训练TensorFlow以预测csv文件中的列

Question

我有一个在csv文件中构造的数据.我希望能够预测在给定所有其他列的情况下,第1列是1还是0.我如何开始训练程序(最好使用神经网络)来使用所有给定的数据来进行预测.有人可以给我看的代码吗？我试过喂它numpy.ndarray,FIF0Que(对不起,如果我拼错了),还有一个DataFrame; 什么都没有效果.这是我运行的代码,直到我收到错误 -

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

data = genfromtxt('cs-training.csv',delimiter=',')

x = tf.placeholder("float", [None, 11])
W = tf.Variable(tf.zeros([11,2]))
b = tf.Variable(tf.zeros([2]))

y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,2])

cross_entropy = -tf.reduce_sum(y_*tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

for i in range(1000):
    batch_xs, batch_ys = data.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

在这一点上我遇到了这个错误 -

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-128-b48741faa01b> in <module>()
      1 for i in range(1000):
----> 2     batch_xs, batch_ys = data.train.next_batch(100)
      3     sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

AttributeError: 'numpy.ndarray' object has no attribute 'train'

任何帮助是极大的赞赏.我需要做的就是预测第1列是1还是0.即使你所做的只是让我超过这一个错误,我应该能够从那里拿走它.

编辑:当我打印出来时,这就是csv的样子.

[[1,0.766126609,45,2,0.802982129,9120,13,0,6,0,2],
[0,0.957151019,40,0,0.121876201,2600,4,0,0,0,1],
[0,0.65818014,38,1,0.085113375,3042,2,1,0,0,0],
[0,0.233809776,30,0,0.036049682,3300,5,0,0,0,0]]

我正在尝试预测第一列.

Answer 1

以下内容从CSV文件读取并构建一个Tensorflow程序。该示例使用了Iris数据集，因为那可能是一个更有意义的示例。但是，它可能也适用于您的数据。

请注意，第一列将为[0,1或2]，因为存在3种虹膜。

#!/usr/bin/env python
import tensorflow as tf
import numpy as np
from numpy import genfromtxt

# Build Example Data is CSV format, but use Iris data
from sklearn import datasets
from sklearn.cross_validation import train_test_split
import sklearn
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-testing.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()


# 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)


buildDataFromIris()


data = genfromtxt('cs-training.csv',delimiter=',')  # Training data
test_data = genfromtxt('cs-testing.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 number of features, 4 in this example
#  B = 3 species of Iris (setosa, virginica and versicolor)
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"))

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

print("...")
# Run the training
for i in range(30):
    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 "Run {},{}".format(i,result)


"""
Below is the ouput
  ...
  Run 0,0.319999992847
  Run 1,0.300000011921
  Run 2,0.379999995232
  Run 3,0.319999992847
  Run 4,0.300000011921
  Run 5,0.699999988079
  Run 6,0.680000007153
  Run 7,0.699999988079
  Run 8,0.680000007153
  Run 9,0.699999988079
  Run 10,0.680000007153
  Run 11,0.680000007153
  Run 12,0.540000021458
  Run 13,0.419999986887
  Run 14,0.680000007153
  Run 15,0.699999988079
  Run 16,0.680000007153
  Run 17,0.699999988079
  Run 18,0.680000007153
  Run 19,0.699999988079
  Run 20,0.699999988079
  Run 21,0.699999988079
  Run 22,0.699999988079
  Run 23,0.699999988079
  Run 24,0.680000007153
  Run 25,0.699999988079
  Run 26,1.0
  Run 27,0.819999992847
  ...

 Ref:
 https://gist.github.com/mchirico/bcc376fb336b73f24b29#file-tensorflowiriscsv-py
"""

我希望这有帮助。

Answer 2

您只需提供与您的 x,y_ 形状匹配的输入。

x = tf.placeholder("float", [None, 11])
y_ = tf.placeholder("float", [None,2])

因此，而不是 data.train.next_batch(100) 创建并使用函数“my_csv_batch(count)”，该函数返回形状为 [[count,11], [count,2]] 的数组。第一组数组是您的 x 和接下来是你的 y_s 标签

my_csv_batch 将从 csv 文件返回一批（如果您有大量数据，则可能是随机生成的）。

顺便说一句，您还需要类似的东西来进行评估。您必须以类似的方式生成一批数据和标签。