如何使用TensorFlow将预测值添加到CSV文件中的空列？

时间：2015-11-24 18:32:34

标签： python csv tensorflow

所以我提供了大量的代码，其预测的准确率大约为93％。我现在想知道如何做的是接受训练有素的程序，让它看看没有答案的实际测试数据，并使其填写答案而不管准确性如何。这是我所拥有的预测准确率达到约93％的代码。

import tensorflow as tf
import numpy as np
from numpy import genfromtxt
import sklearn

# Convert to one hot
def convertOneHot(data):
    y=np.array([int(i[0]) for i in data])
    y_onehot=[0]*len(y)
    for i,j in enumerate(y):
        y_onehot[i]=[0]*(y.max() + 1)
        y_onehot[i][j]=1
    return (y,y_onehot)

data = genfromtxt('cs-training.csv',delimiter=',')  # Training data
test_data = genfromtxt('cs-test.csv',delimiter=',')  # Test data

x_train=np.array([ i[1::] for i in data])
y_train,y_train_onehot = convertOneHot(data)

x_test=np.array([ i[1::] for i in test_data])
y_test,y_test_onehot = convertOneHot(test_data)

A=data.shape[1]-1 # Number of features, Note first is y
B=len(y_train_onehot[0])
tf_in = tf.placeholder("float", [None, A]) # Features
tf_weight = tf.Variable(tf.zeros([A,B]))
tf_bias = tf.Variable(tf.zeros([B]))
tf_softmax = tf.nn.softmax(tf.matmul(tf_in,tf_weight) + tf_bias)

# Training via backpropagation
tf_softmax_correct = tf.placeholder("float", [None,B])
tf_cross_entropy = -tf.reduce_sum(tf_softmax_correct*tf.log(tf_softmax))

# Train using tf.train.GradientDescentOptimizer
tf_train_step = tf.train.GradientDescentOptimizer(0.01).minimize(tf_cross_entropy)

# Add accuracy checking nodes
tf_correct_prediction = tf.equal(tf.argmax(tf_softmax,1), tf.argmax(tf_softmax_correct,1))
tf_accuracy = tf.reduce_mean(tf.cast(tf_correct_prediction, "float"))

saver = tf.train.Saver([tf_weight,tf_bias])

# Initialize and run
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

print("...")
# Run the training
for i in range(100):
    sess.run(tf_train_step, feed_dict={tf_in: x_train, tf_softmax_correct: y_train_onehot})

#Print accuracy
    result = sess.run(tf_accuracy, feed_dict={tf_in: x_test, tf_softmax_correct: y_test_onehot})
print result

现在我有了实际的测试集cs-test-actual.csv，其中第一列完全是空的，我需要用预测的1或0来填充它。我该怎么做呢？

1 个答案:

答案 0 :(得分：3)

上述程序似乎没有保存受过训练的会话。我想你想分两步完成这个。

  1. 训练并保存会话
  2. 恢复保存会话，并通过它运行测试数据。

    3. 第1步： 

     #!/usr/bin/env python

 import tensorflow as tf
 import numpy as np
 from numpy import genfromtxt
 import sklearn

 # Convert to one hot
 def convertOneHot(data):
     y=np.array([int(i[0]) for i in data])
     y_onehot=[0]*len(y)
     for i,j in enumerate(y):
         y_onehot[i]=[0]*(y.max() + 1)
         y_onehot[i][j]=1
     return (y,y_onehot)

 # Build Example Data is CSV format, but use Iris data
 from sklearn import datasets
 from sklearn.model_selection import train_test_split
 def buildDataFromIris():
     iris = datasets.load_iris()
     X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.33, random_state=42)
     f=open('cs-training.csv','w')
     for i,j in enumerate(X_train):
         k=np.append(np.array(y_train[i]),j   )
         f.write(",".join([str(s) for s in k]) + '\n')
     f.close()
     f=open('cs-test.csv','w')
     for i,j in enumerate(X_test):
         k=np.append(np.array(y_test[i]),j   )
         f.write(",".join([str(s) for s in k]) + '\n')
     f.close()

 # Recreate logging and save dir
 # Seems the tensorflow won't always overwrite
 import shutil, os, sys
 TMPDir='./tensorTMP'
 try:
  shutil.rmtree(TMPDir)
 except:
  print "Tmp Dir did not exist...that's okay"
 os.mkdir(TMPDir, 0755 )



 # Populate the data
 buildDataFromIris()

 data = genfromtxt('cs-training.csv',delimiter=',')  # Training data
 test_data = genfromtxt('cs-test.csv',delimiter=',')  # Test data

 x_train=np.array([ i[1::] for i in data])
 y_train,y_train_onehot = convertOneHot(data)

 x_test=np.array([ i[1::] for i in test_data])
 y_test,y_test_onehot = convertOneHot(test_data)

 A=data.shape[1]-1 # Number of features, Note first is y
 B=len(y_train_onehot[0])
 tf_in = tf.placeholder("float", [None, A]) # Features
 tf_weight = tf.Variable(tf.zeros([A,B]))
 tf_bias = tf.Variable(tf.zeros([B]))
 tf_softmax = tf.nn.softmax(tf.matmul(tf_in,tf_weight) + tf_bias)

 # Training via backpropagation
 tf_softmax_correct = tf.placeholder("float", [None,B])
 tf_cross_entropy = -tf.reduce_sum(tf_softmax_correct*tf.log(tf_softmax))

 # Train using tf.train.GradientDescentOptimizer
 tf_train_step = tf.train.GradientDescentOptimizer(0.01).minimize(tf_cross_entropy)

 # Add accuracy checking nodes
 tf_correct_prediction = tf.equal(tf.argmax(tf_softmax,1), tf.argmax(tf_softmax_correct,1))
 tf_accuracy = tf.reduce_mean(tf.cast(tf_correct_prediction, "float"))

 saver = tf.train.Saver([tf_weight,tf_bias])

 # Initialize and run
 init = tf.initialize_all_variables()
 sess = tf.Session()
 sess.run(init)

 THRESHOLD = 0.98
 saved = False
 print("...")
 # Run the training
 for i in range(100):
     sess.run(tf_train_step, feed_dict={tf_in: x_train, tf_softmax_correct: y_train_onehot})
     result = sess.run(tf_accuracy, feed_dict={tf_in: x_test, tf_softmax_correct: y_test_onehot})
     # If it's well trained on this iteration, save it. We just need one save.
     if result > THRESHOLD  and saved == False:
         saved = True
         print "saving result {}".format(result)
         saver.save(sess,TMPDir +"/savedSess")

    唯一的修改是使用Iris生成样本数据，为会话建立THRESHOLD或置信区间。如果它超过了THRESHOLD，则保存会话。运行第一步后，应训练并保存模型。

    第2步：

    恢复已保存的会话，并通过它运行训练数据。

     #!/usr/bin/env python

 import tensorflow as tf
 import numpy as np
 from numpy import genfromtxt
 import sklearn

 # Convert to one hot
 def convertOneHot(data):
     y=np.array([int(i[0]) for i in data])
     y_onehot=[0]*len(y)
     for i,j in enumerate(y):
         y_onehot[i]=[0]*(y.max() + 1)
         y_onehot[i][j]=1
     return (y,y_onehot)


 data = genfromtxt('cs-training.csv',delimiter=',')  # Training data
 test_data = genfromtxt('cs-test.csv',delimiter=',')  # Test data

 x_train=np.array([ i[1::] for i in data])
 y_train,y_train_onehot = convertOneHot(data)

 x_test=np.array([ i[1::] for i in test_data])
 y_test,y_test_onehot = convertOneHot(test_data)

 A=data.shape[1]-1 # Number of features, Note first is y
 B=len(y_train_onehot[0])
 tf_in = tf.placeholder("float", [None, A]) # Features
 tf_weight = tf.Variable(tf.zeros([A,B]))
 tf_bias = tf.Variable(tf.zeros([B]))
 tf_softmax = tf.nn.softmax(tf.matmul(tf_in,tf_weight) + tf_bias)

 # Training via backpropagation
 tf_softmax_correct = tf.placeholder("float", [None,B])
 tf_cross_entropy = -tf.reduce_sum(tf_softmax_correct*tf.log(tf_softmax))

 # Train using tf.train.GradientDescentOptimizer
 tf_train_step = tf.train.GradientDescentOptimizer(0.01).minimize(tf_cross_entropy)

 # Add accuracy checking nodes
 tf_correct_prediction = tf.equal(tf.argmax(tf_softmax,1), tf.argmax(tf_softmax_correct,1))
 tf_accuracy = tf.reduce_mean(tf.cast(tf_correct_prediction, "float"))

 saver = tf.train.Saver([tf_weight,tf_bias])

 # Initialize and run
 init = tf.initialize_all_variables()
 sess = tf.Session()
 sess.run(init)

 TMPDir='./tensorTMP'
 saver.restore(sess, TMPDir + '/savedSess')
 ans = sess.run(tf_softmax, feed_dict={tf_in: x_test, tf_softmax_correct: y_test_onehot})

 print ans

    注意，您的输出将如下所示...... 

    [[  6.17585704e-02   8.63590300e-01   7.46511072e-02]
[  9.98804331e-01   1.19561062e-03   3.25832108e-13]
[  1.52018686e-07   4.49650863e-04   9.99550164e-01]
相关问题
最新问题