编程交流——第1期

revised_one

已于 2023-03-30 22:24:32 修改

阅读量125

点赞数 1

文章标签： python 数据分析

于 2023-03-30 22:06:19 首次发布

本文链接：https://blog.csdn.net/revised_one/article/details/129867633

版权

主题一：数据读取与写入

主题二：Python GDAL库研究

附件

主题一：数据读取与写入

要求：

（1）读取txt、EXCEL、CSV等至少三种格式的数据，数据内容见附件1；

（2）对读取的数字格式数据进行开根号处理，文本类型的数据保持不变；

（3）数据处理完成后将所有数据按照原格式数据输出。

# -*-coding:utf-8 -*-
"""
作者：XJQ
"""
from numpy import *
import pandas as pd
import numpy as np
import os
import xlrd
from openpyxl import load_workbook
import math
from pandas import read_csv

#读取文件夹文件
def readname(f_path):
    filePath = f_path #文件所在位置
    name = os.listdir(filePath)
    return name
def date(para):
    delta = pd.Timedelta(str(int(para))+'days')
    time = pd.to_datetime('1899-12-30') + delta
    return time
def do_excel(path,name):
    books1 = pd.read_excel(path+'\\'+name, header=0, sheet_name='Sheet1')
    books1['时间'] = books1['时间'].apply(date)
    books1['数据1'] = books1['数据1'].apply(math.sqrt)
    books1['数据2'] = books1['数据2'].apply(math.sqrt)
    writer = pd.ExcelWriter(path+'\data_sqrt.xlsx')
    books1.to_excel(writer, sheet_name='data_sqrt', index=False)
    writer.save()
    return
def do_txt(path,name):
    returnMat = pd.read_csv(path+'\\'+name, header = 0, delimiter='\t',encoding='gbk')
    returnMat['数据1'] = returnMat['数据1'].apply(math.sqrt)
    returnMat['数据2'] = returnMat['数据2'].apply(math.sqrt)
    np.savetxt(path+'\\data_sqrt.txt', returnMat, fmt='%s')
    return
def do_csv(path,name):
    # 使用Pandas导入csv数据
    filename = path+'\\'+name
    data = read_csv(filename,header=0,encoding='gbk')
    data['数据1'] = data['数据1'].apply(math.sqrt)
    data['数据2'] = data['数据2'].apply(math.sqrt)
    data.to_csv(path+'\\'+'data_sqrt.csv')
def f_into():
    #输入文件夹所在位置,例如'C:\Users\86136\Desktop\read_data'
    f_path = input("请输入文件夹地址:")
    name = readname(f_path)
    for i in name:
        if ('xlsx' in i):
            do_excel(f_path,i)
        if('txt' in i):
            do_txt(f_path,i)
        if('csv' in i):
            do_csv(f_path,i)
if __name__ == "__main__":
    f_into()

"""
作者：LK
"""

import pandas as pd


# txt读写
def data_txt(data_path, save_path):
    data = pd.read_table(data_path, encoding='GBK')     # 读取数据
    process_list = ['数据1', '数据2']                    # 待处理列名
    for i in process_list:
        data[i] = [round(x**0.5, 2) for x in data[i]]   # 数据处理
    data.to_csv(save_path, sep=' ', index=0,header=0)   # 数据写入


# csv读写
def data_csv(data_path, save_path):
    data = pd.read_csv(data_path, encoding='GBK')
    process_list = ['数据1', '数据2']
    for i in process_list:
        data[i] = [round(x**0.5, 2) for x in data[i]]
    data.to_csv(save_path, sep=',', index=0, header=0)


# excel读写
def data_xls(data_path, save_path):
    data = pd.read_excel(data_path)
    process_list = ['数据1', '数据2']
    for i in process_list:
        data[i] = [round(x**0.5, 2) for x in data[i]]
    data.to_excel(save_path)


if __name__ == '__main__':
    data_path = './data.xlsx'       # 数据路径
    save_path = './data_output.xlsx'    # 保存路径
    data_xls(data_path, save_path)  # 数据读写

"""
作者：HWY
"""
import pandas as pd
import math

# 读取 txt 文件
df1 = pd.read_csv(r'C:\Users\郝文宇\Desktop\开根号.txt', delimiter='\t')

# 读取 Excel 文件
df2 = pd.read_excel(r'C:\Users\郝文宇\Desktop\开根号.xlsx')

# 读取 CSV 文件
df3 = pd.read_csv(r'C:\Users\郝文宇\Desktop\开根号.csv')

# 定义函数：开根号处理数字数据
def sqrt_if_number(x):
    if isinstance(x, (int, float)) and x > 0:
        return math.sqrt(x)
    else:
        return x

# 对实际值的两列进行开根号处理
df1['数据1'] = df1['数据1'].apply(sqrt_if_number)
df1['数据2'] = df1['数据2'].apply(sqrt_if_number)

df2['数据1'] = df2['数据1'].apply(sqrt_if_number)
df2['数据2'] = df2['数据2'].apply(sqrt_if_number)

df3['数据1'] = df3['数据1'].apply(sqrt_if_number)
df3['数据2'] = df3['数据2'].apply(sqrt_if_number)

# 将所有数据按原格式排列
df1.to_csv('output1.txt', sep='\t', index=False)
df2.to_excel('output2.xlsx', index=False)
df3.to_csv('output3.csv', index=False)

"""
作者：DWK
"""
import pandas as pd
import numpy as np

# 定义一个函数，用于处理数据
def process_data(data):
    # 如果数据是数字，对其进行开方处理
    if isinstance(data, (int, float)):
        return np.sqrt(data)
    # 如果数据是文本，则不进行处理
    else:
        return data

# 读取txt、Excel和CSV文件，并处理数据
txt_data_processed = pd.read_table(r'C:\Users\16370\Desktop\read_data\data.txt', encoding='gbk').applymap(process_data)
excel_data_processed = pd.read_excel(r'C:\Users\16370\Desktop\read_data\data.xlsx').applymap(process_data)
csv_data_processed = pd.read_csv(r'C:\Users\16370\Desktop\read_data\data.csv', encoding='gbk').applymap(process_data)

# 将处理后的数据写回文件
txt_data_processed.to_csv('data_processed.txt', sep='\t', index=False)
excel_data_processed.to_excel('data_processed.xlsx', index=False)
csv_data_processed.to_csv('data_processed.csv', index=False)

"""
作者：CYF
"""
import math
import pandas as pd
import numpy as np
import xlrd
import xlwt

def csv():
    newData = []
    rand = np.random.default_rng()
    idx = []
    with open('./py_csv.csv', encoding='GBK') as f:
        data = pd.read_csv(f)
        i = 0
        for line in data.values:
            newData.append([line[0], math.sqrt(line[1]), math.sqrt(line[2])])
            idx.append(i)
            i += 1
        rand.shuffle(newData)
        file = pd.DataFrame(newData, columns=['日期', '数据1', '数据2'])
        file.index = idx
        file.to_csv('./new_py_csv.csv')

def txt():
    newData = []
    rand = np.random.default_rng()
    data = pd.read_csv('./py_txt.txt')
    for line in data.values:
        newData.append([line[0], math.sqrt(line[1]), math.sqrt(line[2])])
    rand.shuffle(newData)
    file = pd.DataFrame(newData, columns=['日期', '数据1', '数据2'])
    file.to_csv('./new_py_txt.txt', index=False, sep=' ')

def excel():
    file = xlrd.open_workbook('./py_excel.xlsx')
    sheet = file.sheet_by_index(0)
    wbk = xlwt.Workbook(encoding='utf-8')
    newSheet = wbk.add_sheet('Sheet1', cell_overwrite_ok=True)
    for j in range(0, sheet.ncols):
        newSheet.write(0, j, sheet.col_values(j)[0])
    for i in range(1, sheet.nrows):
        for j in range(0, sheet.ncols):
            if j > 0:
                newSheet.write(i, j, math.sqrt(sheet.row_values(i)[j]))
            else:
                newSheet.write(i, j, sheet.row_values(i)[j])
    wbk.save('new_py_excel.xls')

csv()
txt()
excel()

"""
作者：ZK
"""
import pandas as pd
import math

# 将 Excel 转换为 TXT 文件
def excel_to_txt(excel_file_path, txt_file_path):
    df = pd.read_excel(excel_file_path)
    df.to_csv(txt_file_path, sep='\t', index=False)

# 将 Excel 转换为 CSV 文件
def excel_to_csv(excel_file_path, csv_file_path):
    df = pd.read_excel(excel_file_path)
    df.to_csv(csv_file_path, index=False)

# 读取 TXT 文件，对数字开根号处理，并输出为 TXT格式
def read_txt(txt_file_path):
    df = pd.read_csv(txt_file_path, header=0,delimiter='\t',encoding='utf-8')
    df['数据1'] = df['数据1'].apply(math.sqrt)
    df['数据2'] = df['数据2'].apply(math.sqrt)
    df.to_csv(r'E:\Pythonxx\data_out.txt', sep='\t', index=False)

# 读取 CSV 文件，对数字开根号处理，并输出为 CSV格式
def read_csv(csv_file_path):
    df = pd.read_csv(csv_file_path,header=0,encoding='utf-8')
    df['数据1'] = df['数据1'].apply(math.sqrt)
    df['数据2'] = df['数据2'].apply(math.sqrt)
    df.to_csv(r'E:\Pythonxx\data_out.csv', index=False)

# 读取 Excel 文件，对数字开根号处理，并输出为Excel 格式
def read_excel(excel_file_path):
    df = pd.read_excel(excel_file_path,header=0)
    df['数据1'] = df['数据1'].apply(math.sqrt)
    df['数据2'] = df['数据2'].apply(math.sqrt)
    df.to_excel(r'E:\Pythonxx\data_out.xlsx', index=False)

#  实数转时间
def date(para):
    delta = pd.Timedelta(str(int(para))+'days')
    time = pd.to_datetime('1899-12-30') + delta
    return time

# 文件路径
excel_file_path =r'E:\Pythonxx\data-excel.xlsx'
txt_file_path = r'E:\Pythonxx\data-txt.txt'
csv_file_path = r'E:\Pythonxx\data-csv.csv'

# 将 Excel 转换为 TXT 和 CSV
excel_to_txt(excel_file_path, txt_file_path)
excel_to_csv(excel_file_path, csv_file_path)

# 读取 TXT、CSV 和 Excel 文件，并输出为三种格式
read_txt(txt_file_path)
read_csv(csv_file_path)
read_excel(excel_file_path)