从目录加载多个 csv 文件并将列存储在数组中

Question

我有一个目录，其中包含多个以类似模式命名的 csv 文件，例如：'1000 x 30.csv'、'1000 y 30'.csv 或 '1111 z 60.csv' 等。我的 csv 文件是 2我想分别存储在数组中的 x 轴和 y 轴值的列。 我想输入如下输入：1000 x 30，以便程序获取 (1000 x 30.csv) 文件的列并存储在数组中。我有一个代码在我输入特定文件的路径时运行，我想遍历目录并在输入文件名时给我数组值。任何建议都会对我有帮助。

import csv
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from scipy.optimize import curve_fit
from scipy import asarray as ar,exp
import lmfit
import glob

# reading the x/y/z values from the respective csv files
xData = []
yData = []
path = r'C:\Users\angel\OneDrive\Documents\CSV_FILES_NV_LAB\1111 x 30.csv'
with open(path, "r") as f_in:
    reader = csv.reader(f_in)
    next(reader)

    for line in reader:
        try:
            float_1, float_2 = float(line[0]), float(line[1])
            xData.append(float_1)
            yData.append(float_2)
        except ValueError:
            continue

Answer 1

我认为下面的解决方案应该可以帮助您入门。我已经在需要的地方注释了代码，并指出了几个 SO 问题/答案。

请注意，请为您的下一个问题提供一些经过修剪和清理的示例输入文件。我不得不猜测一下确切的输入是什么。 记住，你的问题越好，你的答案就越好。

---

输入文件，由keyboard mashing生成

path/to/csv/files/1111 x 30.csv

x,y
156414.4189,84181.46
16989.177,61619.4698974

path/to/csv/files/11 z 205.csv

x,z
3.123123,56.1231
123.6546,645767.654
65465.4561989,97946.56169

---

实际代码：

ma​​in.py

import os
import csv


def get_files_from_path(path: str) -> list:
    """return list of files from path"""
    # see the answer on the link below for a ridiculously 
    # complete answer for this. I tend to use this one.
    # note that it also goes into subdirs of the path
    # https://stackoverflow.com/a/41447012/9267296
    result = []
    for subdir, dirs, files in os.walk(path):
        for filename in files:
            filepath = subdir + os.sep + filename
            # only return .csv files
            if filename.lower().endswith('.csv'):
                result.append(filepath)
    return result


def load_csv(filename: str) -> list:
    """load a CSV file and return it as a list of dict items"""
    result = []
    # note that if you open a file for reading, you don't need
    # to use the 'r' part
    with open(filename) as infile:
        reader = csv.reader(infile)
        # get the column names
        # https://stackoverflow.com/a/28837325/9267296
        # doing this as you state that you're dealing with
        # x/y and x/z values
        column0, column1 = next(reader)

        for line in reader:
            try:
                result.append({column0: float(line[0]), 
                               column1: float(line[1])})
            except Exception as e:
                # I always print out error messages
                # in case of random weird things
                print(e)
                continue

    return result


def load_all(path: str) -> dict:
    """loads all CSV files into a dict"""
    result = {}
    csvfiles = get_files_from_path(path)
    for filename in csvfiles:
        # extract the filename without extension
        # and us it as key name
        # since we only load .csv files we can just
        # remove the last 4 characters from filename
        # https://stackoverflow.com/a/57770000/9267296
        keyname = os.path.basename(filename)[:-4]
        result[keyname] = load_csv(filename)
    return result


from pprint import pprint
all = load_all('path/to/csv/files')
pprint(all)
print('\n--------------------\n')
pprint(all['11 z 205'])

输出

---

{'11 z 205': [{'x': 3.123123, 'z': 56.1231},
              {'x': 123.6546, 'z': 645767.654},
              {'x': 65465.4561989, 'z': 97946.56169}],
 '1111 x 30': [{'x': 156414.4189, 'y': 84181.46},
               {'x': 16989.177, 'y': 61619.4698974}]}

--------------------

[{'x': 3.123123, 'z': 56.1231},
 {'x': 123.6546, 'z': 645767.654},
 {'x': 65465.4561989, 'z': 97946.56169}]