0

每次选择切片时，我都在尝试根据绘图中可见的特征将数据（具有多列的 pandas.DataFrame）切片并保存到单独的文件中。到目前为止，我使用了 matplotlib SpanSelector 和它的onselect函数。但是，这仅适用于全局变量，因为现在似乎有一种简单的方法可以将 DataFrame 传递给函数。有什么解决方案可以避免每次都声明一个全局变量吗？

DataFrame 本身来自将输入文件读入 DataFrame 的程序。

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.widgets import SpanSelector



def get_data():
    # example of DataFrame, real Data will come from input-files
    x = np.arange(100,step=0.2)
    y = np.sin(x)
    y2 = np.cos(x)
    data = pd.DataFrame(np.array((y,y2)).transpose(), index=x, columns=["a","b"])
    return data

def cut_data(data_frame):
    # use a single plot or as many subplots as there are columns in dataframe if more than one
    if data_frame.shape[1] == 1:
        fig, ax = plt.subplots(data_frame.shape[1], 1, sharex=True)
        ax.plot(data_frame)
        span = SpanSelector(ax, onselect, 'horizontal', useblit=True,
                        rectprops=dict(alpha=0.35, facecolor='red'), span_stays=True)
    else:
        fig, axlst = plt.subplots(data_frame.shape[1], 1, sharex=True)
        for n, col in enumerate(data_frame):
            axlst[n].plot(data_frame[col])
        span = SpanSelector(axlst[0], onselect, 'horizontal', useblit=True,
                        rectprops=dict(alpha=0.35, facecolor='red'), span_stays=True)
    plt.show()

def onselect(xmin, xmax):
    pass
    # get indices of x-values each time a subset of the data is selected
    # slice every column in DataFrame and save to file as new DataFrame


cut_data(get_data())
4

1 回答 1

0

我写了一个可调用对象来规避这个问题

class OnselectObject(object):
'''
This classed is used to circumvent the limitations of the matplotlib SpanSelector object
'''
def __init__(self, data_frame):
    self.data = data_frame

def __call__(self, xmin, xmax):
    cut_data = self.data[:][xmin:xmax] # this is awesome
    save_cut_data(cut_data)
于 2020-02-12T10:27:25.957 回答