1 朴素贝叶斯 iris数据集

iris中共150个数据，每个数据包含4个属性。可通过花萼长度，花萼宽度，花瓣长度，花瓣宽度4个属性预测鸢尾花卉属于（Setosa，Versicolour，Virginica）三个种类中的哪一类。
而朴素贝叶斯是基于贝叶斯定理，近似条件是属性相互独立。

# -*- coding: utf-8 -*-
import numpy as np
from sklearn.naive_bayes import GaussianNB
from sklearn import datasets
from sklearn.cross_validation import train_test_split
iris = datasets.load_iris()
iris_X = iris.data
iris_Y = iris.target

X_train, X_test, y_train, y_test = train_test_split(iris_X, iris_Y, test_size=0.3)
print(X_train)
print(y_train)
clf = GaussianNB()
clf.fit(X_train, y_train)
y_pred =clf.predict(X_test)
from sklearn.metrics import accuracy_score 
result=accuracy_score(y_test, y_pred) 
print(result)

2 朴素贝叶斯 20newsgroups数据集

20newsgroups数据集可用于文本分类。共大约20,000左右的新闻组文档，均匀分为20个不同主题的新闻。

# -*- coding: utf-8 -*-
from sklearn.naive_bayes import MultinomialNB
from sklearn.datasets import fetch_20newsgroups
from sklearn.cross_validation import train_test_split
news = fetch_20newsgroups(subset='all')
X_train,X_test,y_train,y_test = train_test_split(news.data,news.target,test_size=0.25,random_state=42)

from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer()
# 训练数据转换特征向量
X_train = vec.fit_transform(X_train)
X_test = vec.transform(X_test)
# 使用平滑处理初始化的朴素贝叶斯模型
mnb = MultinomialNB(alpha=1.0)
# 利用训练数据对模型参数进行估计
mnb.fit(X_train,y_train)
print(X_train)
print(y_train)
# 对测试验本进行类别预测。结果存储在变量y_predict中
y_predict = mnb.predict(X_test)
from sklearn.metrics import accuracy_score 
result=accuracy_score(y_test, y_predict) 
print(result)

3 线性层softmax回归模型 minst数据集

minst数据集是用于识别手写字母

import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder("float", [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
#交叉熵评估loss
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
#初始化
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):
	batch_xs, batch_ys = mnist.train.next_batch(100)
	sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
	
#评估模型
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})

4 多层卷积网络 minst数据集

# -*- coding:utf-8 -*-
import input_data
mnist = input_data.read_data_sets('./', one_hot=True)
import tensorflow as tf

def weight_variable(shape):
	initial = tf.truncated_normal(shape, stddev=0.1)
	return tf.Variable(initial)

def bias_variable(shape):
	initial = tf.constant(0.1, shape=shape)
	return tf.Variable(initial)

def conv2d(x, W):
	return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
	return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')
#第一层
W_conv1 = weight_variable([5, 5, 1, 32])
#[卷积核大小，卷积核大小，输入通道数，输出通道数]
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#第二层，输入14*14*32
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#1024个神经元的全连接层，输入7*7*64
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#softmax层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#评估
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20):
	batch = mnist.train.next_batch(50)
	if i%100 == 0:
		train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
		print "step %d, training accuracy %g"%(i, train_accuracy)
	train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print "test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})