def my_preprocessing(train_data):
  from sklearn import preprocessing
  X_normalized = preprocessing.normalize(train_data ,norm = "l2",axis=0)#使用l2范式，对特征列进行正则
  return X_normalized
 
def my_feature_selection(data, target):
  from sklearn.feature_selection import SelectKBest
  from sklearn.feature_selection import chi2
  data_new = SelectKBest(chi2, k= 50).fit_transform(data,target)
  return data_new
 
def my_PCA(data):#data without target, just train data, withou train target.
  from sklearn import decomposition
  pca_sklearn = decomposition.PCA()
  pca_sklearn.fit(data)
  main_var = pca_sklearn.explained_variance_
  print sum(main_var)*0.9
  import matplotlib.pyplot as plt
  n = 15
  plt.plot(main_var[:n])
  plt.show()
 
def clf_train(data,target):
  from sklearn import svm
  #from sklearn.linear_model import LogisticRegression
  clf = svm.SVC(C=100,kernel="rbf",gamma=0.001)
  clf.fit(data,target)
 
  #clf_LR = LogisticRegression()
  #clf_LR.fit(x_train, y_train)
  #y_pred_LR = clf_LR.predict(x_test)
  return clf
 
def my_confusion_matrix(y_true, y_pred):
  from sklearn.metrics import confusion_matrix
  labels = list(set(y_true))
  conf_mat = confusion_matrix(y_true, y_pred, labels = labels)
  print "confusion_matrix(left labels: y_true, up labels: y_pred):"
  print "labels\t",
  for i in range(len(labels)):
    print labels[i],"\t",
  print 
  for i in range(len(conf_mat)):
    print i,"\t",
    for j in range(len(conf_mat[i])):
      print conf_mat[i][j],'\t',
    print 
  print 
 
def my_classification_report(y_true, y_pred):
  from sklearn.metrics import classification_report
  print "classification_report(left: labels):"
  print classification_report(y_true, y_pred)