自带库：math,time,datetime.os,open,random
三方库：numpy,pandas
math库
python
import math
print(f"平方根{math.sqrt(16)}")
print(f"幂运算{math.pow(2,3)}")
print(f"圆周率{math.pi}")
print(f"向上取整{math.ceil(3.3)}")
print(f"向下取整{math.floor(3.3)}")
print(f"绝对值{math.fabs(-3.3)}")
print(f"对数{math.log(5)}")
print(f"正弦{math.sin(math.pi/2)}")time:
python
import time
#获得当前时间戳
timestamp = time.time()
print(f"时间戳{timestamp}")
#获取当前的时间(将时间戳变得可读)
local_time = time.localtime(timestamp)
print(f"时间可读{time.strftime("%Y-%m-%d %H:%M:%S",local_time)}")
#获取结构化时间
print(time.localtime())
tm = time.localtime()
print(f"年{tm.tm_year},月{tm.tm_mon},日{tm.tm_mday}")datatime:
python
from datetime import datetime,date,timedelta
#获取当前时间
now = datetime.now()
print(f"当前时间{now}")
#创建指定时间
dt = datetime(2024,1,1,1,00,00)
print(f"{dt}")
#将时间格式化
formatted = now.strftime("%Y-%m-%d %H:%M:%S")
print(f"{formatted}")
#日期时间计算
now1 = now + timedelta(days=7)
print(f"七天后{now1}")
#日期对象
now2 = date.today()
print(f"{now2}")os:
python
import os
#获得当前目录
current_dir = os.getcwd()
print(f"当前目录{current_dir}")
#检查文件或目录是否存在
if os.path.exists("test.txt"):
print("test.txt文件存在")
else:
print("test.txt文件不存在")
#检查是否是文件
if os.path.isfile("test.txt"):
print("test.txt是文件")
#检查是否是目录
if os.path.isdir("."):
print("当前目录是文件夹")
# 列出目录中的文件和文件夹
files = os.listdir(".")
print("当前目录内容:",files[5]) #是显示前5个
# 获取文件大小
if os.path.exists("test.txt"):
size = os.path.getsize("test.txt")
print(f"{size}")
#路径操作：
files = os.path.join("fi","file.txt")
print(f"拼接后的路径{files}")
# 获取路径的目录名和文件名
dirname = os.path.dirname("/path/to/list.txt")
basename = os.path.basename("/path/to/list.txt")
print(f"目录名{dirname},文件名：{basename}")random:
python
import random
#生成随机数
num = random.randint(1,100)
print(f"生成随机数(1,100){num}")
#生成随机数浮点数(0,1)
num1 = random.random()
print(f"生成随机浮点数{num1:.2f}")
#从序列中选择一份
fruits = ["苹果","香蕉","橙子"]
num2 = random.choice(fruits)
print(f"随机从序列中选择{num2}")
#从序列中选择多个(不重复)
num3 = random.sample(fruits,2)
print(f"选择多个{num3}")
#打乱列表
rand = [1,2,3,4,5,6]
random.shuffle(rand)
print(f"{rand}")
#生成指定范围内的随机整数
rand_range = random.randrange(0,10)
print(f"{rand_range}")open:
python
with open("Student.txt","w",encoding="utf-8") as f:
f.write("1\n")
f.write("2\n")
print("写入完毕")
# 读取文件全部内容
with open("Student.txt","r",encoding="utf-8") as f:
content = f.read()
print("读取全部内容")
print(content)
# 逐行读取
with open("Student.txt","r",encoding="utf-8") as f:
for line in f:
print(line.strip())
# 读取所有行到列表
with open("Student.txt","r",encoding="utf-8") as f:
lines = f.readlines()
print(f"{lines}")
# 追加模式
with open("Student.txt","a",encoding="utf-8") as f:
f.write("追加内容")
print("OK")pandas:
核心数据结构：
Series： 一维数组，类似列表
DataFrame:二维表格，类似Excel表格
python
try:
import pandas as pd
data = {
"姓名":["张三","李四","王五","赵六"],
"年龄":[20,19,21,20],
"成绩":[85,90,88,92],
"班级":["一班","二班","三班","四班"]
}
df = pd.DataFrame(data)
print("创建的DataFrame")
print(df)
print(f"\nDataFrame形状,{df.shape}") #{行数,列数}
print(f"列名:{df.columns.tolist()}")
except ImportError:
print("pandas未安装,请运行:pip install pandas")读取csv文件：
python
try:
import pandas as pd
data = {
"姓名":["张三","李四","王五","赵六"],
"年龄":[20,19,21,20],
"成绩":[85,90,88,92],
"班级":["一班","二班","三班","四班"]
}
df = pd.DataFrame(data)
df.to_csv("students.csv",index=True,encoding="utf-8")
#读取csv文件
df_read = pd.read_csv("students.csv",encoding="utf-8")
print(df_read)
except ImportError:
print("pandas未安装,请运行: pip install pandas")index = True 和index= False的差别
True的时候 好像是多了个序号
False的时候
写入excel:
python
import pandas as pd
data1 = {
"姓名":["张三","李四","王五","赵六"],
"年龄":[20,19,21,20],
"成绩":[85,90,88,92],
"班级":["一班","二班","三班","四班"]
}
df1 = pd.DataFrame(data1)
data2 = {
"课程":["数学","语文","英语"],
"平均分":[87,85,86]
}
df2 = pd.DataFrame(data2)
#写入单个表
df1.to_excel("output.xlsx",index=False,sheet_name="学生信息")
#写入多个表
with pd.ExcelWriter("output.multi.xlsx",engine="openpyxl") as writer:
df1.to_excel(writer,sheet_name="学生信息",index=False)
df2.to_excel(writer,sheet_name="课程信息",index=False)条件
python
import pandas as pd
data1 = {
"姓名":["张三","李四","王五","赵六"],
"年龄":[20,19,21,20],
"成绩":[85,90,88,92],
"班级":["一班","二班","三班","四班"]
}
df1 = pd.DataFrame(data1)
print(df1[["姓名","成绩"]])
print(df1[df1["成绩"]>85])
print(df1[df1["班级"]=="一班"])
#使用iloc按位置选择
print(df1.iloc[0])
#使用iloc的位置选择
print(df1.iloc[0:2,0:2]) #不包含右边的约束
# data2 = {
# "课程":["数学","语文","英语"],
# "平均分":[87,85,86]
# }
# df2 = pd.DataFrame(data2)
# #写入单个表
# df1.to_excel("output.xlsx",index=False,sheet_name="学生信息")
# #写入多个表
# with pd.ExcelWriter("output.multi.xlsx",engine="openpyxl") as writer:
# df1.to_excel(writer,sheet_name="学生信息",index=False)
# df2.to_excel(writer,sheet_name="课程信息",index=False)同时包含也有
基本统计
print(f"平均值:[df["成绩"].mean():.2f]")
平均值： mean()
最小值： min()
最大值： max()
总和： sum()
标准差：std()
中位数: median()
分组统计：
print(df.groupby("班级")["成绩"].mean)
计数
print(df["班级"].value_counts())
怎么统计多个指标
print(df.groupby("班级").add({
"成绩":["max","min"],
"年龄":"mean"
}))
numpy
矩阵运算
python
try:
import numpy as np
arr1 = np.array([1,2,3,4,5])
arr2 = np.array([6,7,8,9,10])
#加减乘除
print("数组加:",arr1+arr2)
print("数组减:",arr1-arr2)
print("数组相乘",arr1*arr2)
print("数组相除",arr1/arr2)
print("数组的幂运算",arr1**2)
#标量与数组运算
print("每个元素加10",arr1+10)
print("每个元素乘以2",arr2*2)
# 矩阵运算
matrix1 = np.array([[1,2],[3,4]])
matrix2 = np.array([[5,6],[7,8]])
print("矩阵1\n",matrix1)
print("矩阵2\n",matrix2)
print("矩阵相乘\n",matrix1*matrix2)
print("矩阵点积\n",matrix1@matrix2)
print("矩阵点积\n",np.dot(matrix1,matrix2)) #第二种写法
except ImportError:
print("numpy未安装,pip install numpy")数组统计函数
python
try:
import numpy as np
arr = np.array([1,2,3,4,5,6,7,8,9])
arr2d = np.array([
[1,2,3],
[4,5,6],
[7,8,9]
])
print(f"数组{arr}")
print(f"平均值:{np.mean(arr)}")
#最大值一样的写法...
print(f"标准差:{np.std(arr):.2f}")
print(f"方差:{np.var(arr):.2f}")
print(f"二维数组",arr2d)
print(f"每列平均值",np.mean(arr2d,axis=0)) #等于0时沿着列的方向
print(f"每行平均值",np.mean(arr2d,axis=1)) #等于1时时每行
#累计求和
print(f"求和：{np.cumsum(arr)}")
print(f"累积积",np.cumprod([1,2,3,4]))
except ImportError:
print("numpy未安装,请运行:pip install numpy")