-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
86 lines (62 loc) · 2.39 KB
/
model.py
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
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/iris.csv"
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv(url,names=names)
print(dataset.head())
print(dataset.shape)
print(dataset.groupby("class").size())
#for box and whiskers
dataset.plot(kind="box",subplots=True,layout=(2,2),sharex=False,sharey=False)
pyplot.show()
#for histograms
dataset.hist()
pyplot.show()
#for scatter plot matrix
scatter_matrix(dataset)
pyplot.show()
#split out validation set
array=dataset.values
X=array[:,0:4]
y=array[:,4]
X_train,X_validation,Y_train,Y_validation=train_test_split(X,y,test_size=0.2)
models=[]
models.append(("LR",LogisticRegression(solver="liblinear",multi_class="ovr")))
models.append(("LDA",LinearDiscriminantAnalysis()))
models.append(("KNN",KNeighborsClassifier()))
models.append(("CART",DecisionTreeClassifier()))
models.append(("NB",GaussianNB()))
models.append(("SVM",SVC(gamma='auto')))
results=[]
names=[]
for name,model in models:
kfold=StratifiedKFold(n_splits=10,random_state=1,shuffle=True)
cv_results=cross_val_score(model,X_train,Y_train,cv=kfold,scoring="accuracy")
results.append(cv_results)
names.append(name)
print('%s: %f (%f)' % (name, cv_results.mean(), cv_results.std()))
pyplot.boxplot(results,labels=names)
pyplot.show()
model=SVC(gamma='auto')
model.fit(X_train,Y_train)
predictions=model.predict(X_validation)
print(accuracy_score(Y_validation,predictions))
print(confusion_matrix(Y_validation,predictions))
print(classification_report(Y_validation,predictions))
VA=[]
GA=[]
for i in range(len(Y_validation)):
print(Y_train,predictions)