import pandas as pd

# 讀取Excel文件（自動識別第一個(gè)sheet）
df = pd.read_excel('input.xlsx')

# 保存為TXT（默認(rèn)制表符分隔）
df.to_csv('output.txt', sep='\t', index=False, header=False)

import pandas as pd

# 讀取TXT文件（自動推斷分隔符）
df = pd.read_csv('input.txt', sep='\t')  # 明確指定分隔符更可靠

# 保存為Excel（自動創(chuàng)建.xlsx文件）
df.to_excel('output.xlsx', index=False)

import pandas as pd

# 讀取所有sheet
excel_file = pd.ExcelFile('multi_sheet.xlsx')
all_sheets = {sheet: pd.read_excel(excel_file, sheet_name=sheet) 
              for sheet in excel_file.sheet_names}

# 將每個(gè)sheet保存為單獨(dú)TXT文件
for sheet_name, df in all_sheets.items():
    df.to_csv(f'{sheet_name}.txt', sep='\t', index=False)

import pandas as pd

df = pd.read_excel('fixed_width.xlsx')

with open('output_fixed.txt', 'w') as f:
    for _, row in df.iterrows():
        # 假設(shè)需要：列1(10字符)、列2(15字符)、列3(8字符)
        line = f"{str(row['col1']):<10}{str(row['col2']):<15}{str(row['col3']):<8}\n"
        f.write(line)

# 指定引擎（處理舊版Excel時(shí)）
pd.read_excel('old_file.xls', engine='xlrd')

# 定義列數(shù)據(jù)類型（減少內(nèi)存占用）
dtypes = {
    'ID': 'int32',
    'Name': 'string',
    'Price': 'float32',
    'Date': 'datetime64[ns]'
}

df = pd.read_csv('data.txt', sep='\t', dtype=dtypes)

import pandas as pd
from concurrent.futuses import ThreadPoolExecutor
import os

def convert_file(file_path):
    if file_path.endswith('.xlsx'):
        df = pd.read_excel(file_path)
        txt_path = file_path.replace('.xlsx', '.txt')
        df.to_csv(txt_path, sep='\t', index=False)
        return f"Converted: {file_path} → {txt_path}"

# 獲取所有Excel文件
excel_files = [f for f in os.listdir() if f.endswith('.xlsx')]

# 使用4個(gè)線程并行處理
with ThreadPoolExecutor(max_workers=4) as executor:
    results = list(executor.map(convert_file, excel_files))

for result in results:
    print(result)

# 讀取時(shí)指定編碼
df = pd.read_csv('input.txt', sep='\t', encoding='gbk')  # 常見中文編碼

# 寫入時(shí)指定編碼
df.to_csv('output.txt', sep='\t', encoding='utf-8-sig')  # 帶BOM的UTF-8

# 讀取時(shí)轉(zhuǎn)換日期列
df = pd.read_excel('input.xlsx', parse_dates=['DateColumn'])

# 或讀取后轉(zhuǎn)換
df['DateColumn'] = pd.to_datetime(df['DateColumn'], unit='D', origin='1899-12-30')

# 讀取時(shí)指定低精度類型
dtypes = {'NumericCol': 'float32', 'ID': 'int32'}
df = pd.read_csv('large.txt', sep='\t', dtype=dtypes)

import dask.dataframe as dd

ddf = dd.read_csv('huge_file.txt', sep='\t')
ddf.to_excel('output.xlsx', index=False)  # 實(shí)際會分塊處理

import pandas as pd
from datetime import datetime

def process_bank_statement(txt_path):
    # 自定義讀取函數(shù)（處理固定寬度）
    def parse_line(line):
        return {
            'date': line[0:8],
            'type': line[8:12],
            'amount': float(line[12:22])/100,
            'balance': float(line[22:32])/100,
            'remark': line[32:].strip()
        }
    
    # 讀取TXT
    with open(txt_path, 'r', encoding='gbk') as f:
        lines = f.readlines()[1:]  # 跳過表頭
    
    data = [parse_line(line) for line in lines if line.strip()]
    df = pd.DataFrame(data)
    
    # 轉(zhuǎn)換日期格式
    df['date'] = pd.to_datetime(df['date'], format='%Y%m%d')
    
    # 添加分析列
    df['day_of_week'] = df['date'].dt.day_name()
    df['amount_category'] = pd.cut(df['amount'], 
                                  bins=[-1e6, -1000, 0, 1000, 1e6],
                                  labels=['大額支出','支出','收入','大額收入'])
    
    # 保存Excel
    output_path = f"processed_{datetime.now().strftime('%Y%m%d')}.xlsx"
    with pd.ExcelWriter(output_path) as writer:
        df.to_excel(writer, sheet_name='原始數(shù)據(jù)', index=False)
        
        # 添加匯總表
        summary = df.groupby(['day_of_week', 'amount_category']).size().unstack()
        summary.to_excel(writer, sheet_name='匯總分析')
    
    return output_path

# 使用示例
processed_file = process_bank_statement('bank_statement.txt')
print(f"處理完成，結(jié)果已保存至：{processed_file}")