Python 栈溢出 Process finished with exit code -1073741571 (0xC00000FD)

Question

问题遇到的现象和发生背景

运行时出现栈溢出的现象，试过网上大家说的修改栈大小、深度等，但都没有解决问题。我的数据有16万多条，不知道是不是数据太大的问题，还是其他问题。

问题相关代码，请勿粘贴截图

import numpy as np
import sys
import os
from osgeo import gdal
from sklearn import ensemble
from sklearn.model_selection import train_test_split
import joblib
from tqdm import tqdm
import time

# 显示进度条
text = ""
for char in tqdm(["a", "b"]):
    text = text + char
    time.sleep(0.5)


# 读取tif数据
def Read_img2array(img_file_path):
    """
    读取栅格数据，将其转换成对应数组
    img_file_path: 栅格数据路径
    :return: 返回投影，几何信息，和转换后的数组
    """
    dataset = gdal.Open(img_file_path)  # 读取栅格数据
    print('处理图像波段数总共有：', dataset.RasterCount)
    # 判断是否读取到数据
    if dataset is None:
        print('Unable to open *.tif')
        sys.exit(1)  # 退出
   # 直接读取dataset
    img_array = dataset.ReadAsArray()
    return img_array

# tif -> array
def read_tif_array(path, filetype):
    pathDir = os.listdir(path)  # 文件放置在当前文件夹中，用来获取当前文件夹内所有文件目录
    i = 0
    array = [[0] * 1] * 165312
    array = np.array(array)
    array = array.reshape(-2, 1)
    for x in pathDir:
        index = x.rfind('.')
        if x[index:] == filetype:
            img_array = Read_img2array(path + "/" + x)
            mul = np.array(img_array).reshape(-2, 1)
            array = np.column_stack((array, mul))
            i = i + 1
        else:
            i = i
    array = array[:, 1:]
    return array

# 读取特征值
feature = read_tif_array("D:/Personality/paper/GBDT/train", '.tif')
# print(feature.shape)  # 一共有15个特征值

# 读取地质类为标签
label = read_tif_array("D:/Personality/paper/GBDT/label", '.tif')
label = label.ravel()

print(feature.shape, label.shape)

X, y = feature, label
labels, y = np.unique(y, return_inverse=True)  # 标签
X_train, X_test, y_train, y_test = train_test_split(X, y)  # 创建数据集

original_params = {
    "n_estimators": 400,
    "max_leaf_nodes": 4,
    "max_depth": 6,
    "random_state": 2,
    "min_samples_split": 5,
}  # 设置树的基本参数，用于后面计算
setting = {"learning_rate": 0.2, "subsample": 1.0}
params = dict(original_params)  # 转化为字典
params.update(setting)  # 更新字典键值对
clf = ensemble.GradientBoostingClassifier(**params)  # 梯度
clf.fit(X_train, y_train)  # 训练数据集
joblib.dump(clf, 'train_model_result.m')   # 保存模型

y_gbr = clf.predict(X_train)
y_gbr1 = clf.predict(X_test)
acc_train = clf.score(X_train, y_train)
acc_test = clf.score(X_test, y_test)
print(acc_train)
print(acc_test)

运行结果及报错内容

我的解答思路和尝试过的方法

我想要达到的结果

Answer 1

39行的array改成全局的再运行看看

array = [[0] * 1] * 165312