Kaggle房价预测案例分享

在Jupyter Notebook运行可以显示图(--开头是输出的内容，需要注意下)
参考：https://github.com/AliceDudu/Kaggle-projects/blob/master/house-prices-advanced-regression-techniques/house-1-feature.ipynb

# 导入需要的包import pandas as pdimport numpy as npfrom sklearn.model_selection import cross_val_score, train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn.linear_model import LinearRegression, RidgeCV, LassoCV, ElasticNetCVfrom sklearn.metrics import mean_squared_error, make_scorerfrom scipy.stats import skewfrom IPython.display import displayimport matplotlib.pyplot as pltimport seaborn as sns%matplotlib inline# 获取训练数据train = pd.read_csv("train.csv")print("train : " + str(train.shape))--train : (1460, 81)# 获取测试数据test = pd.read_csv("test.csv")print("test : " + str(test.shape))--test : (1459, 80)train.head()

test.head()

# 合并数据 从'MSSubClass'列到'SaleCondition'列all_data = pd.concat((train.loc[:,'MSSubClass':'SaleCondition'],                      test.loc[:,'MSSubClass':'SaleCondition']))all_data.head()

# 查看重复项idsUnique = len(set(train.Id))idsTotal = train.shape[0]idsDupli = idsTotal - idsUniqueprint("There are " + str(idsDupli) + " duplicate IDs for " + str(idsTotal) + " total entries")# 删除Id列train.drop("Id", axis = 1, inplace = True)--There are 0 duplicate IDs for 1460 total entries# 查看重复项idsUnique = len(set(test.Id))idsTotal = test.shape[0]idsDupli = idsTotal - idsUniqueprint("There are " + str(idsDupli) + " duplicate IDs for " + str(idsTotal) + " total entries")# 删除Id列test.drop("Id", axis = 1, inplace = True)--There are 0 duplicate IDs for 1459 total entries# 寻找异常值，如 https://ww2.amstat.org/publications/jse/v19n3/decock.pdfplt.scatter(train.GrLivArea, train.SalePrice, c = "blue", marker = "s")plt.title("Looking for outliers")plt.xlabel("GrLivArea")plt.ylabel("SalePrice")plt.show()train = train[train.GrLivArea < 4000]

print("train : " + str(train.shape))--train : (1456, 80)all_data = pd.concat((train.loc[:,'MSSubClass':'SaleCondition'],                      test.loc[:,'MSSubClass':'SaleCondition']))all_data.head()

# 转换官方得分的目标train.SalePrice = np.log1p(train.SalePrice)y = train.SalePricedef fill_missing(dataset):    # 处理中值/平均值或最常见值无意义的特征的缺失值    # Alley : data description says NA means "no alley access"    dataset.loc[:, "Alley"] = dataset.loc[:, "Alley"].fillna("None")    # BedroomAbvGr : NA most likely means 0    dataset.loc[:, "BedroomAbvGr"] = dataset.loc[:, "BedroomAbvGr"].fillna(0)    # BsmtQual etc : data description says NA for basement features is "no basement"    dataset.loc[:, "BsmtQual"] = dataset.loc[:, "BsmtQual"].fillna("No")    dataset.loc[:, "BsmtCond"] = dataset.loc[:, "BsmtCond"].fillna("No")    dataset.loc[:, "BsmtExposure"] = dataset.loc[:, "BsmtExposure"].fillna("No")    dataset.loc[:, "BsmtFinType1"] = dataset.loc[:, "BsmtFinType1"].fillna("No")    dataset.loc[:, "BsmtFinType2"] = dataset.loc[:, "BsmtFinType2"].fillna("No")    dataset.loc[:, "BsmtFullBath"] = dataset.loc[:, "BsmtFullBath"].fillna(0)    dataset.loc[:, "BsmtHalfBath"] = dataset.loc[:, "BsmtHalfBath"].fillna(0)    dataset.loc[:, "BsmtUnfSF"] = dataset.loc[:, "BsmtUnfSF"].fillna(0)    # CentralAir : NA most likely means No    dataset.loc[:, "CentralAir"] = dataset.loc[:, "CentralAir"].fillna("N")    # Condition : NA most likely means Normal    dataset.loc[:, "Condition1"] = dataset.loc[:, "Condition1"].fillna("Norm")    dataset.loc[:, "Condition2"] = dataset.loc[:, "Condition2"].fillna("Norm")    # EnclosedPorch : NA most likely means no enclosed porch    dataset.loc[:, "EnclosedPorch"] = dataset.loc[:, "EnclosedPorch"].fillna(0)    # External stuff : NA most likely means average    dataset.loc[:, "ExterCond"] = dataset.loc[:, "ExterCond"].fillna("TA")    dataset.loc[:, "ExterQual"] = dataset.loc[:, "ExterQual"].fillna("TA")    # Fence : data description says NA means "no fence"    dataset.loc[:, "Fence"] = dataset.loc[:, "Fence"].fillna("No")    # FireplaceQu : data description says NA means "no fireplace"    dataset.loc[:, "FireplaceQu"] = dataset.loc[:, "FireplaceQu"].fillna("No")    dataset.loc[:, "Fireplaces"] = dataset.loc[:, "Fireplaces"].fillna(0)    # Functional : data description says NA means typical    dataset.loc[:, "Functional"] = dataset.loc[:, "Functional"].fillna("Typ")    # GarageType etc : data description says NA for garage features is "no garage"    dataset.loc[:, "GarageType"] = dataset.loc[:, "GarageType"].fillna("No")    dataset.loc[:, "GarageFinish"] = dataset.loc[:, "GarageFinish"].fillna("No")    dataset.loc[:, "GarageQual"] = dataset.loc[:, "GarageQual"].fillna("No")    dataset.loc[:, "GarageCond"] = dataset.loc[:, "GarageCond"].fillna("No")    dataset.loc[:, "GarageArea"] = dataset.loc[:, "GarageArea"].fillna(0)    dataset.loc[:, "GarageCars"] = dataset.loc[:, "GarageCars"].fillna(0)    # HalfBath : NA most likely means no half baths above grade    dataset.loc[:, "HalfBath"] = dataset.loc[:, "HalfBath"].fillna(0)    # HeatingQC : NA most likely means typical    dataset.loc[:, "HeatingQC"] = dataset.loc[:, "HeatingQC"].fillna("TA")    # KitchenAbvGr : NA most likely means 0    dataset.loc[:, "KitchenAbvGr"] = dataset.loc[:, "KitchenAbvGr"].fillna(0)    # KitchenQual : NA most likely means typical    dataset.loc[:, "KitchenQual"] = dataset.loc[:, "KitchenQual"].fillna("TA")    # LotFrontage : NA most likely means no lot frontage    dataset.loc[:, "LotFrontage"] = dataset.loc[:, "LotFrontage"].fillna(0)    # LotShape : NA most likely means regular    dataset.loc[:, "LotShape"] = dataset.loc[:, "LotShape"].fillna("Reg")    # MasVnrType : NA most likely means no veneer    dataset.loc[:, "MasVnrType"] = dataset.loc[:, "MasVnrType"].fillna("None")    dataset.loc[:, "MasVnrArea"] = dataset.loc[:, "MasVnrArea"].fillna(0)    # MiscFeature : data description says NA means "no misc feature"    dataset.loc[:, "MiscFeature"] = dataset.loc[:, "MiscFeature"].fillna("No")    dataset.loc[:, "MiscVal"] = dataset.loc[:, "MiscVal"].fillna(0)    # OpenPorchSF : NA most likely means no open porch    dataset.loc[:, "OpenPorchSF"] = dataset.loc[:, "OpenPorchSF"].fillna(0)    # PavedDrive : NA most likely means not paved    dataset.loc[:, "PavedDrive"] = dataset.loc[:, "PavedDrive"].fillna("N")    # PoolQC : data description says NA means "no pool"    dataset.loc[:, "PoolQC"] = dataset.loc[:, "PoolQC"].fillna("No")    dataset.loc[:, "PoolArea"] = dataset.loc[:, "PoolArea"].fillna(0)    # SaleCondition : NA most likely means normal sale    dataset.loc[:, "SaleCondition"] = dataset.loc[:, "SaleCondition"].fillna("Normal")    # ScreenPorch : NA most likely means no screen porch    dataset.loc[:, "ScreenPorch"] = dataset.loc[:, "ScreenPorch"].fillna(0)    # TotRmsAbvGrd : NA most likely means 0    dataset.loc[:, "TotRmsAbvGrd"] = dataset.loc[:, "TotRmsAbvGrd"].fillna(0)    # Utilities : NA most likely means all public utilities    dataset.loc[:, "Utilities"] = dataset.loc[:, "Utilities"].fillna("AllPub")    # WoodDeckSF : NA most likely means no wood deck    dataset.loc[:, "WoodDeckSF"] = dataset.loc[:, "WoodDeckSF"].fillna(0)        return datasettrain = fill_missing(train)train.head()用test得到test newtest_new = fill_missing(test)test_new.head()all_data = fill_missing(all_data)all_data.head()def num_to_cat(dataset):    # 一些数字特征实际上是真正的类别    dataset = dataset.replace({"MSSubClass" : {20 : "SC20", 30 : "SC30", 40 : "SC40", 45 : "SC45",                                           50 : "SC50", 60 : "SC60", 70 : "SC70", 75 : "SC75",                                           80 : "SC80", 85 : "SC85", 90 : "SC90", 120 : "SC120",                                           150 : "SC150", 160 : "SC160", 180 : "SC180", 190 : "SC190"},                           "MoSold" : {1 : "Jan", 2 : "Feb", 3 : "Mar", 4 : "Apr", 5 : "May", 6 : "Jun",                                       7 : "Jul", 8 : "Aug", 9 : "Sep", 10 : "Oct", 11 : "Nov", 12 : "Dec"}                          })    return datasettrain = num_to_cat(train)train.head()test_new = num_to_cat(test_new)test_new.head()all_data = num_to_cat(all_data)all_data.head()def order_cat(dataset):    # 当订单中有信息时，将一些分类功能编码为有序数字    dataset = dataset.replace({"Alley" : {"Grvl" : 1, "Pave" : 2},                           "BsmtCond" : {"No" : 0, "Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "BsmtExposure" : {"No" : 0, "Mn" : 1, "Av": 2, "Gd" : 3},                           "BsmtFinType1" : {"No" : 0, "Unf" : 1, "LwQ": 2, "Rec" : 3, "BLQ" : 4,                                             "ALQ" : 5, "GLQ" : 6},                           "BsmtFinType2" : {"No" : 0, "Unf" : 1, "LwQ": 2, "Rec" : 3, "BLQ" : 4,                                             "ALQ" : 5, "GLQ" : 6},                           "BsmtQual" : {"No" : 0, "Po" : 1, "Fa" : 2, "TA": 3, "Gd" : 4, "Ex" : 5},                           "ExterCond" : {"Po" : 1, "Fa" : 2, "TA": 3, "Gd": 4, "Ex" : 5},                           "ExterQual" : {"Po" : 1, "Fa" : 2, "TA": 3, "Gd": 4, "Ex" : 5},                           "FireplaceQu" : {"No" : 0, "Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "Functional" : {"Sal" : 1, "Sev" : 2, "Maj2" : 3, "Maj1" : 4, "Mod": 5,                                           "Min2" : 6, "Min1" : 7, "Typ" : 8},                           "GarageCond" : {"No" : 0, "Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "GarageQual" : {"No" : 0, "Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "HeatingQC" : {"Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "KitchenQual" : {"Po" : 1, "Fa" : 2, "TA" : 3, "Gd" : 4, "Ex" : 5},                           "LandSlope" : {"Sev" : 1, "Mod" : 2, "Gtl" : 3},                           "LotShape" : {"IR3" : 1, "IR2" : 2, "IR1" : 3, "Reg" : 4},                           "PavedDrive" : {"N" : 0, "P" : 1, "Y" : 2},                           "PoolQC" : {"No" : 0, "Fa" : 1, "TA" : 2, "Gd" : 3, "Ex" : 4},                           "Street" : {"Grvl" : 1, "Pave" : 2},                           "Utilities" : {"ELO" : 1, "NoSeWa" : 2, "NoSewr" : 3, "AllPub" : 4}}                         )    return datasettrain = order_cat(train)train.head()test_new = order_cat(test_new)test_new.head()all_data = order_cat(all_data)all_data.head()#增加新特征def new_feature(dataset):    # Create new features    # 1* Simplifications of existing features    dataset["SimplOverallQual"] = dataset.OverallQual.replace({1 : 1, 2 : 1, 3 : 1, # bad                                                           4 : 2, 5 : 2, 6 : 2, # average                                                           7 : 3, 8 : 3, 9 : 3, 10 : 3 # good                                                          })    dataset["SimplOverallCond"] = dataset.OverallCond.replace({1 : 1, 2 : 1, 3 : 1, # bad                                                           4 : 2, 5 : 2, 6 : 2, # average                                                           7 : 3, 8 : 3, 9 : 3, 10 : 3 # good                                                          })    dataset["SimplPoolQC"] = dataset.PoolQC.replace({1 : 1, 2 : 1, # average                                                 3 : 2, 4 : 2 # good                                                })    dataset["SimplGarageCond"] = dataset.GarageCond.replace({1 : 1, # bad                                                         2 : 1, 3 : 1, # average                                                         4 : 2, 5 : 2 # good                                                        })    dataset["SimplGarageQual"] = dataset.GarageQual.replace({1 : 1, # bad                                                         2 : 1, 3 : 1, # average                                                         4 : 2, 5 : 2 # good                                                        })    dataset["SimplFireplaceQu"] = dataset.FireplaceQu.replace({1 : 1, # bad                                                           2 : 1, 3 : 1, # average                                                           4 : 2, 5 : 2 # good                                                          })    dataset["SimplFireplaceQu"] = dataset.FireplaceQu.replace({1 : 1, # bad                                                           2 : 1, 3 : 1, # average                                                           4 : 2, 5 : 2 # good                                                          })    dataset["SimplFunctional"] = dataset.Functional.replace({1 : 1, 2 : 1, # bad                                                         3 : 2, 4 : 2, # major                                                         5 : 3, 6 : 3, 7 : 3, # minor                                                         8 : 4 # typical                                                        })    dataset["SimplKitchenQual"] = dataset.KitchenQual.replace({1 : 1, # bad                                                           2 : 1, 3 : 1, # average                                                           4 : 2, 5 : 2 # good                                                          })    dataset["SimplHeatingQC"] = dataset.HeatingQC.replace({1 : 1, # bad                                                       2 : 1, 3 : 1, # average                                                       4 : 2, 5 : 2 # good                                                      })    dataset["SimplBsmtFinType1"] = dataset.BsmtFinType1.replace({1 : 1, # unfinished                                                             2 : 1, 3 : 1, # rec room                                                             4 : 2, 5 : 2, 6 : 2 # living quarters                                                            })    dataset["SimplBsmtFinType2"] = dataset.BsmtFinType2.replace({1 : 1, # unfinished                                                             2 : 1, 3 : 1, # rec room                                                             4 : 2, 5 : 2, 6 : 2 # living quarters                                                            })    dataset["SimplBsmtCond"] = dataset.BsmtCond.replace({1 : 1, # bad                                                     2 : 1, 3 : 1, # average                                                     4 : 2, 5 : 2 # good                                                    })    dataset["SimplBsmtQual"] = dataset.BsmtQual.replace({1 : 1, # bad                                                     2 : 1, 3 : 1, # average                                                     4 : 2, 5 : 2 # good                                                    })    dataset["SimplExterCond"] = dataset.ExterCond.replace({1 : 1, # bad                                                       2 : 1, 3 : 1, # average                                                       4 : 2, 5 : 2 # good                                                      })    dataset["SimplExterQual"] = dataset.ExterQual.replace({1 : 1, # bad                                                       2 : 1, 3 : 1, # average                                                       4 : 2, 5 : 2 # good                                                      })    # 2* Combinations of existing features    # 2* Combinations of existing features    # Overall quality of the house    dataset["OverallGrade"] = dataset["OverallQual"] * dataset["OverallCond"]    # Overall quality of the garage    dataset["GarageGrade"] = dataset["GarageQual"] * dataset["GarageCond"]    # Overall quality of the exterior    dataset["ExterGrade"] = dataset["ExterQual"] * dataset["ExterCond"]    # Overall kitchen score    dataset["KitchenScore"] = dataset["KitchenAbvGr"] * dataset["KitchenQual"]    # Overall fireplace score    dataset["FireplaceScore"] = dataset["Fireplaces"] * dataset["FireplaceQu"]    # Overall garage score    dataset["GarageScore"] = dataset["GarageArea"] * dataset["GarageQual"]    # Overall pool score    dataset["PoolScore"] = dataset["PoolArea"] * dataset["PoolQC"]    # Simplified overall quality of the house    dataset["SimplOverallGrade"] = dataset["SimplOverallQual"] * dataset["SimplOverallCond"]    # Simplified overall quality of the exterior    dataset["SimplExterGrade"] = dataset["SimplExterQual"] * dataset["SimplExterCond"]    # Simplified overall pool score    dataset["SimplPoolScore"] = dataset["PoolArea"] * dataset["SimplPoolQC"]    # Simplified overall garage score    dataset["SimplGarageScore"] = dataset["GarageArea"] * dataset["SimplGarageQual"]    # Simplified overall fireplace score    dataset["SimplFireplaceScore"] = dataset["Fireplaces"] * dataset["SimplFireplaceQu"]    # Simplified overall kitchen score    dataset["SimplKitchenScore"] = dataset["KitchenAbvGr"] * dataset["SimplKitchenQual"]    # Total number of bathrooms    dataset["TotalBath"] = dataset["BsmtFullBath"] + (0.5 * dataset["BsmtHalfBath"]) + \    dataset["FullBath"] + (0.5 * dataset["HalfBath"])    # Total SF for house (incl. basement)    dataset["AllSF"] = dataset["GrLivArea"] + dataset["TotalBsmtSF"]    # Total SF for 1st + 2nd floors    dataset["AllFlrsSF"] = dataset["1stFlrSF"] + dataset["2ndFlrSF"]    # Total SF for porch    dataset["AllPorchSF"] = dataset["OpenPorchSF"] + dataset["EnclosedPorch"] + \    dataset["3SsnPorch"] + dataset["ScreenPorch"]    # Has masonry veneer or not    dataset["HasMasVnr"] = dataset.MasVnrType.replace({"BrkCmn" : 1, "BrkFace" : 1, "CBlock" : 1,                                                    "Stone" : 1, "None" : 0})    # House completed before sale or not    dataset["BoughtOffPlan"] = dataset.SaleCondition.replace({"Abnorml" : 0, "Alloca" : 0, "AdjLand" : 0,                                                           "Family" : 0, "Normal" : 0, "Partial" : 1})        return datasettrain = new_feature(train)train.head()test_new = new_feature(test_new)test_new.head()all_data = new_feature(all_data)all_data.head()# 找到最重要的字段# Find most important features relative to targetprint("Find most important features relative to target")corr = train.corr()corr.sort_values(["SalePrice"], ascending = False, inplace = True)print(corr.SalePrice)输出内容：Find most important features relative to targetSalePrice            1.000OverallQual          0.819AllSF                0.817AllFlrsSF            0.729GrLivArea            0.719SimplOverallQual     0.708ExterQual            0.681GarageCars           0.680TotalBath            0.673KitchenQual          0.667GarageArea           0.655BsmtQual             0.653TotalBsmtSF          0.642SimplExterQual       0.636GarageScore          0.6181stFlrSF             0.614SimplKitchenQual     0.610OverallGrade         0.604FullBath             0.591YearBuilt            0.589ExterGrade           0.587SimplGarageScore     0.585SimplBsmtQual        0.578YearRemodAdd         0.569GarageYrBlt          0.544TotRmsAbvGrd         0.533SimplOverallGrade    0.527SimplKitchenScore    0.523SimplExterGrade      0.488Fireplaces           0.487                     ...  GarageQual           0.192GarageGrade          0.184GarageCond           0.172PoolQC               0.164SimplFunctional      0.137Functional           0.136ScreenPorch          0.124SimplPoolQC          0.122SimplBsmtCond        0.104Street               0.0583SsnPorch            0.056ExterCond            0.051SimplGarageQual      0.047PoolArea             0.041Utilities            0.013BsmtFinSF2           0.006SimplGarageCond     -0.015BsmtHalfBath        -0.015MiscVal             -0.020SimplBsmtFinType2   -0.020SimplOverallCond    -0.028BsmtFinType2        -0.030YrSold              -0.034OverallCond         -0.037LowQualFinSF        -0.038LandSlope           -0.040SimplExterCond      -0.042KitchenAbvGr        -0.148EnclosedPorch       -0.149LotShape            -0.286Name: SalePrice, dtype: float64def poly_feature(dataset):    # Create new features    # 3* Polynomials on the top 10 existing features    dataset["OverallQual-s2"] = dataset["OverallQual"] ** 2    dataset["OverallQual-s3"] = dataset["OverallQual"] ** 3    dataset["OverallQual-Sq"] = np.sqrt(dataset["OverallQual"])    dataset["AllSF-2"] = dataset["AllSF"] ** 2    dataset["AllSF-3"] = dataset["AllSF"] ** 3    dataset["AllSF-Sq"] = np.sqrt(dataset["AllSF"])    dataset["AllFlrsSF-2"] = dataset["AllFlrsSF"] ** 2    dataset["AllFlrsSF-3"] = dataset["AllFlrsSF"] ** 3    dataset["AllFlrsSF-Sq"] = np.sqrt(dataset["AllFlrsSF"])    dataset["GrLivArea-2"] = dataset["GrLivArea"] ** 2    dataset["GrLivArea-3"] = dataset["GrLivArea"] ** 3    dataset["GrLivArea-Sq"] = np.sqrt(dataset["GrLivArea"])    dataset["SimplOverallQual-s2"] = dataset["SimplOverallQual"] ** 2    dataset["SimplOverallQual-s3"] = dataset["SimplOverallQual"] ** 3    dataset["SimplOverallQual-Sq"] = np.sqrt(dataset["SimplOverallQual"])    dataset["ExterQual-2"] = dataset["ExterQual"] ** 2    dataset["ExterQual-3"] = dataset["ExterQual"] ** 3    dataset["ExterQual-Sq"] = np.sqrt(dataset["ExterQual"])    dataset["GarageCars-2"] = dataset["GarageCars"] ** 2    dataset["GarageCars-3"] = dataset["GarageCars"] ** 3    dataset["GarageCars-Sq"] = np.sqrt(dataset["GarageCars"])    dataset["TotalBath-2"] = dataset["TotalBath"] ** 2    dataset["TotalBath-3"] = dataset["TotalBath"] ** 3    dataset["TotalBath-Sq"] = np.sqrt(dataset["TotalBath"])    dataset["KitchenQual-2"] = dataset["KitchenQual"] ** 2    dataset["KitchenQual-3"] = dataset["KitchenQual"] ** 3    dataset["KitchenQual-Sq"] = np.sqrt(dataset["KitchenQual"])    dataset["GarageScore-2"] = dataset["GarageScore"] ** 2    dataset["GarageScore-3"] = dataset["GarageScore"] ** 3    dataset["GarageScore-Sq"] = np.sqrt(dataset["GarageScore"])        return datasettrain = poly_feature(train)train.head()test_new = poly_feature(test_new)test_new.head()all_data = poly_feature(all_data)all_data.head()# train# 区分数值特征（减去目标）和分类特征 # Differentiate numerical features (minus the target) and categorical featurescategorical_features = train.select_dtypes(include = ["object"]).columnsnumerical_features = train.select_dtypes(exclude = ["object"]).columnsnumerical_features = numerical_features.drop("SalePrice")print("Numerical features : " + str(len(numerical_features)))print("Categorical features : " + str(len(categorical_features)))train_num = train[numerical_features]train_cat = train[categorical_features]--Numerical features : 118--Categorical features : 25因为有第一列ID# test_new# Differentiate numerical features (minus the target) and categorical featurescategorical_features = test_new.select_dtypes(include = ["object"]).columnsnumerical_features = test_new.select_dtypes(exclude = ["object"]).columns# numerical_features = numerical_features.drop("SalePrice")print("Numerical features : " + str(len(numerical_features)))print("Categorical features : " + str(len(categorical_features)))test_new_num = test_new[numerical_features]test_new_cat = test_new[categorical_features]--Numerical features : 120--Categorical features : 24# all_data# Differentiate numerical features (minus the target) and categorical featurescategorical_features = all_data.select_dtypes(include = ["object"]).columnsnumerical_features = all_data.select_dtypes(exclude = ["object"]).columns# numerical_features = numerical_features.drop("SalePrice")print("Numerical features : " + str(len(numerical_features)))print("Categorical features : " + str(len(categorical_features)))all_data_num = all_data[numerical_features]all_data_cat = all_data[categorical_features]--Numerical features : 117--Categorical features : 26# Handle remaining missing values for numerical features by using median as replacementprint("NAs for numerical features in train : " + str(train_num.isnull().values.sum()))train_num = train_num.fillna(train_num.median())print("Remaining NAs for numerical features in train : " + str(train_num.isnull().values.sum()))--NAs for numerical features in train : 11431--Remaining NAs for numerical features in train : 0# Handle remaining missing values for numerical features by using median as replacementprint("NAs for numerical features in test_new : " + str(test_new_num.isnull().values.sum()))test_new_num = test_new_num.fillna(test_new_num.median())print("Remaining NAs for numerical features in test_new : " + str(test_new_num.isnull().values.sum()))--NAs for numerical features in test_new : 85--Remaining NAs for numerical features in test_new : 0# Handle remaining missing values for numerical features by using median as replacementprint("NAs for numerical features in all_data : " + str(all_data_num.isnull().values.sum()))all_data_num = all_data_num.fillna(all_data_num.median())print("Remaining NAs for numerical features in all_data : " + str(all_data_num.isnull().values.sum()))--NAs for numerical features in all_data : 166--Remaining NAs for numerical features in all_data : 0# 对变量数值特征进行Log变换，以减少异常值的影响# 由Alexandru Papiu的脚本启发：https：//www.kaggle.com/apapiu/house-prices-advanced-regression-techniques/regularized-linear-models# 作为一般的经验法则，绝对值> 0.5的偏度被认为至少适度地偏斜# Log transform of the skewed numerical features to lessen impact of outliers# Inspired by Alexandru Papiu's script : https://www.kaggle.com/apapiu/house-prices-advanced-regression-techniques/regularized-linear-models# As a general rule of thumb, a skewness with an absolute value > 0.5 is considered at least moderately skewedskewness = train_num.apply(lambda x: skew(x))skewness = skewness[abs(skewness) > 0.5]print(str(skewness.shape[0]) + " skewed numerical features to log transform")skewed_features = skewness.indextrain_num[skewed_features] = np.log1p(train_num[skewed_features])--87 skewed numerical features to log transform# Log transform of the skewed numerical features to lessen impact of outliers# Inspired by Alexandru Papiu's script : https://www.kaggle.com/apapiu/house-prices-advanced-regression-techniques/regularized-linear-models# As a general rule of thumb, a skewness with an absolute value > 0.5 is considered at least moderately skewedskewness = test_new_num.apply(lambda x: skew(x))skewness = skewness[abs(skewness) > 0.5]print(str(skewness.shape[0]) + " skewed numerical features to log transform")skewed_features = skewness.indextest_new_num[skewed_features] = np.log1p(test_new_num[skewed_features])--87 skewed numerical features to log transform# Log transform of the skewed numerical features to lessen impact of outliers# Inspired by Alexandru Papiu's script : https://www.kaggle.com/apapiu/house-prices-advanced-regression-techniques/regularized-linear-models# As a general rule of thumb, a skewness with an absolute value > 0.5 is considered at least moderately skewedskewness = all_data_num.apply(lambda x: skew(x))skewness = skewness[abs(skewness) > 0.5]print(str(skewness.shape[0]) + " skewed numerical features to log transform")skewed_features = skewness.indexall_data_num[skewed_features] = np.log1p(all_data_num[skewed_features])--86 skewed numerical features to log transform# 通过单热编码为分类值创建虚拟特征# Create dummy features for categorical values via one-hot encodingprint("NAs for categorical features in train : " + str(train_cat.isnull().values.sum()))train_cat = pd.get_dummies(train_cat)print("Remaining NAs for categorical features in train : " + str(train_cat.isnull().values.sum()))--NAs for categorical features in train : 2749--Remaining NAs for categorical features in train : 0# Create dummy features for categorical values via one-hot encodingprint("NAs for categorical features in test_new : " + str(test_new_cat.isnull().values.sum()))test_new_cat = pd.get_dummies(test_new_cat)print("Remaining NAs for categorical features in test_new : " + str(test_new_cat.isnull().values.sum()))--NAs for categorical features in test_new : 7--Remaining NAs for categorical features in test_new : 0# Create dummy features for categorical values via one-hot encodingprint("NAs for categorical features in all_data : " + str(all_data_cat.isnull().values.sum()))all_data_cat = pd.get_dummies(all_data_cat)print("Remaining NAs for categorical features in all_data : " + str(all_data_cat.isnull().values.sum()))--NAs for categorical features in all_data : 8--Remaining NAs for categorical features in all_data : 0test_new.head()# 合并分类和数值特性# Join categorical and numerical featurestrain = pd.concat([train_num, train_cat], axis = 1)print("New number of features : " + str(train.shape[1]))--New number of features : 295# Join categorical and numerical featurestest_new = pd.concat([test_new_num, test_new_cat], axis = 1)print("New number of features : " + str(test_new.shape[1]))--New number of features : 281# Join categorical and numerical featuresall_data = pd.concat([all_data_num, all_data_cat], axis = 1)print("New number of features : " + str(all_data.shape[1]))--New number of features : 320test_new.head()train.shape[0]--1456train = all_data[:train.shape[0]]test = all_data[train.shape[0]:]y.head()输出：0   12.2481   12.1092   12.3173   11.8494   12.429Name: SalePrice, dtype: float64#分割数据集# Partition the dataset in train + validation setsX_train, X_test, y_train, y_test = train_test_split(train, y, test_size = 0.3, random_state = 0)print("X_train : " + str(X_train.shape))print("X_test : " + str(X_test.shape))print("y_train : " + str(y_train.shape))print("y_test : " + str(y_test.shape))X_train : (1022, 295)X_test : (438, 295)y_train : (1022,)y_test : (438,)# Partition the dataset in train + validation setsX_train, X_test, y_train, y_test = train_test_split(train, y, test_size = 0.3, random_state = 0)print("X_train : " + str(X_train.shape))print("X_test : " + str(X_test.shape))print("y_train : " + str(y_train.shape))print("y_test : " + str(y_test.shape))X_train : (1019, 320)X_test : (437, 320)y_train : (1019,)y_test : (437,)# 标准化数值特性# Standardize numerical featuresstdSc = StandardScaler()X_train.loc[:, numerical_features] = stdSc.fit_transform(X_train.loc[:, numerical_features])X_test.loc[:, numerical_features] = stdSc.transform(X_test.loc[:, numerical_features])# 定义官方评分的误差度量：RMSE# Define error measure for official scoring : RMSEscorer = make_scorer(mean_squared_error, greater_is_better = False)def rmse_cv_train(model):    rmse= np.sqrt(-cross_val_score(model, X_train, y_train, scoring = scorer, cv = 10))    return(rmse)def rmse_cv_test(model):    rmse= np.sqrt(-cross_val_score(model, X_test, y_test, scoring = scorer, cv = 10))    return(rmse)# Linear Regressionlr = LinearRegression()lr.fit(X_train, y_train)# 看看训练和验证集的预测# Look at predictions on training and validation setprint("RMSE on Training set :", rmse_cv_train(lr).mean())print("RMSE on Test set :", rmse_cv_test(lr).mean())y_train_pred = lr.predict(X_train)y_test_pred = lr.predict(X_test)# 绘制残差# Plot residualsplt.scatter(y_train_pred, y_train_pred - y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_pred, y_test_pred - y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression")plt.xlabel("Predicted values")plt.ylabel("Residuals")plt.legend(loc = "upper left")plt.hlines(y = 0, xmin = 10.5, xmax = 13.5, color = "red")plt.show()# 绘制预测# Plot predictionsplt.scatter(y_train_pred, y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_pred, y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression")plt.xlabel("Predicted values")plt.ylabel("Real values")plt.legend(loc = "upper left")plt.plot([10.5, 13.5], [10.5, 13.5], c = "red")plt.show()--('RMSE on Training set :', 0.2994379109222855)--('RMSE on Test set :', 0.38449735311625766) 

# 2* Ridgeridge = RidgeCV(alphas = [0.01, 0.03, 0.06, 0.1, 0.3, 0.6, 1, 3, 6, 10, 30, 60])ridge.fit(X_train, y_train)alpha = ridge.alpha_print("Best alpha :", alpha)print("Try again for more precision with alphas centered around " + str(alpha))ridge = RidgeCV(alphas = [alpha * .6, alpha * .65, alpha * .7, alpha * .75, alpha * .8, alpha * .85,                          alpha * .9, alpha * .95, alpha, alpha * 1.05, alpha * 1.1, alpha * 1.15,                          alpha * 1.25, alpha * 1.3, alpha * 1.35, alpha * 1.4],                cv = 10)ridge.fit(X_train, y_train)alpha = ridge.alpha_print("Best alpha :", alpha)print("Ridge RMSE on Training set :", rmse_cv_train(ridge).mean())print("Ridge RMSE on Test set :", rmse_cv_test(ridge).mean())y_train_rdg = ridge.predict(X_train)y_test_rdg = ridge.predict(X_test)# Plot residualsplt.scatter(y_train_rdg, y_train_rdg - y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_rdg, y_test_rdg - y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression with Ridge regularization")plt.xlabel("Predicted values")plt.ylabel("Residuals")plt.legend(loc = "upper left")plt.hlines(y = 0, xmin = 10.5, xmax = 13.5, color = "red")plt.show()# Plot predictionsplt.scatter(y_train_rdg, y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_rdg, y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression with Ridge regularization")plt.xlabel("Predicted values")plt.ylabel("Real values")plt.legend(loc = "upper left")plt.plot([10.5, 13.5], [10.5, 13.5], c = "red")plt.show()# 绘制重要系数# Plot important coefficientscoefs = pd.Series(ridge.coef_, index = X_train.columns)print("Ridge picked " + str(sum(coefs != 0)) + " features and eliminated the other " +  \      str(sum(coefs == 0)) + " features")imp_coefs = pd.concat([coefs.sort_values().head(10),                     coefs.sort_values().tail(10)])imp_coefs.plot(kind = "barh")plt.title("Coefficients in the Ridge Model")plt.show()--('Best alpha :', 30.0)--Try again for more precision with alphas centered around 30.0--('Best alpha :', 22.5)--('Ridge RMSE on Training set :', 0.11517100992467055)--('Ridge RMSE on Test set :', 0.11636013229778504)

# 3* Lassolasso = LassoCV(alphas = [0.0001, 0.0003, 0.0006, 0.001, 0.003, 0.006, 0.01, 0.03, 0.06, 0.1,                          0.3, 0.6, 1],                max_iter = 50000, cv = 10)lasso.fit(X_train, y_train)alpha = lasso.alpha_print("Best alpha :", alpha)print("Try again for more precision with alphas centered around " + str(alpha))lasso = LassoCV(alphas = [alpha * .6, alpha * .65, alpha * .7, alpha * .75, alpha * .8,                          alpha * .85, alpha * .9, alpha * .95, alpha, alpha * 1.05,                          alpha * 1.1, alpha * 1.15, alpha * 1.25, alpha * 1.3, alpha * 1.35,                          alpha * 1.4],                max_iter = 50000, cv = 10)lasso.fit(X_train, y_train)alpha = lasso.alpha_print("Best alpha :", alpha)print("Lasso RMSE on Training set :", rmse_cv_train(lasso).mean())print("Lasso RMSE on Test set :", rmse_cv_test(lasso).mean())y_train_las = lasso.predict(X_train)y_test_las = lasso.predict(X_test)# Plot residualsplt.scatter(y_train_las, y_train_las - y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_las, y_test_las - y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression with Lasso regularization")plt.xlabel("Predicted values")plt.ylabel("Residuals")plt.legend(loc = "upper left")plt.hlines(y = 0, xmin = 10.5, xmax = 13.5, color = "red")plt.show()# Plot predictionsplt.scatter(y_train_las, y_train, c = "blue", marker = "s", label = "Training data")plt.scatter(y_test_las, y_test, c = "lightgreen", marker = "s", label = "Validation data")plt.title("Linear regression with Lasso regularization")plt.xlabel("Predicted values")plt.ylabel("Real values")plt.legend(loc = "upper left")plt.plot([10.5, 13.5], [10.5, 13.5], c = "red")plt.show()# Plot important coefficientscoefs = pd.Series(lasso.coef_, index = X_train.columns)print("Lasso picked " + str(sum(coefs != 0)) + " features and eliminated the other " +  \      str(sum(coefs == 0)) + " features")imp_coefs = pd.concat([coefs.sort_values().head(10),                     coefs.sort_values().tail(10)])imp_coefs.plot(kind = "barh")plt.title("Coefficients in the Lasso Model")plt.show()--('Best alpha :', 0.00059999999999999995)--Try again for more precision with alphas centered around 0.0006--('Best alpha :', 0.00059999999999999995)--('Lasso RMSE on Training set :', 0.11403954212405014)--('Lasso RMSE on Test set :', 0.11585280771533035)

X_train.head()X_test.head()test.head()y_pred_lasso = lasso.predict(test)y_pred_lasso--array([ 90.59653003,  62.86892549,  74.88361726, ...,  81.39766545,        39.54093941,  87.80713916])y_pred_lasso = np.exp(y_pred_lasso)y_pred_lasso--array([  2.21601691e+39,   2.01199745e+27,   3.32308738e+32, ...,         2.24159394e+35,   1.48734526e+17,   1.36193383e+38])pred_df = pd.DataFrame(y_pred_lasso, index=test_new["Id"], columns=["SalePrice"])pred_df.to_csv('output.csv', header=True, index_label='Id')# Get datatest_data = pd.read_csv("test.csv")print("test : " + str(test_data.shape))pred_df = pd.DataFrame(y_pred_lasso, index=test_data["Id"], columns=["SalePrice"])pred_df.to_csv('output_lasso.csv', header=True, index_label='Id')