5、结构化数据分析

# 打开文件
fo = open("test.txt", "w+")
print("文件名: ", fo.name)
str = '''www.sugonedu.com01
www.sugonedu.com02
www.sugonedu.com03
www.sugonedu.com04
www.sugonedu.com05
'''
line = fo.write(str)
# 关闭文件
fo.close()

fo = open("test.txt", "r+")
line = fo.read()
print("读取的字符串: %s" % (line))
# 关闭文件
fo.close()

fo = open("test.txt", "r+")
line = fo.read(10)
print("读取的字符串: %s" % (line))
# 关闭文件
fo.close()

fo = open("test.txt", "r+")
line = fo.readline()
print("读取第一行 %s" % (line))
line = fo.readline()
print("读取第二行 %s" % (line))
# 关闭文件
fo.close()

fo = open("test.txt", "r")
# 依次读取每行
for line in fo.readlines():
    # 去掉每行头尾空白
    line = line.strip()
    print("读取的数据为: %s" % (line))
    # 关闭文件
    fo.close()

fo = open("test.txt", "r+")
str = "www.sugonedu.com06\n"
# 在文件末尾写入一行
fo.seek(0, 2)
line = fo.write(str)
# 关闭文件
fo.close()

# 打开文件
fo = open("test.txt", "r+")
print("文件名为: ", fo.name)
# 换行需要制定换行符\n
strs = ["www.sugonedu.com07\n",
        "www.sugonedu.com08\n"]
# 在文件末尾写入
fo.seek(0, 2)
fo.writelines(strs)
# 关闭文件
fo.close()

# 导入os模块
import os

# 输出当前目录
print('当前目录为%s' % os.getcwd())
print('test.txt的绝对路径为%s' % os.path.abspath('test.txt'))
print('/home/ubuntu和test.txt路径拼接结果为%s' % os.path.join('/home/ubuntu', 'test.txt'))
# 判断存在的路径
print('/home/ubuntu路径是否存在=%s' % os.path.exists('/home/ubuntu'))
# 判断不存在的路径
print('/home/hello路径是否存在=%s' % os.path.exists('/home/hello'))
# 判断存在的文件
print('/home/ubuntu/test.txt文件是否存在=%s' % os.path.exists('/home/ubuntu/test.txt'))
# 判断不存在的文件
print('/home/ubuntu/aaa.txt文件是否存在=%s' % os.path.exists('/home/ubuntu/aaa.txt'))

# 创建的目录
path = "/home/ubuntu/testdir"
os.mkdir(path, 0o755)
print("目录已创建")
# 创建的目录
path = "/home/ubuntu/monthly/daily"
os.makedirs(path, 0o777)
print("路径被创建")

# 显示文件"test.txt"信息
statinfo = os.stat('test.txt')
print(statinfo)

# 重命名目录
os.renames("/home/ubuntu/testdir", "/home/ubuntu/newdir")
# 重命名文件
os.renames("test.txt", "newdir/aanew.txt")
os.rmdir("/home/ubuntu/monthly/daily")
os.remove("newdir/aanew.txt")
for root, dirs, files in os.walk("/home/ubuntu", topdown=False):
    for name in files:
        print(os.path.join(root, name))
    for name in dirs:
        print(os.path.join(root, name))

import csv

header = ['姓名', '语文', '数学', '英语']
data = [['张三', '98', '80', '87'],
        ['李四', '65', '92', '78'],
        ['王五', '83', '78', '93'],
        ['赵六', '54', '66', '43'],
        ['刘七', '72', '75', '69']]
with open('scores.csv', 'w', encoding='utf-8', newline='') as f: writer = csv.writer(f)
writer.writerow(header)
writer.writerows(data)

import csv

header = ['姓名', '语文', '数学', '英语']
data = [{'姓名': '张飞', '语文': '43', '数学': '53', '英语': '49'},
        {'姓名': '赵云', '语文': '95', '数学': '100', '英语': '98'}]
with open('scores2.csv', 'w', encoding='utf-8', newline='') as f:
    writer = csv.DictWriter(f, header)
    writer.writeheader()
    writer.writerows(data)

import csv

with open('scores.csv', encoding='utf-8') as f:
    reader = csv.reader(f)
    header = next(reader)
    print(header)
    for row in reader:
        print(row)

import csv

with open('scores.csv', encoding='utf-8') as f:
    reader = csv.DictReader(f)
    for row in reader:
        if row['姓名'] == '张三':
            print('姓名=%s, 语文成绩=%s' % (row['姓名'], row['语文']))

import json

data = [
    {'姓名': '张三', '语文': '98', '数学': '80', '英语': '87'},
    {'姓名': '李四', '语文': '65', '数学': '92', '英语': '78'},
    {'姓名': '王五', '语文': '83', '数学': '78', '英语': '93'},
    {'姓名': '赵六', '语文': '54', '数学': '66', '英语': '43'},
    {'姓名': '刘七', '语文': '72', '数学': '75', '英语': '69'}]
with open("scores.json", "w", encoding='utf-8') as f:
    # indent 超级好用，格式化保存字典，默认为None，小于0为零个空格
    json.dump(data, f, indent=4, ensure_ascii=False)

import json

with open("scores.json", "r", encoding='utf-8') as f:
    datas = json.load(f)
    for data in datas:
        if data['姓名'] == '张三':
            print(f'姓名：{data["姓名"]},语文成绩:{data["语文"]}')

import pickle

data = [
    {'姓名': '张三', '语文': '98', '数学': '80', '英语': '87'},
    {'姓名': '李四', '语文': '65', '数学': '92', '英语': '78'},
    {'姓名': '王五', '语文': '83', '数学': '78', '英语': '93'},
    {'姓名': '赵六', '语文': '54', '数学': '66', '英语': '43'},
    {'姓名': '刘七', '语文': '72', '数学': '75', '英语': '69'}]
with open("scores.dmp", "wb") as f:
    # indent 超级好用，格式化保存字典，默认为None，小于0为零个空格
    pickle.dump(data, f)

import pickle

with open("scores.dmp", "rb") as f:
    datas = pickle.load(f)
for data in datas:
    if data['姓名'] == '张三':
        print(f'姓名：{data["姓名"]},语文成绩:{data["语文"]}')