python sklearn 分类案例：事件预测

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
"""
    事件预测 案例
"""
import numpy as np
import sklearn.preprocessing as sp
import sklearn.model_selection as ms
import sklearn.svm as svm
import sklearn.metrics as sm
import sklearn.naive_bayes as nb


class DigitEncoder:
    """
        数字与字符串互转
    """

    def fit_transform(self, y):
        return y.astype(int)

    def transform(self, y):
        return y.astype(int)

    def inverse_transform(self, y):
        return y.astype(str)


# 读取数据集 整理数据集
lines = np.loadtxt(r".event.txt", delimiter=',', dtype='str')
print(lines.shape)
print(lines[0])
# 读取数据
# 删除第二列
lines_T = np.delete(lines.T, 1, axis=0)
print(lines_T.shape)
lines_T = np.array(lines_T)
# 整理样本空间 并编码 （对列执行标签编码）
train_x, train_y = [], []
encoders = []  # 标签编码数组
for index, row in enumerate(lines_T):
    rowStr = row[index]
    if rowStr.isdigit():  # 是否为数字类型
        encoder = DigitEncoder()
    else:
        encoder = sp.LabelEncoder()  # 标签编码

    if index < (len(lines_T) - 1):  # 训练样本 X
        train_x.append(encoder.fit_transform(row))
    else:
        train_y = encoder.fit_transform(row)  # 训练样本结果 Y
    encoders.append(encoder)

train_x = np.array(train_x).T  # 转置
train_y = np.array(train_y)

print(train_x.shape, train_y.shape)
print(train_x[0], train_y[0])

train_x, test_x, train_y, test_y 
    = ms.train_test_split(train_x, train_y, test_size=0.25, random_state=7)

# 选择模型 训练模型
model = nb.GaussianNB()
# model = svm.SVC(kernel="rbf", degree=3, class_weight="balanced")

# 交叉验证
print(ms.cross_val_score(model, train_x, train_y, cv=3, scoring='accuracy').mean())
model.fit(train_x, train_y)
# 预测
prd_test_y = model.predict(test_x)

# 打印分类报告
print(sm.classification_report(test_y, prd_test_y))

# 真实数据预测
data = [['Tuesday', '13:30:00', '21', '23'],
        ['Tuesday', '14:30:00', '63', '62'],
        ['Tuesday', '01:30:00', '3', '2']]
data = np.array(data).T
x = []
for row in range(len(data)):
    encoder = encoders[row]
    x.append(encoder.transform(data[row]))
x = np.array(x).T
prd_y = model.predict(x)
print(prd_y, encoders[-1].inverse_transform(prd_y))