
train_y = np.array(train_y)
result,test_x,test_file = nb.func3(testdir,category)
test_x = np.array(test_x)
test_file = np.array(test_file)
nb.write(train_x,'train_x')
nb.write(train_y,'train_y')
nb.write(category,'category')
nb.write(result,'result')
nb.write(test_x,'test_x')
nb.write(test_file,'test_file')
def preprocess():
traindir = './data/training'
testdir = './data/test'
tokens_all_x = nb.read('tokens_all_x')
train_x, train_y, category = nb.func2(traindir)
train_x = np.array(train_x)
train_y = np.array(train_y)
result, test_x, test_file = nb.func3(testdir, category)
test_x = np.array(test_x)
test_file = np.array(test_file)
nb.write(train_x, 'train_x')
nb.write(train_y, 'train_y')
nb.write(category, 'category')
nb.write(result, 'result')
nb.write(test_x, 'test_x')
nb.write(test_file, 'test_file')
