Kaggle 手写识别题

原文链接：http://blog.csdn.net/wiking__acm/article/details/43491611
手写体数字的识别，一个比较简单的问题。主要是特征太多，所以用PCA降维处理，然后用knn就可以得到一个准确率相当不错的结果了。

ipython notebook 下根据测试数据生成数字图案的代码：

%pylab  
import pandas as pd  

img = pd.read_csv('test.csv')  

p1 = img.values[1]  
pix = []  
for i in range(28):  
    pix.append([])  
    for j in range(28):  
        pix[i].append(p1[i*28+j])  

plt.imshow(pix) 

pca+knn 代码：

    import csv  
    import numpy  
    import pandas as pd  
    from sklearn.neighbors import KNeighborsClassifier  
    from sklearn.ensemble import BaggingClassifier  
    from sklearn.cross_validation import cross_val_score  
    from sklearn.decomposition import PCA  

    input_df = pd.read_csv('train.csv', header=0)  
    submit_df  = pd.read_csv('test.csv',  header=0)  

    # merge the two DataFrames into one  
    df = pd.concat([input_df, submit_df])  
    df = df .reset_index()  
    df = df.drop('index', axis=1)  
    df = df.reindex_axis(input_df.columns, axis=1)  


    features = input_df.values[:, 1:]  
    labels = input_df.values[:,0]  

    pca = PCA(n_components = 64)  
    pca.fit(df.values[:,1:])  
    features = pca.transform(features)  
    pred_data = pca.transform(submit_df.values)  

    clf = KNeighborsClassifier().fit(features, labels)  
    #print cross_val_score(clf, features, labels)  
    output = clf.predict(pred_data).astype(int)  
    ids = range(1, 28001)  
    # write to csv file  
    predictions_file = open("KNN.csv", "wb")  
    open_file_object = csv.writer(predictions_file)  
    open_file_object.writerow(["ImageId","Label"])  
    open_file_object.writerows(zip(ids, output))  
    predictions_file.close()  

    print "done."