# In[361]:
metastatic_exp = pd.read_csv(os.path.join(external_data_dir,
"gse18549_expression.csv"),
index_col=0).T.values
metastatic_exp_scaled = scale(metastatic_exp)
metastatic_exp_robust = RobustScaler(
quantile_range=(1.0, 99.0)).fit_transform(metastatic_exp)
metastatic_exp_normed = normalize(metastatic_exp)
metastatic_exp_scaled_normed = normalize(scale(metastatic_exp))
# In[362]:
print(metastatic_exp.min().min(), metastatic_exp.max().max())
print(metastatic_exp_scaled.min().min(), metastatic_exp_scaled.max().max())
print(metastatic_exp_robust.min().min(), metastatic_exp_robust.max().max())
print(metastatic_exp_normed.min().min(), metastatic_exp_normed.max().max())
print(metastatic_exp_scaled_normed.min().min(),
metastatic_exp_scaled_normed.max().max())
# In[366]:
_ = plt.hist(metastatic_exp.flatten(), bins=50, normed=True, label='raw')
_ = plt.hist(metastatic_exp_scaled.flatten(),
bins=50,
normed=True,
label='scale')
_ = plt.hist(metastatic_exp_robust.flatten(),
bins=50,
normed=True,
label='quantile')
X_scale=minmax_scale(X)
elif c==0:#不进行归一化
X_scale=X
elif c==3:#鲁棒性归一化
from sklearn.preprocessing import RobustScaler
X_scale=RobustScaler().fit_transform(X)
print 'the standar result of X is:',X_scale
##测试X_scale,正常情况下均值为0，方差为1
#1.
print 'mean=',X_scale.mean()
print 'std=',X_scale.std()
#2.
print 'min=',X_scale.min()
print 'max=',X_scale.max()
csv_file1.close()
##为了理解方便、表示方法简单
X=X_scale
##归一化之后的统计信息
##获得X的统计信息
statistics(X)
##频率分布图
#drawHist(X,'AOD','Frequency','the Frequency of standar AOD')
##频率累计图
#drawCumulativeHist(X,'AOD','Frequency','Curve cumulative of standar AOD')
##箱图
#drawBox(X.reshape(264,),'AOD','BOX of standar AOD')
