KNN预测QSAR生物浓缩类别
数据来源：http://archive.ics.uci.edu/ml/datasets/QSAR+Bioconcentration+classes+dataset
import numpy
import pandas #导入Excel文件
from sklearn.neighbors import KNeighborsClassifier #机器学习算法库，没有深度学习算法
shen=pandas.read_csv(r"D:\Python\代码\Machine-Learn\1-KNN\data\shenwu.csv")
print("总数据条数：{}；列数：{}".format(shen.shape[0],shen.shape[1]))
shen.head()
总数据条数：779；列数：14
| | CAS | SMILES | Set | nHM | piPC09 | PCD | X2Av | MLOGP | ON1V | N-072 | B02[C-N] | F04[C-O] | Class | logBCF |
|---|
| 0 |
100-02-7 |
O=[N+](c1ccc(cc1)O)[O-] |
Train |
0 |
0.0 |
1.49 |
0.14 |
1.35 |
0.72 |
0 |
1 |
5 |
1 |
0.74 |
|---|
| 1 |
100-17-4 |
O=[N+](c1ccc(cc1)OC)[O-] |
Train |
0 |
0.0 |
1.47 |
0.14 |
1.70 |
0.88 |
0 |
1 |
5 |
1 |
0.93 |
|---|
| 2 |
100-18-5 |
c1cc(ccc1C(C)C)C(C)C |
Train |
0 |
0.0 |
1.20 |
0.25 |
4.14 |
2.06 |
0 |
0 |
0 |
3 |
3.24 |
|---|
| 3 |
100-25-4 |
O=[N+]([O-])c1ccc(cc1)[N+](=O)[O-] |
Train |
0 |
0.0 |
1.69 |
0.13 |
1.89 |
0.79 |
0 |
1 |
8 |
3 |
-0.40 |
|---|
| 4 |
100-40-3 |
C=CC1CCC=CC1 |
Train |
0 |
0.0 |
0.52 |
0.25 |
2.65 |
1.31 |
0 |
0 |
0 |
1 |
2.24 |
|---|
# 筛选set值为Train的训练数据
shen_train=shen[shen.Set.isin(["Train"])]
shen_test=shen[shen.Set.isin(["Test"])]
print("训练数据：{}个\n测试数据：{}个".format((shen_train.shape)[0],(shen_test.shape[0])))
shen_test.head()
训练数据：584个
测试数据：195个
| | CAS | SMILES | Set | nHM | piPC09 | PCD | X2Av | MLOGP | ON1V | N-072 | B02[C-N] | F04[C-O] | Class | logBCF |
|---|
| 5 |
100-42-5 |
C=Cc1ccccc1 |
Test |
0 |
0.000 |
1.40 |
0.18 |
2.85 |
0.86 |
0 |
0 |
0 |
3 |
1.13 |
|---|
| 12 |
101-53-1 |
Oc1ccc(cc1)Cc1ccccc1 |
Test |
0 |
5.768 |
2.21 |
0.18 |
3.40 |
1.47 |
0 |
0 |
1 |
3 |
1.40 |
|---|
| 15 |
101-84-8 |
O(c1ccccc1)c1ccccc1 |
Test |
0 |
5.614 |
2.21 |
0.16 |
3.40 |
1.31 |
0 |
0 |
2 |
1 |
2.57 |
|---|
| 16 |
102-06-7 |
N=C(Nc1ccccc1)Nc1ccccc1 |
Test |
0 |
5.030 |
2.07 |
0.16 |
3.09 |
1.54 |
0 |
1 |
0 |
2 |
1.05 |
|---|
| 19 |
10315-98-7 |
O1CCN(CC1)CC(C)C |
Test |
0 |
0.000 |
0.00 |
0.28 |
1.00 |
1.80 |
0 |
1 |
1 |
1 |
0.23 |
|---|
获得训练，测试数据中的训练数据和结果
# 筛选训练数据中的结果数据
y_train=shen_train.iloc[:,[-2,-1]]
y_test=shen_test.iloc[:,[-2,-1]]
print("训练数据结果：\n{}\n测试数据结果：\n{}\n".format(y_train.head(),y_test.head()))
训练数据结果：
Class logBCF
0 1 0.74
1 1 0.93
2 3 3.24
3 3 -0.40
4 1 2.24
测试数据结果：
Class logBCF
5 3 1.13
12 3 1.40
15 1 2.57
16 2 1.05
19 1 0.23
# 筛选训练数据中的训练数据
x_train=shen_train.iloc[:,[3,4,5,6,7,8,9,10,11]]
x_test=shen_test.iloc[:,[3,4,5,6,7,8,9,10,11]]
print("训练数据：\n{}\n测试数据：\n{}\n".format(x_train.head(),x_test.head()))
训练数据：
nHM piPC09 PCD X2Av MLOGP ON1V N-072 B02[C-N] F04[C-O]
0 0 0.0 1.49 0.14 1.35 0.72 0 1 5
1 0 0.0 1.47 0.14 1.70 0.88 0 1 5
2 0 0.0 1.20 0.25 4.14 2.06 0 0 0
3 0 0.0 1.69 0.13 1.89 0.79 0 1 8
4 0 0.0 0.52 0.25 2.65 1.31 0 0 0
测试数据：
nHM piPC09 PCD X2Av MLOGP ON1V N-072 B02[C-N] F04[C-O]
5 0 0.000 1.40 0.18 2.85 0.86 0 0 0
12 0 5.768 2.21 0.18 3.40 1.47 0 0 1
15 0 5.614 2.21 0.16 3.40 1.31 0 0 2
16 0 5.030 2.07 0.16 3.09 1.54 0 1 0
19 0 0.000 0.00 0.28 1.00 1.80 0 1 1
# 查看训练数据的数据类型，当数据类型不是int时要将数据映射为数字才能进行训练
y_train.info()
Int64Index: 584 entries, 0 to 776
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Class 584 non-null int64
1 logBCF 584 non-null float64
dtypes: float64(1), int64(1)
memory usage: 13.7 KB
将非int类型的数据量化为整数
def change_type(values):
for col in values.columns[:]:
u=values[col].unique()
# 获取每个属性的具体属性值，argwhere方法可以获取属性值的索引值（0,1,2...），并将具体属性值映射为索引值
def conver(x):
return numpy.argwhere(u==x)[0,0]
values[col]=values[col].map(conver)
change_type(x_train)
change_type(x_test)
change_type(y_train)
change_type(y_test)
y_train
584 rows × 2 columns
| | Class | logBCF |
|---|
| 0 |
0 |
0 |
|---|
| 1 |
0 |
1 |
|---|
| 2 |
1 |
2 |
|---|
| 3 |
1 |
3 |
|---|
| 4 |
0 |
4 |
|---|
| ... |
... |
... |
|---|
| 771 |
0 |
333 |
|---|
| 772 |
0 |
334 |
|---|
| 773 |
0 |
41 |
|---|
| 774 |
0 |
142 |
|---|
| 776 |
0 |
335 |
|---|
knn=KNeighborsClassifier(n_neighbors=5,weights="distance",n_jobs=-1)
knn.fit(x_train, y_train)
y_=knn.predict(x_test)
acc=(y_==y_test).mean()
print("预测生物富集因子准确率：{}；预测生物富集等级准确率：{}".format(acc[1],acc[0]))
预测生物富集因子准确率：0.041025641025641026；预测生物富集等级准确率：0.4153846153846154
提高算法准确率
1，修改算法参数
knn=KNeighborsClassifier(n_neighbors=3,weights="distance",p=1,n_jobs=-1)
knn.fit(x_train, y_train)
y_=knn.predict(x_test)
acc=(y_==y_test).mean()
print("预测生物富集因子准确率：{}；预测生物富集等级准确率：{}".format(acc[1],acc[0]))
预测生物富集因子准确率：0.06666666666666667；预测生物富集等级准确率：0.441025641025641
2，修改训练数据
# 最大值最小值归一化（当数据间隔很大时可以有效提高准确率，消除属性之间的差异）
x_train_min=x_train.min()
x_train_max=x_train.max()
x2_train=(x_train-x_train_min)/(x_train_max-x_train_min)
x_test_min=x_test.min()
x_test_max=x_test.max()
x2_test=(x_test-x_test_min)/(x_test_max-x_test_min)
x2_test.head()
|
| nHM | piPC09 | PCD | X2Av | MLOGP | ON1V | N-072 | B02[C-N] | F04[C-O] |
|---|
| 5 |
0.0 |
0.000000 |
0.000000 |
0.000000 |
0.000000 |
0.000000 |
0.0 |
0.0 |
0.000000 |
|---|
| 12 |
0.0 |
0.008929 |
0.009524 |
0.000000 |
0.006849 |
0.007874 |
0.0 |
0.0 |
0.058824 |
|---|
| 15 |
0.0 |
0.017857 |
0.009524 |
0.029412 |
0.006849 |
0.015748 |
0.0 |
0.0 |
0.117647 |
|---|
| 16 |
0.0 |
0.026786 |
0.019048 |
0.029412 |
0.013699 |
0.023622 |
0.0 |
1.0 |
0.000000 |
|---|
| 19 |
0.0 |
0.000000 |
0.028571 |
0.058824 |
0.020548 |
0.031496 |
0.0 |
1.0 |
0.058824 |
|---|
knn=KNeighborsClassifier(n_neighbors=3,weights="distance",p=1,n_jobs=-1)
knn.fit(x2_train, y_train)
y_=knn.predict(x2_test)
acc=(y_==y_test).mean()
print("预测生物富集因子准确率：{}；预测生物富集等级准确率：{}".format(acc[1],acc[0]))
预测生物富集因子准确率：0.02564102564102564；预测生物富集等级准确率：0.4358974358974359
# Z-score归一化
# 求平均值
x_train_mean=x_train.mean()
# 求方差
x_train_std=x_train.std()
x3_train=(x_train-x_train_mean)/x_train_std
x3_train.head()
# 求平均值
x_test_mean=x_test.mean()
# 求方差
x_test_std=x_test.std()
x3_test=(x_test-x_test_mean)/x_test_std
x3_test.head()
| | nHM | piPC09 | PCD | X2Av | MLOGP | ON1V | N-072 | B02[C-N] | F04[C-O] |
|---|
| 5 |
-0.858971 |
-0.961536 |
-1.433213 |
-1.308189 |
-1.621471 |
-1.571899 |
-0.37945 |
-0.885971 |
-0.901314 |
|---|
| 12 |
-0.858971 |
-0.934067 |
-1.399267 |
-1.308189 |
-1.597619 |
-1.544272 |
-0.37945 |
-0.885971 |
-0.706463 |
|---|
| 15 |
-0.858971 |
-0.906599 |
-1.399267 |
-1.184954 |
-1.597619 |
-1.516645 |
-0.37945 |
-0.885971 |
-0.511611 |
|---|
| 16 |
-0.858971 |
-0.879131 |
-1.365321 |
-1.184954 |
-1.573767 |
-1.489018 |
-0.37945 |
1.122917 |
-0.901314 |
|---|
| 19 |
-0.858971 |
-0.961536 |
-1.331375 |
-1.061719 |
-1.549914 |
-1.461391 |
-0.37945 |
1.122917 |
-0.706463 |
|---|
knn=KNeighborsClassifier(n_neighbors=3,weights="distance",p=1,n_jobs=-1)
knn.fit(x3_train, y_train)
y_=knn.predict(x3_test)
acc=(y_==y_test).mean()
print("预测生物富集因子准确率：{}；预测生物富集等级准确率：{}".format(acc[1],acc[0]))
预测生物富集因子准确率：0.015384615384615385；预测生物富集等级准确率：0.41025641025641024
# sklearn封装为的z-score归一化操作
from sklearn.preprocessing import StandardScaler,MinMaxScaler
s=StandardScaler()
x4_train=s.fit_transform(x_train)
# x4_train 为z-score归一化后的数据
x4_test=s.fit_transform(x_test)
m=MinMaxScaler()
x5_train=m.fit_transform(x_train)
x5_test=m.fit_transform(x_test)
# x5_train 为最大值，最小值归一化后的数据
保存算法模型
from sklearn.externals import joblib
joblib.dump(knn,'./model',cache_size=9) # 保存模型，默认保存为压缩类型，会保存所有数据，cache_size=9时为压缩最小大小
# 加载模型
model=joblib.load('./model')
x=model.predict(x2_test)
acc=(y_==y_test).mean()
print("预测生物富集因子准确率：{}；预测生物富集等级准确率：{}".format(acc[1],acc[0]))
预测生物富集因子准确率：0.020512820512820513；预测生物富集等级准确率：0.41025641025641024