第 4 章 · 数据处理

# 写文件（没有会自动创建）
with open("note.txt", "w", encoding="utf-8") as f:
    f.write("码上问学\n")
    f.write("Python 第4章\n")

# 读文件
with open("note.txt", "r", encoding="utf-8") as f:
    content = f.read()
print(content)

# 生活化：把购物清单“存”下来，再读出来
with open("shopping.txt", "w", encoding="utf-8") as f:
    for item in ["牛奶", "鸡蛋", "面包"]:
        f.write(item + "\n")

with open("shopping.txt", "r", encoding="utf-8") as f:
    items = f.read().splitlines()
print("要买：", items)
print("共", len(items), "件")

# 实战片段：逐行读取并标注行号（处理日志/数据文件常用）
with open("notes.txt", "w", encoding="utf-8") as f:
    f.write("买菜\n取快递\n写作业\n")

with open("notes.txt", "r", encoding="utf-8") as f:
    lines = f.readlines()

for i, line in enumerate(lines, 1):
    print(f"{i}. {line.strip()}")

import csv, json

# CSV：表格数据（逗号分隔）
rows = [["姓名", "分数"], ["张三", 90], ["李四", 85]]
with open("scores.csv", "w", newline="", encoding="utf-8") as f:
    w = csv.writer(f)
    w.writerows(rows)

# JSON：结构化的“键值”数据，前后端通用
data = {"class": "一班", "avg": 87.5, "top": ["张三", "李四"]}
with open("info.json", "w", encoding="utf-8") as f:
    json.dump(data, f, ensure_ascii=False, indent=2)

# 读回来
with open("info.json", "r", encoding="utf-8") as f:
    back = json.load(f)
print(back["top"])    # ['张三', '李四']

import csv

# 生活化：记一笔每天的开支，再统计总支出
records = [
    ["日期", "项目", "金额"],
    ["10-01", "早餐", 12],
    ["10-01", "公交", 4],
    ["10-02", "午餐", 25],
]
with open("ledger.csv", "w", newline="", encoding="utf-8") as f:
    csv.writer(f).writerows(records)

total = 0
with open("ledger.csv", "r", encoding="utf-8") as f:
    for row in csv.reader(f):
        if row[0] != "日期":
            total += int(row[2])
print("总支出：", total, "元")

import json

# 实战片段：把程序设置存成 JSON，再读回来
config = {"主题": "深色", "字体": 14, "自动保存": True}
text = json.dumps(config, ensure_ascii=False)
print("保存为：", text)

back = json.loads(text)
print("读取主题：", back["主题"])

import os, datetime

print(os.getcwd())                 # 当前目录
print(os.listdir("."))             # 当前目录下的文件列表
print(datetime.date.today())       # 今天日期
print(datetime.datetime.now().strftime("%Y-%m-%d %H:%M"))  # 格式化时间

import math

# 生活化：算一块圆形披萨的面积
r = 8
area = math.pi * r ** 2
print(f"半径 {r} 的披萨面积：{area:.1f}")

from collections import Counter

# 实战片段：统计一次投票结果（贴近项目里的“计数统计”）
votes = ["Python", "Java", "Python", "C++", "Python", "Java"]
result = Counter(votes)
print("各语言得票：", dict(result))
print("第一名：", result.most_common(1))

import pandas as pd

df = pd.DataFrame({
    "姓名": ["张三", "李四", "王五"],
    "数学": [90, 85, 77],
    "英语": [88, 92, 70],
})

print(df.mean(numeric_only=True))   # 每科平均分
print(df[df["数学"] > 80])          # 筛出数学 > 80 的行

# 生活化：记录一周步数，看看平均和达标天数
# （pandas 里一行：steps["步数"].mean() / steps[steps["步数"]>=10000]）
data = [
    ("一", 8000), ("二", 12000), ("三", 6000),
    ("四", 11000), ("五", 9000),
]
vals = [v for _, v in data]
print("平均每天：", sum(vals) // len(vals))
达标 = [d for d in data if d[1] >= 10000]
print("达标天数：", len(达标))

import csv

# 实战片段：读一份成绩 CSV 并做“一行 pandas”的等效统计
# （pandas 等效：df = pd.read_csv("score.csv"); print(df.describe())）
rows = []
with open("score.csv", "w", newline="", encoding="utf-8") as f:
    f.write("姓名,数学,英语\n张三,90,88\n李四,85,92\n王五,77,70\n")

with open("score.csv", "r", encoding="utf-8") as f:
    for row in csv.DictReader(f):
        rows.append((row["姓名"], int(row["数学"]), int(row["英语"])))

math_scores = [r[1] for r in rows]
eng_scores = [r[2] for r in rows]
print("数学：共", len(math_scores), "人 平均",
      round(sum(math_scores)/len(math_scores), 1))
print("英语：共", len(eng_scores), "人 平均",
      round(sum(eng_scores)/len(eng_scores), 1))
print("最高数学：", max(rows, key=lambda r: r[1])[0])