274 lines
7.8 KiB
Plaintext
274 lines
7.8 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# 使用说明：\n",
|
||
" 1.需要修改chdir到当前目录\n",
|
||
" 2.需要修改最后输出的文件名称\n",
|
||
" 3.依据情况需要修改保留的列数"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"import os"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"文件中所有CSV文件: ['ag888_2019.csv', 'ag888_2020.csv', 'ag888_2021.csv', 'ag888_2022.csv', 'ag888_2022_2023.csv', 'ag888_2023.csv']\n",
|
||
"需要筛选的文件名关键字: ['_2022']\n",
|
||
"使用新年份格式采集!!!\n",
|
||
"筛选结果后的CSV文件: ['ag888_2022.csv', 'ag888_2022_2023.csv']\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"os.chdir('E:/data/ag')\n",
|
||
"all_csv_files = [file for file in os.listdir('.') if file.endswith('.csv')]\n",
|
||
"all_csv_files = sorted(all_csv_files)\n",
|
||
"print(\"文件中所有CSV文件:\",all_csv_files)\n",
|
||
"\n",
|
||
"sp_chars = ['_2022']\n",
|
||
"sp_chars = sorted(sp_chars)\n",
|
||
"print(\"需要筛选的文件名关键字:\",sp_chars)\n",
|
||
"\n",
|
||
"# 设置后面数据的采集对于的行数# 用 \"old_type\" 或者 \"new_type\" 区分\n",
|
||
"if all(char in ['_2019','_2020','_2021'] for char in sp_chars):\n",
|
||
" year_type = 'old_type'\n",
|
||
" print(\"使用旧年份格式采集!!!\")\n",
|
||
"elif all(char in ['_2022','_2023'] for char in sp_chars):\n",
|
||
" year_type = 'new_type' \n",
|
||
" print(\"使用新年份格式采集!!!\")\n",
|
||
"else:\n",
|
||
" print(\"文件夹中CSV没有相关年份的数据或者新旧年份混用!!!\")\n",
|
||
"\n",
|
||
"csv_files = [file for file in all_csv_files if any(sp_char in file for sp_char in sp_chars)]\n",
|
||
"print(\"筛选结果后的CSV文件:\",csv_files)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = pd.DataFrame()\n",
|
||
"for f in csv_files:\n",
|
||
" if year_type == 'old_type':\n",
|
||
" df_temp = pd.read_csv(\n",
|
||
" f,\n",
|
||
" usecols=[1, 2, 3, 4, 8, 13, 14, 15, 16],\n",
|
||
" names=[\n",
|
||
" \"统一代码\",\n",
|
||
" \"合约代码\",\n",
|
||
" \"时间\",\n",
|
||
" \"最新\",\n",
|
||
" \"成交量\",\n",
|
||
" \"买一价\",\n",
|
||
" \"卖一价\",\n",
|
||
" \"买一量\",\n",
|
||
" \"卖一量\",\n",
|
||
" ],\n",
|
||
" skiprows=1,\n",
|
||
" encoding=\"utf-8\",\n",
|
||
" )\n",
|
||
" elif year_type == 'new_type':\n",
|
||
" df_temp = pd.read_csv(\n",
|
||
" f,\n",
|
||
" usecols=[0, 1, 2, 5, 12, 21, 22, 23, 24, 25, 26, 44],\n",
|
||
" names=[\n",
|
||
" \"交易日\",\n",
|
||
" \"统一代码\",\n",
|
||
" \"合约代码\",\n",
|
||
" \"最新价\",\n",
|
||
" \"数量\",\n",
|
||
" \"最后修改时间\",\n",
|
||
" \"最后修改毫秒\",\n",
|
||
" \"申买价一\",\n",
|
||
" \"申买量一\",\n",
|
||
" \"申卖价一\",\n",
|
||
" \"申卖量一\",\n",
|
||
" \"业务日期\",\n",
|
||
" ],\n",
|
||
" skiprows=1,\n",
|
||
" encoding=\"utf-8\",\n",
|
||
" )\n",
|
||
"\n",
|
||
" # df_temp = pd.read_csv(f, usecols=[0,5], names=[\n",
|
||
" # 'datetime', 'volume'])\n",
|
||
" df = pd.concat([df, df_temp])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# 查看数据的头部和尾部：head()、tail()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.reset_index(drop=True, inplace=True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 查看dataframe的基本情况\n",
|
||
"df.info()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"# 等比复权,先不考虑\n",
|
||
"# df['复权因子'] = df['卖一价'].shift() / df['买一价']\n",
|
||
"df['复权因子'] = np.where(df['合约代码'] != df['合约代码'].shift(), df['卖一价'].shift() / df['买一价'], 1)\n",
|
||
"df['复权因子'] = df['复权因子'].fillna(1)\n",
|
||
"# df['复权因子'].loc[0] = 1\n",
|
||
"df['买一价_adj'] = df['买一价'] * df['复权因子'].cumprod()\n",
|
||
"df['卖一价_adj'] = df['卖一价'] * df['复权因子'].cumprod()\n",
|
||
"df['最新_adj'] = df['最新'] * df['复权因子'].cumprod()\n",
|
||
"# df['low_adj'] = df['low'] * adjust.cumprod()\n",
|
||
"# df['high_adj'] = df['high'] * adjust.cumprod()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 等差复权\n",
|
||
"df['复权因子'] = np.where(df['合约代码'] != df['合约代码'].shift(), df['申卖价一'].shift() - df['申买价一'], 0)\n",
|
||
"df['复权因子'] = df['复权因子'].fillna(0)\n",
|
||
"# df['复权因子'].loc[0] = 1\n",
|
||
"df['申买价一_adj'] = df['申买价一'] + df['复权因子'].cumsum()\n",
|
||
"df['申卖价一_adj'] = df['申卖价一'] + df['复权因子'].cumsum()\n",
|
||
"df['最新价_adj'] = df['最新价'] + df['复权因子'].cumsum()\n",
|
||
"# df['low_adj'] = df['low'] + df['复权因子'].cumsum()\n",
|
||
"# df['high_adj'] = df['high'] + df['复权因子'].cumsum()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 查找换期需要复权的索引\n",
|
||
"non_zero_indices = df[df['复权因子'] != 0].index\n",
|
||
"print(non_zero_indices)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 查看未调整买价、卖价和最新价的数据\n",
|
||
"df.loc[non_zero_indices[0]-5:non_zero_indices[0]+5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 将调整后的数值替换原来的值\n",
|
||
"df['申买价一'] = df['申买价一_adj']\n",
|
||
"df['申卖价一'] = df['申卖价一_adj']\n",
|
||
"df['最新价'] = df['最新价_adj']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 查看调整买价、卖价和最新价的数据\n",
|
||
"df.loc[non_zero_indices[0]-5:non_zero_indices[0]+5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 删除多余的值\n",
|
||
"del df['复权因子']\n",
|
||
"del df['申买价一_adj']\n",
|
||
"del df['申卖价一_adj']\n",
|
||
"del df['最新价_adj']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.loc[non_zero_indices[0]-5:non_zero_indices[0]+5]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df.to_csv('./ag888_2022_2023.csv', index=False)"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "orderflow",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.10.9"
|
||
},
|
||
"orig_nbformat": 4
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|