-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathML.py
More file actions
168 lines (147 loc) · 6.9 KB
/
Copy pathML.py
File metadata and controls
168 lines (147 loc) · 6.9 KB
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
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
from collections import Counter
from sklearn.metrics import f1_score, accuracy_score, confusion_matrix,precision_score, recall_score, matthews_corrcoef,cohen_kappa_score
import sys
#######################################
data = pd.read_csv("/public/slst/home/ningwei/methylation/process_data/train_data/train_data_smote_12_6.csv")
Class = data['project_id'].unique()
Class_dict = dict(zip(Class, range(len(Class))))
train_y = data['project_id'].apply(lambda x: Class_dict[x])
train_x = data.iloc[:,1:data.shape[1]]
data = pd.read_csv("/public/slst/home/ningwei/methylation/process_data/train_data/test_data_smote_12_6.csv")
test_y = data['project_id'].apply(lambda x: Class_dict[x])
test_x = data.iloc[:,1:data.shape[1]]
target_names = list(Class_dict.keys())
########################## K-NN
import pandas as pd
import numpy as np
import operator
import os
from sklearn.neighbors import KNeighborsClassifier
clf_sk = KNeighborsClassifier()
clf_sk.fit(train_x, train_y)
k_predcit = clf_sk.predict(test_x)
accuracy = accuracy_score(test_y,k_predcit)
F1_score = f1_score(test_y, k_predcit,average='macro')
recall = recall_score(test_y, k_predcit, average='weighted')
precision = precision_score(test_y, k_predcit,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"K-紧邻_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n") #换行
f.write("test_F1: "+str(F1_score)) #
f.write("\n") #换行
f.close()
################### NB
from sklearn.naive_bayes import MultinomialNB
nb=MultinomialNB()
nb.fit(train_x, train_y)
print(nb.predict(test_x))
p_predict = nb.predict(test_x)
accuracy = accuracy_score(test_y,p_predict)
F1_score = f1_score(test_y, p_predict,average='macro')
recall = recall_score(test_y, p_predict, average='weighted')
precision = precision_score(test_y, p_predict,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"朴素贝叶斯_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n") #换行
f.write("test_F1: "+str(F1_score)) #
f.write("\n") #换行
f.close()
###################
from sklearn.model_selection import cross_val_score
from sklearn.datasets import make_blobs
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.tree import DecisionTreeClassifier
## DT
clf1 = DecisionTreeClassifier(max_depth=None, min_samples_split=2,random_state=0)
#scores1 = cross_val_score(clf1, train_x, train_y)
#print(scores1.mean())
clf1.fit(train_x,train_y)
print(clf1.predict(test_x))
j_predict = clf1.predict(test_x)
accuracy = accuracy_score(test_y,j_predict)
F1_score = f1_score(test_y, j_predict,average='macro')
recall = recall_score(test_y, j_predict, average='weighted')
precision = precision_score(test_y, j_predict,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"决策树_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n") #换行
f.write("test_F1: "+str(F1_score)) #
f.write("\n") #换行
f.close()
## RF
clf2 = RandomForestClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
#scores2 = cross_val_score(clf2, X, y)
#print(scores2.mean())
clf2.fit(train_x,train_y)
print(clf2.predict(test_x))
R_predict = clf2.predict(test_x)
accuracy = accuracy_score(test_y,R_predict)
F1_score = f1_score(test_y,R_predict,average='macro')
recall = recall_score(test_y, R_predict, average='weighted')
precision = precision_score(test_y, R_predict,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"随机森林_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n")
f.write("test_F1: "+str(F1_score)) #
f.write("\n")
f.close()
## ExtraTree
clf_Extra = ExtraTreesClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
# scores3 = cross_val_score(clf3, X, y)
# print(scores3.mean())
clf_Extra.fit(train_x,train_y)
print(clf_Extra.predict(test_x))
e_predict = clf_Extra.predict(test_x)
accuracy = accuracy_score(test_y,e_predict)
F1_score = f1_score(test_y, e_predict,average='macro')
recall = recall_score(test_y, e_predict, average='weighted')
precision = precision_score(test_y, e_predict,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"ExtraTree_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n") #换行
f.write("test_F1: "+str(F1_score)) #
f.write("\n") #换行
f.close()
################### XGBOOST
import xgboost as xgb
model = xgb.XGBClassifier(max_depth=5,learning_rate=0.1,n_estimators=160,silent=True,objective='multi:softmax')
model.fit(train_x,train_y)
X_pred = model.predict(test_x)
accuracy = accuracy_score(test_y,X_pred)
F1_score = f1_score(test_y, X_pred,average='macro')
recall = recall_score(test_y, X_pred, average='weighted')
precision = precision_score(test_y, X_pred,average='weighted')
f = open("/public/slst/home/ningwei/methylation/process_data/ML_result/"+"XGBOOST_11_23"+".txt",'a') #若文件不存在，系统自动创建。'a'表示可连续写入到文件，保留原内容，在原内容之后写入。可修改该模式（'w+','w','wb'等）
f.write("test_acc: "+str(accuracy)) #
f.write("\n") #
f.write("test_recall: "+str(recall)) #
f.write("\n") #
f.write("test_precision: "+str(precision)) #
f.write("\n")
f.write("test_F1: "+str(F1_score)) #
f.write("\n")
f.close()