python数据处理，连续相同的标签取最大值

哈哈，直接上数据和代码吧！

大概意思就是根据label列，在特征值列根据label列连续相同标签的区间取最大值，比如：在黄色背景内取3.2，在绿色背景内取24.2，以此类推！

import pandas as pd
import numpy as np

# 读入数据
path = "stock_data.xlsx"
data = pd.read_excel(path)

# 将标签转换为列表
stock_data = np.array(data)
stock_label = list(stock_data[:,1])
stock_label = list(map(int, stock_label))

# 找出“-1”和“1”分割位置
split_index = []
for index in range(len(stock_label)):
    if index < len(stock_label)-1 and stock_label[index]== 1 and stock_label[index+1]==-1:
        split_index.append(index)
    elif   index < len(stock_label)-1 and stock_label[index]== -1 and stock_label[index+1]==1:
        split_index.append(index)
        
split_len = len(stock_label)
split_index.append(split_len)

split_idx = [i+1 for i in split_index]
split_idx.insert(0,0)

# 取出“特征值”列每个对应区间的最大值
index_interval = []
s_1 = list(stock_data[:,0])
for idx,ele in enumerate(split_idx):
    print(ele)
    if idx < len(split_idx)-1:
        num_max = max(s_1[ele:split_index[idx]+1])
        print("the max num is: ", num_max)

本文地址：https://blog.csdn.net/u013313168/article/details/108267455