Python loadData2示例

示例#1

文件： classify_use_tree.py 项目： FF120/python

@author: FF120
"""
import numpy as np
from time import time
from sklearn.svm import SVC
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFromModel
from sklearn.cross_validation import StratifiedKFold


import fmriUtils as fm
n_folds = 10

f = fm.outTo() #输出重定向到文件
X,y = fm.loadData2()   
y = fm.defineClass(y)
t0 = time()
forest = ExtraTreesClassifier(n_estimators=1000,
                              max_features=1000,
                              n_jobs=2,
                              random_state=0)
                              
forest.fit(X, y)
model = SelectFromModel(forest, threshold='2*mean',prefit=True)
XX = model.transform(X)

yy = y
cv = StratifiedKFold(yy,n_folds)
cv_scores = []
for train, test in cv:

示例#2

文件： classify_use_randomLR.py 项目： FF120/python

@author: FF120
"""
import numpy as np

from sklearn.linear_model import LogisticRegression
from sklearn.feature_selection import SelectFromModel
from sklearn.svm import SVC
from sklearn.cross_validation import StratifiedKFold
from sklearn.linear_model import RandomizedLogisticRegression
import fmriUtils as fm  #自定义函数

n_folds = 10

f = fm.outTo()  #输出重定向到文件
X, y = fm.loadData2()
X2, y2 = fm.loadData2()

y = fm.defineClass(y)

randomized_logistic = RandomizedLogisticRegression(C=0.1, n_jobs=2)
randomized_logistic.fit(X, y)
XX = randomized_logistic.transform(X)
print "============选择后剩余的特征================"
print XX.shape

yy = y
cv = StratifiedKFold(yy, n_folds)
cv_scores = []
for train, test in cv:
    svc = SVC(kernel='linear')

示例#3

# -*- coding: utf-8 -*-
"""
使用递归特征消除选取特征
"""
from sklearn.svm import SVC
from sklearn.cross_validation import StratifiedKFold
from sklearn.feature_selection import RFECV

import numpy as np
import fmriUtils as fm

n_folds = 5

f = fm.outTo()  #输出重定向到文件
X, y = fm.loadData2()

y = fm.defineClass(y)

svc = SVC(kernel="linear")
rfecv = RFECV(estimator=svc,
              step=1,
              cv=StratifiedKFold(y, n_folds),
              scoring='accuracy')
rfecv.fit(X, y)
print("Optimal number of features : %d" % rfecv.n_features_)

示例#4

文件： classify_use_randomLR.py 项目： FF120/python

@author: FF120
"""
import numpy as np

from sklearn.linear_model import LogisticRegression
from sklearn.feature_selection import SelectFromModel
from sklearn.svm import SVC
from sklearn.cross_validation import StratifiedKFold
from sklearn.linear_model import RandomizedLogisticRegression
import fmriUtils as fm  #自定义函数

n_folds = 10

f = fm.outTo() #输出重定向到文件
X,y = fm.loadData2()   
X2,y2 = fm.loadData2()   

y = fm.defineClass(y)

randomized_logistic = RandomizedLogisticRegression(C=0.1,n_jobs=2)
randomized_logistic.fit(X,y)
XX = randomized_logistic.transform(X)
print "============选择后剩余的特征================"
print XX.shape

yy = y
cv = StratifiedKFold(yy,n_folds)
cv_scores = []
for train, test in cv:
    svc = SVC(kernel='linear')