量化5个城市的PM2.5随时间的变化情况

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

一、加载数据

bj = pd.read_csv(r"PM2.5\BeijingPM20100101_20151231.csv")
cd = pd.read_csv(r"PM2.5\ChengduPM20100101_20151231.csv")
gz = pd.read_csv(r"PM2.5\GuangzhouPM20100101_20151231.csv")
sh = pd.read_csv(r"PM2.5\ShanghaiPM20100101_20151231.csv")
sy = pd.read_csv(r"PM2.5\ShenyangPM20100101_20151231.csv")

lst = [bj, cd, gz, sh, sy]

二、把分开的时间字符串通过periodIndex的方法转化为pandas的时间类型

for df in lst:
    period = pd.PeriodIndex(year=df["year"], month=df["month"], day=df["day"], hour=df["hour"], freq="H")
    df["datatime"] = period
    df.set_index("datatime", inplace=True)
    # print(df.head(5))

三、降采样

for i in range(len(lst)):
    lst[i] = lst[i].resample("14D").mean()

四、绘图

plt.figure(figsize=(40,20), dpi=80)

city = ["beijing", "chengdu", "guangzhou", "shanghai", "shenyang"]

for i in range(len(lst)):
    df = lst[i]
    data = df["PM_US Post"]
    
    _x = data.index
    _y = data.values

    plt.plot(range(len(_x)), _y, label=city[i])
    plt.xticks(range(0, len(_x), 1), list(_x)[::1], rotation=45)

    plt.title("PM2.5")
    plt.legend(loc='best')

plt.show()