本笔记来源于B站Up主: 有Li 的影像组学系列教学视频
本节(10)主要介绍: T检验+lasso+随机森林
李博士借用和女朋友一起吃饭这个实例来说明：爱情和机器学习一样，复杂深奥、难以揣测。
import pandas as pd
import numpy as np
from sklearn.utils import shuffle
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LassoCV
from sklearn.model_selection import train_test_split, cross_val_score,KFold,RepeatedKFold,GridSearchCV
from scipy.stats import pearsonr, ttest_ind, levene
from sklearn.ensemble import RandomForestClassifier
from sklearn import svm
xlsx1_filePath = 'C:/Users/RONG/Desktop/PythonBasic/data_A.xlsx'
xlsx2_filePath = 'C:/Users/RONG/Desktop/PythonBasic/data_B.xlsx'
data_1 = pd.read_excel(xlsx1_filePath)
data_2 = pd.read_excel(xlsx2_filePath)
rows_1,__ = data_1.shape
rows_2,__ = data_2.shape
data_1.insert(0,'label',[0]*rows_1)
data_2.insert(0,'label',[1]*rows_2)
data = pd.concat([data_1,data_2])
data = shuffle(data)
data = data.fillna(0)
X = data[data.columns[1:]]
y = data['label']
colNames = X.columns
X = X.astype(np.float64)
X = StandardScaler().fit_transform(X)
X = pd.DataFrame(X)
X.columns = colNames
# t-test for feature selection
index = []
for colName in data.columns[1:]:
if levene(data_1[colName],data_2[colName])[1] > 0.05:
if ttest_ind(data_1[colName],data_2[colName])[1] < 0.05:
index.append(colName)
else:
if ttest_ind(data_1[colName],data_2[colName],equal_var = False)[1] < 0.05:
index.append(colName)
print(len(colName))
# to select the 'positive' features
if 'label' not in index:index = ['label']+index
data_1 = data_1[index]
data_2 = data_2[index]
data = pd.concat([data_1,data_2])
data = shuffle(data)
data.index = range(len(data))#re-label after mixure
X = data[data.columns[1:]]
y = data['label']
X = X.apply(pd.to_numeric,errors = 'ignore') # transform the type of the data
colNames = X.columns # to read the feature's name
X = X.fillna(0)
X = X.astype(np.float64)
X = StandardScaler().fit_transform(X)
X = pd.DataFrame(X)
X.columns = colNames
# lasso for further feature selection
alphas = np.logspace(-3,1,30)
model_lassoCV = LassoCV(alphas = alphas, cv = 10, max_iter = 100000).fit(X,y)
print(model_lassoCV.alpha_)
coef = pd.Series(model_lassoCV.coef_,index = X.columns)
print('Lasso picked ' + str(sum(coef !=0))+' variables and eliminated the other ' + str(sum(coef == 0))
index = coef[coef != 0].index
X = X[index]
X.head()
print(coef[coef !=0])
# RandomFrorest
X_train, X_test,y_train,y_test = train_test_split(X,y,test_size = 0.3)
model_rf = RandomForestClassifier(n_estimators = 20).fit(X_train,y_train)
score_rf = model_rf.score(X_test,y_test)
print(score_rf)
