南大《探索数据的奥秘》课件示例代码笔记12

In [9]: import pandas as pd
import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
from sklearn import datasets
iris=datasets.load_iris()
print(type(iris.data))
print(iris.data)
#print(type(iris.target))
#print(iris.target)
<class 'numpy.ndarray'>
[[5.1 3.5 1.4 0.2]
[4.9 3. 1.4 0.2]
[4.7 3.2 1.3 0.2]
[4.6 3.1 1.5 0.2]
[5. 3.6 1.4 0.2]
[5.4 3.9 1.7 0.4]
[4.6 3.4 1.4 0.3]
[5. 3.4 1.5 0.2]
[4.4 2.9 1.4 0.2]
[4.9 3.1 1.5 0.1]
[5.4 3.7 1.5 0.2]
[4.8 3.4 1.6 0.2]
[4.8 3. 1.4 0.1]
[4.3 3. 1.1 0.1]
[5.8 4. 1.2 0.2]
[5.7 4.4 1.5 0.4]
[5.4 3.9 1.3 0.4]
[5.1 3.5 1.4 0.3]
[5.7 3.8 1.7 0.3]
[5.1 3.8 1.5 0.3]
[5.4 3.4 1.7 0.2]
[5.1 3.7 1.5 0.4]
[4.6 3.6 1. 0.2]
[5.1 3.3 1.7 0.5]
[4.8 3.4 1.9 0.2]
[5. 3. 1.6 0.2]
[5. 3.4 1.6 0.4]
[5.2 3.5 1.5 0.2]
[5.2 3.4 1.4 0.2]
[4.7 3.2 1.6 0.2]
[4.8 3.1 1.6 0.2]
[5.4 3.4 1.5 0.4]
[5.2 4.1 1.5 0.1]
[5.5 4.2 1.4 0.2]
[4.9 3.1 1.5 0.1]
[5. 3.2 1.2 0.2]
[5.5 3.5 1.3 0.2]
[4.9 3.1 1.5 0.1]
[4.4 3. 1.3 0.2]
[5.1 3.4 1.5 0.2]
[5. 3.5 1.3 0.3]
[4.5 2.3 1.3 0.3]
[4.4 3.2 1.3 0.2]
[5. 3.5 1.6 0.6]
[5.1 3.8 1.9 0.4]
[4.8 3. 1.4 0.3]
[5.1 3.8 1.6 0.2]
[4.6 3.2 1.4 0.2]
[5.3 3.7 1.5 0.2]
[5. 3.3 1.4 0.2]
[7. 3.2 4.7 1.4]
[6.4 3.2 4.5 1.5]
[6.9 3.1 4.9 1.5]
[5.5 2.3 4. 1.3]
[6.5 2.8 4.6 1.5]
[5.7 2.8 4.5 1.3]
[6.3 3.3 4.7 1.6]
[4.9 2.4 3.3 1. ]
[6.6 2.9 4.6 1.3]
[5.2 2.7 3.9 1.4]
[5. 2. 3.5 1. ]
[5.9 3. 4.2 1.5]
[6. 2.2 4. 1. ]
[6.1 2.9 4.7 1.4]
[5.6 2.9 3.6 1.3]
[6.7 3.1 4.4 1.4]
[5.6 3. 4.5 1.5]
[5.8 2.7 4.1 1. ]
[6.2 2.2 4.5 1.5]
[5.6 2.5 3.9 1.1]
[5.9 3.2 4.8 1.8]
[6.1 2.8 4. 1.3]
[6.3 2.5 4.9 1.5]
[6.1 2.8 4.7 1.2]
[6.4 2.9 4.3 1.3]
[6.6 3. 4.4 1.4]
[6.8 2.8 4.8 1.4]
[6.7 3. 5. 1.7]
[6. 2.9 4.5 1.5]
[5.7 2.6 3.5 1. ]
[5.5 2.4 3.8 1.1]
[5.5 2.4 3.7 1. ]
[5.8 2.7 3.9 1.2]
[6. 2.7 5.1 1.6]
[5.4 3. 4.5 1.5]
[6. 3.4 4.5 1.6]
[6.7 3.1 4.7 1.5]
[6.3 2.3 4.4 1.3]
[5.6 3. 4.1 1.3]
[5.5 2.5 4. 1.3]
[5.5 2.6 4.4 1.2]
[6.1 3. 4.6 1.4]
[5.8 2.6 4. 1.2]
[5. 2.3 3.3 1. ]
[5.6 2.7 4.2 1.3]
[5.7 3. 4.2 1.2]
[5.7 2.9 4.2 1.3]
[6.2 2.9 4.3 1.3]
[5.1 2.5 3. 1.1]
[5.7 2.8 4.1 1.3]
[6.3 3.3 6. 2.5]
[5.8 2.7 5.1 1.9]
[7.1 3. 5.9 2.1]
[6.3 2.9 5.6 1.8]
[6.5 3. 5.8 2.2]
[7.6 3. 6.6 2.1]
[4.9 2.5 4.5 1.7]
[7.3 2.9 6.3 1.8]
[6.7 2.5 5.8 1.8]
[7.2 3.6 6.1 2.5]
[6.5 3.2 5.1 2. ]
[6.4 2.7 5.3 1.9]
[6.8 3. 5.5 2.1]
[5.7 2.5 5. 2. ]
[5.8 2.8 5.1 2.4]
[6.4 3.2 5.3 2.3]
[6.5 3. 5.5 1.8]
[7.7 3.8 6.7 2.2]
[7.7 2.6 6.9 2.3]
[6. 2.2 5. 1.5]
[6.9 3.2 5.7 2.3]
[5.6 2.8 4.9 2. ]
[7.7 2.8 6.7 2. ]
[6.3 2.7 4.9 1.8]
[6.7 3.3 5.7 2.1]
[7.2 3.2 6. 1.8]
[6.2 2.8 4.8 1.8]
[6.1 3. 4.9 1.8]
[6.4 2.8 5.6 2.1]
[7.2 3. 5.8 1.6]
[7.4 2.8 6.1 1.9]
[7.9 3.8 6.4 2. ]
[6.4 2.8 5.6 2.2]
[6.3 2.8 5.1 1.5]
[6.1 2.6 5.6 1.4]
[7.7 3. 6.1 2.3]
[6.3 3.4 5.6 2.4]
[6.4 3.1 5.5 1.8]
[6. 3. 4.8 1.8]
[6.9 3.1 5.4 2.1]
[6.7 3.1 5.6 2.4]
[6.9 3.1 5.1 2.3]
[5.8 2.7 5.1 1.9]
[6.8 3.2 5.9 2.3]
[6.7 3.3 5.7 2.5]
[6.7 3. 5.2 2.3]
[6.3 2.5 5. 1.9]
[6.5 3. 5.2 2. ]
[6.2 3.4 5.4 2.3]
[5.9 3. 5.1 1.8]]

In [11]: import pandas as pd
import numpy as np
from sklearn import datasets
from scipy import stats
import matplotlib.pyplot as plt
iris=datasets.load_iris()
#print((iris))
plt.figure(figsize=(12,15))
for n in range(4):
print(n)
for m in range(3):
x=(
iris.data[m*50:m*50+50,n]-iris.data[m*50:m*50+50,n].mean())/iris.data
[m*50:m*50+50,n].std()
plt.subplot(4,3,n*3+m+1)
stats.probplot(x,dist='norm',plot=plt)
plt.text(-2,2,iris.feature_names[n])
if n==0:
plt.title(iris.target_names[m])
else:
plt.title('')
plt.xlim([-2.5,2.5])
plt.ylim([-2.5,2.5])
plt.plot([-2.5,2.5],[-2.5,2.5],c='g')
plt.savefig('chap72.png')
0 
1 
2 
3

In [40]: my_data=iris.data[:,:2]
print((my_data).shape)
(150, 2)
In [41]: from sklearn.model_selection import train_test_split
#X_train,X_test,Y_train,Y_test=train_test_split(iris.data,iris.target,test_size=0.2,
random_state=0)test_size=0.2,random_state=0)
X_train,X_test,Y_train,Y_test=train_test_split(my_data,iris.target,
test_size=0.2,random_state=0)
test_size=0.2,random_state=0)
from sklearn.naive_bayes import GaussianNB
clf=GaussianNB()
clf.fit(X_train,Y_train)
y_pred=clf.predict(X_test)
Y=pd.DataFrame(np.transpose([Y_test,y_pred]),columns={'true_type','predict_type'})
Y.head(30)
Out[41]: predict_type true_type
0 2 1
1 1 1
2 0 0
3 2 2
4 0 0
5 2 2
6 0 0
7 1 2
8 1 2
9 1 1
10 2 1
11 1 2
12 1 1
13 1 2
14 1 1
15 0 0
16 1 1
17 1 1
18 0 0
19 0 0
20 2 1
21 1 1
22 0 0
23 0 0
24 2 1
25 0 0
26 0 0
27 1 1
28 1 1
29 0 0
In [42]: from sklearn.metrics import confusion_matrix
print(confusion_matrix(y_pred,Y_test))
[[11 0 0]
[ 0 9 4]
[ 0 4 2]]
In [43]: from sklearn.metrics import classification_report
print(classification_report(y_pred,Y_test))
precision recall f1-score support
0 1.00 1.00 1.00 11
1 0.69 0.69 0.69 13
2 0.33 0.33 0.33 6
avg / total 0.73 0.73 0.73 30
In [44]: from sklearn.metrics import roc_curve
from sklearn.metrics import roc_auc_score
my_auc=[]
for n in range(4):
#fpr,tpr,th=roc_curve(iris.target[:100],iris.data[:,n)
my_auc.append(roc_auc_score(iris.target[:100],iris.data[:100,n]))
print(my_auc)
#print(iris.target[:100])
#print(iris.data[:100,:])
[0.9325999999999999, 0.07780000000000002, 1.0, 1.0]
In [56]: plt.plot(np.ones([50,1]),iris.data[:50,0],'or')
plt.plot(np.ones([50,1])+0.2,iris.data[50:100,0],'*g')
plt.plot(np.ones([50,1])+1,iris.data[:50,1],'or')
plt.plot(np.ones([50,1])+1.2,iris.data[50:100,1],'*g')
plt.plot(np.ones([50,1])+2,iris.data[:50,2],'or')
plt.plot(np.ones([50,1])+2.2,iris.data[50:100,2],'*g')
plt.plot(np.ones([50,1])+3,iris.data[:50,3],'or')
plt.plot(np.ones([50,1])+3.2,iris.data[50:100,3],'*g')
plt.xticks([1,2,3,4],iris.feature_names)
plt.legend(iris.target_names[:2])
Out[56]: <matplotlib.legend.Legend at 0x272c66ebac8>

In [21]: plt.figure(figsize=(5,12))
plt.subplot(3,1,1)
plt.scatter(iris.data[:50,0],iris.data[:50,1],c='r',marker='o')
plt.scatter(iris.data[50:100,0],iris.data[50:100,1],c='b',marker='*')
plt.subplot(3,1,2)
plt.scatter(iris.data[:50,0],iris.data[:50,2],c='r',marker='o')
plt.scatter(iris.data[50:100,0],iris.data[50:100,2],c='b',marker='*')
plt.subplot(3,1,3)
plt.scatter(iris.data[:50,0],iris.data[:50,3],c='r',marker='o')
plt.scatter(iris.data[50:100,0],iris.data[50:100,3],c='b',marker='*')
Out[21]: <matplotlib.collections.PathCollection at 0x272c83ff9e8>