import numpy as np
import pandas as pd
from pandas import Series,DataFrame
import matplotlib.pyplot as plt
from pylab import mpl
mpl.rcParams[‘font.sans-serif‘] = [‘FangSong‘] # 指定默认字体
mpl.rcParams[‘axes.unicode_minus‘] = False # 解决保存图像是负号‘-‘显示为方块的问题

ferrara1 = pd.read_csv(‘./ferrara_150715.csv‘)
ferrara2 = pd.read_csv(‘./ferrara_250715.csv‘)
ferrara3 = pd.read_csv(‘./ferrara_270615.csv‘)
ferrara=pd.concat([ferrara1,ferrara2,ferrara3],ignore_index=True)

torino1 = pd.read_csv(‘./torino_150715.csv‘)
torino2 = pd.read_csv(‘./torino_250715.csv‘)
torino3 = pd.read_csv(‘./torino_270615.csv‘)
torino = pd.concat([torino1,torino2,torino3],ignore_index=True) 

mantova1 = pd.read_csv(‘./mantova_150715.csv‘)
mantova2 = pd.read_csv(‘./mantova_250715.csv‘)
mantova3 = pd.read_csv(‘./mantova_270615.csv‘)
mantova = pd.concat([mantova1,mantova2,mantova3],ignore_index=True) 

milano1 = pd.read_csv(‘./milano_150715.csv‘)
milano2 = pd.read_csv(‘./milano_250715.csv‘)
milano3 = pd.read_csv(‘./milano_270615.csv‘)
milano = pd.concat([milano1,milano2,milano3],ignore_index=True) 

ravenna1 = pd.read_csv(‘./ravenna_150715.csv‘)
ravenna2 = pd.read_csv(‘./ravenna_250715.csv‘)
ravenna3 = pd.read_csv(‘./ravenna_270615.csv‘)
ravenna = pd.concat([ravenna1,ravenna2,ravenna3],ignore_index=True)

asti1 = pd.read_csv(‘./asti_150715.csv‘)
asti2 = pd.read_csv(‘./asti_250715.csv‘)
asti3 = pd.read_csv(‘./asti_270615.csv‘)
asti = pd.concat([asti1,asti2,asti3],ignore_index=True)

bologna1 = pd.read_csv(‘./bologna_150715.csv‘)
bologna2 = pd.read_csv(‘./bologna_250715.csv‘)
bologna3 = pd.read_csv(‘./bologna_270615.csv‘)
bologna = pd.concat([bologna1,bologna2,bologna3],ignore_index=True)

piacenza1 = pd.read_csv(‘./piacenza_150715.csv‘)
piacenza2 = pd.read_csv(‘./piacenza_250715.csv‘)
piacenza3 = pd.read_csv(‘./piacenza_270615.csv‘)
piacenza = pd.concat([piacenza1,piacenza2,piacenza3],ignore_index=True)

cesena1 = pd.read_csv(‘./cesena_150715.csv‘)
cesena2 = pd.read_csv(‘./cesena_250715.csv‘)
cesena3 = pd.read_csv(‘./cesena_270615.csv‘)
cesena = pd.concat([cesena1,cesena2,cesena3],ignore_index=True)

faenza1 = pd.read_csv(‘./faenza_150715.csv‘)
faenza2 = pd.read_csv(‘./faenza_250715.csv‘)
faenza3 = pd.read_csv(‘./faenza_270615.csv‘)
faenza = pd.concat([faenza1,faenza2,faenza3],ignore_index=True)

cesena.head(5)

city_list = [ferrara,torino,mantova,milano,ravenna,asti,bologna,piacenza,cesena,faenza]
for city in city_list:
    city.drop(labels=‘Unnamed: 0‘,axis=1,inplace=True)

city_max_temp = []
city_dist = []
for city in city_list:
    max_temp = city[‘temp‘].max()
    city_max_temp.append(max_temp)
    dist = city[‘dist‘][0]
    city_dist.append(dist)

city_max_temp

city_dist

plt.scatter(city_dist,city_max_temp)
plt.xlabel(‘距离‘)
plt.ylabel(‘最高温度‘)
plt.title(‘距离和温度之间的关系图‘)

#找出所有的近海城市(温度和距离)
np_city_dist = np.array(city_dist)
np_city_max_temp = np.array(city_max_temp)

near_condition = np_city_dist < 100
near_city_dist = np_city_dist[near_condition]
near_city_max_temp = np_city_max_temp[near_condition]

plt.scatter(near_city_dist,near_city_max_temp)

#1.导包
from sklearn.linear_model import LinearRegression

#2.实例化模型对象
linner = LinearRegression()

#3.提取样本数据

#4.训练模型
linner.fit(near_city_dist.reshape(-1,1),near_city_max_temp)

#5.预测
linner.predict(38)

linner.score(near_city_dist.reshape(-1,1),near_city_max_temp)

#绘制回归曲线
x = np.linspace(10,70,num=100)
y = linner.predict(x.reshape(-1,1))

plt.scatter(near_city_dist,near_city_max_temp)
plt.scatter(x,y,marker=1)