Newer
Older
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
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
# ## Learning
# In[111]:
# In[112]:
preprocessing
# In[113]:
# Declare complete pipeline
pipeline = Pipeline([
('scaler', MinMaxScaler()), # scaling the data
('preprocessing', FeatureUnion(preprocessing)), # preprocessing
# Pipeline([('sg1',pp.SavitzkyGolay()),('sg2',pp.SavitzkyGolay())]),
# ('sg1',pp.SavitzkyGolay()),('sg2',pp.SavitzkyGolay()),
# preprocessing - nested pipeline to perform the Savitzky-Golay method twice for 2nd order preprocessing
('PLS', PLSRegression()) # regressor
])
# In[114]:
pipeline
# In[115]:
# Estimator including y values scaling
estimator = TransformedTargetRegressor(regressor = pipeline, transformer = MinMaxScaler())
# In[116]:
estimator
# In[117]:
# Training
estimator.fit(X_train, y_train)
# In[110]:
estimator.score(X_test,y_test)
# In[ ]:
# Predictions
Y_preds = estimator.predict(X_test) # make predictions on test data and assign to Y_preds variable
print("R²", r2_score(y_test, Y_preds))
# ## Résultats de prédiction
# In[ ]:
print("MAE", mean_absolute_error(y_test, Y_preds))
print("MSE", mean_squared_error(y_test, Y_preds))
print("MAPE", mean_absolute_percentage_error(y_test, Y_preds))
print("R²", r2_score(y_test, Y_preds))
# print(estimator.get_params())
# ## Cross Validation
# In[ ]:
print("CV_scores", cross_val_score(estimator, x, y, cv=3))
print("-- CV predict --")
Y_preds = cross_val_predict(estimator, x, y, cv=3)
print("MAE", mean_absolute_error(y, Y_preds))
print("MSE", mean_squared_error(y, Y_preds))
print("MAPE", mean_absolute_percentage_error(y, Y_preds))
print("R²", r2_score(y, Y_preds))
print("-- Cross Validate --")
cv_results = cross_validate(estimator, x, y, cv=3, return_train_score=True, n_jobs=3)
for key in cv_results.keys():
print(key, cv_results[key])