在kaggle上做的第一個專案，作為資料分析的初學者，學習到了很多東西

專案說明

在本次比賽中，您的目標是正確識別來自數萬個手寫影象資料集的數字。我們策劃了一套教程式的核心，涵蓋從迴歸到神經網路的一切。我們鼓勵您嘗試使用不同的演算法來學習第一手什麼工作良好以及技術如何比較。

這裡我使用了SVM和MLP兩種方法解決，程式碼如下

PCA+SVM

#-*- coding: utf-8 -*-

import pandas as pd
from sklearn import svm, metrics
from sklearn.decomposition import PCA

train = pd.read_csv('../input/train.csv')
test = pd.read_csv('../input/test.csv')
train_x = train.ix[:,1:].values.astype('int32')
train_y = train.ix[:,0].values.astype('int32')
test_x = test.ix[:,:].values.astype('int32')

# PCA reduction
pca = PCA(n_components=36, whiten=True)
pca.fit(train_x)
train_x = pca.transform(train_x)
test_x = pca.transform(test_x)

# print train_y
# print type(train_x), type(train_y)
# print len(train_y), len(train_x)
# print train_x[0], train_y[0]

# SVM classifier
clf = svm.SVC()
clf.fit(train_x, train_y)

# test output
def write_preds(preds, fname):
    pd.DataFrame({"ImageId": range(1,len(preds)+1), "Label": preds}).to_csv(fname, index=False, header=True)
test_y = clf.predict(test_x)
write_preds(test_y, 'out.csv')
 

MLP+Normalization

#-*- coding: utf-8 -*-

from keras.models import Sequential
from keras.utils import np_utils
from keras.layers.core import Dense, Activation, Dropout

import pandas as pd
import numpy as np

# Read data
train = pd.read_csv('../input/train.csv')
labels = train.ix[:,0].values.astype('int32')
X_train = (train.ix[:,1:].values).astype('float32')
X_test = (pd.read_csv('../input/test.csv').values).astype('float32')

# convert list of labels to binary class matrix
y_train = np_utils.to_categorical(labels) 

# pre-processing: divide by max and substract mean
scale = np.max(X_train)
X_train /= scale
X_test /= scale

mean = np.std(X_train)
X_train -= mean
X_test -= mean

input_dim = X_train.shape[1]
nb_classes = y_train.shape[1]

# Here's a Deep Dumb MLP (DDMLP)
model = Sequential()
model.add(Dense(128, input_dim=input_dim))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

# we'll use categorical xent for the loss, and RMSprop as the optimizer
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

print("Training...")
model.fit(X_train, y_train, nb_epoch=10, batch_size=16, validation_split=0.1, verbose=2)

print("Generating test predictions...")
preds = model.predict_classes(X_test, verbose=0)

def write_preds(preds, fname):
    pd.DataFrame({"ImageId": list(range(1,len(preds)+1)), "Label": preds}).to_csv(fname, index=False, header=True)

write_preds(preds, "mlp.csv")
 

提交資料，準確率0.96814