KNN鳶尾花數據分類

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
import warnings

import sklearn
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier#KNN
from sklearn.preprocessing import label_binarize
from sklearn import metrics

## 設置字符集，防止中文亂碼
mpl.rcParams['font.sans-serif']=[u'simHei']
mpl.rcParams['axes.unicode_minus']=False

## 數據加載
path = "datas/iris.data"
names = ['sepal length', 'sepal width', 'petal length', 'petal width', 'cla']
df = pd.read_csv(path, header=None, names=names)
df['cla'].value_counts()
df.head()

	sepal length	sepal width	petal length	petal width	cla
0	5.1	3.5	1.4	0.2	Iris-setosa
1	4.9	3.0	1.4	0.2	Iris-setosa
2	4.7	3.2	1.3	0.2	Iris-setosa
3	4.6	3.1	1.5	0.2	Iris-setosa
4	5.0	3.6	1.4	0.2	Iris-setosa

def parseRecord(record):
    result=[]
    r = zip(names,record)
    for name,v in r:
        if name == 'cla':
            if v == 'Iris-setosa':
                result.append(1)
            elif v == 'Iris-versicolor':
                result.append(2)
            elif v == 'Iris-virginica':
                result.append(3)
            else:
                result.append(np.nan)
        else:
            result.append(float(v))
    return result

### 1. 數據轉換為數字以及分割
## 數據轉換
datas = df.apply(lambda r: parseRecord(r), axis=1)
## 異常數據刪除
datas = datas.dropna(how='any')
## 數據分割
X = datas[names[0:-1]]
Y = datas[names[-1]]
## 數據抽樣(訓練數據和測試數據分割)
X_train,X_test,Y_train,Y_test = train_test_split(X, Y, test_size=0.4, random_state=0)

print ("原始數據條數:%d；訓練數據條數:%d；特征個數:%d；測試樣本條數:%d" % (len(X), len(X_train), X_train.shape[1], X_test.shape[0]))

原始數據條數:150；訓練數據條數:90；特征個數:4；測試樣本條數:60

##### KNN算法實現
# a. 模型構建
# 模型中介紹的K值：n_neighbors
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(X_train, Y_train)

# b. 模型效果輸出
## 將正確的數據轉換為矩陣形式
y_test_hot = label_binarize(Y_test,classes=(1,2,3))
## 得到預測屬於某個類別的概率值
knn_y_score = knn.predict_proba(X_test)
## 計算roc的值
knn_fpr, knn_tpr, knn_threasholds = metrics.roc_curve(y_test_hot.ravel(),knn_y_score.ravel())
## 計算auc的值
knn_auc = metrics.auc(knn_fpr, knn_tpr)
print ("KNN算法R值：", knn.score(X_train, Y_train))
print ("KNN算法AUC值：", knn_auc)

# c. 模型預測
knn_y_predict = knn.predict(X_test)

KNN算法R值： 0.9888888888888889
KNN算法AUC值： 0.9700000000000001

## 畫圖2：預測結果畫圖
x_test_len = range(len(X_test))
plt.figure(figsize=(12, 9), facecolor='w')
plt.ylim(0.5,3.5)
plt.plot(x_test_len, Y_test, 'ro',markersize = 6, zorder=3, label=u'真實值')
plt.plot(x_test_len, knn_y_predict, 'yo', markersize = 16, zorder=1, label=u'KNN算法預測值,$R^2$=%.3f' % knn.score(X_test, Y_test))
plt.legend(loc = 'lower right')
plt.xlabel(u'數據編號', fontsize=18)
plt.ylabel(u'種類', fontsize=18)
plt.title(u'鳶尾花數據分類', fontsize=20)
plt.show()