组织分类模型的构建¶

#安装scikit-learn
pip install -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple -U scikit-learn pandas matplotlib
#检查安装版本
python -c "import sklearn; sklearn.show_versions()"

#以下代码95%以上都为chatGPT生成
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler,LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.decomposition import PCA
import pickle

# 自定义函数
## PCA聚类并可视化
def plot_PCA(X, y, title):
    pca = PCA(n_components=2)  # 将数据降至 2 维
    X_pca = pca.fit_transform(X)

    plt.figure(figsize=(8, 6))
    for label in np.unique(y):
        plt.scatter(X_pca[y == label, 0], X_pca[y == label, 1], label=label_encoder.inverse_transform([label])[0])

    plt.title(title)
    plt.xlabel('Principal Component 1')
    plt.ylabel('Principal Component 2')
    plt.legend()
    plt.show()

## LDA聚类并可视化
def plot_LDA(X, y, title):
    lda = LinearDiscriminantAnalysis(n_components=2)  # 选择两个主要成分用于可视化
    X_lda = lda.fit_transform(X, y)

    plt.figure(figsize=(8, 6))
    for label in np.unique(y):
        plt.scatter(X_lda[y == label, 0], X_lda[y == label, 1], label=label_encoder.inverse_transform([label])[0])

    plt.title(title)
    plt.xlabel('LDA Component 1')
    plt.ylabel('LDA Component 2')
    plt.legend()
    plt.show()


# 1. 读取数据
data = pd.read_csv('dataset.txt', header=0, sep='\t')

# 2. 将最后一列作为标签，其余列作为特征
X = data.iloc[:, 1:-1].values  # 特征
y = data.iloc[:, -1].values   # 标签（最后一列）
#将标签转换为数值（"blood" -> 0, "liver" -> 1, "muscle" -> 2, "small intestine" -> 2）
label_encoder = LabelEncoder()
y_encoded = label_encoder.fit_transform(y)
print("Label mapping:", label_encoder.classes_)

# 3. 对特征进行标准化
X_log = np.log1p(X) #转录组数据常用的一种标准化方法log(x+1)
# scaler = StandardScaler()
# X_scaled = scaler.fit_transform(X_log)  # 标准化后的特征
# 4. 数据初步可视化
plot_PCA(X_log, y_encoded, 'PCA of the dataset')
plot_LDA(X_log, y_encoded, 'LDA of the dataset')


# 5. 将数据分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_log, y_encoded, test_size=0.2, random_state=42)

# 6. 选择分类模型（例如随机森林分类器）
# clf = RandomForestClassifier(random_state=42)
clf = LogisticRegression()

# 7. 训练模型
clf.fit(X_train, y_train)

# 8. 在测试集上进行预测
y_pred = clf.predict(X_test)

# 9. 评估模型准确性
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy * 100:.2f}%')

# 10. 保存模型
with open('tissue_clf.pkl', 'wb') as f:
    pickle.dump(clf, f)

# 11. 加载模型
with open('tissue_clf.pkl', 'rb') as f:
    clf2 = pickle.load(f)

# 12. 使用加载的模型进行预测
y_pred_loaded = clf2.predict(X_test)
accuracy = accuracy_score(y_test, y_pred_loaded)
print(f'Accuracy: {accuracy * 100:.2f}%')

apt install python3
pip3 install -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple -U scikit-learn pandas matplotlib

ssh fat01
cd /data2/dongkeai/group2/105042024802
mkdir ai_work
cd ai_work
cp /data2/dongkeai/00Data/AI/* ./
python classification.py