python_93040206/基础信息/get_pkl.py

import pandas as pd
import numpy as np
import target as target
from sklearn.impute import SimpleImputer
from sklearn.metrics import accuracy_score
import joblib
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.feature_selection import VarianceThreshold
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from bioconductor import maftools

# 1. 准备数据
# 读取 maf 文件
maf_df = pd.read_csv('example.maf', sep='\t', comment='#')

# 转为 csv 文件
maf_df.to_csv('example.csv', index=False)

# 1. 准备数据
data = pd.read_csv('example.csv')
data=data.drop(data[data['all_effects'] == 'MAPKBP1'].index)
# 删除无关特征
# data.drop(['id', 'class'], axis=1, inplace=True)

# 填充缺失值
# imputer = SimpleImputer(strategy='mean', fill_value=0)
# data = imputer.fit_transform(data)

# 标准化
scaler = StandardScaler()
data = scaler.fit_transform(data)

# 方差选择
selector = VarianceThreshold(threshold=0.01)
data = selector.fit_transform(data)

print('data.shape', data.shape)
# 假设您的 target 数组原来的形状为 (57, 2)
# target = np.argmax(data.shape, axis=1)  # 将二元分类标签转换为单个类标签
# target = target.reshape((-1,))  # 将形状修改为 (57,)
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data, data.shape, test_size=0.2, random_state=42)

# 建立随机森林模型
rfc = RandomForestClassifier(n_estimators=100, max_depth=10, random_state=42)
rfc.fit(X_train, y_train)



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

# 计算模型评估指标
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Accuracy:", accuracy)
print("Precision:", precision)
print("Recall:", recall)
print("F1 score:", f1)



# data=data.drop(data[data['all_effects'] == 'MAPKBP1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'BPNT1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'MAPKBP1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'TNS1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'KCNH8'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'FOXL2NB'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'GHSR'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'WNK1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'F12'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'ASB5'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'TBCCD1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'GPR39'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'KCNF1'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'GDF7'].index)
# data=data.drop(data[data['Hugo_Symbol'] == 'TCF23'].index)
# data=data.drop(data[data['SYMBOL'] == 'MAPKBP1'].index)
#
#
# data.drop('all_effects', axis=1, inplace=True)
#
# for index, row in data.iterrows():
#     if index == 42:
#         # print(row)
#         for elm_index in data.columns:
#             print(row[elm_index])


#
# # print(303030, data[data['Hugo_Symbol'] == 'MAPKBP1'].index)
# # print(303030, data[data['Hugo_Symbol'] == 'MAPKBP1'])
#
# # df = data.drop(data.select_dtypes(include=['object']), axis=1)
# X = data.iloc[:, :-1]
# y = data.iloc[:, -1]
#
# # 2. 划分训练集和测试集
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
#
#
# # 删除不需要的列
# # data.drop( index=45, axis=1, inplace=True)
# # data.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
#
#
#
#
#
#
#
#
# # 3. 选择算法
# rfc = RandomForestClassifier(n_estimators=100, random_state=42)
#
# # 4. 训练模型
# rfc.fit(X_train, y_train)
#
#
#
# # 5. 评估模型
# y_pred = rfc.predict(X_test)
# accuracy = accuracy_score(y_test, y_pred)
# print(f"Accuracy: {accuracy:.2f}")
#
# # 6. 模型保存
# joblib.dump(rfc, 'snp_model.pkl')