from sklearn.datasets import make_classification创建分类数据集
make_classification创建用于分类的数据集，官方文档
例子：
|
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
|
### 创建模型def create_model(): # 生成数据 from sklearn.datasets import make_classification X, y = make_classification(n_samples=10000, # 样本个数 n_features=25, # 特征个数 n_informative=3, # 有效特征个数 n_redundant=2, # 冗余特征个数（有效特征的随机组合） n_repeated=0, # 重复特征个数（有效特征和冗余特征的随机组合） n_classes=3, # 样本类别 n_clusters_per_class=1, # 簇的个数 random_state=0) print("原始特征维度",X.shape) # 读取数据 print("读取数据") #import pandas as pd #data = pd.read_csv(datapath) # 数据划分 print("数据划分") from sklearn.model_selection import train_test_split global x_train,x_valid,x_test,y_train,y_valid,y_test x_train,x_test,y_train,y_test = train_test_split(X,y,random_state = 33,test_size = 0.25) x_train,x_valid,y_train,y_valid = train_test_split(x_train,y_train,random_state = 33,test_size = 0.25) # 创建模型 print("创建模型") from sklearn.linear_model import LogisticRegression global model model = LogisticRegression(penalty = 'l2').fit(x_train,y_train)### 保存模型 def save_model(): print("保存模型") from sklearn.externals import joblib joblib.dump(model,'model.pkl')### 模型验证 def validate_model(): print("模型验证") print(model.score(x_valid,y_valid)) ### 模型预测def predict_model(): print("模型预测") global pred pred = model.predict_proba(x_test) print(pred) if __name__ == "__main__": create_model() save_model() validate_model() predict_model() |
