github地址 ： github.com/yangjinghit…

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
复制代码

data1 = pd.read_csv('lianjia1.csv', encoding='gbk')
data2 = pd.read_csv('lianjia2.csv', encoding='gbk')
data3 = pd.read_csv('lianjia3.csv', encoding='utf-8')
data4 = pd.read_csv('lianjia4.csv', encoding='utf-8')
data5 = pd.read_csv('lianjia5.csv', encoding='utf-8')
data6 = pd.read_csv('lianjia6.csv', encoding='utf-8')
data7 = pd.read_csv('lianjia7.csv', encoding='utf-8')
复制代码

data = pd.concat([data1, data2, data3, data4, data5,data6,data7])
复制代码

len(data)
复制代码

162227
复制代码

data = data.dropna()
复制代码

len(data)
复制代码

144531
复制代码

data.cjdanjia = np.round(data.cjdanjia.str.replace('元/平','').astype(np.float32).map(lambda x: x/10000), 2)
复制代码

data.cjshijian = pd.to_datetime(data.cjshijian.map(lambda x :x[5:]))
复制代码

data = data[data.cjxiaoqu.str.contains('远洋山水')]
复制代码

data = data.sort_values(by='cjshijian')
复制代码

data.set_index('cjshijian', inplace=True)
复制代码

data = data['2012':]
复制代码

#data.set_index('cjshijian',inplace=True)['2012':]
复制代码

data = data[data.cjdanjia > 1]
复制代码

data.head(3)
复制代码

data = data.assign(time = (data.index - pd.to_datetime('2012-01-01')).days)
复制代码

data = data[['time', 'cjdanjia']]
复制代码

data.head(5)
复制代码

plt.scatter(data.time, data.cjdanjia)
复制代码

<matplotlib.collections.PathCollection at 0x119fcb7f0>
复制代码

X = data.time
Y = data.cjdanjia
复制代码

from sklearn.linear_model import LinearRegression
复制代码

model = LinearRegression() model.fit(pd.DataFrame(X), Y)

model = LinearRegression() 
model.fit(pd.DataFrame(X), Y)
复制代码

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
复制代码

x = [[0], [1800]]
y = model.predict(pd.DataFrame(x))
plt.figure(figsize = (10, 8))
plt.plot(x, y)
plt.scatter(data.time, data.cjdanjia)
复制代码

<matplotlib.collections.PathCollection at 0x12068e400>
复制代码

model2 = LinearRegression()
model2.fit(pd.DataFrame({'x2': X*X, 'x1':X}), Y)
复制代码

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
复制代码

x = np.linspace(0, 1800)
y = model2.predict(pd.DataFrame({'x2': x*x, 'x1':x}))
plt.figure(figsize=(10,8))
plt.plot(x,y,color='r')
plt.scatter(data.time, data.cjdanjia)
复制代码

<matplotlib.collections.PathCollection at 0x10f357198>
复制代码

from sklearn.preprocessing import PolynomialFeatures
复制代码

q3 = PolynomialFeatures(degree=3)
复制代码

X3 = q3.fit_transform(pd.DataFrame(X))
复制代码

model3 = LinearRegression()
model3.fit(X3, Y)
复制代码

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
复制代码

x = np.linspace(0, 1800)
x_ = q3.fit_transform(pd.DataFrame(x))
y = model3.predict(x_)
plt.figure(figsize=(10,8))
plt.plot(x,y,color='r')
plt.scatter(data.time, data.cjdanjia)
复制代码

<matplotlib.collections.PathCollection at 0x11002f860>
复制代码