def classify(data, labels):
method = sys.argv[1].upper()
method_name = {'SVM': 'SVM', 'RF': 'Random Forest'}
test_size_arr = [0.6, 0.5, 0.4]
print '方法：%s' % method_name[method]
for test_size in test_size_arr:
if (method == 'SVM'):
train_score, test_score = svm.run(data, labels, test_size)
elif (method == 'RF'):
train_score, test_score = rf.run(data, labels, test_size)
else:
train_score, test_score = svm.run(data, labels, test_size)
print '============================================='
print '训练集 %s | 测试集 %s' % (1 - test_size, test_size)
print '训练集正确率：%s' % train_score
print '测试集正确率：%s' % test_score
def result():
sns.set(palette="muted", color_codes=True)
# 3a
print '============================================='
print 'HW1-3a'
print '============================================='
# fittingGaussian('average_age')
normalTest(df['average_age'].values, name='Col[7]')
# 3b
print '============================================='
print 'HW1-3b'
print '============================================='
arr_7 = grouping('average_age')
for i in range(0, 5):
normalTest(arr_7[i], name='Col[7] in Group %s' % (i + 1))
print '---------------------------------------------'
leveneTest(arr_7, name='Col[7]')
# 3c
print '============================================='
print 'HW1-3c'
print '============================================='
oneway(arr_7, name='Col[7]')
# 4
print '============================================='
print 'HW1-4'
print '============================================='
selectCol = ['message_number', 'variance_age', 'conversation_number']
for key in selectCol:
normalTest(df[key].values, name='Col[%s]' % key)
print '---------------------------------------------'
for key in selectCol:
normalTest(np.log(df[key].values), name='log Col[%s]' % key)
# 5b
print '============================================='
print 'HW1-5'
print '============================================='
# no box-cox
for key in selectCol:
arr = grouping(key)
oneway(arr, 'Col[%s]' % key)
print '---------------------------------------------'
# box-cox
for key in selectCol:
arr = grouping(key, mode=True)
oneway(arr, 'box-cox Col[%s]' % key)
# 6
print '============================================='
print 'HW1-5'
print '============================================='
testSizeArr = [0.6, 0.5, 0.4]
print "SVM ['average_age', 'variance_age']"
for size in testSizeArr:
train_score, test_score = svm.run(df[['average_age', 'variance_age']],
df['group_category'], size)
print '[train:test = %s:%s] train correct=%s,test correct=%s.' % (
1 - size, size, train_score, test_score)
print '---------------------------------------------'
print "Random Forest ['average_age', 'variance_age']"
for size in testSizeArr:
train_score, test_score = rf.run(df[['average_age', 'variance_age']],
df['group_category'], size)
print '[train:test = %s:%s] train correct=%s,test correct=%s.' % (
1 - size, size, train_score, test_score)
if __name__ == "__main__":
loan_2 = 'data/loan_2.csv'
sourceData = np.loadtxt(loan_2,
dtype=float,
delimiter=',',
converters={0: loan_type},
skiprows=1)
# x是数据 y是标签
y, x = np.split(sourceData, (1, ), axis=1)
method = sys.argv[1].upper()
method_name = {'SVM': 'SVM', 'RF': 'Random Forest'}
test_size_arr = [0.6, 0.5, 0.4]
print '方法：%s' % method_name[method]
for test_size in test_size_arr:
if (method == 'SVM'):
train_score, test_score = svm.run(x, y, test_size)
elif (method == 'RF'):
train_score, test_score = rf.run(x, y, test_size)
else:
train_score, test_score = svm.run(x, y, test_size)
print '============================================='
print '训练集 %s | 测试集 %s' % (1 - test_size, test_size)
print '训练集正确率：%s' % train_score
print '测试集正确率：%s' % test_score
def fun():
rf.run()
converters={0: loan_type},
skiprows=1)
# x是数据 y是标签
y, x = np.split(sourceData, (1, ), axis=1)
method = sys.argv[1].upper()
method_name = {'SVM': 'SVM', 'RF': 'Random Forest'}
test_size_arr = [0.6, 0.5, 0.4]
print '方法：%s' % method_name[method]
for test_size in test_size_arr:
if (method == 'SVM'):
train_score, test_score, a_score, b_score, c_score = svm.run(
x, y, test_size)
elif (method == 'RF'):
train_score, test_score, a_score, b_score, c_score = rf.run(
x, y, test_size)
else:
train_score, test_score, a_score, b_score, c_score = svm.run(
x, y, test_size)
print '============================================='
print '训练集 %s | 测试集 %s' % (1 - test_size, test_size)
print '训练集正确率：%s' % train_score
print '测试集正确率：%s' % test_score
print 'good 正确率：%s' % a_score
print 'bad 正确率：%s' % b_score
print 'neutral 正确率：%s' % c_score