房價預測

資料集描述

資料共有81個特徵

SalePrice - the property’s sale price in dollars. This is the target variable that you’re trying to predict.
MSSubClass: The building class
MSZoning: The general zoning classification
LotFrontage: Linear feet of street connected to property
LotArea: Lot size in square feet
Street: Type of road access
Alley: Type of alley access
LotShape: General shape of property
LandContour: Flatness of the property
Utilities: Type of utilities available
LotConfig: Lot configuration
LandSlope: Slope of property
….

匯入所需模組

import numpy as np
import pandas as pd 

import matplotlib.pyplot as plt
import seaborn as sns
import math as mat

from scipy import stats
from scipy.stats import norm
from sklearn import preprocessing

import statsmodels.api as sm
from patsy import dmatrices

import warnings
warnings.filterwarnings('ignore'
 
)
%matplotlib inline

import sklearn.linear_model as LinReg
import sklearn.metrics as metrics

匯入資料

#loading the data 
data_train = pd.read_csv('../DATA/SalePrice_train.csv')
data_test = pd.read_csv('../DATA/SalePrice_test.csv')

資料共有81個特徵，為了便於說明只挑選7個特徵
OverallQual
GrLivArea
GarageCars
TotalBsmtSF
1stFlrSF
FullBath
YearBuilt
因為這些資料與房子的售賣價格相關性比較大

具體如何選擇特徵，見資料清理

資料預處理

data_train.shape

(1460, 81)  

vars = ['OverallQual', 'GrLivArea', 'GarageCars', 'TotalBsmtSF', 'FullBath','YearBuilt']
Y = data_train[['SalePrice']] #dim (1460, 1)
ID_train = data_train[['Id']] #dim (1460, 1)
ID_test = data_test[['Id']]   #dim (1459, 1)
#extract only the relevant feature with cross correlation >0.5 respect to SalePrice
X_matrix = data_train[vars]
X_matrix.shape  #dim (1460,6)

X_test = data_test[vars]  
X_test.shape   #dim (1459,6)

(1459, 6)

檢視丟失資料

#check for missing data:
#missing data
total = X_matrix.isnull().sum().sort_values(ascending=False)
percent = (X_matrix.isnull().sum()/X_matrix.count()).sort_values(ascending=False)
missing_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_data.head(20)
#no missing data in this training set

total = X_test.isnull().sum().sort_values(ascending=False)
percent = (X_test.isnull().sum()/X_test.count()).sort_values(ascending=False)
missing_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_data.head(20)
#missing data in this test set

#help(mat.ceil) #去上限

使用均值代替缺失的資料

#使用均值代替缺失的資料
X_test['TotalBsmtSF'] = X_test['TotalBsmtSF'].fillna(X_test['TotalBsmtSF'].mean())
X_test['GarageCars'] = X_test['GarageCars'].fillna(mat.ceil(X_test['GarageCars'].mean()))

total = X_test.isnull().sum().sort_values(ascending=False)
percent = (X_test.isnull().sum()/X_test.count()).sort_values(ascending=False)
missing_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
missing_data.head(20)

X_test.shape

(1459, 6)

• 然後預處理模組的特徵縮放和均值歸一化。 進一步提供了一個實用類StandardScaler，它實現了變換方法來計算訓練集上的均值和標準差，以便稍後能夠在測試集上重新應用相同的變換。

max_abs_scaler = preprocessing.MaxAbsScaler()
X_train_maxabs = max_abs_scaler.fit_transform(X_matrix)
print(X_train_maxabs)

[[ 0.7         0.30308401  0.5         0.1400982   0.66666667  0.99651741]       
 [ 0.6         0.22367955  0.5         0.20654664  0.66666667  0.98308458]     
 [ 0.7         0.31655441  0.5         0.15057283  0.66666667  0.99552239] 
 ...,    
 [ 0.7         0.41474654  0.25        0.18854337  0.66666667  0.96567164]
 [ 0.5         0.191067    0.25        0.17643208  0.33333333  0.97014925]  
 [ 0.5         0.22261609  0.25        0.20556465  0.33333333  0.97761194]] 

X_test_maxabs = max_abs_scaler.fit_transform(X_test)
print(X_test_maxabs)

[[ 0.5         0.17585868  0.2         0.17311089  0.25        0.97562189]   
 [ 0.6         0.26084396  0.2         0.26084396  0.25        0.97412935]    
 [ 0.5         0.31972522  0.4         0.18213935  0.5         0.99353234] 
 ..., 
 [ 0.5         0.24023553  0.4         0.24023553  0.25        0.97512438]   
 [ 0.5         0.19038273  0.          0.17899902  0.25        0.99104478]
 [ 0.7         0.39254171  0.6         0.19548577  0.5         0.99154229]]

模型訓練

lr=LinReg.LinearRegression().fit(X_train_maxabs,Y)

模型預測

Y_pred_train = lr.predict(X_train_maxabs)
print("Los Reg performance evaluation on Y_pred_train")
print("R-squared =", metrics.r2_score(Y, Y_pred_train))  

Los Reg performance evaluation on Y_pred_train   
R-squared = 0.768647335422 

Y_pred_test = lr.predict(X_test_maxabs)  
print("Lin Reg performance evaluation on X_test")
#print("R-squared =", metrics.r2_score(Y, Y_pred_test))
print("Coefficients =", lr.coef_)

Lin Reg performance evaluation on X_test 
Coefficients = [[ 205199.68775757  305095.8264889    58585.26325362  178302.68126933
   -16511.92112734  676458.9666186 ]] 

Logistic Regression

匯入模組

#匯入模組  
import pandas as pd
import numpy as np

資料預處理

#建立特徵列表表頭  
column_names = ['Sample code number','Clump Thickness','Uniformity of Cell Size','Uniformity of Cell Shape','Marginal Adhesion','Single Epithelial Cell Size','Bare Nuclei','Bland Chromatin','Normal Nucleoli','Mitoses','Class']
#使用pandas.read_csv函式從網上讀取資料集
data = pd.read_csv('DATA/data.csv',names=column_names)
#將？替換為標準缺失值表示
data = data.replace(to_replace='?',value = np.nan)
#丟棄帶有缺失值的資料(只要有一個維度有缺失便丟棄)
data = data.dropna(how='any')
#檢視data的資料量和維度
data.shape

(683, 11)

data.head(10)

由於原始資料沒有提供對應的測試樣本用於評估模型效能，這裡對帶標記的資料進行分割，25%作為測試集，其餘作為訓練集

#使用sklearn.cross_validation裡的train_test_split模組分割資料集
from sklearn.cross_validation import train_test_split
#隨機取樣25%的資料用於測試，剩下的75%用於構建訓練集
X_train,X_test,y_train,y_test = train_test_split(data[column_names[1:10]],data[column_names[10]],test_size = 0.25,random_state = 33)
#檢視訓練樣本的數量和類別分佈
y_train.value_counts()   

2    344
4    168
Name: Class, dtype: int64

#檢視測試樣本的數量和類別分佈
y_test.value_counts()

2    100
4     71
Name: Class, dtype: int64

建立模型，預測資料

#從sklearn.preprocessing匯入StandardScaler
from sklearn.preprocessing import StandardScaler
#從sklearn.linear_model匯入LogisticRegression（邏輯斯蒂迴歸）
from sklearn.linear_model import LogisticRegression
#從sklearn.linear_model匯入SGDClassifier（隨機梯度引數）
from sklearn.linear_model import SGDClassifier 

ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

lr = LogisticRegression()
#呼叫邏輯斯蒂迴歸，使用fit函式訓練模型引數
lr.fit(X_train,y_train)
lr_y_predict = lr.predict(X_test)
#呼叫隨機梯度的fit函式訓練模型

lr_y_predict

array([2, 2, 4, 4, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 4, 4, 4, 4, 2, 2, 4, 4,
       2, 4, 4, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 2,
       4, 2, 2, 4, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 2, 2, 4, 2, 2, 2,
       2, 4, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 4, 2, 4, 4,
       2, 2, 2, 2, 4, 4, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 
       2, 2, 4, 2, 2, 4, 4, 2, 4, 2, 2, 2, 4, 2, 2, 4, 4, 2, 4, 4, 2, 2, 2,
       2, 4, 2, 4, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 4, 2, 4, 2, 2, 2, 2, 4,
       4, 4, 2, 4, 2, 2, 4, 2, 4, 4], dtype=int64) 

使用線性分類模型進行良/惡性腫瘤預測任務的效能分析

#從sklearn.metrics匯入classification_report
from sklearn.metrics import classification_report

#使用邏輯斯蒂迴歸模型自帶的評分函式score獲得模型在測試集上的準確性結果
print('Accuracy of LR Classifier:',lr.score(X_test,y_test))
#使用classification_report模組獲得邏輯斯蒂模型其他三個指標的結果（召回率，精確率，調和平均數）
print(classification_report(y_test,lr_y_predict,target_names=['Benign','Malignant']))

Accuracy of LR Classifier: 0.988304093567
             precision    recall  f1-score   support

     Benign       0.99      0.99      0.99       100
  Malignant       0.99      0.99      0.99        71

avg / total       0.99      0.99      0.99       171