第一次提交：用于根河用户towersif原始数据分割

1. 任总：csv中的2个光谱仪分别有6个位置的数据，位置1、3、5实际上都是测的光纤位置1的数据（测天空），所以分割后都改为P1；
2. 添加了界面分别输入原始数据文件夹和输出文件夹，在输出文件夹中新建文件夹split1、split2和split3用于保存分割后的数据；

.gitignore

@@ -0,0 +1,166 @@
+# 唐超添加
+/.idea
+*.zip
+/Data
+Data_split
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

main.py

@@ -0,0 +1,14 @@
+import easygui
+from towerDataSplit import DataSplit
+
+
+inputDataPath = easygui.diropenbox('第1/2步', '选择towersif原始数据文件夹')
+outputDataPath = easygui.diropenbox('第2/2步', '选择输出文件夹')
+
+# inputDataPath = r"D:\PycharmProjects\towerDataSplit\sampleData"
+# outputDataPath = r"D:\PycharmProjects\towerDataSplit\Data_split"
+
+data_split = DataSplit(inputDataPath, outputDataPath)
+data_split.start_split_process()
+
+easygui.msgbox("数据分割完成！", "提示")

towerDataSplit.py

@@ -0,0 +1,121 @@
+import numpy as np
+import pandas as pd
+import os
+from datetime import datetime
+import time
+import math
+import argparse
+import copy
+
+
+class DataSplit:
+    def __init__(self, inputDataPath, outputDataPath):
+        self.inputPath = inputDataPath
+        self.outputPath = outputDataPath
+
+    def create_directory(self, directory):
+        """
+        可直接创建深层文件夹，例如，如果B和C没有，直接创建/A/B/C/D也能成功
+        :param directory:
+        :return:
+        """
+        if not os.path.exists(directory):  # 判断所在目录下是否有该文件名的文件夹
+            os.makedirs(directory)
+
+    def read_data(self, file_path):
+        """
+        读取csv数据，并修改信息以适配分割后的csv
+        :param file_path:
+        :return:
+        """
+        guess_column_number = 10000
+
+        df = pd.read_csv(file_path, header=None, sep=',', names=range(guess_column_number))
+        correct_column_number = max(df.iloc[2, 6], df.iloc[4, 6]) + 3
+
+        df.drop(list(range(int(correct_column_number), guess_column_number)), axis=1,
+                inplace=True)  # inplace=True会就地修改，不会创建副本
+        # df = pd.read_csv(file_path, header=None, sep=',', names=range(int(correct_column_number)))  # 重新读文件
+
+        # 修改信息
+        df.iloc[1, 3] = 2
+
+        # 任总：数据中显示的P3也是采集的位置1的数据，老师嫌采集时间过长，想采集2次天空
+        df.iloc[9, 0] = df.iloc[9, 0].replace("3", "1")
+        df.iloc[11, 0] = df.iloc[11, 0].replace("5", "1")
+        df.iloc[15, 0] = df.iloc[15, 0].replace("3", "1")
+        df.iloc[17, 0] = df.iloc[17, 0].replace("5", "1")
+
+        return df
+
+    def split_data(self, df):
+        """
+        分割pandas的dataframe的对应的那些行到新的dataframe中，并返回
+        :param df:
+        :return:
+        """
+        df1 = df.iloc[[0, 1, 2, 3, 4, 5, 6, 7, 8, 13, 14]]
+        df2 = df.iloc[[0, 1, 2, 3, 4, 5, 6, 9, 10, 15, 16]]
+        df3 = df.iloc[[0, 1, 2, 3, 4, 5, 6, 11, 12, 17, 18]]
+
+        return df1, df2, df3
+
+    def write_data(self, df, file_path):
+        # 写csv方式1的问题：有的整数会在后面加.0（例如77777 → 77777.0，后期在c# 写的easysif中不能直接转int，需要先转double，在转int）
+        df.to_csv(file_path, index=False, header=False)
+
+        # 写csv方式2：也有方式1的问题，推测pandas是基于numpy实现的，所以numpy具有此问题，那么pandas也具有此问题
+        # np.array(df1).tofile(file_path_out1, sep=',')
+
+    def start_split_process(self):
+        """
+        分割处理数据主函数
+        :return:
+        """
+        time_start = time.time()  # 记录开始时间
+
+        directories = os.listdir(self.inputPath)
+        self.validFiles = []
+
+        for directory in directories:
+            directory1_tmp = os.path.join(self.outputPath, "split1", directory)
+            directory2_tmp = os.path.join(self.outputPath, "split2", directory)
+            directory3_tmp = os.path.join(self.outputPath, "split3", directory)
+            self.create_directory(directory1_tmp)
+            self.create_directory(directory2_tmp)
+            self.create_directory(directory3_tmp)
+
+            files = os.listdir(os.path.join(self.inputPath, directory))
+            for file in files:
+                file_path = os.path.join(self.inputPath, directory, file)
+                if os.path.splitext(file_path)[1] != '.csv':
+                    continue
+
+                df = self.read_data(file_path)
+                df1, df2, df3 = self.split_data(df)
+
+                file_path_out1 = os.path.join(directory1_tmp, file)
+                file_path_out2 = os.path.join(directory2_tmp, file)
+                file_path_out3 = os.path.join(directory3_tmp, file)
+
+                self.write_data(df1, file_path_out1)
+                self.write_data(df2, file_path_out2)
+                self.write_data(df3, file_path_out3)
+
+        time_end = time.time()  # 记录结束时间
+        time_sum = time_end - time_start  # 计算的时间差为程序的执行时间，单位为秒/s
+        print("处理用时：%d" % time_sum)
+
+        return 0
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("inputDataPath", help="输入数据路径")
+    parser.add_argument("outputDataPath", help="输出路径。")
+    args = parser.parse_args()
+
+    data_split = DataSplit(args.inputDataPath, args.outputDataPath)
+    data_split.start_split_process()
+
+    print("completed!!")