我一直在努力让张量流程解决多类的讨价还价问题。基本上，数据包含6个我已转换为所有数字观察的特征。目标是使用这6个特征来预测行程类型，其中有38种不同的行程类型。我一直在尝试使用tensorflow来预测这些行程类型。以下代码是我到目前为止的代码，包括我用来格式化csv文件的代码。代码将运行，但是对于运行1，输出开始正常，然后非常差，其余运行的输出相同。以下是运行时输出的示例：
Run 0,0.268728911877
Run 1,0.0108088823035
Run 2,0.0108088823035
Run 3,0.0108088823035
Run 4,0.0108088823035
Run 5,0.0108088823035
Run 6,0.0108088823035
Run 7,0.0108088823035
Run 8,0.0108088823035
Run 9,0.0108088823035
Run 10,0.0108088823035
Run 11,0.0108088823035
Run 12,0.0108088823035
Run 13,0.0108088823035
Run 14,0.0108088823035
代码：
import tensorflow as tf
import numpy as np
from numpy import genfromtxt
import sklearn
import pandas as pd
from sklearn.cross_validation import train_test_split
import sklearn
# function buildWalMartData takes in a csv file, converts to numpy array, splits into training
# and testing, then saves the file to specified target directory
def buildWalmartData():
df = pd.read_csv('/Users/analyticsmachine/Desktop/Kaggle/WallMart_Kaggle/Data/full_train_complete.csv')
df = df.drop('Unnamed: 0', 1) # 1 specifies axis to remove
df_data = np.array(df.drop('TripType', 1).values) # convert to numpy array
df_label = np.array(df['TripType'].values) # convert to numpy array
X_train, X_test, y_train, y_test = train_test_split(df_data, df_label, test_size=0.25, random_state=50)
f = open('/Users/analyticsmachine/Desktop/Kaggle/WallMart_Kaggle/Data/wm-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('/Users/analyticsmachine/Desktop/Kaggle/WallMart_Kaggle/Data/wm-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()
buildWalmartData()
# function convertOnehot takes in data and converts to tensorflow oneHot
# The corresponding labels in Wallmat TripType are numbers between 1 and 38, describing
# which trip is taken. We have already converted the labels to a one-hot vector, which is a
# vector that is 0 in most dimensions, and 1 in a single dimension. In this case, the nth triptype
# will be represented as a vector which is 1 in the nth dimensions.
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)
# import training data
data = genfromtxt('/Users/analyticsmachine/Desktop/Kaggle/WallMart_Kaggle/Data/wm-training.csv', delimiter=',')
# import testing data
test_data = genfromtxt('/Users/analyticsmachine/Desktop/Kaggle/WallMart_Kaggle/Data/wm-testing.csv', delimiter=',')
x_train = np.array([i[1::] for i in data])
# example output for x_train:
#array([[ 7.06940000e+04, 5.00000000e+00, 7.91005185e+09,
# 1.00000000e+00, 8.00000000e+00, 2.15000000e+02],
# [ 1.54653000e+05, 4.00000000e+00, 5.20001225e+09,
# 1.00000000e+00, 5.00000000e+00, 4.60700000e+03],
# [ 1.86178000e+05, 3.00000000e+00, 4.32136106e+09,
# -1.00000000e+00, 5.00000000e+01, 1.90000000e+03],
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)
# exmaple y_test output
#array([ 5, 32, 24, ..., 31, 28, 5])
# and example y_test_onehot:
#[0,...
# 0,
# 0,
# 0,
# 0,
# 0,
# 0,
# 1,
# 0,
# 0,
# 0,
# 0,
# 0]
# A is the number of features, 6 in the wallmart data
# B=38, which is the number of trip types
A = data.shape[1]-1
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 backpropogation
tf_softmax_correct = tf.placeholder('float', [None, B])
tf_cross_entropy = - tf.reduce_sum(tf_softmax_correct*tf.log(tf_softmax))
# training using tf.train.GradientDescentOptimizer
tf_train_step = tf.train.GradientDescentOptimizer(0.01).minimize(tf_cross_entropy)
# add accuracy 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)
# running the training
for i in range(20):
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)
关于为什么跑步会像这样退化可能会出现什么问题的任何想法都将非常感激。谢谢！