【影像组学】从特征筛选到分类建模全流程实践及作图

---

• 应用：入门级影像组学文章解析

1. 数据准备

# 导入包
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from scipy.stats import ttest_ind, levene
from sklearn.linear_model import LassoCV
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
import seaborn as sns # 作图包
import matplotlib.pyplot as plt # 作图包
from sklearn.metrics import roc_curve, roc_auc_score, classification_report # ROC 曲线 AUC 分类报告

# 导入数据
xlsx_a = 'data/featureTable/aa.xlsx'
xlsx_b = 'data/featureTable/bb.xlsx'
data_a = pd.read_excel(xlsx_a)
data_b = pd.read_excel(xlsx_b)
print(data_a.shape,data_b.shape)
# (212, 30) (357, 30)

# 数据预处理（加分组标签后合并）
rows_a,cols_a = data_a.shape
rows_b,cols_b = data_b.shape
labels_a = np.zeros(rows_a)
labels_b = np.ones(rows_b)
data_a.insert(0, 'label', labels_a)
data_b.insert(0, 'label', labels_b)
data = pd.concat([data_a,data_b])

# 数据集划分
data_train, data_test = train_test_split(data,test_size=0.3, random_state = 15)
data_train_a = data_train[:][data_train['label'] == 0]
data_train_b = data_train[:][data_train['label'] == 1]
data_test_a = data_test[:][data_test['label'] == 0]
data_test_b = data_test[:][data_test['label'] == 1]
print(data_train_a.shape)
print(data_train_b.shape)
print(data_test_a.shape)
print(data_test_b.shape)
# (150, 31)
# (248, 31)
# (62, 31)
# (109, 31)

# T 检验特征筛选（训练集）</