-
Notifications
You must be signed in to change notification settings - Fork 27
/
Copy pathelasticnet_gboost.py
151 lines (139 loc) · 8.14 KB
/
elasticnet_gboost.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
import pandas as pd
import numpy as np
from sklearn import ensemble, linear_model
from sklearn.metrics import r2_score, mean_squared_error
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.utils import shuffle
import warnings
warnings.filterwarnings('ignore')
'''
Method 2: process each feature one-by-one...
'''
train = pd.read_csv('../train.csv')
test = pd.read_csv('../test.csv')
# Spliting to features and labels and deleting variable I don't need
train_labels = train.pop('SalePrice')
features = pd.concat([train, test], keys=['train', 'test'])
# I decided to get rid of features that have more than half of missing information or do not correlate to SalePrice
features.drop(['Utilities', 'RoofMatl', 'MasVnrArea', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'Heating',
'LowQualFinSF', 'BsmtFullBath', 'BsmtHalfBath', 'Functional', 'GarageYrBlt', 'GarageArea', 'GarageCond',
'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'PoolQC', 'Fence',
'MiscFeature', 'MiscVal'], axis=1, inplace=True)
# MSSubClass as str
features['MSSubClass'] = features['MSSubClass'].astype(str)
# MSZoning NA in pred. filling with most popular values
features['MSZoning'] = features['MSZoning'].fillna(features['MSZoning'].mode()[0])
# LotFrontage NA in all. I suppose NA means 0
features['LotFrontage'] = features['LotFrontage'].fillna(features['LotFrontage'].mean())
# Alley NA in all. NA means no access
features['Alley'] = features['Alley'].fillna('NOACCESS')
# Converting OverallCond to str
features.OverallCond = features.OverallCond.astype(str)
# MasVnrType NA in all. filling with most popular values
features['MasVnrType'] = features['MasVnrType'].fillna(features['MasVnrType'].mode()[0])
# BsmtQual, BsmtCond, BsmtExposure, BsmtFinType1, BsmtFinType2
# NA in all. NA means No basement
for col in ('BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2'):
features[col] = features[col].fillna('NoBSMT')
# TotalBsmtSF NA in pred. I suppose NA means 0
features['TotalBsmtSF'] = features['TotalBsmtSF'].fillna(0)
# Electrical NA in pred. filling with most popular values
features['Electrical'] = features['Electrical'].fillna(features['Electrical'].mode()[0])
# KitchenAbvGr to categorical
features['KitchenAbvGr'] = features['KitchenAbvGr'].astype(str)
# KitchenQual NA in pred. filling with most popular values
features['KitchenQual'] = features['KitchenQual'].fillna(features['KitchenQual'].mode()[0])
# FireplaceQu NA in all. NA means No Fireplace
features['FireplaceQu'] = features['FireplaceQu'].fillna('NoFP')
# GarageType, GarageFinish, GarageQual NA in all. NA means No Garage
for col in ('GarageType', 'GarageFinish', 'GarageQual'):
features[col] = features[col].fillna('NoGRG')
# GarageCars NA in pred. I suppose NA means 0
features['GarageCars'] = features['GarageCars'].fillna(0.0)
# SaleType NA in pred. filling with most popular values
features['SaleType'] = features['SaleType'].fillna(features['SaleType'].mode()[0])
# Year and Month to categorical
features['YrSold'] = features['YrSold'].astype(str)
features['MoSold'] = features['MoSold'].astype(str)
# Adding total sqfootage feature and removing Basement, 1st and 2nd floor features
features['TotalSF'] = features['TotalBsmtSF'] + features['1stFlrSF'] + features['2ndFlrSF']
features.drop(['TotalBsmtSF', '1stFlrSF', '2ndFlrSF'], axis=1, inplace=True)
# Log transformation of labels
train_labels = np.log(train_labels)
# Standardizing numeric features
numeric_features = features.loc[:, ['LotFrontage', 'LotArea', 'GrLivArea', 'TotalSF']]
numeric_features_standardized = (numeric_features - numeric_features.mean())/numeric_features.std()
# Getting Dummies from Condition1 and Condition2
conditions = set([x for x in features['Condition1']] + [x for x in features['Condition2']])
dummies = pd.DataFrame(data=np.zeros((len(features.index), len(conditions))), index=features.index, columns=conditions)
for i, cond in enumerate(zip(features['Condition1'], features['Condition2'])):
dummies.ix[i, cond] = 1
features = pd.concat([features, dummies.add_prefix('Condition_')], axis=1)
features.drop(['Condition1', 'Condition2'], axis=1, inplace=True)
# Getting Dummies from Exterior1st and Exterior2nd
exteriors = set([x for x in features['Exterior1st']] + [x for x in features['Exterior2nd']])
dummies = pd.DataFrame(data=np.zeros((len(features.index), len(exteriors))), index=features.index, columns=exteriors)
for i, ext in enumerate(zip(features['Exterior1st'], features['Exterior2nd'])):
dummies.ix[i, ext] = 1
features = pd.concat([features, dummies.add_prefix('Exterior_')], axis=1)
features.drop(['Exterior1st', 'Exterior2nd', 'Exterior_nan'], axis=1, inplace=True)
# Getting Dummies from all other categorical vars
for col in features.dtypes[features.dtypes == 'object'].index:
for_dummy = features.pop(col)
features = pd.concat([features, pd.get_dummies(for_dummy, prefix=col)], axis=1)
# Copying features
features_standardized = features.copy()
# Replacing numeric features by standardized values
features_standardized.update(numeric_features_standardized)
# Splitting features
train_features = features.loc['train'].drop('Id', axis=1).select_dtypes(include=[np.number]).values
test_features = features.loc['test'].drop('Id', axis=1).select_dtypes(include=[np.number]).values
# Splitting standardized features
train_features_st = features_standardized.loc['train'].drop('Id', axis=1).select_dtypes(include=[np.number]).values
test_features_st = features_standardized.loc['test'].drop('Id', axis=1).select_dtypes(include=[np.number]).values
# Shuffling train sets
train_features_st, train_features, train_labels = shuffle(train_features_st, train_features, train_labels,
random_state=5)
# Splitting
x_train, x_test, y_train, y_test = train_test_split(train_features, train_labels, test_size=0.1, random_state=200)
x_train_st, x_test_st, y_train_st, y_test_st = train_test_split(train_features_st, train_labels, test_size=0.1,
random_state=200)
# Prints R2 and RMSE scores
def get_score(prediction, labels):
print('R2: {}'.format(r2_score(prediction, labels)))
print('RMSE: {}'.format(np.sqrt(mean_squared_error(prediction, labels))))
# Shows scores for train and validation sets
def train_test(estimator, x_trn, x_tst, y_trn, y_tst):
prediction_train = estimator.predict(x_trn)
# Printing estimator
print(estimator)
# Printing train scores
get_score(prediction_train, y_trn)
prediction_test = estimator.predict(x_tst)
# Printing test scores
print("Test")
get_score(prediction_test, y_tst)
ens_test = linear_model.ElasticNetCV(alphas=[0.0001, 0.0005, 0.001, 0.01, 0.1, 1, 10], l1_ratio=[.01, .1, .5, .9, .99],
max_iter=5000).fit(x_train_st, y_train_st)
train_test(ens_test, x_train_st, x_test_st, y_train_st, y_test_st)
# Average R2 score and standard deviation of 5-fold cross-validation
scores = cross_val_score(ens_test, train_features_st, train_labels, cv=5)
print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
g_best = ensemble.GradientBoostingRegressor(n_estimators=3000, learning_rate=0.05, max_depth=3, max_features='sqrt',
min_samples_leaf=15, min_samples_split=10, loss='huber').fit(x_train,
y_train)
train_test(g_best, x_train, x_test, y_train, y_test)
# Average R2 score and standard deviation of 5-fold cross-validation
scores = cross_val_score(g_best, train_features_st, train_labels, cv=5)
print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
# Retraining models
gb_model = g_best.fit(train_features, train_labels)
enst_model = ens_test.fit(train_features_st, train_labels)
# Getting our SalePrice estimation
final_labels = (np.exp(gb_model.predict(test_features)) + np.exp(enst_model.predict(test_features_st))) / 2
# print result
output = pd.DataFrame({'Id': test.Id, 'SalePrice': final_labels})
print('\nPredictions:')
print(output)
# Saving to CSV
# output.to_csv('submission.csv', index=False)