-
Notifications
You must be signed in to change notification settings - Fork 7
/
Copy path最终.py
executable file
·390 lines (387 loc) · 18.4 KB
/
最终.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sun Dec 20 22:32:11 2016
@author: 匡盟盟
"""
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import Lasso
import warnings
import seaborn as sns
from scipy.stats import skew
from scipy.stats.stats import pearsonr
from sklearn.cross_validation import cross_val_score
from sklearn.metrics import make_scorer, mean_squared_error
from sklearn.linear_model import Ridge, RidgeCV, ElasticNet, LassoCV, LassoLarsCV
from sklearn.model_selection import cross_val_score
from operator import itemgetter
import itertools
import xgboost as xgb
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
p_poly_val = np.polyfit(train['OverallQual'], train['SalePrice'], 3)
all_data = pd.concat((train.loc[:,'MSSubClass':'SaleCondition'], test.loc[:,'MSSubClass':'SaleCondition']), ignore_index=True)
warnings.simplefilter('ignore', np.RankWarning)
x = all_data.loc[np.logical_not(all_data["LotFrontage"].isnull()), "LotArea"]
y = all_data.loc[np.logical_not(all_data["LotFrontage"].isnull()), "LotFrontage"]
t = (x <= 25000) & (y <= 150)
p = np.polyfit(x[t], y[t], 1)
all_data.loc[all_data['LotFrontage'].isnull(), 'LotFrontage'] = np.polyval(p, all_data.loc[all_data['LotFrontage'].isnull(), 'LotArea'])
all_data = all_data.fillna({
'Alley' : 'NoAlley',
'MasVnrType': 'None',
'FireplaceQu': 'NoFireplace',
'GarageType': 'NoGarage',
'GarageFinish': 'NoGarage',
'GarageQual': 'NoGarage',
'GarageCond': 'NoGarage',
'BsmtFullBath': 0,
'BsmtHalfBath': 0,
'BsmtQual' : 'NoBsmt',
'BsmtCond' : 'NoBsmt',
'BsmtExposure' : 'NoBsmt',
'BsmtFinType1' : 'NoBsmt',
'BsmtFinType2' : 'NoBsmt',
'KitchenQual' : 'TA',
'MSZoning' : 'RL',
'Utilities' : 'AllPub',
'Exterior1st' : 'VinylSd',
'Exterior2nd' : 'VinylSd',
'Functional' : 'Typ',
'PoolQC' : 'NoPool',
'Fence' : 'NoFence',
'MiscFeature' : 'None',
'Electrical' : 'SBrkr'
})
all_data.loc[all_data.SaleCondition.isnull(), 'SaleCondition'] = 'Normal'
all_data.loc[all_data.SaleCondition.isnull(), 'SaleType'] = 'WD'
all_data.loc[all_data.MasVnrType == 'None', 'MasVnrArea'] = 0
all_data.loc[all_data.BsmtFinType1=='NoBsmt', 'BsmtFinSF1'] = 0
all_data.loc[all_data.BsmtFinType2=='NoBsmt', 'BsmtFinSF2'] = 0
all_data.loc[all_data.BsmtFinSF1.isnull(), 'BsmtFinSF1'] = all_data.BsmtFinSF1.median()
all_data.loc[all_data.BsmtQual=='NoBsmt', 'BsmtUnfSF'] = 0
all_data.loc[all_data.BsmtUnfSF.isnull(), 'BsmtUnfSF'] = all_data.BsmtUnfSF.median()
all_data.loc[all_data.BsmtQual=='NoBsmt', 'TotalBsmtSF'] = 0
all_data.loc[all_data['GarageArea'].isnull(), 'GarageArea'] = all_data.loc[all_data['GarageType']=='Detchd', 'GarageArea'].mean()
all_data.loc[all_data['GarageCars'].isnull(), 'GarageCars'] = all_data.loc[all_data['GarageType']=='Detchd', 'GarageCars'].median()
all_data = all_data.replace({'Utilities': {'AllPub': 1, 'NoSeWa': 0, 'NoSewr': 0, 'ELO': 0},
'Street': {'Pave': 1, 'Grvl': 0 },
'FireplaceQu': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1,
'NoFireplace': 0
},
'Fence': {'GdPrv': 2,
'GdWo': 2,
'MnPrv': 1,
'MnWw': 1,
'NoFence': 0},
'ExterQual': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1
},
'ExterCond': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1
},
'BsmtQual': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1,
'NoBsmt': 0},
'BsmtExposure': {'Gd': 3,
'Av': 2,
'Mn': 1,
'No': 0,
'NoBsmt': 0},
'BsmtCond': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1,
'NoBsmt': 0},
'GarageQual': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1,
'NoGarage': 0},
'GarageCond': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1,
'NoGarage': 0},
'KitchenQual': {'Ex': 5,
'Gd': 4,
'TA': 3,
'Fa': 2,
'Po': 1},
'Functional': {'Typ': 0,
'Min1': 1,
'Min2': 1,
'Mod': 2,
'Maj1': 3,
'Maj2': 4,
'Sev': 5,
'Sal': 6}
})
all_data = all_data.replace({'CentralAir': {'Y': 1,
'N': 0}})
all_data = all_data.replace({'PavedDrive': {'Y': 1,
'P': 0,
'N': 0}})
newer_dwelling = all_data.MSSubClass.replace({20: 1,
30: 0,
40: 0,
45: 0,
50: 0,
60: 1,
70: 0,
75: 0,
80: 0,
85: 0,
90: 0,
120: 1,
150: 0,
160: 0,
180: 0,
190: 0})
newer_dwelling.name = 'newer_dwelling'
all_data = all_data.replace({'MSSubClass': {20: 'SubClass_20',
30: 'SubClass_30',
40: 'SubClass_40',
45: 'SubClass_45',
50: 'SubClass_50',
60: 'SubClass_60',
70: 'SubClass_70',
75: 'SubClass_75',
80: 'SubClass_80',
85: 'SubClass_85',
90: 'SubClass_90',
120: 'SubClass_120',
150: 'SubClass_150',
160: 'SubClass_160',
180: 'SubClass_180',
190: 'SubClass_190'}})
overall_poor_qu = all_data.OverallQual.copy()
overall_poor_qu = 5 - overall_poor_qu
overall_poor_qu[overall_poor_qu<0] = 0
overall_poor_qu.name = 'overall_poor_qu'
overall_good_qu = all_data.OverallQual.copy()
overall_good_qu = overall_good_qu - 5
overall_good_qu[overall_good_qu<0] = 0
overall_good_qu.name = 'overall_good_qu'
overall_poor_cond = all_data.OverallCond.copy()
overall_poor_cond = 5 - overall_poor_cond
overall_poor_cond[overall_poor_cond<0] = 0
overall_poor_cond.name = 'overall_poor_cond'
overall_good_cond = all_data.OverallCond.copy()
overall_good_cond = overall_good_cond - 5
overall_good_cond[overall_good_cond<0] = 0
overall_good_cond.name = 'overall_good_cond'
exter_poor_qu = all_data.ExterQual.copy()
exter_poor_qu[exter_poor_qu<3] = 1
exter_poor_qu[exter_poor_qu>=3] = 0
exter_poor_qu.name = 'exter_poor_qu'
exter_good_qu = all_data.ExterQual.copy()
exter_good_qu[exter_good_qu<=3] = 0
exter_good_qu[exter_good_qu>3] = 1
exter_good_qu.name = 'exter_good_qu'
exter_poor_cond = all_data.ExterCond.copy()
exter_poor_cond[exter_poor_cond<3] = 1
exter_poor_cond[exter_poor_cond>=3] = 0
exter_poor_cond.name = 'exter_poor_cond'
exter_good_cond = all_data.ExterCond.copy()
exter_good_cond[exter_good_cond<=3] = 0
exter_good_cond[exter_good_cond>3] = 1
exter_good_cond.name = 'exter_good_cond'
bsmt_poor_cond = all_data.BsmtCond.copy()
bsmt_poor_cond[bsmt_poor_cond<3] = 1
bsmt_poor_cond[bsmt_poor_cond>=3] = 0
bsmt_poor_cond.name = 'bsmt_poor_cond'
bsmt_good_cond = all_data.BsmtCond.copy()
bsmt_good_cond[bsmt_good_cond<=3] = 0
bsmt_good_cond[bsmt_good_cond>3] = 1
bsmt_good_cond.name = 'bsmt_good_cond'
garage_poor_qu = all_data.GarageQual.copy()
garage_poor_qu[garage_poor_qu<3] = 1
garage_poor_qu[garage_poor_qu>=3] = 0
garage_poor_qu.name = 'garage_poor_qu'
garage_good_qu = all_data.GarageQual.copy()
garage_good_qu[garage_good_qu<=3] = 0
garage_good_qu[garage_good_qu>3] = 1
garage_good_qu.name = 'garage_good_qu'
garage_poor_cond = all_data.GarageCond.copy()
garage_poor_cond[garage_poor_cond<3] = 1
garage_poor_cond[garage_poor_cond>=3] = 0
garage_poor_cond.name = 'garage_poor_cond'
garage_good_cond = all_data.GarageCond.copy()
garage_good_cond[garage_good_cond<=3] = 0
garage_good_cond[garage_good_cond>3] = 1
garage_good_cond.name = 'garage_good_cond'
kitchen_poor_qu = all_data.KitchenQual.copy()
kitchen_poor_qu[kitchen_poor_qu<3] = 1
kitchen_poor_qu[kitchen_poor_qu>=3] = 0
kitchen_poor_qu.name = 'kitchen_poor_qu'
kitchen_good_qu = all_data.KitchenQual.copy()
kitchen_good_qu[kitchen_good_qu<=3] = 0
kitchen_good_qu[kitchen_good_qu>3] = 1
kitchen_good_qu.name = 'kitchen_good_qu'
qu_list = pd.concat((overall_poor_qu, overall_good_qu, overall_poor_cond, overall_good_cond, exter_poor_qu,
exter_good_qu, exter_poor_cond, exter_good_cond, bsmt_poor_cond, bsmt_good_cond, garage_poor_qu,
garage_good_qu, garage_poor_cond, garage_good_cond, kitchen_poor_qu, kitchen_good_qu), axis=1)
bad_heating = all_data.HeatingQC.replace({'Ex': 0,
'Gd': 0,
'TA': 0,
'Fa': 1,
'Po': 1})
bad_heating.name = 'bad_heating'
MasVnrType_Any = all_data.MasVnrType.replace({'BrkCmn': 1,
'BrkFace': 1,
'CBlock': 1,
'Stone': 1,
'None': 0})
MasVnrType_Any.name = 'MasVnrType_Any'
SaleCondition_PriceDown = all_data.SaleCondition.replace({'Abnorml': 1,
'Alloca': 1,
'AdjLand': 1,
'Family': 1,
'Normal': 0,
'Partial': 0})
SaleCondition_PriceDown.name = 'SaleCondition_PriceDown'
Neighborhood_Good = pd.DataFrame(np.zeros((all_data.shape[0],1)), columns=['Neighborhood_Good'])
Neighborhood_Good[all_data.Neighborhood=='NridgHt'] = 1
Neighborhood_Good[all_data.Neighborhood=='Crawfor'] = 1
Neighborhood_Good[all_data.Neighborhood=='StoneBr'] = 1
Neighborhood_Good[all_data.Neighborhood=='Somerst'] = 1
Neighborhood_Good[all_data.Neighborhood=='NoRidge'] = 1
from sklearn.svm import SVC
svm = SVC(C=100, gamma=0.0001, kernel='rbf')
pc = pd.Series(np.zeros(train.shape[0]))
pc[:] = 'pc1'
pc[train.SalePrice >= 150000] = 'pc2'
pc[train.SalePrice >= 220000] = 'pc3'
columns_for_pc = ['Exterior1st', 'Exterior2nd', 'RoofMatl', 'Condition1', 'Condition2', 'BldgType']
X_t = pd.get_dummies(train.loc[:, columns_for_pc], sparse=True)
svm.fit(X_t, pc) #Training
pc_pred = svm.predict(X_t)
p = train.SalePrice/100000
price_category = pd.DataFrame(np.zeros((all_data.shape[0],1)), columns=['pc'])
X_t = pd.get_dummies(all_data.loc[:, columns_for_pc], sparse=True)
pc_pred = svm.predict(X_t)
price_category[pc_pred=='pc2'] = 1
price_category[pc_pred=='pc3'] = 2
price_category = price_category.to_sparse()
season = all_data.MoSold.replace( {1: 0,
2: 0,
3: 0,
4: 1,
5: 1,
6: 1,
7: 1,
8: 0,
9: 0,
10: 0,
11: 0,
12: 0})
season.name = 'season'
all_data = all_data.replace({'MoSold': {1: 'Yan',
2: 'Feb',
3: 'Mar',
4: 'Apr',
5: 'May',
6: 'Jun',
7: 'Jul',
8: 'Avg',
9: 'Sep',
10: 'Oct',
11: 'Nov',
12: 'Dec'}})
reconstruct = pd.DataFrame(np.zeros((all_data.shape[0],1)), columns=['Reconstruct'])
reconstruct[all_data.YrSold < all_data.YearRemodAdd] = 1
reconstruct = reconstruct.to_sparse()
recon_after_buy = pd.DataFrame(np.zeros((all_data.shape[0],1)), columns=['ReconstructAfterBuy'])
recon_after_buy[all_data.YearRemodAdd >= all_data.YrSold] = 1
recon_after_buy = recon_after_buy.to_sparse()
build_eq_buy = pd.DataFrame(np.zeros((all_data.shape[0],1)), columns=['Build.eq.Buy'])
build_eq_buy[all_data.YearBuilt >= all_data.YrSold] = 1
build_eq_buy = build_eq_buy.to_sparse()
all_data.YrSold = 2010 - all_data.YrSold
year_map = pd.concat(pd.Series('YearGroup' + str(i+1), index=range(1871+i*20,1891+i*20)) for i in range(0, 7))
all_data.GarageYrBlt = all_data.GarageYrBlt.map(year_map)
all_data.loc[all_data['GarageYrBlt'].isnull(), 'GarageYrBlt'] = 'NoGarage'
all_data.YearBuilt = all_data.YearBuilt.map(year_map)
all_data.YearRemodAdd = all_data.YearRemodAdd.map(year_map)
numeric_feats = all_data.dtypes[all_data.dtypes != "object"].index
t = all_data[numeric_feats].quantile(.75)
use_75_scater = t[t != 0].index
all_data[use_75_scater] = all_data[use_75_scater]/all_data[use_75_scater].quantile(.75)
t = ['LotFrontage', 'LotArea', 'MasVnrArea', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF',
'1stFlrSF', '2ndFlrSF', 'LowQualFinSF', 'GrLivArea', 'GarageArea', 'WoodDeckSF', 'OpenPorchSF',
'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal']
all_data.loc[:, t] = np.log1p(all_data.loc[:, t])
train["SalePrice"] = np.log1p(train["SalePrice"])
X = pd.get_dummies(all_data)
X = X.fillna(X.mean())
X = X.drop('RoofMatl_ClyTile', axis=1)
X = X.drop('Condition2_PosN', axis=1)
X = X.drop('MSZoning_C (all)', axis=1)
X = X.drop('MSSubClass_SubClass_160', axis=1)
X = pd.concat((X, newer_dwelling, season, reconstruct, recon_after_buy,
qu_list, bad_heating, MasVnrType_Any, price_category, build_eq_buy), axis=1)
from itertools import product, chain
def poly(X):
areas = ['LotArea', 'TotalBsmtSF', 'GrLivArea', 'GarageArea', 'BsmtUnfSF']
t = chain(qu_list.axes[1].get_values(),
['OverallQual', 'OverallCond', 'ExterQual', 'ExterCond', 'BsmtCond', 'GarageQual', 'GarageCond',
'KitchenQual', 'HeatingQC', 'bad_heating', 'MasVnrType_Any', 'SaleCondition_PriceDown', 'Reconstruct',
'ReconstructAfterBuy', 'Build.eq.Buy'])
for a, t in product(areas, t):
x = X.loc[:, [a, t]].prod(1)
x.name = a + '_' + t
yield x
XP = pd.concat(poly(X), axis=1)
X = pd.concat((X, XP), axis=1)
X_train = X[:train.shape[0]]
X_test = X[train.shape[0]:]
y = train.SalePrice
outliers_id = np.array([523,1298])
X_train = X_train.drop(outliers_id)
y = y.drop(outliers_id)
def rmse_cv(model):
rmse= np.sqrt(-cross_val_score(model, X_train, y, scoring="neg_mean_squared_error", cv = 5))
return(rmse)
#LASSO MODEL
clf1 = LassoCV(alphas = [1, 0.1, 0.001, 0.0005, 5e-4])
clf1.fit(X_train, y)
lasso_preds = np.expm1(clf1.predict(X_test))
#ELASTIC NET
clf2 = ElasticNet(alpha=0.0005, l1_ratio=0.9)
clf2.fit(X_train, y)
elas_preds = np.expm1(clf2.predict(X_test))
#XGBOOST
clf3=xgb.XGBRegressor(colsample_bytree=0.4,
gamma=0.045,
learning_rate=0.07,
max_depth=20,
min_child_weight=1.5,
n_estimators=300,
reg_alpha=0.65,
reg_lambda=0.45,
subsample=0.95)
clf3.fit(X_train, y)
xgb_preds = np.expm1(clf3.predict(X_test))
print (xgb_preds)
final_result = 0.45*lasso_preds + 0.25*xgb_preds+0.30*elas_preds
solution = pd.DataFrame({"id":test.Id, "SalePrice":final_result}, columns=['id', 'SalePrice'])
solution.to_csv("result.csv", index = False)