kaggle-识别手写数字

import numpy as np
import csv
import pandas as pd

def load_data(csv):
    lines = csv.reader(open(csv))
    l = []
    for line in lines:
        l.append(line)
    return l

l = load_data('train.csv')
l = np.array(l[1:], dtype=float)
train = l[1:,1:]
label = l[1:,0]

a = pd.DataFrame(train)
# 二值化，不影响数字显示
a[a > 1] = 1


l = load_data('test.csv')
test = np.array(l[1:], dtype=float)
a = pd.DataFrame(test)
# 二值化，不影响数字显示
a[a > 1] = 1

import seaborn as sns
%matplotlib inline
df = pd.DataFrame(np.hstack((train, label[:,None])),
               columns = range(train.shape[1]) + ["class"])
plt.figure(figsize=(8, 6))
_ = sns.heatmap(df.corr(), annot=False)

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score

X_train = train
y_train = label
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)

lr = LogisticRegression(C=10000.0, random_state=0)
lr.fit(X_train_std, y_train)

y_pred = lr.predict(X_train_std)
print('Misclassified samples: %.8f' % ((y_train != y_pred).sum()/float(len(y_train))))

OUT:Misclassified samples: 0.06795400

X_test = test
X_test_std = sc.transform(X_test)
'''sc.scale_标准差, sc.mean_平均值, sc.var_方差'''
y_pred = lr.predict(X_test_std)
print y_pred

OUT: [ 2.  0.  9. ...,  3.  9.  2.]

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import csv

test1 = test[1]
test2 = []
for el in test1:
    test2.append([0,0,el])

img = np.array(test2)
print img.shape
img1 = img.reshape((28,28,3))
plt.figure("dog")
plt.imshow(img1)
plt.axis('off')
plt.show()