SKlearn迴歸模型調包練習
看了錄播後照著程式碼敲了一遍 sklearn常用分類迴歸演算法簡介 對能瞭解SKlearn常規套路，但模型具體的引數需要進一步瞭解。
# 引入必要的第三方包
from sklearn.cross_validation import train_test_split
from sklearn import metrics
import pandas as pd
import time
# 讀資料，並進行處理
data = pd.read_csv(’/home/whn/Downloads/all_window.csv’).fillna(0,axis=1)
X = data.drop(‘label’,axis=1)
# min_max_scale = StandardScaler()
# X = min_max_scale.fit_transform(X)
y = data[‘label’]
history = []
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=
# 線性迴歸：LR、Rigde(L2) 和 Lasso(L1)
from sklearn import linear_model
start = time.time()
reg = linear_model.LinearRegression()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘LinearRegression’
history.append([name,loss,
start = time.time()
reg = linear_model.Ridge()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘Rigde’
history.append([name,loss,end-start])
start = time.time()
reg = linear_model.Ridge(alpha=0.5)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘Ridge_alpha=0.5’
history.append([name,loss,end-start])
start = time.time()
reg = linear_model.Lasso()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘Lasso’
history.append([name,loss,end-start])
start = time.time()
reg = linear_model.Lasso(alpha=2)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘Lasso_alpha=2’
history.append([name,loss,end-start])
start = time.time()
reg = linear_model.Lasso(alpha=2,max_iter=10)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘Lasso_alpha=2_max_iter=10’
history.append([name,loss,end-start])
# 整合模型：RF
from sklearn.ensemble import RandomForestRegressor
start = time.time()
reg = RandomForestRegressor()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘RandomForestRegressor’
history.append([name,loss,end-start])
start = time.time()
reg = RandomForestRegressor(n_estimators=200,random_state=0)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘RandomForestRegressor_n_estimators=200’
history.append([name,loss,end-start])
from sklearn.ensemble.forest import ExtraTreeRegressor
start = time.time()
reg = ExtraTreeRegressor()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘ExtraTreeRegressor’
history.append([name,loss,end-start])
start = time.time()
reg = ExtraTreeRegressor(n_estimators=100,max_depth=7,min_samples_leaf=10)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘ExtraTreeRegressor_s’
history.append([name,loss,end-start])
# 神經網路：MLP
from sklearn.neural_network import MLPRegressor
start = time.time()
reg = MLPRegressor()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘MLPRegressor’
history.append([name,loss,end-start])
start = time.time()
reg = MLPRegressor(batch_size=50, hidden_layer_sizes=20, learning_rate_init=0.1,
max_iter=300,random_state=0,early_stopping=True)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘MLPRegressor_s’
history.append([name,loss,end-start])
# SVM
from sklearn.svm import SVR, LinearSVR
start = time.time()
reg = SVR()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘SVR’
history.append([name,loss,end-start])
start = time.time()
reg = SVR(kernel=‘rbf’,C=0.1, epsilon=0.1,max_iter=100)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘SVR_s’
history.append([name,loss,end-start])
# XGBOOST
from xgboost.sklearn import XGBRegressor
start = time.time()
reg = XGBRegressor()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘XGBRegressor’
history.append([name,loss,end-start])
start = time.time()
reg = XGBRegressor(max_depth=4, n_estimators=500, min_child_weight=10,
subsample=0.7, colsample_bytree=0.7, reg_alpha=0, reg_lambda=0.5)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘XGBRegressor_s’
history.append([name,loss,end-start])
# lightGBM
from lightgbm import LGBMRegressor
start = time.time()
reg = LGBMRegressor()
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘LGBMRegressor’
history.append([name,loss,end-start])
start = time.time()
reg = LGBMRegressor(num_leaves=40,max_depth=7,n_estimators=200,min_child_weight=10,
subsample=0.7, colsample_bytree=0.7,reg_alpha=0, reg_lambda=0.5)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘LGBMRegressor_s’
history.append([name,loss,end-start])
from sklearn.neighbors.regression import KNeighborsRegressor
start = time.time()
reg = KNeighborsRegressor(n_neighbors=4,algorithm=‘kd_tree’)
reg.fit(X_train, y_train)
end = time.time()
y_pred = reg.predict(X_test)
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘KNeighborsRegressor_s’
history.append([name,loss,end-start])
# 融合
start = time.time()
reg = LGBMRegressor()
reg.fit(X_train, y_train)
y_pred_lgb = reg.predict(X_test)
reg = linear_model.Lasso(alpha=2,max_iter=10)
reg.fit(X_train, y_train)
y_pred_lr = reg.predict(X_test)
y_pred = (y_pred_lgb + y_pred_lr) / 2
end = time.time()
loss = metrics.mean_squared_error(y_test, y_pred)
name = ‘LGBMRegressor+Lasso’
history.append([name,loss,end-start])
- 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
結果如下：
In [216]: history
Out[216]:[['LinearRegression', 5616.27782832045, 0.23373723030090332],
['Rigde', 5625.959154564378, 0.18334627151489258],
['Ridge_alpha=0.5', 5622.655065407929, 0.18333888053894043],
['Lasso', 4957.000025059516, 0.516655683517456],
['Lasso_alpha=2', 4741.355578668198, 0.5424296855926514],
['Lasso_alpha=2_max_iter=10', 4233.225156683616, 0.20163559913635254],
['DecisionTreeRegressor', 14380.923876533841, 0.3124210834503174],
['RandomForestRegressor', 8305.730287150229, 2.3668367862701416],
['RandomForestRegressor_n_estimators=200', 5410.864295873489, 43.549724102020264],
['MLPRegressor', 3629898.708004297, 0.3255181312561035],
['MLPRegressor_s', 30620.511077612777, 0.2955296039581299],
['SVR', 57030.14962918571, 2.7514443397521973],
['SVR_s', 77562.5821631834, 0.3735840320587158],
['XGBRegressor', 7435.130163942215, 1.4277334213256836],
['XGBRegressor_s', 6465.628256746952, 6.708096981048584],
['LGBMRegressor', 6386.790622782424, 2.187742233276367],
['LGBMRegressor_s', 6874.105186792729, 1.4423110485076904],
['ExtraTreeRegressor', 7343.10613304338, 0.2813429832458496],
['ExtraTreeRegressor_s', 24685.212690420427, 0.28301167488098145],
['KNeighborsRegressor_s', 43321.059426229505, 0.21740508079528809],
['LGBMRegressor+Lasso', 4589.754232812634, 2.578683376312256]]
看了錄播後照著程式碼敲了一遍 sklearn常用分類迴歸演算法簡介 對能瞭解SKlearn常規套路，但模型具體的引數需要進一步瞭解。
# 引入必要的第三方包
from sklearn.cross_validation import train_test_split
from sklearn import metrics
import pandas as pd
import time